Unnamed: 0
int64 0
354
| Company
stringclasses 13
values | Fichier
stringlengths 7
123
| Content
stringlengths 1.77k
32.8k
|
---|---|---|---|
0 | ey | ey-execs-double-down-on-ai-explore-5-ai-adoption-strategies-for-success.pdf | Execs double down
on AI: explore 5 AI
adoption strategies
for success
AI Pulse Survey — July 2024
About the survey
The EY AI Pulse Survey, conducted in May 2024, captures the investment trends
and attitudes toward artificial intelligence (AI) among 500 senior US executives as
they prepare to scale AI technologies in 2024. The survey highlights a significant
projected increase in AI investments, emphasizing the technology’s growing
importance in corporate strategy. The findings suggest that successful AI
adoption requires a holistic approach, including strategic diversified AI investments,
responsible AI practices and workforce upskilling. The insights offered aim to
guide executives in navigating the complexities of AI integration, with strategic
recommendations for those seeking to lead in the AI-driven business landscape.
2 | Execs double down on AI: explore 5 AI adoption strategies for success
Artificial intelligence is redefining the However, despite the forecast investment boom,
competitive business landscape, with our findings also indicate that many leaders are
leaders actively investing to capitalize on ignoring the foundational functions AI needs in
its transformative promise. To investigate order to thrive. Successful AI adoption demands
top-tier investment trends and perceptions more than just technological integration; it’s
in AI technology adoption among corporate about adapting to a new paradigm whereby
leaders, as well as uncover the state of AI in AI reshapes every aspect of the enterprise.
the US, we commissioned a survey among From building a scalable data infrastructure
500 senior executives across a spectrum of to fostering a workforce fluent in emerging
industries. Survey findings indicate a projected technologies, the research emphasizes the
nearly twofold increase in AI investments, need for a holistic approach to AI adoption.
exceeding US$10 million or more in the next As we stand on the cusp of an AI-driven era,
year, among those who are already investing, the message is clear: Those who invest wisely
signaling AI’s shift to a central role in corporate in AI today will be the industry trailblazers
growth strategies. of tomorrow.
This sentiment follows a year in which AI This article illuminates the essential strategies
investments had already significantly increased executives should deploy to navigate the
in pace. Just three years ago, about half of complexities of AI adoption as their investments
senior leaders said their organization spent less increase, including five key takeaways:
than 5% of its total budget on AI investments.
In contrast, today, 88% of those same leaders Adopt diversified AI investment
1
spend 5% or more of their total budget on AI. strategies.
It’s a number that is set to grow even higher, as
half of senior leaders said they would dedicate 2 Prioritize return on investment
25% or more of their total budget toward AI (ROI)-driven AI deployment.
investments in the coming year.
Align your business and AI maturity
3
At the same time, those already doubling roadmap.
down on investments are seeing the impact.
While nearly all are investing in AI, our findings
Invest in responsible AI as a
4
indicate a divergence between companies competitive edge.
experimenting in small ways and those making
larger investments. Senior leaders whose Embrace talent development as a
5
organizations are investing in AI and whose value driver.
current budget for AI investments is 5% or more
of their total budget saw higher rates of positive
return across dimensions surveyed compared
with those who spend less than 5%.
3 | Execs double down on AI: explore 5 AI adoption strategies for success
Leaders should adopt diversified
AI investment strategies
In the search for operational excellency, Figure 1: Leaders should adopt diversified AI
investment strategies
businesses are turning to AI as a transformative
technology. Custom AI development stands
out for its ability to enhance an enterprise’s With 95% of senior leaders
saying their organization is
operations, delivering peak efficiency and
currently investing in AI.
intelligent workflow management tailored to the
intricate needs of the business. Simultaneously,
the allure of pre-built AI technologies lies in 95%
their ability to offer immediate implementation
and a more favorable cost structure. Discerning
businesses should undertake a comprehensive
analysis of their operational requirements,
56%
competitive landscape and long-term goals
to determine the optimal blend of in-house
56%
developed and off-the-shelf AI solutions.
By doing so, they position themselves to
The key investment focus
leverage the full spectrum of AI benefits, lies in balancing custom
The acquisition of AI development.
ensuring a strategic advantage in the rapidly
ready-made AI products.
evolving marketplace.
This strategy allows for tailored solutions where necessary
while also leveraging the speed and cost efficiency of pre-built
AI technologies.
4 | Execs double down on AI: explore 5 AI adoption strategies for success
Prioritize ROI-driven AI deployment
Forward-thinking enterprises are looking to Figure 2: Prioritize ROI-driven AI deployment
AI as a catalyst for business transformation.
Strategic deployment of AI is crucial for firms
aiming to strengthen their performance About a third (34%) of senior
leaders say their organization is
and realize cost efficiencies. By focusing
tracking the impact of AI initiatives
on AI solutions that improve operational fully and at scale.
workflows and enhance employee productivity,
organizations can convert traditional business
34%
models into intelligent, AI-powered operations.
This advancement goes beyond simple task
improvement — it calls for a radical redesign of
77%
business processes to be AI-centric. By doing
so, companies are not just automating; they are
innovating, ensuring that their investments in AI
74%
yield measurable financial returns and solidify
their standing for the future.
The survey shows that
among organizations
investing in AI, those
investments are delivering
Employee positive returns, especially
productivity (74%). in areas like operational
efficiencies (77%).
5 | Execs double down on AI: explore 5 AI adoption strategies for success
33
Align your business and AI
maturity roadmap
Capturing the full potential of AI requires more Figure 3: Align your business and AI maturity roadmap
than just technological investment; it demands a
strategic alignment that integrates AI initiatives About 1/3 (34%) of senior
executives report that their
with the core objectives of the business. A
organization is aligning 34%
robust and well-structured data infrastructure AI strategy with business
objectives fully and at scale.
is critical as it underpins intelligent operations
and aligns with the company’s strategic
A third (36%) of senior
pursuits. This alignment paves the way for
leaders report that their
enhanced decision-making capabilities and organization is investing
36% in data infrastructure (i.e.,
a fertile environment for innovation. By
quality, accessibility and
achieving strategic AI maturity, organizations governance of data) fully
and at scale,
can transition into “superfluid” entities,
characterized by their seamless decision-making
processes and a relentless drive for innovation. and 35% report that their
In this way, a strong data foundation not only organization is creating a 35%
roadmap for AI implementation
supports AI but also propels businesses toward
fully and at scale.
their goals with unprecedented efficiency
and insight.
A superfluid enterprise is a highly agile
and adaptable organization, leveraging
digital innovation to swiftly respond to
market shifts, optimize processes and drive
continuous growth, ensuring sustained
competitive advantage.
6 | Execs double down on AI: explore 5 AI adoption strategies for success
44
Champion responsible AI
as a competitive edge
The surge in executive interest toward Figure 4: Champion responsible AI as a competitive edge
responsible AI marks a pivotal shift in business
strategy, placing ethical considerations at
the forefront of AI adoption. To navigate About a third (34%) of senior
this new terrain, companies should invest in leaders say their organization
is building an AI governance
comprehensive AI governance frameworks and
framework fully and at scale.
strategies for mitigating bias, thereby ensuring
that their AI systems uphold fairness and
transparency. Firms that excel in responsible AI
not only distinguish themselves in a competitive 34%
marketplace but also fortify themselves against
future regulatory issues. In addition, ethical
AI practices are a linchpin in the creation of
32%
a “superfluid” enterprise, where stakeholder
trust is strengthened, compliance is effortlessly 53%
maintained and operational friction is reduced,
all of which propels innovation. Pioneers in this About as many (32%)
senior leaders say their
are setting a new industry standard, providing
organization is addressing
services that are both transparent and With 53% of senior leaders bias in AI models fully and
equitable and charting the course for the future whose organization is at scale.
investing in AI reporting
of AI-powered businesses. There is clear interest
increased organizational
in responsible AI, but
interest in responsible
leaders are not taking the
AI over the past year,
necessary steps to realize
businesses should prioritize
this interest.
ethical considerations in
their AI strategies.
7 | Execs double down on AI: explore 5 AI adoption strategies for success
55
Embrace talent development
as a value driver
The scarcity of AI skills in the job market is a Figure 5: Embrace talent development as a value driver
clarion call for businesses to invest in extensive
employee upskilling programs. By cultivating AI
There is clearly a gap and talent is
skills within their existing workforce, companies hard to find, but only 4 in 10 (40%)
senior leaders are encouraging
can not only expedite the adoption of AI Additionally, only 37% of
employees to embrace AI fully and
senior leaders say their
technologies but also secure a vital competitive at scale.
organization is training/
advantage. Developing an internal pipeline of AI upskilling employees on
AI fully and at scale.
talent is essential for fostering a workforce that
is not just proficient but superfluid — adaptable, 40%
innovative and fully equipped to leverage AI
37%
for maximum impact. Moreover, by placing a
premium on attracting and nurturing AI-savvy
employees, organizations can establish that 83%
their operations are driven by professionals that
can unlock the full spectrum of AI’s capabilities, 78%
positioning the business at the forefront of
technological advancement.
With 83% of senior
leaders prioritizing
attracting workers who The difficulty in finding
are knowledgeable of AI, employees with the
businesses must recognize AI skill set needed for
the importance of building their organization (78%)
an AI-competent workforce. underscores the need for
comprehensive upskilling
programs.
8 | Execs double down on AI: explore 5 AI adoption strategies for success
Conclusion
The burgeoning influence of AI on the business landscape is undeniable, with our survey of 500
senior executives revealing a significant uptick in AI investments. This is not merely a trend but a
strategic imperative; companies that do not actively engage with AI risk being left behind in a market
that increasingly rewards innovation and agility. As we have seen, the future belongs to those who
recognize AI’s potential to redefine every facet of their operations — from process improvement to
decision-making — and invest accordingly.
A diversified AI investment strategy is paramount. Companies must balance the allure of ready-made
AI technology solutions with the bespoke advantages of custom development to create a hybrid model
that aligns with their unique business needs. This approach enables organizations to harness AI’s
full potential while maintaining flexibility in a dynamic market. In addition, the focus must be on ROI-
driven AI deployment. Investments in AI should not be made for the sake of technology alone; they
must be tied to clear, measurable business outcomes. Organizations that prioritize AI applications
with direct impact on operational efficiency and productivity will not only see immediate benefits but
also set the stage for long-term financial success.
It’s important to note that championing responsible AI is not just an ethical mandate but a competitive
differentiator. As AI becomes more widespread, companies that lead with transparency, fairness and
governance will build trust and resilience, positioning themselves favorably in the eyes of consumers
and regulators alike.
And aligning business and AI maturity roadmaps is crucial. Organizations must verify that their data
infrastructure and AI initiatives are in lockstep with their strategic goals. This synergy will enable
them to make smarter decisions faster and foster an environment ripe for continuous innovation.
Finally, talent development is a critical value driver in the AI equation. The scarcity of AI competencies
necessitates a proactive approach to upskilling and attracting top talent. Companies that build a
robust internal pipeline of AI skills will not only accelerate technology integration but also secure a
lasting competitive edge.
9 | Execs double down on AI: explore 5 AI adoption strategies for success
Methodology
Ernst & Young LLP commissioned a third party to conduct the 2024 EY AI Pulse Survey. The
online survey was conducted among n=500 US-employed decision-makers (SVP+) in the health;
life sciences, energy, technology, media and telecommunications (TMT); government and public
sector; consumer products and retail; advanced manufacturing and mobility (AMM); financial
services; private equity; and real estate, hospitality and construction (RHC) industries (i.e., n=50
per industry). The survey was fielded between April 29 and May 6, 2024. The margin of error
for the total sample is +/- 4 percentage points.
Ernst & Young LLP contacts
Dan Diasio
EY Global Artificial Intelligence Consulting Leader
[email protected]
Traci Gusher
EY Americas Data and Analytics Leader
[email protected]
Samta Kapoor
EY Americas Energy AI and Trusted AI Leader
[email protected]
10 | Execs double down on AI: explore 5 AI adoption strategies for success
EY | Building a better working world
EY exists to build a better working world, helping
to create long-term value for clients, people and
society and build trust in the capital markets.
Enabled by data and technology, diverse EY
teams in over 150 countries provide trust
through assurance and help clients grow, transform
and operate.
Working across assurance, consulting, law,
strategy, tax and transactions, EY teams ask better
questions to find new answers for the complex
issues facing our world today.
EY refers to the global organization, and may refer to one or more, of the
member firms of Ernst & Young Global Limited, each of which is a separate
legal entity. Ernst & Young Global Limited, a UK company limited by guarantee,
does not provide services to clients. Information about how EY collects and
uses personal data and a description of the rights individuals have under data
protection legislation are available via ey.com/privacy. EY member firms do not
practice law where prohibited by local laws. For more information about our
organization, please visit ey.com.
Ernst & Young LLP is a client-serving member firm of
Ernst & Young Global Limited operating in the US.
© 2024 Ernst & Young LLP.
All Rights Reserved.
2406-4556497
ED None
This material has been prepared for general informational purposes only and is not intended to be relied
upon as accounting, tax, legal or other professional advice. Please refer to your advisors for specific
advice.
ey.com |
1 | ey | ey-ukc-short-report-ai-and-productivity.pdf | How can AI
augment your
people to realise
their full potential?
Contents
Chapter One: Setting the scene 1
What’s the value of AI innovation? 1
What tasks will AI augment? 2
Chapter two: How can AI enhance productivity 3
for UK business?
What magnitude of productivity savings could AI bring 3
to the UK economy?
Benefits of AI adoption for the workforce 4
What are the potential risks? 4
How can organisations retain and protect female talent? 4
Chapter three: AI and the UK regions 5
Where does this leave the regions? 6
Chapter four: Balancing rapid adoption with 8
ethical innovation
Cultural and operational risks 8
How can you create the right environment for AI innovation? 8
Chapter five: Create the right conditions 9
for enhanced productivity
Contacts
Catriona Campbell
Client Technology & Innovation Officer, Ernst & Young LLP
https://www.ey.com/en_uk/people/catriona-campbell
Harvey Lewis
Partner, Client Technology & Innovation, Ernst & Young LLP
https://www.ey.com/en_uk/people/harvey-lewis
Sofia Ihsan
EY Global Responsible AI, Consulting Leader, Ernst & Young LLP
https://www.ey.com/en_uk/people/sofia-ihsan
Chapter one
Chapter one:
Setting the scene
Policymakers worldwide recognise that artificial How is AI impacting
intelligence (AI) has the potential to drive enormous gains productivity?
in productivity and growth, with forecasts suggesting a
Implemented effectively,
contribution of between $13 trillion and $15.7 trillion to
AI could effectively add
the global economy by 2030.1 9.8 million
workers to the
In findings published by EY and Liberty Global in the report, Wired for AI,2 from a UK workforce
labour market perspective, 50% of jobs in the US, EU, UK and Switzerland could
be complemented by AI because the latest technology can help people become Create additional
more efficient in at least half of their tasks. productivity
equivalent to
As the UK economy takes its first tentative steps towards a more buoyant $7 trillion
economic outlook in 2024, AI has the potential to accelerate economic recovery,
in wages
thanks to the vast productivity and efficiency gains on offer to reinvigorate GDP,3
arising from AI’s ability to enhance work output and quality.
46%
Indeed, assuming the maximum potential efficiency gains for all workers, the of UK
total additional ‘productive capacity’ that could be unlocked within the combined jobs could be
complemented by AI
economies of the US, UK and Europe by AI is equivalent to 124 million workers:
around 62 million in Europe, 51 million in the US, 9.8 million in the UK and
1.4 million in Switzerland. The total value of this additional productive capacity
equates to approximately $7 trillion in yearly wages.
What’s the value of AI innovation?
Around 400 million people are employed across the US, EU, UK and Switzerland.
Of that figure, EY and Liberty Global analysis4 suggests that 50% of these jobs
could be complemented by AI because the technology can help people become
more efficient in at least half of their tasks. This means there are benefits on
offer for the majority of businesses in all sectors and markets. Put into the
context of workforce output, this acceleration of productivity is equal to adding
124 million more workers into the economies of the US, EU, UK and Switzerland.
Our results are consistent with estimates published by the IMF, who suggest that
60% of jobs in advanced economies could be impacted by AI, 40% in emerging
markets and 26% in low-income countries.5 The research suggests that AI could
have the greatest impact in Luxembourg, where nearly 56% of jobs could be
complemented; in the UK, that figure currently stands at 46%. With the impact of
AI set to target such a significant proportion of the UK workforce, understanding
its true benefit is crucial.
1
Chapter one
Percentage of jobs that can be complimented by AI
Figure 1. Percentage of jobs that can be complemented by AI and GenAI in the US, UK, Switzerland and
individual countries in Europe, showing the contribution from highly network dependent jobs
Source: EY and Liberty Global21
What tasks will AI augment?
As a general-purpose technology, AI’s principal impacts are likely to be felt
in improved efficiency and new business models across industries, providing
opportunities for business transformation and job creation. In the US, EY estimates
that generative AI (GenAI) is set to provide a substantial lift to productivity, likely
delivering a boost worth $650 billion over the next decade and lifting real GDP by
nearly 2.5% by 2033.6 Moreover, Goldman Sachs indicates that further progress
in the field of GenAI could add an extra $7 trillion to global output over the next
decade, as innovative tools like ChatGPT become increasingly woven into the fabric
of business and society.7
With the World Economic Forum predicting that 44% of roles will be disrupted
in the next five years, there is, of course, a fear that AI will displace workers in
sectors which are unable to adapt quickly.8 Yet, this is not the only possible future.
As economists Erik Brynjolfsson and Gabriel Unger suggest, “There is a scenario
in which AI leads to a higher-productivity-growth future. AI might be applied
to a substantial share of the tasks done by most workers and massively boost
productivity in those tasks.” 9
This report will explore where AI will have the biggest impact, how business leaders
can prepare their workforce for the new reality of AI augmented work, and the
regulatory and ethical watch outs — particularly when it comes to supporting women
in the workplace — that businesses should be wary of to ensure AI innovation does
not eclipse the needs of the workforce.
Responsible quantum computing for everyone | 22
Chapter two
Chapter two:
How can AI enhance
productivity for UK business?
In 2024, business leaders and policymakers alike will need
to address urgent issues in the labour market, namely the
number of people in work and the skill levels across the
workforce. As we enter a new epoch of technology innovation
in our workplaces, businesses will need more widespread tech
skill than ever before.
With AI presenting opportunities for net gains in employment figures, business
leaders and policy makers would be wise to focus on developing AI skills amongst
the existing workforce to prevent employee loss and provide opportunities for those
out of work to access AI skills courses. This can expedite their return to work, future
proof their skills and prevent unnecessary delays to AI innovation.
Addressing inactivity by encouraging people back into work through the creation of
AI-related roles could help contribute to closing some of the disparities in regional
growth performance. In a study conducted by the Institute for the Future of Work,
although 47% of respondents said AI and automation had eliminated positions within
their company, almost 67% reported the technology had created new positions.10
What magnitude of productivity savings could AI bring to the UK economy?
An accurate assessment of AI’s potential effect on productivity is difficult to
establish because it is a broad and rapidly evolving field. Considerable uncertainty
also remains about how it will be adopted by people and integrated into established
business processes. However, there are ways to assess its impact on the workforce
by considering how it can help people to carry out tasks more efficiently.
For organisations looking to retain top talent in a sluggish talent market, AI
innovation can be instrumental in improving workforce conditions, particularly in a
marketplace where budgets for learning and development are contracting; findings
from the recent EY CEO Outlook survey11 indicate 96% of UK leaders are considering
restructures or hiring freezes, a reduced focus on learning and development and
a move from permanent to contract workers. By prioritising opportunities for AI
innovation in areas where the technology can help to reduce the workload, free up
workers to enjoy more skillful work and embrace a better work-life balance; AI could
be the vehicle needed to redress potential workforce issues before firmer tactics,
such as redundancy, are adopted.
3
Chapter two
What are the potential risks?
Despite the evident benefits of integrating AI into the everyday lives of the
workforce, it’s essential that organisations remain aware of the potential damage AI
can have on diversity and inclusion, particularly in how it impacts women or lower
skilled workers.
In findings published by McKinsey Global12, the industries expected to shrink
as a direct result of AI automation include food services, customer service and
sales, and office support- all industries in which women are disproportionately
overrepresented. In the UK, women account for 53% of workers in food service13,
and over 60% of total workers across the service and administrative sectors.
Seniority also adds to the burden placed on women; there’s well established evidence
that women hold more lower paying jobs than men: currently only 41% of managerial
roles are held by women, this figure decreases to 38%14 when looking at senior
business leading positions. And with AI poised to drive operational efficiencies that
reduce administrative and repetitive workstreams, those in more junior positions-
who are predominantly women — also stand to be more affected.
How can organisations retain and protect female talent?
Considering AI’s potential to unduly damage the careers of women, it’s essential that
workplaces invest in comprehensive training and development programmes to upskill
workers and provide opportunities for growth into roles that are augmented by AI
rather than subsumed by it. By fostering a culture of continuous learning, companies
can ensure that all individuals remain at the forefront of AI advancements. As a
result, businesses can reduce potential layoffs and the exacerbation of skill gaps that
prevent employees from advancing, therefore avoiding an abyss of talent with those
with AI skills on one side, and those without stranded on the other.
Despite the gloomy outlook in some sectors, there will also real opportunities for
women thanks to AI innovation. McKinsey Global15 reports that in spite of real
challenges to workplace equality, AI innovation will generate a demand for work and
workers, which will only increase as economies grow, facilitated by AI: by 2030, the
same research indicates there will be a 17% increase in women’s jobs gained in the
UK as a result of AI. Men will also experience the same uplift.
Benefits of AI adoption for the workforce:
• Achieve an improved work- • Improve delivery times for
life balance, which may work, without an increase in
reduce attrition and work- stress or demand for overtime.
related stress. • Introduce lower skilled
• Perform other meaningful individuals to the workforce,
work, which increases output thanks to AI tools being able
quality or enhances value. to take the strain of more
• Spend more time with their complicated tasks.
clients, which increases client • Reducing burden of repetitive
satisfaction and may lead to or administrative tasks.
growth in future sales.
• Foster innovation because
creative thinking requires time.
• Increase work quality since
they have more time for
4
each task.
Chapter three
Chapter three:
AI and the UK regions
Despite AI’s potential to generate huge opportunities for the
UK — it has already delivered £3.7bn in gross revenue and
created 54,000 jobs — a staggering 75% of all AI activity is
taking place in just three regions: London, the South East
and the East of England, according to the Department for
Science, Innovation & Technology, leaving other UK regions
vulnerable to slower economic recovery and less opportunity
for productivity enhancement.16 Whilst ‘the golden triangle’ is
generating value for the UK economy, activity across the rest
of the UK is sluggish, particularly in the North, Midlands and
South West.
In the recently published EY Regional Economic Forecast17, it was found that London
and the southern regions of the UK are expected to lead the economic recovery,
thanks to a still strong labour market, a recovery in consumer spending, and robust
growth expected in information and communication, professional services, and a
recovering retail sector.
London’s success continues to be driven by the distinctiveness of its economy,
which is characterised by knowledge-based sectors such as professional services,
information and communication, and the concentration of high-skilled workers in
these sectors. AI is undoubtedly supporting that surge in economic recovery.
The UK Sectors Most Impacted by AI
Finance, IT and professional services will be most impacted by AI
Finance & insurance Information & Professional, Property Public Education
communication scientific & administration
technical & defence
Source: Department for Education, Unit for Future Skills, the impact of AI on UK jobs and training report
5
Chapter three
In research undertaken by the Department for Education18, London was the city
identified as most likely to the experience the earliest impacts and benefits of AI
innovation due to its high concentration of roles in these sectors. When considered
alongside the fact that 75% of AI focussed organisations are based in London, and
the density of professions that will be most quickly and intensely impacted by AI, it’s
unsurprising that London is currently at the forefront of AI innovation and is able to
realise its benefits before other UK regions.
Where does this leave the regions?
Whilst AI has the potential to exacerbate existing regional inequalities due to
disparities in AI preparedness, harnessing the technology could galvanise economic
growth across the regions, and help upskill workers cross-sector. But it will
take investment.
A report published by the Institute for the Future for Work19, expounds the
importance of developing workforce skills rather than focussing on AI alone,
emphasising that training and upskilling will have the biggest impact on regions
currently displaying the lowest levels of AI preparedness. The report says:
“Investments in training, complemented by the sharing of information about new
technologies, consultation on technology adoption, and an orientation towards
empowerment and autonomy, are expected to influence whether new technologies
have a positive or negative impact on work and workers. First, a highly skilled
workforce will be more likely to understand the need for the new technology, its
technical aspects, and its benefits, and feel less threatened by it (as noted by the
OECD in 2023), this will facilitate approaches to AI adoption in which labour is
complemented by technology.”
By upskilling workers, and providing opportunities for their personal development,
the fast-moving organisations can successfully use these technologies, and by
preparing the workforce first, and at scale, regional leaders can better enhance the
overall preparedness of their regions.
Nurturing high-value sectors can boost resilience in tough times and
accelerate growth in better years, but doing so requires regions to
build their own tailored growth plans that consider which industries
are set to flourish and how to cultivate them locally. High-value
sectors will require a high-value workforce, so building in-demand
skillsets and competencies with latest technology should help a
region attract investment while bolstering the local economy. For
example, Generative AI has the potential to enhance regional and
UK productivity rates, but will require a shift in skills to ensure the
workforce can collaborate with and complement the technology.
Rohan Malik, EY UK&I Managing Partner for Government & Infrastructure, EY UK regional economic forecast.20
66
Chapter three
Despite the south dominating AI growth, EY research projects that, between 2024-
2027, Manchester will experience the greatest Gross Value Add (GVA) growth at
2.2% compared to any other city in the UK, including London (0.6%)21. Whilst the
northern city undoubtedly lags behind the ‘golden triangle’ when it comes to AI,
economic value in Manchester is accelerating faster than any other, as investment
pours in. With initiatives such as the newly established AI Foundry helping SMEs
in the area make headway with AI innovation, and investment in AI research at
Manchester University increasing — this February the university received £12 million
in funding for AI research22 — it’s only a matter of time until this vibrant city closes
the gap on its southern counterparts.
Whilst there’s obvious work to be done to help the North embrace
all that AI has to offer, Manchester is undoubtedly benefiting from
a boost in GVA, that other cities across the country can’t rival.
With more spending power to invest in emerging technologies, it’s
essential that cities in the north embrace AI to help continue this
positive outlook, and to close the gap on the ‘golden triangle’.
Stephen Church, EY UK&I North Markets Leader & Manchester Office Managing Partner
77
Chapter four
Chapter four:
Balancing rapid adoption
with ethical innovation
Cultural and operational risks
The rapid evolution of AI technologies poses its own set of challenges. As AI technologies
advance, keeping up with the latest developments and understanding which innovations
are most applicable to individual businesses and sectors becomes increasingly complex.
This rapid progression can lead to a misalignment between AI capabilities and business
needs, potentially resulting in investments in technologies that are either outdated shortly
after implementation or do not deliver the expected value.
The fundamental challenge of business adoption lies not just in the successful
implementation of AI pilots and projects but also in cultivating an environment where
innovation is nurtured, and the workforce is ready and prepared to adapt alongside
these advancements.
Companies often struggle with rigid organisational and cultural structures that can
significantly impede the speed and success of AI implementations. Such structures
typically foster siloed departments and a resistance to change, making it challenging to
embrace the collaborative and agile methodologies required for effective AI integration.
Centralised approaches, while offering streamlined decision-making, may lack the
flexibility and localised insights necessary for innovative AI solutions. Conversely,
federated structures can encourage autonomy and innovation at the departmental level
but may suffer from a lack of cohesion and unified risk management or strategic direction.
To support both workplaces and the workforce towards embracing AI innovation in their
day-to-day work, creating the right environment for innovation will be crucial.
How can you create the right environment for AI innovation?
There is a critical need for clear and robust guidelines on the ethical use
of AI in the workplace, both in how the workforce interact with AI and how
1 Provide clients’ and consumer data is treated. Policymakers must formulate and
guardrails for enforce regulations like the EU’s AI Act, while businesses should establish
AI’s use comprehensive governance frameworks. This will ensure that AI is used
responsibly, with a focus on data privacy, fairness and transparency.
Companies should prioritise organisational agility to adapt swiftly to the
Nurture
2 changing AI landscape and to nurture curiosity that cuts across teams and
curiosity and
functions. Emphasising flexible, collaborative work environments and a culture
increase agility of continuous innovation will be key. This approach will enable businesses to
respond effectively to new AI advancements and market demands.
Keep As AI transforms the UK workforce, targeted investment in skill development
3 upskilling at and workforce training is imperative. Businesses should focus on equipping
the heart of AI their employees with the necessary skills to navigate and leverage AI
transformation technologies. Policymakers can support this initiative by providing incentives and
frameworks for continual learning and skill enhancement in the AI field.
8
Chapter five
Chapter five:
Create the right conditions
for enhanced productivity
As AI transforms the UK workplace, targeted investment in skills development and
workforce training is imperative to realise the 46% productivity growth potential on
offer for the UK.23
To rise to the challenge, companies should focus on equipping their employees with
the necessary skills to navigate and leverage AI technologies. Businesses can do this
by creating the necessary guardrails to create business environments in which AI can
be used safely whilst still promoting greater creativity and efficiency.
Policymakers can support business leaders by providing incentives and frameworks
for continual learning and skill enhancement in the AI field, that not only incentivise
individual businesses but help accelerate both productivity and output across the
whole of the United Kingdom.
The productivity boosts that are enabled will be significant for both the UK’s
economy and skills market as more workers upskill in preparation for a future
of work enabled by AI. But capitalising on AI’s full potential demands targeted
investment across the whole of the UK, cultivating new skills and strategic
organisational realignment. In essence, the UK is primed for a new digital
transformation, but leaders must prioritise developing AI skills to realise the promise
of a more productive future that benefits everyone.
Questions for those charged with leading AI innovation:
• What opportunities am I providing the workforce to upskill in AI technology?
• Do I have the right guardrails in place to guide AI innovation?
• Where is the potential in my organisation to use AI for greater impact?
• What does success look like for my organisation?
Acknowledgements
This report was written by Dr Harvey Lewis, Partner at EY and Catherine Jones from the Ernst
& Young LLP, Brand, Marketing and Communications team with support from EY ITEM club.
Some of the content in this report has been taken from the Wired for AI report, written in
conjunction with Liberty Global, published in February 2024.
The proprietary EY sourced analysis in this report was undertaken by Dr Harvey Lewis
and Timea Ivacson, Manager, from the Ernst & Young LLP, Data and AI team. Additional
contributions were gratefully received from Gareth Shier, Director in the Ernst & Young LLP
Econometrics and Modelling team, Sofia Ihsan, Director in the Ernst & Young LLP, Technology
Risk team, and Dr Ansgar Koene, Director and Global Leader for AI Ethics and Regulation.
The report has been designed by the Ernst & Young LLP, Creative Services Group.
9
References:
1. “Economic impacts of artificial intelligence”, europa.eu, 13. “Official census and labour market statistics”, Nomis.
accessed 11 December, 2023 co.uk, https://www.nomisweb.co.uk/, accessed 23 April
2. “Wired for AI”, EY.com https://assets.ey.com/content/ 14. “Women remain underrepresented in senior and
dam/ey-sites/ey-com/en_uk/topics/ai/wired-for-ai-ey-and- strategic management positions research shows”, Managers.
liberty-global-report.pdf, accessed 14 April, 2024 org.uk, https://www.managers.org.uk/about-cmi/media-
centre/press-releases/women-remain-underrepresented-
3. “Regional UK economic growth gap to widen, with
in-senior-and-strategic-management-positions-research-
Southern England ahead”, EY.com, https://www.ey.com/
shows/, accessed 23 April
en_uk/news/2024/03/regional-uk-economic-growth-gap-to-
widen-from-2024-to-2027, accessed 14 April, 2024 15. “The future of women at work — transitions in the age
of automation”, McKinsey.com https://www.mckinsey.com/
4. “Wired for AI”, EY.com https://assets.ey.com/content/
featured-insights/gender-equality/the-future-of-women-at-
dam/ey-sites/ey-com/en_uk/topics/ai/wired-for-ai-ey-and-
work-transitions-in-the-age-of-automation, accessed 23 April
liberty-global-report.pdf, accessed 14 April, 2024
16. “Artificial Intelligence Sector Study”, Gov.uk, https://
5. “Gen-AI: Artificial Intelligence and the Future of Work”,
assets.publishing.service.gov.uk/government/uploads/
imf.org, https://www.imf.org/en/Publications/Staff-
system/uploads/attachment_data/file/1145582/artifical_
Discussion-Notes/Issues/2024/01/14/Gen-AI-Artificial-
intelligence_sector_study.pdf, accessed 23 April
Intelligence-and-the-Future-of-Work-542379, accessed
9 February, 2024 17. “Regional UK economic growth gap to widen, with
Southern England ahead”, EY.com, https://www.ey.com/
6. “The productivity potential of GenAI”, EY.com, https://
en_uk/news/2024/03/regional-uk-economic-growth-gap-to-
www.ey.com/en_us/ai/productivity-potential-gen-ai, accessed
widen-from-2024-to-2027, accessed 14 April, 2024
19 February, 2024
18. “The impact of AI on UK jobs and training”, Gov.uk,
7. “Generative AI Could Raise Global GDP by 7%”,
https://www.gov.uk/government/publications/the-impact-of-
Goldmansachs.com, https://www.goldmansachs.com/
ai-on-uk-jobs-and-training, accessed 23 April, 2024
intelligence/pages/generative-ai-could-raise-global-gdp-by-7-
percent.html, accessed 11 December, 2023 19. “What drives UK firms to adopt AI and robotics, and
what are the consequences for jobs?”, Gov.uk, https://
8. “How to harness the power of generative AI for
assets-global.website-files.com/64d5f73a7fc5e8a240310
better jobs”, Weforum.org, https://www.weforum.org/
c4d/650a05c1b2daf9e31b0ae741_FINAL%20WP%20-%20
agenda/2023/09/how-to-harness-the-power-of-generative-
Adoption%20of%20Automation%20and%20AI%20in%20
ai-for-better-jobs/, accessed 26 January, 2024
the%20UK.pdf, accessed 23 April
9. “The Macroeconomics of Artificial Intelligence”,
20. “Regional UK economic growth gap to widen, with
imf.org, https://www.imf.org/en/Publications/fandd/
Southern England ahead”, EY.com, https://www.ey.com/
issues/2023/12/Macroeconomics-of-artificial-intelligence-
en_uk/news/2024/03/regional-uk-economic-growth-gap-to-
Brynjolfsson-Unger, accessed 12 April, 2024
widen-from-2024-to-2027, accessed 14 April, 2024
10. “What drives UK firms to adopt AI and robotics, and
21. “Regional UK economic growth gap to widen, with
what are the consequences for jobs?” Gov.uk, https://
Southern England ahead”, EY.com, https://www.ey.com/
assets-global.website-files.com/64d5f73a7fc5e8a240310
en_uk/news/2024/03/regional-uk-economic-growth-gap-to-
c4d/650a05c1b2daf9e31b0ae741_FINAL%20WP%20-%20
widen-from-2024-to-2027, accessed 14 April, 2024
Adoption%20of%20Automation%20and%20AI%20in%20
the%20UK.pdf, accessed 22 April 22. “Universities secure £12 million boost for AI
innovation”, Manchester.ac.uk, https://www.manchester.
11. “EY CEO Outlook Global Report”, EY.com, https://
ac.uk/discover/news/universities-secures-12-million-boost-
www.ey.com/en_uk/ceo/ceo-outlook-global-report?WT.mc_
for-ai-innovation/, accessed 26 April, 2024
id=3501113&AA.tsrc=sponsorship, accessed 22 April
23. “Wired for AI”, EY.com, https://assets.ey.com/content/
12. “The future of women at work — transitions in the age
dam/ey-sites/ey-com/en_uk/topics/ai/wired-for-ai-ey-and-
of automation”, McKinsey.com, https://www.mckinsey.com/
liberty-global-report.pdf, accessed 14 April, 2024
featured-insights/gender-equality/the-future-of-women-at-
work-transitions-in-the-age-of-automation, accessed 23 April
10
EY | Building a better working world
EY exists to build a better working world, helping
to create long-term value for clients, people and
society and build trust in the capital markets.
Enabled by data and technology, diverse EY
teams in over 150 countries provide trust
through assurance and help clients grow,
transform and operate.
Working across assurance, consulting, law,
strategy, tax and transactions, EY teams ask better
questions to find new answers for the complex
issues facing our world today.
EY refers to the global organization, and may refer to one or more, of
the member firms of Ernst & Young Global Limited, each of which is
a separate legal entity. Ernst & Young Global Limited, a UK company
limited by guarantee, does not provide services to clients. Information
about how EY collects and uses personal data and a description of the
rights individuals have under data protection legislation are available via
ey.com/privacy. EY member firms do not practice law where prohibited
by local laws. For more information about our organization, please visit
ey.com.
Ernst & Young LLP
The UK firm Ernst & Young LLP is a limited liability partnership
registered in England and Wales with registered number OC300001 and
is a member firm of Ernst & Young Global Limited.
Ernst & Young LLP, 1 More London Place, London, SE1 2AF.
© 2024 Ernst & Young LLP. Published in the UK.
All Rights Reserved.
EYSCORE 004982-24-UK
UKC-033844.indd 06/24. Artwork by Creative UK.
ED None
Information in this publication is intended to provide only a general
outline of the subjects covered. It should neither be regarded as
comprehensive nor sufficient for making decisions, nor should it be
used in place of professional advice. Ernst & Young LLP accepts no
responsibility for any loss arising from any action taken or not taken by
anyone using this material.
The views of the third parties set out in this publication are not
necessarily the views of the global EY organization or its member
firms. Moreover, they should be seen in the context of the time they
were made.
ey.com/uk |
2 | ey | ey-european-ai-barometer-2024.pdf | From challenges
to opportunities:
How EY and AI work
hand in hand
EY European AI Barometer
June 2024
From challenges to opportunities: How EY and AI work hand in hand
Contents
3
Introduction
1 4
The AI revolution
2 6
Adoption
3 8
Benefits
4 10
Impact on workforce
5 14
Capability building
6 18
Future of AI technology
7 19
Use cases
22
Study design
23
Contacts
2
From challenges to opportunities: How EY and AI work hand in hand
Introduction
In a world shaped by relentless technological progress, companies that fail
to evolve could disappear from the map. Artificial intelligence (AI) is sweeping
through the business landscape with fierce intensity – reshaping industries
and economies at an unprecedented pace. As AI advances to the forefront
of technological innovation, some brace themselves for the inevitable
challenges a step change of this magnitude will bring, while others fervently
seek to unlock the immense opportunities it promises.
Irrespective of AI technology’s many facets and manifestations, one thing
is certain: it will fundamentally redefine the way we work, the way we live and the
way we interact. Businesses need to give careful consideration to some bedrock
questions: should they embrace AI without reservation or proceed with caution?
What pitfalls and paybacks can they expect? How will AI impact the world of work?
And what regulatory frameworks do companies need to observe and how?
Nobody can lay claim to having all the answers in this rapidly evolving new
reality. But since the inception of the AI revolution, our EY teams have stepped
up to the challenge and have been helping clients chart their course for successful
transformation, pinpointing where they can best invest their resources
to extract value from AI for their respective businesses – and creating a better
working world for all stakeholders in the process.
This report seeks to share our experience with, and shed light on, the
multifaceted impact of AI in its many manifestations, examining how managers
and non-executive employees view the challenges and opportunities ahead.
We deep-dive into different sectors to understand the latest approaches to
harnessing the power of AI, with a particular focus on Europe, while maintaining
a global perspective. Our overarching goal is to unlock AI’s potential to create
positive impact in our economies and our communities, advocating for
a responsible, people-centered approach that prioritizes value
creation for everybody.
3
From challenges to opportunities: How EY and AI work hand in hand
1.
The AI revolution
Unlike past technological revolutions that largely involved adequately equipped by their employers to tackle the AI
the automation of manual labor, AI marks a paradigm shift transformation process with suitable training? Are they
in its focus on assisting and automating complex cognitive seeing a meaningful evolution of their job profiles and tasks?
functions, with unavoidable consequences for knowledge
workers. Entire industries and all manner of professions Around the world, regulators too are shifting their attention
are on the cusp of profound change. toward AI and its implications for the economy and for
society more broadly. Government commissions and tasks
AI has the potential to enhance workers’ efficiency and forces are investigating the likely impact on all sectors, from
unearth productivity gains throughout the economy. Our healthcare and financial services through to transportation,
AI survey of multidisciplinary professionals across levels, as they seek to address a host of concerns: citizens’ privacy,
sectors – and across Europe – already provides insights bias in algorithms, job displacement – the list goes on.
of the depth and scale of the AI-driven productivity In May 2024, for instance, the EU introduced the Artificial
boost in major economies, and an indication of its potential Intelligence Act (AIA), which aims to regulate the
contribution to the global economy. That said, unlocking development and use of AI systems within its borders,
productivity gains that AI promises will likely take time, to protect the safety, security and fundamental rights
effort, and wise strategy. of its people. To navigate the global regulatory complexity
that is rapidly emerging, companies will need to designate
One use case we are already seeing gaining traction is the compliance responsibilities for AI deployment and
deployment of AI as a powerful knowledge tool. By distilling use across their entire organization, not just
key insights from vast volumes of data, AI is already helping technical departments.
businesses and their teams make more accurate and in turn
better decisions. Forward-thinking executives are wasting Notwithstanding all the advancements promised, one thing
no time and have set to work exploring how AI can empower can never change: humans need to remain at the heart of AI
informed decision-making, while breaking down silos and development. Moving forward, the emphasis must be on AI
allowing more voices to be heared than ever before. But how empowering employees across all industries to work smarter,
exactly is Europe faring in the AI revolution? Do employees better and more efficiently. It’s not just a question of bringing
here feel that they are a part of the change and are to market better products and solutions: AI holds the
potential to craft a more sustainable global economy – for
people and for the environment.
AI
4
From challenges to opportunities: How EY and AI work hand in hand
Getting AI right
With a human-centered approach to AI, we help hone
technology to maximize talent, driving efficiency and
Most companies recognize the need to accelerate their AI productivity gains across business functions. EY teams
initiatives to gain a competitive edge. Yet concerns persist of leading multi-disciplinary professionals spanning risk,
as regards the pace of AI adoption and the maturity of strategy, technology, and transformation work hand in hand
solutions. Some caution against overinvesting in tools or use with clients to assist them in an implementation process that
cases likely to become obsolete all too soon. Others question is aligned with their purpose, culture, values, and key
whether the timeline touted by AI visionaries is realistic to stakeholders so that AI drives positive human impact.
unfold a truly transformative impact.
In the following, we gauge the current state of AI in European
There is no shortage of questions, and problems still remain businesses across a range of industries and determine the
unresolved. There is no one-size-fits-all model when it comes level and challenges of adoption, the perceived and captured
to AI. Drawing on the rich experience we have already gained benefits, the impact on the workforce, and approaches
working shoulder-to-shoulder with the clients across a broad to capability building, and cast a glance ahead at the future
spectrum of industries and a huge variety of use cases, we of this rapidly evolving technology.
are convinced that it is possible to create meaningful value
by taking a broad approach to AI and by augmenting people
potential to drive extraordinary outcomes.
Key takeaways
Adoption
Many organizations are still struggling with the operationalization of AI.
Barriers need to be removed; a clear tone from the top is needed.
Benefits
Cost benefits are already evident. The frame needs to be expanded to include
other benefits, including creating more meaningful and attractive work profiles
and hence improved employer branding.
Impact on workforce
AI is certain to have a huge and imminent impact on the workforce across all
sectors and professions. Upskilling is key.
Capability building
Organizations need to accelerate their investment in AI capabilities and make
sure they place their bets on the right technologies in a field that is undergoing
fast-paced innovation and whose future is difficult to predict. Appropriate
training programs are key.
Future of AI technology
AI technology is advancing along many different avenues. Tomorrow’s winners
are already making bold moves today.
5
From challenges to opportunities: How EY and AI work hand in hand
2.
Adoption
Beyond the specifics of where AI can be used, what a lot of decision-
makers want to know is the broader success factors for getting the
most long-term value from implementation. First and foremost, they
want to determine the technological foundations required for AI, with
a strong focus on data and the cloud, and their attention is on making
investments that deliver value. Stakeholders also note the importance
of workforce buy-in and adoption to ensure success at scale, with the
primary focus typically on building employees’ confidence to use AI
to improve their day-to-day efficiency.
The adoption of AI in European businesses continues to Security, accuracy, and explainability are viewed as crucial
evolve, albeit with its fair share of challenges. While the factors on the road to success when implementing AI – more
potential benefits are undeniable, organizations are still so with respect to business viability than ethics. At the top
grappling with operationalization. Barriers to adoption of the agenda are security and privacy, discussed from a
include internal policies, external regulation, and the technical as well as a responsibility angle. Secure internal
complexity of the new technologies. GPT models as well as the need to comply with regulation
(current and future) around data and AI are of high
Although some knowledge workers have been keen to importance to stakeholders and decision-makers.
experiment with AI, others are still reticent. In a recent
survey, EY teams asked members of the workforce from
Hurdles to adoption
all over Europe to share their experience with AI.
Almost three-quarters of all respondents (73%) already have
hands-on experience with AI technologies. Most of them use Organizations face a number of hurdles in the
AI in their private lives (38%), rather than at work (12%). operationalization of AI. For one thing, companies
The remaining respondents (23%) have AI experience themselves often impose restrictive policies on AI use by
in both spheres. employees. In some countries, only a relatively low share
of employees in the EY survey report being permitted by
From a regional perspective, the share of AI early-adopters their employer to use AI applications, most notably in
is highest in Spain (84%), followed by Switzerland (82%) Germany (42%) and Austria (46%). That contrasts markedly
and Italy (77%). On the other end of the scale, early with the situation in Switzerland (73%) and Spain (63%),
adopters are less common in the Netherlands (66%) and where most employees are permitted by their employers
Germany (67%). Men (75%) have experience using AI to use AI applications in their work. The share is likewise
applications more often than women (70%). Differences are relatively high in Portugal (58%), Belgium (57%), Italy (56%),
also evident between ranks, with more than 84% of managers and France (55%), all of which exceed the European average
saying they use or have used AI applications, compared with of 52%.
just 67% of respondents among non-executive employees.
In the following we look at some of the most common Complexity is another issue organizations are grappling
barriers to AI adoption in a work setting. with. Six out of ten respondents (67%) point to the
complexity of the implementation process for AI systems
in their organization. Adding another layer of complexity
6
From challenges to opportunities: How EY and AI work hand in hand
subject to increasing regulatory scrutiny, and Europe “systemic risks”. For instance, low-risk AI such as chatbots
is no exception (see EU AI Act). used in customer service will be subject to few requirements
beyond notifying users that they are interacting with AI.
Another important factor is the tone from the top. In AI intended for high-risk application areas that may impact
Switzerland, most respondents (56%) give their employer health, safety, or fundamental rights of people will have to
a good report card when it comes to the extent to which comply with stricter controls,while some applications areas,
management has a positive attitude as regards making such as subliminal manipulation of vulnerable groups,
progress with AI applications. However, only 5% describe are outright prohibited.
their employer as very open when it comes to implementation.
Switzerland ranks lowest in the category, together To comply with the AI Act, companies will need to clearly
with Germany. assign within their organizations responsibilities for
overseeing AI deployment and compliance. The mandated
The level of adoption of AI varies across Europe, with some responsibility extends beyond technical departments to
countries and sectors embracing it more readily than others. encompass the entire corporate fabric. Non-compliance
However, regardless of geographical location or industry, a exposes companies to severe risks, including heavy penalties
clear tone from the top is essential for successful integration. with maximum fines that even surpass the maximum fines
Leaders need to champion AI initiatives, fostering a culture under the EU’s General Data Protection Regulation (GDPR).
that encourages experimentation and innovation while
Compliance strategy and adaptation
addressing justified concerns about job, displacement,
ethical and legal considerations.
A strategic approach to implementation of AI Act compliance
Regulatory framework
begins with companies identifying gaps in their current
practices and outlining a meticulous plan customized to the
The European Union’s AI Act unifies how AI is regulated specific manifestation of AI deployment in their organizations.
across the single market of the 27 EU member states. It also The approach involves an as-is assessment encompassing
has important extraterritorial implications, as it covers all AI current procedures, employee training levels, and a technical
systems impacting people in the EU, regardless of where understanding of AI solutions, including an exhaustive
these systems are developed or deployed from. The AI Act inventory of the AI solutions deployed in the organization,
aims to standardize the use of AI across all its member what they are used for by whom.
states. Ratified by the European Parliament on 13 March
2024 and approved by the Council of the European Member Given the phased transition period, with enforcement of the
States on 14 May 2024, the act is expected to enter into AI Act prohibitions taking effect within 6 months, obligations
force in June 2024. It introduces a new regulatory for General Purpose AI mode developers starting after 1 year
framework for AI technology focused on the protection of and most of the obligations for high-risk AI applications
safety, security and fundamental rights of people in the EU. coming into force after 2 years, companies must hasten
to adjust their operations and implement the required
Risk and compliance framework
changes in a phased, monitored process. Not only is initial
compliance by the end of the implementation deadline
The AI Act adopts a risk-based approach to compliance critical, it also needs to be accompanied by a sustained
obligations, categorizing AI systems by application areas commitment to adapt to ongoing legislative amendments
and target groups into distinct risk levels. In this tiered and to provide staff with appropriate training at regular
compliance framework most requirements fall upon the intervals. In this way, companies can align with the EU’s
developers and deployers of AI systems classified as goal of ensuring safe AI use without stifling innovation.
“high-risk”, and on general-purpose AI models (including
foundation models and generative AI) deemed to pose
7
From challenges to opportunities: How EY and AI work hand in hand
3.
Benefits
How companies can add value by embedding AI into their products
is a major topic for managers in all sectors. Delivering convenient and
enjoyable experiences, using GenAI to improve chatbots, including
virtual try-on, or current checkout-free stores are prominent examples
that help make AI success stories and progress tangible and visible. In
addition, strategies are often directly linked to revenue generation.
Despite the challenges, the benefits of AI adoption are By function, the use cases in which AI has been
already evident, most notably as measured by cost savings. operationalized vary widely, from streamlining supply chain
However, the narrative surrounding AI benefits needs to be operations to optimizing marketing strategies and enhancing
expanded beyond just financial gains. While cost improvement customer experiences. At present, organizations are seeing
remains a primary driver, AI also enables organizations to the greatest benefits in IT (35%), followed closely by
improve decision-making processes, unlock new revenue marketing (30%) and cybersecurity (27%). Interestingly,
streams, and raise their employer brand value. legal and compliance departments see little scope for
AI implementation at present (see figure 2). That said,
First and foremost, what executives invariably want to know with little more than initial inroads made so far in AI
is their return on AI investment. Across Europe, almost half implementation and operationalization, most eyes are
of managers (45%) say that AI use has allowed them to save still fixed on future iterations of the technology.
costs, increase profits – or both (see figure 1). Measured
by these two criteria, AI deployment to date has been most Aside from cost and efficiency improvements, embracing
successful in Switzerland, where 81% of managers have AI allows businesses to automate repetitive tasks, freeing
had a positive experience with the technology. The share up employees to focus on more strategic and creative
of satisfied managers is also above average in Spain (60%) endeavors. Indeed, most respondents expect artificial
and Italy (58%). On the other hand, respondents intelligence to take over parts of their work (65%), with
in the Netherlands, Austria, and Germany (all 34%) some anticipating that they’ll be handing over some of their
are less impressed. workload to AI in the very near future (14%). If they get
it right, organizations have a tremendous opportunity to
leverage AI to enhance job descriptions. A shift toward
AI
more intellectually stimulating work profiles would not only
improve employee satisfaction but also enhance employer
branding, attracting top talent in a fiercely competitive
labor market. That said, all stakeholders need to address
legitimate concerns about job displacement, an issue we
investigate in the following section.
8
From challenges to opportunities: How EY and AI work hand in hand
Figure 1
?
Has AI already led to cost savings or increased profits within your company?
Switzerland 22% 14% 45% 12% 7%
Spain 20% 21% 19% 26% 14%
Italy 14% 26% 18% 26% 17%
Belgium 17% 17% 13% 38% 15%
France 12% 18% 16% 36% 18%
Portugal 14% 10% 15% 41% 20%
Germany 11% 11% 12% 33% 33%
Austria 12% 12% 10% 32% 34%
Netherlands 8% 12% 14% 38% 28%
Europe West 13% 16% 16% 32% 23%
Yes, we did save costs Yes, we increased revenues Yes, both It is too early to say that No, neither
Figure 2
?
In which area do you think AI can already help improve your business? (up to three answers)
IT 34,5%
Marketing 30,1%
Cyber security 26,6%
Emplyomee support 21,9%
Sales 21,7%
Human ressources 18,7%
Operations 18,7%
Legal/compliance 8,4%
Other 5,1%
I do not think AI can help my business 13,4%
9
From challenges to opportunities: How EY and AI work hand in hand
4.
Impact on workforce
Most of the leading minds in business AI say that employees will
be empowered by the new technology to work smarter and more
effectively. Speed and time savings are emphasized a lot. You often hear
talk of augmenting and freeing up employees – typically in conjunction
with reassurances that AI will not replace them and highlighting how
it will allow them to spend more time on value-added, creative, and
collaborative tasks. While employee efficiency gets the greatest
attention, improvement in other areas is also noted.
As AI technologies continue to advance, they are having Figure 4 shows the general consensus among respondents
an ever-increasing impact on the workforce. Job losses across the nine analyzed European countries, with more than
due to automation are a legitimate concern, particularly one in two (53%) stating that AI applications will influence
in industries with routine, repetitive tasks. However, the their work – or are already doing so. In Italy and Switzerland
broader impact extends beyond displacement, with AI (59% each), the figure is almost six out of ten. The
reshaping job profiles and necessitating new skill sets. proportion is also above average in the Netherlands (57%),
and Austria and Germany (56%). On the other hand, it is
When asked whether the use of AI will lead to job losses, below average in France (47%), Belgium (48%), as well as
respondents’ views vary greatly across European countries. in Spain and Portugal (both 49%).
Overall, slightly more than two out of three respondents
(68%) say that they expect fewer employees will be needed As discussed in the previous section, most respondents
as AI systems become more established and the number and expect artificial intelligence to take over elements of their
scope of use cases increases (see figure 3). The proportion work and redefine their job profiles. Analyzed by country,
is particularly high in Portugal (80%), Spain (78%), Italy more than three out of four respondents in Switzerland
(76%), and Belgium (74%). In contrast, there is somewhat (76%) assume that artificial intelligence will take over some
less concern about job losses as a consequence of AI of their tasks. This if followed by Spain and Portugal (72%
in Switzerland (57%), Germany (59%), and the each), Italy (70%), and Belgium (68%), where employees are
Netherlands (64%). likewise sure that – sooner or later – some of their tasks will
be taken over by applications from the field of AI.
One in three respondents in Italy (34%) expects that the The average among all respondents is 65%. In Germany
new technology will replace human labor on a large scale. (57%) and Austria (59%), the figure is below average.
The figure is similarly high in Portugal (31%). In contrast,
the proportion is significantly lower among respondents in Viewed by rank, managers (72%) are more likely to assume
Germany (14%), Switzerland (16%), and Austria (17%). that they will hand over tasks to AI-powered programs and
machines in the future than non-management employees
(61%). From a sector perspective, oil and gas (91%),
technology, media and telecommunications (81%),
financial services (81%), and insurance (81%) stand out.
10
From challenges to opportunities: How EY and AI work hand in hand
Figure 3
?
Do you think the use of Al will lead to companies needing fewer staff?
Portugal 25% 55% 18% 2%
Spain 18% 60% 20% 2%
Italy 20% 56% 21% 3%
Belgium 22% 52% 19% 7%
France 21% 48% 26% 5%
Austria 20% 45% 26% 9%
Netherlands 15% 49% 28% 8%
Germany 16% 43% 31% 10%
Switzerland 13% 44% 39% 5%
Europe West 19% 49% 26% 6%
Yes, definitely Yes, rather No, not so much No, definitely
Figure 4
?
Do you think your job is affected by the developments around artificial intelligence?
Italy 14% 45% 27% 14%
Switzerland 9% 50% 28% 13%
Netherlands 10% 47% 31% 12%
Austria 12% 44% 31% 13%
Germany 12% 44% 29% 15%
Portugal 11% 38% 30% 21%
Spain 10% 39% 33% 18%
Belgium 10% 38% 33% 19%
France 11% 36% 26% 27%
Europe West 11% 42% 29% 18%
Yes, very strongly Yes, partially No, hardly No, not at all
11
From challenges to opportunities: How EY and AI work hand in hand
On average in Europe, almost one in five respondents (19%) Upskilling and reskilling initiatives are of paramount
say that AI is already influencing their work – in Italy, it is importance to mitigate any negative consequences of
almost one in four (24%), while in Belgium, it is just over AI on employment. Organizations must invest in training
one in ten respondents (12%). programs to equip their workforce with the necessary
competencies to thrive in an AI-driven economy. Additionally,
A sizable 38% of all respondents expect to see a noticeable fostering a culture of lifelong learning is essential to ensure
increase in the influence of AI applications on their jobs that employees remain adaptable and resilient in the face
within the next three years. Here, respondents in of technological disruptions. According to our survey results,
Switzerland (54%) clearly stand out. not enough respondents are satisfied with the level of
training on AI they get at work. Switzerland leads the way,
That said, an interesting dichotomy is evident in that a not where 36% say their employer is providing enough training.
insignificant number of respondents think it unlikely that Employers in other countries need to do a lot better, most
artificial intelligence will take over parts of their work (35%). notably in Portugal, where only 14% of employees are
And of those who do anticipate having to hand over some satisfied with the current level of AI training they are
of their workload to AI, the vast majority don’t see that receiving. Most employees want live training and workshops
happening anytime soon (see figure 5). It appears that a (43%), followed by online courses (38%). In the following
substantial section of the workforce still believes that AI is section, we take a closer look at the investment priorities
not an imminent concern or it’s something that happens to of organizations in AI capabilities, including training.
somebody else. Either way, organizations clearly need to do
more to sensitize sections of the workforce about the scale
and scope of the AI revolution, an area in which training has
critical role to play.
AI
12
From challenges to opportunities: How EY and AI work hand in hand
Figure 5
?
How likely is it in your opinion, that parts of your tasks on the job will be done by programs and applications from the
field of artificial intelligence?
Switzerland 12% 64% 19% 6%
Spain 16% 56% 22% 5%
Portugal 21% 51% 22% 6%
Italy 16% 54% 23% 7%
Belgium 12% 56% 22% 10%
Netherlands 9% 56% 24% 11%
France 16% 47% 27% 10%
Austria 13% 46% 31% 10%
Germany 10% 47% 31% 13%
Europe West 14% 51% 26% 9%
Likely and very soon Likely but it will take some time Unlikely That is not going to happen
Figure 6
?
How likely is it in your opinion, that parts of your tasks on the job will be done by programs and applications from the
field of artificial intelligence?
Europe West Female Male
62,9% 65,7%
9%
14%
Likely and very soon
26% Likely but it will take some time
Management Non-management
Unlikely
That is not going to happen
51%
72,3% 60,7%
13
From challenges to opportunities: How EY and AI work hand in hand
5.
Capability building
With the rapid development of AI in mind, many decision-makers
across various sectors emphasize the need to accelerate AI initiatives
to gain a competitive edge, and are increasing investment accordingly.
Discussion of partnerships to accelerate innovation is common, while
a few are pursuing equity investments in AI specialists. However,
several companies also express concerns regarding the pace and
maturity of AI development, including both those investing and others
taking a more cautious approach. Some warn against overinvesting in
tools or use cases that could soon become obsolete.
To fully leverage the potential of AI, organizations must Analyzed by sector, employees in private equity (71%),
prioritize capability building. Assessing AI readiness is crucial financial services (66%), the energy sector (62%), and
to identify gaps and allocate resources effectively. Holistic advanced manufacturing and mobility (62%) are confident
capability building involves not only investing in cutting-edge of their employers’ ability to pursue the AI
technologies but also cultivating a data-driven culture and transformation journey.
nurturing talent with expertise in AI in all its manifestations,
from machine learning to large language models. Most employees in Switzerland (57%) expect AI to be a top
investment priority in the coming year, followed by Spain
Taking a look at the current situation, employees in (54%). Prospects for AI investment are bleaker in Germany,
Switzerland (58%) are most confident about the where only 25% of respondents expect AI to be prioritized
possibilities for AI implementation in their company. and Austria with a mere 22%.
In Italy, too, a majority (52%) confirm that their employer
has the knowledge and the will to tackle the AI Respondents see new software (35%) and employee
transformation. Employees in Germany (34%) and Portugal qualification (33%) as top investment priorities for their
(35%), on the other hand, are more skeptical about their organization when it comes to AI. Interestingly, forecasting
company’s ability to implement and leverage AI capabilities rank lowest in the list of investment priorities.
(see figure 7). That might seem surprising given the possibilities already
demonstrated by AI-driven high-precision forecasting in
many sectors.
14
From challenges to opportunities: How EY and AI work hand in hand
Figure 7
?
Do you feel that your company has sufficient knowledge to implement and use AI effectively and start the
transformation process that comes with it? Percentage of respondents who answered “yes”.
Switzerland 58,0%
Italy 51,7%
France 45,2%
Spain 41,4%
Belgium 40,4%
Netherlands 39,4%
Austria 37,3%
Portugal 35,2%
Germany 34,0%
Europe West 41,7%
15
From challenges to opportunities: How EY and AI work hand in hand
Taking a closer look at the people factor, managers in In many instances, employees are taking the initiative and
Switzerland (72%) are most confident that their people have availing themselves of self-learning opportunities, be it
adequate training to work effectively with AI or are ready for privately, professionally, or a combination of the two.
the transformation process ahead. This compares with 56% Self-education in the field of AI is most widespread in
in Belgium, 54% in Italy, and 51% in Spain. At the other end Switzerland (60%), Italy (54%), and Spain (54%). Employees
of the scale are Austria and Germany both with 34%. in Germany are least likely to be engaged in self-education
activities (37%), indicating a clear need to sensitize the
Broken down by sector, managers in advanced workforce there as to the importance of AI skills for the
manufacturing (69%) are most confident that their people future of work and their career prospects.
have adequate training to work effectively with AI or are
ready for the transformation process ahead. This compares AI can be a powerful tool in the hands of skilled and
with 65% in financial services, 65% in agriculture, and 63% well-trained employees, promising massive productivity
in private equity. Lagging well behind at only 19% is the gains. Companies need to adopt an active role in training
public sector practice. and upskilling their people. Among other initiatives,
strategic partnerships with academic institutions and
Training programs tailored to the specific needs of each technology providers can also facilitate knowledge
region, sector, and function are essential for ensuring the exchange and accelerate innovation. By investing
successful integration of AI into business operations. in AI capabilities today, organizations can position
Employees are beginning to recognize the imperative themselves as leaders in an increasingly
of honing their AI acumen for their careers, with 44% of competitive landscape.
respondents stating that they are educating themselves
in the field of AI. Revealing a concerning gender bias,
our survey indicates that male employees (49%) are
more likely to be brushing up on their AI skills than their
female colleagues (40%).
AI
16
From challenges to opportunities: How EY and AI work hand in hand
Figure 8
?
Which specific field will be a top investment priority over the next year for your company when it comes to AI?
(up to five answers)
New software 34,5%
Employee qualification 33,0%
Cyber security 26,2%
Optimzing/automating current processes 25,7%
(Data)Analytics 23,3%
New hardware 23,2%
Logistics 20,1%
Manufacturing 17,5%
Analyzing customer/client data 16,6%
Customer contact/services 14,2%
Analyzing in general 12,7%
Accounting 12,7%
Copy writing 12,4%
Analyzing processes within the company 11,4%
Human ressources 10,2%
Controlling 8,7%
Procurement 8,6%
Knowledge management 8,6%
Forecasting 6,4%
Other fields 1,2%
Figure 9
?
Are you educating yours |
3 | ey | ey-gl-adobe-genai-marketing-guide-06-2024.pdf | GUIDE
Leading generative
AI deployment for
marketing.
Overcoming three hurdles in
generative AI adoption.
1
Contents
Executive Summary 3
Thought leaders in generative AI 4
Dial up transparency as you improve the relevance of customer experiences. 4
Be transparent while building your first-party data. 5
Match generative AI to customer expectations. 5
Make customer benefits central to decisions. 6
Amplify creativity without replacing human judgement. 6
Transform skeptical and novice employees to empowered generative AI pros. 6
Prioritize upskilling at all levels. 7
Begin with content creation. 8
Use short-term comparison metrics. 8
Appoint generative AI pioneers. 9
Drive generative AI innovation with confident governance. 9
Map and mitigate novel generative AI risks. 10
Establish a single point of control. 11
Organize your goals into the right sequence. 11
A checklist to start now. 12
Conclusion 13
Methodology 14
Sources 14
About Adobe 15
About EY 15
2
Executive Summary
Generative AI is defining the next generation of marketing We spoke with leading executives around the world across
today. Delivering hyper-personalized, multi-channel customer marketing, creative, CX, data, legal, risk, and compliance.
experiences at a fraction of the time and cost. Helping you glean
insights from your data in an instant. Detecting and responding to We uncovered three primary challenges to generative AI
conversion opportunities in real time. Experimenting to enhance adoption: managing customer privacy and experience
customer experience and deliver results at pace. expectations, transforming employees concerned about their jobs
into champions and innovators, and establishing governance that
This year, 98% of CEOs will invest in their company’s generative enables generative AI innovation to flourish.
AI capability. But 66% remain uncertain of the optimal adoption
path for their organization.1 To assist, Adobe collaborated with Through our interviews with early adopters, we found
the EY organization to undertake a series of structured, these consistent challenges and uncovered resolutions to
qualitative interviews to learn from generative AI first movers. overcome them.
Customers
80
Dial up transparency as you improve the relevance of customer experiences.
%
With generative AI, customers expect improved personalization from brands—but their trust
in organizations to use their data responsibly is limited. Generative AI can help you please your
of customers prioritize
customers with relevant and timely experiences. But to stand out in a crowded field, your focus
knowing when they are
on their needs must be tangible at every touchpoint.
talking to a human being
Resolution: Design every step in your generative AI journey for transparency and accountability or a bot.2
to customers to deliver meaningful experiences they trust.
Employees
Transform skeptical and novice employees to empowered, generative AI pros.
81
% Early adopters are making their first returns on investment in generative AI by automating
lower-value, repetitive tasks, for example, in content production. However, this is also where
employees will be most anxious about role reductions. To make progress, organizations should
Employees expect AI to
reassure and incentivize employees to master the tools, to experiment, and to contribute toward
free them to focus on
the future of their function.
higher-value tasks.3
Resolution: Prove the value of generative AI to employees, demonstrating job enrichment, time
savings, new opportunities, and career advancement.
Organization
#2 Priority
Drive generative AI innovation with confident governance.
Innovation in generative AI can drive efficiency and deliver new opportunities for revenue, but the
Data security and AI
pace at which you realize these gains is dependent on governance. Your external vendors and partners
should offer not just innovative tools, but also responsibly developed ones. You’ll also need your internal governance frameworks
stakeholders to flag the right opportunities, share data, and collaborate on new governance processes to are second only to
work at pace with your vendors.
employee skills in execs’
2024 priorities for AI.4
Resolution: Level up your leadership oversight and governance processes and focus on commercially
safe solutions that help you manage risk while taking advantage of the opportunities generative AI offers.
3
Thought leaders in generative AI.
Adobe and EY specialists are privileged to work with a wide range of organizations around the world,
facilitating their deployment of generative AI especially in the domain of customer experience (CX).
The world’s leading brands and agencies are partnering with Adobe to drive greater efficiency
in their organizations, applying our natively integrated generative AI in Creative Cloud and
Experience Cloud today to empower their teams to boost productivity and deliver personalization
at scale. We believe 2024 will be a watershed moment in developing customer experience.”
Eric Hall
SVP and Chief Marketing Officer,
Digital Experience, Adobe
Far from taking away creative work, we see generative AI supercharging it, creating exponential
value, and putting a new palette of CX capabilities at the fingertips of your whole team, which
further builds confidence. Customer expectations will change in 2024 through exposure to hyper-
personalized experiences. We are inspired by this generational opportunity, and the extraordinary
uses our clients are already making of it, keeping people at the center.”
Laurence Buchanan
Global Customer and Growth Leader, EY
From this experience and discussion with industry leaders we’ve distilled insights to support marketing
and CX leaders as they evaluate, implement, and harness the power of generative AI. This guide
concludes with a checklist to help you assess and refine your immediate priorities this year.
90
%
of $5 billion+ revenue companies remain at proof-of-concept or isolated capabilities in generative AI
Source: May 2023: EY Innovation Realized pulse survey, C-suite executives from majority $5bn+ global companies
4
Dial up transparency as you improve the relevance
of customer experiences.
Adobe’s State of Digital Customer Experience research revealed that 56% of consumers believe that generative AI
will make digital experiences more personalized, 54% believe content will be more relevant to their preferences,
and 53% expect to see an increase in product and service innovation.6
However, generative AI also poses new questions about privacy, transparency, and control. Consumers are
wary—79% are concerned or very concerned about how companies are using their personal data.7 So, CX leaders
must bring the voice of the customer to every part of the business that’s experimenting with this technology.
Marketing leaders must validate that every touchpoint that makes up the brand experience remains meaningful
and authentic. The organization will need their leadership to keep the focus on differentiating the brand and
building trust, regardless of function or touchpoint. On this solid foundation, you can push forward to deliver the
personalization that customers value.
To help resolve the tension between privacy and relevance, take these
actions that we see first movers doing:
Be transparent while building your
first-party data.
Organizations are adapting to a cookieless future by
expanding and enriching their own first-party customer Customer acquisition costs through digital
data, with the right permissions and consents. This also marketing are still pretty high right now. One
means working with your data partners to determine change that motivates is to really think about
how to collaborate to enrich data without relying on your first-party data—what data do we want to
third-party cookies. own and how do we get that data with the right
consent and permissions to be able to use it?”
As you shift to a clear first-party data strategy you must
also set clear expectations as you gather data. One CDO
Laurence Buchanan
at a global consumer packaged goods (CPG) business
Global Customer and Growth Leader, EY
explained to us that offering customers clarity in the
moment about how the company will hold and use
data is essential to winning trust and the consents they
need to engage customers with their augmented reality
experiences.
5
Match generative AI to customer As a creative team, we decided from day one
expectations. that we need to make sure that we’re upfront
about when we’re using AI versus not. Part of
Organizations need guidelines for disclosure around the
why we work with Adobe is because of their
use of generative AI. Regulators and governments do
not always keep up with the rapid pace of change, so stance on ethics. The idea that they’re making
marketing leaders need to champion the best interests sure that they’re pulling everything from their
of their customers. own stock images which are sourced ethically,
that was a big deal for us. They are also
An example of this is to take extra care when leveraging working on creating watermarking, so viewers
generative AI to represent human appearance or voice— know when it was generated by AI, that we can
customers may be upset by mistaking a generative AI then adapt in our marketing material.”
experience for an actual human being. A global CPG
organization commits not to use generative AI for any
Bridget Esposito
front-of-packaging images of people—employing it instead
Vice President, Head of Creative, Brand,
for close-ups where customers expect to see illustrations or
Prudential
infographics. A US top-5 insurer has set similar guidelines
that permit the use of generative AI for creating product
images, but never for images of humans.
Make customer benefits central to decisions.
It’s vital to look beyond immediate business value to target
potential benefits for customers. How are you considering
We have some special opportunities
customer preferences? Could the generative AI you’re
and possibilities to create quite stunning
deploying today make a customer experience more
digital experiences for our customers, or
empathetic, more accessible, or more timely?
to have a much more immersive shopping
experience. That is a super big moon shot
As you weigh your priority initiatives, factor in satisfaction
ratings or other customer experience indicators—to start but you can imagine a tool that would
where the real customer value is and to monitor the generate how a product would look in your
impact on your customer experiences. space. These are real possibilities.”
One multinational retail organization measures the Stefan Esping
impact of their generative AI chatbot not only through Data & Machine Learning Domain Manager,
customer satisfaction ratings, but also by the percentage Ingka
of conversations contained within the chatbot rather than
being transferred to an employee, and any increases in
sales following a chatbot interaction.
Amplify creativity without replacing human judgement.
Have a clear strategy to validate that any generative AI content is true to your brand, creatively enriching, and never generic.
As you free up creative teams from lower-value tasks such as image variation, the team can refocus on larger, more impactful
creative work for your brand.
Additionally, it is critical to apply generative AI via a custom model that can be trained on your own brand content, tone, style,
images, and standards so the outputs retain your brand’s unique traits.
6
First movers tell us they retain a human in the loop to keep consistency in brand messaging, imagery, and tone of voice. This
helps you to guarantee meaningful customer experiences every time.
A technology executive for a CPG company explained that generative AI is already deployed in drafting a significant
proportion of the product copy that’s displayed on retail websites in the US and the UK to engage consumers with their
products’ features and benefits. None of it goes live without human approval. In a global fashion brand, generative AI
develops prompts and visualizations for product designers, drawing on trends harvested from customer sentiment analysis.
Transform skeptical and novice employees to
empowered generative AI pros.
Demonstrate generative AI as a creative, career-building opportunity.
Generative AI creates real opportunity for professional development and career enhancement, but it’s only
natural that some employees may feel anxious around generative AI initiatives within their organizations. This
tension may be the most important blocker you face. You need your teams to have appetite for exploring
generative AI, before they can begin to capture the new opportunities it brings.
98 12
% to %
Reduction in proportion of employees concerned about generative AI after participating in pilot.
Source: January 2024: EY generative AI tool deployment – internal study
The senior executives surveyed in Adobe Digital Trends 2024 cited “advanced AI skills training for key staff” and
“basic AI understanding for all employees” as their top two priorities for preparing their employees to work
effectively with generative AI.8 Assigning pilot projects and letting insight grow organically is an essential first
step. Marketing leaders need to make these opportunities visible and relevant to each team member, to build the
“what’s in it for me” of the technology.
As one leader explained, on average, employees can expect their roles to become more strategic.
Our interviewees recommend content creation and content workflows as tasks that allow you to move swiftly to
demonstrate benefits for employees and customers. In an analysis of a generative AI deployment undertaken by
EY LLP, a 12-week pilot in a specific use case dramatically improved employees’ ability to grasp the opportunity
beyond the risks 9:
■ Understanding the potential of generative AI grew from 37% to 84%
■ Concerns about using generative AI fell from 99% to 12%
■ Confidence in personal ability to work with generative AI improved from 28% to 77%
7
To turn uncertain novices into empowered professionals, marketing leaders need to:
A digital executive in a CPG organization spoke about
Prioritize upskilling at all levels.
building a Center of Excellence. They provided education for
Success depends on the readiness of your teams to leverage
every one of their 10,000 employees to create a common
generative AI tools and processes. To enable them to become
baseline of understanding across every employee, and
fluent in generative AI, define and deliver training programs
published white papers about generative AI on the company
for all employees, from executives to practitioners.
portal. One Global Chief Marketing Officer in professional
services holds “promptathons,” a series of prompting
One marketing leader at a global professional services
sessions to upskill her team in the “art of the prompt.”
firm recommends creating “learning labs” with access to
generative AI tools, giving employees guidance and hands-
Adobe has established an AI Center of Excellence that
on experience with tools to reduce uncertainty. Another
oversees strategic alignment, compliance, and governance of
organization has an internal portal where employees can
AI initiatives. To ensure employees are equipped to apply AI
request a license for pre-approved generative AI tools.
in their roles, Adobe has comprehensive training programs,
resources, and podcasts to upskill the workforce and
personalize career development.
At Shiseido, we prioritize the continuous learning and development of our employees. Through our internal
Digital Academy, we provide accessible programs and certifications in data and AI advancements.
This education is crucial for our team’s success.”
Angelica Munson
Global Chief Digital Officer,
Shiseido
Begin with content creation.
We consistently hear that optimizing content creation or
content workflows is a powerful first move. It’s where your
employees are spending a lot of time and does not require
a lot of data connectivity to get started. Starting points for
generative AI usage in content workflows include: If you think about the previous world, you
■ Creative concepting and ideation would have a great concept, a great idea.
That would take time to really bring to life
■ Copy drafting and iterations
to share with your ‘buyer’. Now generative
■ Image drafting and refinement
AI can bring that idea very quickly to some
■ Production of content variations for testing across: sort of visualization. That speed is a clear
■ different channels benefit.”
■ different markets
■ different personas Duncan Avis
Americas Customer & Growth Leader, EY
Generative AI helps teams overcome the content
scalability challenge, boosting the quality, quantity,
velocity, findability, and reusability of the content you need
to drive personalization across multiple channels.
8
Use short-term comparison metrics. Choose metrics that build confidence:
■ Workplace satisfaction
Several first-movers report success using comparison
metrics to motivate employees and engage budget-
■ Time saved
holders with the before-and-after progress they’re making.
For example, 82% of employees taking part in a global
professional services generative AI pilot reported faster ■ Volume of content created
task completion.10
■ People required
■ Cost per asset
■ Speed to launch
Appoint generative AI pioneers.
In some areas, activating the organization to adopt
generative AI will be similar to change programs you
may have led in the past. The network of early adopters
in your org needs to be experienced in their professional
disciplines and able to mentor others.
To identify your generative AI pioneers across the
organization, start with employees who:
What has worked well for us is taking
■ Have a direct interest in AI capabilities, from the
perspectives of the business, marketing, tech, and risk an employee ‘influencer’ approach by
identifying people who are hungry to
■ Have the skills and appetite to communicate the benefits change, hungry to learn, and building out
and to positively influence employee culture the process with those employees. This
will then be cascaded throughout the
■ Hold aspirational, mid-level roles with a degree of organization more broadly.”
decision-making, managing more junior levels in the
organization
Chris Chesebro
Chief Digital Officer, Wella
■ Are commercially aware and risk-informed, capable of
assessing innovations from both perspectives
Collaborate with them to research and propose a set
of generative AI design principles and equip them to
experiment. Their example and enthusiasm can inspire the
team to move faster and move past any uncertainties.
One CPG organization has chosen 30 employees from
middle management to take part in the first generative
AI pilot in a sandbox environment. They were tasked to
identify risks and share learnings.
9
Drive generative AI innovation with
confident governance.
Develop generative AI controls and partners that can help you navigate risk
and opportunity.
To deliver business outcomes such as cost savings or content acceleration with generative AI, companies must
choose solutions that are built for business use cases. The right generative AI tools will need to meet some
unique criteria and have the right controls in place:
■ The base model must give you transparency into the data provenance and be designed for commercial safety.
■ You must be able to apply custom models that are trained on your own data to keep outputs relevant for
your brand and your business.
■ Your data must be secure and private, not shared with other businesses or used to train a publicly
available model.
■ Your partners should prioritize ethical, responsible AI development to protect your brand.
In addition to careful selection of the generative AI solutions that fit your business, companies must optimize
governance of those tools within their organization. Your existing internal controls framework will need to evolve.
AI governance is not just about setting rules, it’s about striking the right balance. It’s about
fostering creativity and innovation while ensuring accountability, responsibility, and transparency.
At the heart of AI governance is the commitment to respect our customers and align with our
values. It’s about turning AI potential into real-world applications, responsibly and ethically.”
Cynthia Stoddard
CIO of Adobe
10
To unleash the full potential of innovating in generative AI,
leaders have learned how to:
Map and mitigate novel generative AI risks.
Use an evaluation framework for generative AI tools that
screen for solutions with responsibility engineered into
their tools, including:
■ Clear intellectual property rights accounted for and
indemnification provided to minimize lawsuit risk
I don’t want to use an AI that’s been trained on
■ Robust security and privacy of your data non-licensed materials. We expect our bigger
■ Fairness and bias controls built-in agencies to self-certify for responsible practices
and we will write it into their contracts.”
■ Transparency in how models are built
Select vendors and partners who are passionate about IT Engineering Director,
preserving intellectual property and content credentials Global packaged good organization
and are helping to guide global regulation. Check if they
participate in industry standard-setting, for example
in the Content Authenticity Initiative, the NIST AI Risk
Management Framework or the EU AI Elections Accord. By
thinking ahead of regulations, these vendors will help to
future-proof your developing generative AI capability.
Establish a single point of control.
As marketing organizations move generative AI from
pilot to production, they need “air traffic control”—a
team comprising marketing, compliance, and technology
It’s crucial for marketing to be positioned
heads—to coordinate and direct generative AI development
at the heart of an AI control tower strategy,
across the organization. They will:
serving as a central hub that coordinates with
■ Define and communicate a governance framework for
legal, cybersecurity, privacy, and technology
generative AI
stakeholders to harness and action data
■ Assess risk for new generative AI vendors and proposals insights effectively. This centralized approach
helps establish that the CMO and marketing
■ Prioritize for customer and commercial relevance
teams are integral to the collaborative network,
■ Direct capital investment in generative AI
facilitating a unified direction and decision-
making across the various departments, to
This control function should be a distinct practice of an
overall delivery-focused generative AI Center of Excellence, move at the speed of business while mitigating
whose scope it is to govern: risk.”
■ The business model—generative AI opportunities
Tom Edwards,
for product portfolios, value proposition, growth
Managing Director,
opportunities
Applied & Generative AI Lead, EY
■ The operating model—generative AI potential to reduce
cost, accelerate, evolve the organization
■ Risk management—identifying and mitigating novel
11
risks, such as data privacy, bias, IP, and so on
11
Organize your goals into the right sequence.
A key role for leaders governing generative AI in their organization is to recognize the different ways it affects customers
and employees and to sequence your projects to suit.
Aim to prove concepts and cultivate skill and insight within the team before taking on more complex use cases.
The typical order, from simple to complex, will be:
Integrate vendor tools into your content creation
workflows to add creative uplift, scale, and
accelerate content production.
In parallel to your content creation
opportunities, kick off work to audit, connect,
clean, and structure your data. This will help
you prepare for more data-heavy generative
Develop customized content using generation AI use cases like personalization.
models trained on proprietary content, brand
guidelines, and historic campaigns.
Personalize marketing campaigns—build tailored messaging, content, and journeys
across channels for each customer.
Harness unstructured data by using generative AI to query, gather, and democratize insights from broad
datasets. This also helps you strengthen your personalized marketing campaigns noted above.
12
A checklist to start now.
To get started now and deliver on the full potential of generative AI in marketing and CX, organizations
should focus on the following key areas identified from our research with marketing leaders and subject
matter experts:
1. Customer trust
■ Do we have a list of customer pain points?
■ Is customer experience fully visible and factored into the way we assess generative AI priorities?
■ Have we defined specific customer-centric principles for uses of generative AI?
■ Does our existing research gather data on customer attitudes to generative AI?
■ Have we reviewed current brand guidelines to fit with generative AI applications?
2. Employee empowerment
■ Do we have a cross-functional list of employee pain points?
■ Do we have the right communications plan and training resources in place?
■ Do we have experiments up and running—and are we capturing what we learn?
■ Have we created space for open-ended innovation during generative AI discovery and experimentation?
■ Does the team have a mandate to discover its own metrics as projects progress?
■ Are we investing in generative AI training for all levels?
■ Have we created simple, accessible ways for employees to access and familiarize themselves with generative AI tools?
■ Are we refining roles and responsibilities to keep a human in the loop?
■ Have we defined scope and nominated advocates for a network of generative AI champions?
3. Organizational opportunity
■ Do we have an evaluation process in place to screen tools for risk mitigation?
■ Do we understand where generative AI is being assessed or implemented across the organization?
■ Is there a team in place applying a common framework or governance to align and maximize benefits?
■ Have we defined an efficient process to evaluate and implement generative AI technology in partnership with our
technology and legal peers?
■ Are we clear how our vendors and strategic partners’ generative AI initiatives map to our needs? Have we made full use
of their advice and resources?
■ Have we considered our customers and employees in the sequencing of our generative AI initiatives?
■ Is our mid- to long-term data transformation plan defined?
13
Conclusion
Leading the marketing function in the era of
generative AI.
Generative AI is here to stay as a transformative force across every part of the organization. But it has special
relevance for marketing and CX. In some capacity, 83% of creative professionals are already using generative AI
tools in their work. Among Gen-Zs, it’s above 90%.11
As a marketing or CX leader, applying generative AI means designing a plan for the marketing function that helps
drive profitable demand, inspires your employees, and enriches the customer experiences you deliver. It’s critical
to keep these three challenges in mind at every step: for your organization, your employees, and your customers.
Methodology
Structured interviews were conducted with participants in 30-, 45-, or 60-minute sessions with external
organizations (n=11) and subject matter experts (n=10).
Sample consisted of participants from across marketing, CX, digital, data, legal, and creative.
Focus of the discussion looked to explore relevant use cases, partnerships, and lived experiences from individuals
in the support of, exploration, and deployment of generative AI within a commercial context to gather lived
experiences and practical advice from participants.
Sources
1 EY CEO Imperatives quarterly update, January 2024
2 Adobe Digital Trends 2024, March 2024
3 EY - US, How organizations can stop skyrocketing AI use from fueling anxiety, October 2023
4 Adobe Digital Trends 2024, March 2024
5 EY Innovation Realized pulse survey, C-suite executives from majority $5bn+ global companies, May 2023
6 Adobe, The State of Digital Customer Experience Report 2023, October 2023
7 Adobe Trust Report - Customer trust is earned or broken with every experience, March 2022
8 Adobe Digital Trends 2024, March 2024
9 EY generative AI tool deployment – internal study, January 2024
10 EY generative AI tool deployment – internal study, January 2024
11 Adobe Blog - Creative pros are leveraging Generative AI to do more and better work, February 2024 14
ABOUT ADOBE
Adobe Experience Cloud is the most comprehensive suite of customer experience management
tools on the market. With solutions for data, content delivery, commerce, personalization, and
more, this marketing stack is created with the world’s first platform designed specifically to
create engaging customer experiences. Each product has built-in artificial intelligence and works
seamlessly with other Adobe products. And they integrate with your existing technology and
future innovations, so you can consistently deliver the right experience every time.
ABOUT EY
EY exists to build a better working world, helping create long-term value for clients, people and
society and build trust in the capital markets. Enabled by data and technology, diverse EY teams
in over 150 countries provide trust through assurance and help clients grow, transform and
operate. Working across assurance, consulting, law, strategy, tax and transactions, EY teams ask
better questions to find new answers for the complex issues facing our world today.
EY refers to the global organization, and may refer to one or more, of the member firms of Ernst
& Young Global Limited, each of which is a separate legal entity. Ernst & Young Global Limited, a
UK company limited by guarantee, does not provide services to clients. Information about how
EY collects and uses personal data and a description of the rights individuals have under data
protection legislation are available via ey.com/privacy. EY member firms do not practice law
where prohibited by local laws. For more information about our organization, please visit ey.com.
© 2024 EYGM Limited. All Rights Reserved.
EYG no. 005649-24Gbl
This material has been prepared for general informational purposes only and is not intended to be relied upon as accounting, tax, legal or other professional advice.
Please refer to your advisors for specific advice. The views of third parties set out in this publication are not necessarily the views of the global EY organization or its
member firms. Moreover, they should be seen in the context of the time they were made.
15 |
4 | ey | ey-idc-maketscape-worldwide-ai-services-2023-vendor-assessment.pdf | IDC MarketScape
IDC MarketScape: Worldwide Artificial Intelligence Services
2023 Vendor Assessment
Jennifer Hamel
THIS IDC MARKETSCAPE EXCERPT FEATURES EY
IDC MARKETSCAPE FIGURE
FIGURE 1
IDC MarketScape Worldwide Artificial Intelligence Services Vendor Assessment
Source: IDC, 2023
Please see the Appendix for detailed methodology, market definition, and scoring criteria.
May 2023, IDC #US49647023e
IN THIS EXCERPT
The content for this excerpt was taken directly from IDC MarketScape: Worldwide Artificial Intelligence
Services 2023 Vendor Assessment (Doc # US49647023). All or parts of the following sections are
included in this excerpt: IDC Opinion, IDC MarketScape Vendor Inclusion Criteria, Essential Guidance,
Vendor Summary Profile, Appendix and Learn More. Also included is Figure 1, 2 and 3.
IDC OPINION
This IDC study represents a vendor assessment of the 2023 artificial intelligence (AI) services market
through the IDC MarketScape model. IDC last assessed this market in 2021. In the past two years, we
have revised our evaluation criteria and buyer perception survey instrument to refine our assessment
methodology and reflect market evolution. Thriving vendors in today's AI services market can both
clearly articulate their strategies for enabling clients' adoption of AI solutions and readily demonstrate
their current capabilities and proof points through existing client engagements.
Organizations increasingly look to AI solutions to drive revenue and profit growth as well as improve
outcomes in areas such as customer satisfaction, operational efficiency, sustainability, process speed
and accuracy, and speed to market for new products and services. However, many challenges persist,
including employees' lack of data literacy and technology training, technical complexity, lack of
resources to support end users and maintain AI systems, and issues related to security, privacy, and
governance. Professional services firms remain a critical source of expertise, skills, and tools to
incorporate AI into digital business strategies, build production-grade solutions, and realize ROI.
In this assessment, IDC evaluated AI services vendors across scoring criteria and collected feedback
from customers on their perception of the key characteristics and the capabilities of these vendors.
Key findings include:
▪ The most critical vendor attribute for successful AI services engagements, according to IDC's
Artificial Intelligence Services Buyer Perception Survey, remains "ability to achieve business
outcomes." The perceived priority of this attribute over all others was unchanged from the
2021 study.
▪ When buyers were asked about the primary business objective driving their engagement of
their artificial intelligence services vendor, at a worldwide level, the most frequent responses
were "improve operational efficiency," "build capability for tomorrow's business," and "drive
higher revenue growth, gain market share." Nearly 30% of the buyers we surveyed said they
achieved 30% or greater improvement in measurable KPIs from their AI services engagement.
▪ The top-rated vendor attribute, in aggregate, was the ability to "integrate vendor project team
with internal team." This aligns with IDC's evaluation of client adoption strategies around
workshops and stakeholder alignment and AI program enablement as top areas of strength on
average across AI services vendors.
IDC MARKETSCAPE VENDOR INCLUSION CRITERIA
This research includes analysis of AI services providers with global scale and broad portfolios
spanning IDC's research coverage. This assessment is designed to evaluate the characteristics of
each firm — as opposed to its size or the breadth of its services. In determining the group of vendors for
analysis in this IDC MarketScape, IDC considered the following set of inclusion criteria:
©2023 IDC #US49647023e 2
▪ Worldwide AI services revenue of at least $100 million over the last calendar year, with
revenue generated in each major geographic region (i.e., Americas, EMEA, and Asia/Pacific)
▪ Offerings across the life cycle of AI business and IT services (e.g., project-based, managed,
support, and training)
▪ AI services offerings and solutions addressing a range of industry verticals and business
functions
▪ Go-to-market alliances with a range of AI software providers
ADVICE FOR TECHNOLOGY BUYERS
▪ Maturity assessment. Challenges exist at every stage of the AI adoption journey that often
require expert advice to navigate. Look for services firms to assess your organization's AI
maturity, readiness, talent, and data needs and assist you with creating or refining AI
strategies and operating models to achieve specific business objectives and prepare you for
the next stage of adoption. Even organizations with previously established AI programs may
find your strategies and governance frameworks need adjustment to consider new implications
(ethical, regulatory, or otherwise) of generative AI capabilities and to incorporate appropriate
guardrails for developing and using the technology.
▪ Use case development. In today's economic climate, there is a heightened need to connect AI
solution innovation to real business outcomes. Seek a services partner that can provide
frameworks, methodologies, and tools to help you source innovation ideas from within your
business, discover and prioritize use cases, define KPIs for measuring business value, create
a strong innovation foundation across your organization, and produce deployable and scalable
AI solutions. As several of the customer reference interviews IDC conducted for this study
indicated, vendors' industry and functional domain knowledge gained from experience working
with many different customers helps accelerate the process of identifying and developing
impactful AI use cases.
▪ Skills. AI talent gaps are neither new nor abating for organizations anytime soon. IDC research
suggests that organizations will not solve their AI talent issues by merely hiring more data
scientists. Seek a services partner that can provide expertise not only in core AI model
development and your chosen AI platform but also in scaling and operationalizing AI models
(whether custom-developed algorithms or repurposed "off the shelf" solutions) and in
empowering your business end users to leverage AI-driven insights in their roles. Also,
consider guidance and support from services partners beyond staff augmentation to help you
build AI skills in your organization. Ask for best practices, recruiting resources, access to on-
demand AI talent pools, and pod-based or build-operate-transfer models that enable your
employees to learn AI skills while working with expert teams.
▪ Innovation and delivery accelerators. The fundamental value that AI services vendors offer is
helping customers achieve ROI from AI more quickly than they would on their own. Consider
the proprietary assets that vendors may propose as part of their AI services offerings, which
can include pretrained industry- or function-specific models, reusable component repositories,
curated and annotated training data sets, developer tools and microservices, and even full-
fledged products and platforms. These assets can fill gaps in commercial software products,
address specific business domain or technical challenges (such as integrating legacy
enterprise systems with new AI capabilities), or industrialize AI solution development and
management. Also consider the ecosystem of partners that AI services vendors collaborate
with to provide access to innovation that benefits your organization.
©2023 IDC #US49647023e 3
▪ Stakeholder alignment. According to IDC's Artificial Intelligence Services Buyer Perception
Survey, the most common project sponsors for AI services engagements were CIOs/CTOs,
information technology (IT) directors and managers, chief analytics/data officers, and line-of-
business (LOB) heads. Choose a vendor that can work across IT, LOB, and data teams to
ensure solutions address key stakeholder priorities. Buyers also rated "knowledge
transfer/training for our internal team" as one of the top 10 most critical attributes for AI
services engagement success. Seek out vendors that not only speak with budget holders but
also communicate effectively with end users, who will be interacting with and supporting AI
solutions, through workshops and change management programs.
▪ Data and AI governance. Strong foundations for data quality and privacy, responsible AI, and
MLOps are critical for enterprise-grade AI solutions that are both functional for business needs
and compliant with regulatory and risk management requirements. Seek services providers
that offer thought leadership and frameworks for data privacy, responsible AI, and MLOps and
proactively help you consider these issues as early as possible in the design process, as well
as through the deployment and monitoring of solutions, to mitigate potential risks.
▪ Vendor selection. Use this IDC MarketScape in contract negotiations and as a tool to not only
short list vendors for AI services bids but also evaluate vendors' proposals and oral
presentations. Make sure you understand where these players are truly differentiated and take
advantage of their expertise, technical, industry base, or otherwise.
VENDOR SUMMARY PROFILES
This section briefly explains IDC's key observations resulting in a vendor's position in the IDC
MarketScape. While every vendor is evaluated against each of the criteria outlined in the Appendix,
the description here provides a summary of each vendor's strengths and challenges.
EY
According to IDC analysis and buyer perception, EY is positioned in the Leaders category in this 2023
IDC MarketScape for worldwide artificial intelligence services.
EY places data and AI at the core of its Transformation Realized approach, which aims to enable
clients to envision their future business models and then design transformations that develop technical
capability at scale and manage organizational change. The firm's offerings cover both direct expansion
of large-scale AI programs and infusion of AI into transformational programs driven by C-suite buyer
agendas. Increasingly, EY integrates resources from its AI practice with strategy consultants from EY-
Parthenon to engage with boards and to shape AI strategies and has recently launched a generative
AI strategy and road map offering. The firm also continues to invest in proprietary technology
capabilities on the EY Fabric Intelligence ecosystem to provide responsible AI solutions (ShEYzam
including fairness as a service, NLP as a service) and reusable assets (e.g., EY Lighthouse). EY has
also created a collection of prebuilt AI solutions made available to clients through a marketplace called
EY ASpace. EY also leverages strategic partnerships with AI technology providers such as Microsoft,
SAP, IBM, Databricks, and Snowflake to codevelop solutions in quickly evolving areas such as
fairness, sustainability, and generative AI.
Strengths
According to customers, EY's strengths are the company's ability to deliver across the life cycle of AI
services, provide solutions using their preferred AI technology providers, integrate EY's project team
with their internal team, deliver AI-enabled automation services, and resolve problems or issues
©2023 IDC #US49647023e 4
related to customer service. IDC considers EY's strategies around offerings, platform-based delivery,
client adoption, sales enablement, alliances, growth, innovation and R&D, technology skills, and
employee retention as key strengths. EY also showcased strengths in achieving business outcomes
for clients with AI services.
Challenges
IDC believes EY's go-to-market strategy, though strong overall, could be improved further by more
collaboration with specialist AI software providers and data annotation services or crowdsourcing
providers on go-to-market initiatives for AI services. EY could also benefit from continued investment
in new asset-based AI services.
APPENDIX
Reading an IDC MarketScape Graph
For the purposes of this analysis, IDC divided potential key measures for success into two primary
categories: capabilities and strategies.
Positioning on the y-axis reflects the vendor's current capabilities and menu of services and how well
aligned the vendor is to customer needs. The capabilities category focuses on the capabilities of the
company and product today, here and now. Under this category, IDC analysts will look at how well a
vendor is building/delivering capabilities that enable it to execute its chosen strategy in the market.
Positioning on the x-axis, or strategies axis, indicates how well the vendor's future strategy aligns with
what customers will require in three to five years. The strategies category focuses on high-level
decisions and underlying assumptions about offerings, customer segments, and business and go-to-
market plans for the next three to five years.
The size of the individual vendor markers in the IDC MarketScape represents the market share of each
individual vendor within the specific market segment being assessed.
IDC MarketScape Methodology
IDC MarketScape criteria selection, weightings, and vendor scores represent well-researched IDC
judgment about the market and specific vendors. IDC analysts tailor the range of standard
characteristics by which vendors are measured through structured discussions, surveys, and
interviews with market leaders, participants, and end users. Market weightings are based on user
interviews, buyer surveys, and the input of IDC experts in each market. IDC analysts base individual
vendor scores, and ultimately vendor positions on the IDC MarketScape, on detailed surveys and
interviews with the vendors, publicly available information, and end-user experiences in an effort to
provide an accurate and consistent assessment of each vendor's characteristics, behavior, and
capability.
Market Definition
IDC defines AI as systems that learn, reason, and self-correct. These systems hypothesize and
formulate possible answers based on available evidence, can be trained through the ingestion of vast
amounts of content, and automatically adapt and learn from their mistakes and failures.
Recommendations, predictions, and advice based on this AI provide users with answers and
assistance in a wide range of applications and use cases.
©2023 IDC #US49647023e 5
AI services are utilized to assess, plan, design, implement, and operate the following:
▪ AI platforms facilitate the development of artificial intelligence models and applications,
including intelligent assistants that may mimic human cognitive abilities.
▪ AI applications include process and industry applications that automatically learn, discover,
and make recommendations or predictions.
Detailed definitions of the software tools and platforms that are relevant for AI services engagements
are available in IDC's Worldwide Software Taxonomy, 2023 (IDC #US50513623, April 2023). The
underlying data services are a critical component to AI systems, serving as the basis upon which initial
analysis and learning are conducted. Data services are highly specific to the function and process of
the AI system and may come from a wide range of sources, both unstructured and structured. These
data services include the processes needed to ingest, organize, cleanse, and utilize the data within the
AI-enabled applications.
AI services providers engage with clients to build AI capabilities through business services and IT
services (see Figure 2). For a detailed definition of the services markets illustrated in Figure 2, see
IDC's Worldwide Services Taxonomy, 2022 (IDC #US47769222, July 2022).
FIGURE 2
Artificial Intelligence Services
Source: IDC, 2023
Customer Perceptions of AI Services Vendors
A significant and unique component of this evaluation is the inclusion of the perceptions of AI services
buyers of both the key characteristics and the capabilities of the vendors evaluated. The buyers
participating in IDC's Artificial Intelligence Services Buyer Perception Survey have partnered with at
©2023 IDC #US49647023e 6
least one of the participating vendors directly on an AI services engagement within their company. The
survey findings highlight key areas where buyers expect AI services providers to showcase a range of
capabilities. The buyers consider these capabilities a must-have for AI services to be able to fulfill the
requirements of many business and IT issues that challenge the buyers.
Figure 3 illustrates the order of factors important for a successful AI services engagement for the AI
services customers surveyed in 2023. Survey findings suggest that the ability to achieve desired
business outcomes by the consulting and delivery teams working on an AI services engagement is the
most critical factor for the successful completion of the engagement. Customers also indicated a
vendor's ability to create quality data sets and pipelines for AI model training, provide quality skills in
and knowledge of AI, provide technical insights and competency, and provide security and governance
of AI algorithms, APIs, and training data to be among the most critical attributes for an engagement's
success.
©2023 IDC #US49647023e 7
FIGURE 3
Top 10 Factors for Successful Artificial Intelligence Services Engagements, 2023
Q. In order for an AI services engagement to be successful, please indicate the importance of
each of the following characteristics.
n = 116
Note: Mean scores are based on a scale of 1–5, where 1 is highly detrimental to success and 5 is essential to success.
Source: IDC's Artificial Intelligence Services Buyer Perception Survey, 2023
©2023 IDC #US49647023e 8
LEARN MORE
Related Research
▪ Artificial Intelligence Services Findings from Enterprise Intelligence Services Survey, 2022
(IDC #US49230423, January 2023)
▪ IDC FutureScape: Worldwide Artificial Intelligence and Automation 2023 Predictions (IDC
#US49748122, October 2022)
▪ Market Analysis Perspective: Worldwide Analytics and Intelligence Automation Services, 2022
(IDC #US48206022, September 2022)
▪ Worldwide Artificial Intelligence Services Forecast, 2022–2026 (IDC #US48206222, August
2022)
▪ Worldwide and U.S. Artificial Intelligence Services Market Shares, 2021: Adapting to Evolving
Client Needs (IDC #US48206622, August 2022)
▪ IDC's Worldwide Services Taxonomy, 2022 (IDC #US47769222, July 2022)
▪ IDC MarketScape: Worldwide Artificial Intelligence Services 2021 Vendor Assessment (IDC
#US46741921, May 2021)
Synopsis
This IDC study represents a vendor assessment of the artificial intelligence (AI) services market
through the IDC MarketScape model. This assessment discusses both quantitative and qualitative
characteristics that explain success in the AI services market. This IDC MarketScape covers a variety
of vendors participating in the AI services space. The evaluation is based on a comprehensive and
rigorous framework that assesses vendors relative to the criteria and to one another and highlights the
factors expected to be the most influential for success in the market in both the short term and the long
term.
"With rising public awareness of AI capabilities, spurred most recently by the ability to interact with
free, web-based generative AI tools, organizations are feeling pressure to move faster to incorporate
AI into digital business strategies or risk being left behind by competitors," says Jennifer Hamel,
research director, Analytics and Intelligent Automation Services at IDC. "Successful AI services
providers continue to evolve their portfolios to meet ever-evolving client needs while remaining trusted
advisors to cut through hype and hysteria, set reasonable expectations for what AI can and should do
for their businesses, and develop road maps for adopting and managing AI solutions at scale."
©2023 IDC #US49647023e 9
About IDC
International Data Corporation (IDC) is the premier global provider of market intelligence, advisory
services, and events for the information technology, telecommunications and consumer technology
markets. IDC helps IT professionals, business executives, and the investment community make fact-
based decisions on technology purchases and business strategy. More than 1,100 IDC analysts
provide global, regional, and local expertise on technology and industry opportunities and trends in
over 110 countries worldwide. For 50 years, IDC has provided strategic insights to help our clients
achieve their key business objectives. IDC is a subsidiary of IDG, the world's leading technology
media, research, and events company.
Global Headquarters
140 Kendrick Street
Building B
Needham, MA 02494
USA
508.872.8200
Twitter: @IDC
blogs.idc.com
www.idc.com
Copyright and Trademark Notice
This IDC research document was published as part of an IDC continuous intelligence service, providing written
research, analyst interactions, telebriefings, and conferences. Visit www.idc.com to learn more about IDC
subscription and consulting services. To view a list of IDC offices worldwide, visit www.idc.com/offices. Please
contact the IDC Hotline at 800.343.4952, ext. 7988 (or +1.508.988.7988) or [email protected] for information on
applying the price of this document toward the purchase of an IDC service or for information on additional copies
or web rights. IDC and IDC MarketScape are trademarks of International Data Group, Inc.
Copyright 2023 IDC. Reproduction is forbidden unless authorized. All rights reserved. |
5 | ey | ey-the-aidea-of-india-2025-how-much-productivity-can-genai-unlock-in-india.pdf | How much
productivity
can GenAI
unlock in India?
The AIdea of India: 2025
The AIdea of India: 2025 1
2 The AIdea of India: 2025
stnetnoC
Foreword
Chapter 1
Generative AI:
Shaping tomorrow
Executive
summary
Chapter 2
Pivoting to
AI-first digital
transformation
40
:on
egaP
60
:on
egaP
41
:on
egaP
23:on
egaP
Chapter 3
Chapter 6
Transforming work
Policy agenda
with GenAI
for India
Chapter 4
Industries in
transformation Annexures
Chapter 5
Government
Services
The AIdea of India: 2025 3
84
:on
egaP
85
:on
egaP
011
:on
egaP
611
:on
egaP
421
:on
egaP
Foreword
Over the past few years, innovation possible to use open-source models for as
in Generative AI (GenAI) has low as a few thousand rupees a month
progressed at an extraordinary in India.
pace, reaffirming its transformative
Yet, amidst all this innovation, enterprise
potential across a number of domains.
adoption rates of GenAI remain very low.
The possibilities are vast and hold the
Our survey shows that 36% of Indian
promise of profound changes on the
enterprises have allocated budgets and
horizon for millions of Indian citizens.
begun investing in GenAI, while another
Technical breakthroughs have been jaw 24% are testing its potential. Technology
dropping. We have quickly moved from sector clients are leading the way, with
auto-complete chatbots to reasoning Life Sciences and Financial Services
machines capable of spinning out following suit. Despite this, the business
credible, human like ‘Chains of Thought’ value remains limited, with just
(CoT) to find solutions to complex 15% having GenAI workloads in
problems. Today, multi-modal large production and only 8% able to fully
language models (LLMs) can enable measure and allocate AI costs.
seamless processing of text, audio,
This is not surprising – it takes time for
image, and video. Emerging trends like
innovation to be packaged and made
Agentic AI are enabling autonomous
ready for enterprise adoption. Enterprises
entities capable of taking actions. The
need clarity on ROI and guarantees
evolution of new hardware platforms
around issues like hallucination, data
and new AI accelerators has ensured
privacy and algorithmic bias as they craft
the computational power to support
their digital transformation roadmaps.
increasingly sophisticated models,
Over the next few years, we expect an
having even a trillion parameters and
explosion of enterprise adoption as these
groundbreaking efficiency.
issues are addressed and AI and GenAI
Along the way, the cost of intelligence models make their way into the
has fallen, driven by the open-source enterprise mainstream.
movement and the trend to use purpose
Just as during the earlier era of mobile
specific small language models (SLMs).
disruption, fintech and healthtech
This is making AI accessible to smaller
enterprise adoption will lead to the birth
businesses and very soon it may become
4 The AIdea of India: 2025
of AI-first companies with new business potential as the use case and data capital
models and revamped economics. These of the world. The focus will need to be on
firms will compete with digital interfaces enhancing data accessibility and compute
powered by chat, voice and regional infrastructure, fostering AI research
language models. Algorithms and new and innovation through initiatives like
datasets will help drive population-scale localized LLMs, and addressing challenges
operations. AI-driven apps will transform in responsible governance, intellectual
knowledge work. property rights, and data protection.
On the other hand, we need to address
The coming wave of change has
the coming potential job dislocation in
significant implications for India.
the workforce by implementing
In industries like financial services,
aggressive skilling programs and
healthcare and retail, we expect AI
apprentice schemes.
to reshape basic processes including
customer acquisition, operations and This report is an in-depth exploration
service. Industries including IT/ITeS and of GenAI’s current state in Indian
BPO will undergo more dramatic changes. enterprises, key trends shaping its
Next-generation industries like biotech, future, and implications for Indian
advanced manufacturing and renewables enterprises and policymakers.
will have the potential to leapfrog to
I hope you find this report valuable
AI-first business models.
- happy reading!
Our analysis reveals that, at a macro
level, the AI platform shift will impact
38 million employees, potentially
driving a 2.61% boost in productivity
by 2030 in the organized sector.
Enterprises will need to reorient Rajiv Memani
themselves rapidly to deal with this
Chairman and CEO,
coming impending tides of change.
EY India
There will also be significant pressure
on India’s policy agenda. On one hand,
there is the imperative to realize India’s
The AIdea of India: 2025 5
6 The AIdea of India: 2025
Executive
summary
Th e entire earth will be be paired with practical applications that solve
converted into a huge real-world problems, empower users, and bridge gaps in
brain, as it were, capable digital access and infrastructure.
of response in every one of its
parts.” This was Nikola Tesla, in
1904, predicting the impact of Innovation in GenAI continues at
the radio on the world.
a scorching pace
Every generation believes
it stands on the brink of
Innovation in GenAI surged in 2024, marking a
transformation, fueled by the
transformative year for the technology.
technologies of its time. Today,
as we contemplate the AI era, There was rapid progress in Multimodal AI, integrating
it feels like one of those pivotal text, images, audio and video into unified models that
moments. On one hand, there significantly enhance real-world usability. This was
is exponential innovation — particularly evident in the incorporation of these models
AI’s promise is vast, with the into AI-powered phones and emerging form factors like
potential to revolutionize smart glasses, enabling seamless and intuitive interactions
industries, redefine work, across diverse applications.
and unlock unprecedented
The open-source movement gathered steam. Leading
creativity and productivity.
open-source large language models (LLMs) such as
Breakthroughs in GenAI have
Meta’s Llama 3 and Mistral Large set new benchmarks for
been astounding, and the
performance while addressing critical concerns about data
possibilities appear limitless.
privacy and security. Simultaneously, there was a growing
Yet, there is the critical challenge realization that smaller, domain-specific models could
of making this transformation often outperform their larger counterparts in
relevant and accessible to targeted tasks.
consumers and enterprises. For
Year 2024 also saw breakthroughs in reasoning. Models
AI to truly deliver on its promise,
such as OpenAI’s GPT-4o31, and Google’s AlphaProof2
cutting-edge innovation needs to
1. https://openai.com/index/deliberative-alignment/
2. https://www.ebi.ac.uk/training/online/courses/alphafold/inputs-and-outputs/a-high-level-overview
The AIdea of India: 2025 7
GenAI in India: The current state of play
EY India’s C-suite GenAI survey
We conducted an in-depth GenAI survey covering more than 125 C-suite executives across India. They
represent diverse sectors, including Financial Services, Retail, Life sciences, Media and Entertainment,
Technology, Automotive, Industrials and Energy.
GenAI journey GenAI strategy: Direction and alignment
Integration with existing software means enterprises’ More than half of the enterprises have a GenAI strategy
exposure to GenAI is high. However, only a few have the but only some have a fully integrated strategy with clear
technology in production. execution plans
Fully integrated strategy
12% 22% with clear execution plans
36%
11% Strategy aligned with
business goals, but
34% 15% 18% execution plans are lacking
8% Strategy exists, but not
30% 9% aligned with business
goals
Basic understanding, no
POCs completed Productionalization in progress formal strategy
POCs in progress AI adopted
No POCs done No clear impact 39% No clear strategy
Architecture: GenAI platform and Implementation: Buy versus build
integration approach approach
Architecture integration is limited and enterprises are Approximately one in four have defined approach but
looking at ways to increase application application is uneven
11% Fully integrated and 16% 10% Well-defined and
19% optimized platform c ao pn ps rois at ce hntly applied
Integrated architecture in
4% place; facing utilization Defined approach, but
challenges not consistently applied
Platform selected; Preliminary approach, not
integration just started fully defined or executed
Platforms identified, but 21% Aware of options, but no
no integrated architecture clear decision framework
43% 23% N ino te p gl ra at tfo ior nm a s pe pl re oc ate cd h / 21% 32% N vso . c bo un ils di d ye er tation of buy
defined
Data: Platform readiness for GenAI Talent: Resource availability for GenAI
adoption adoption
Enterprises in India are at different stages of data AI expertise is a key need for most enterprises as they
readiness, with only a few at a mature level undergo GenAI transformation
3% 16% Fully ready and mature
3% 16% Extensive expertise and
Mostly ready, minor gaps resources for effective
deployment
Partially ready, requires Talent exists but
enhancements insufficient to support all
initiatives
Needs significant
23% improvements Have some skills but need
significant investment
22%
Not ready Aware of skills but lack
them and have no
19% 39% acquisition strategy
Have not thought about
35%
24% specific GenAI skill
requirement
8 The AIdea of India: 2025
GenAI in India: The current state of play achieved remarkable progress in solving GenAI in India: Shaping tomorrow
complex problems across disciplines like science,
mathematics and programming, consistently
India will chart a unique path as this technology
surpassing previous benchmarks. These advanced
evolves. We see five key trends that will
capabilities started to get packaged into agentic AI
significantly influence India’s AI evolution.
systems which aim to independently plan, reason,
and execute tasks by dynamically leveraging tools
and resources. Though still in its infancy, this
agent-driven paradigm promises to fundamentally 01 Chat, voice, regional languages
reshape our understanding of work and the way we augment digital interfaces
design software systems.
Hardware innovations continued to underpin these
02 Agents enable the transformation
advancements in GenAI. NVIDIA maintained its
of knowledge work
leadership with the Blackwell platform, enabling
trillion-parameter models while competitors drove
significant breakthroughs in AI accelerators.
03 LLMs are not all you need:
Toward compound AI systems
Moving from demos and labs to
enterprise grade capabilities
04
The falling cost of AI
Yet, despite these breakthroughs there is also
increasing doubt about the pace and magnitude
of the impact of GenAI. Goldman Sachs, for 05 The evolution of an
instance, has highlighted the imbalance between Indic AI ecosystem
the massive investments being funneled into AI and
the uncertain returns. In a June 2024 report titled
“Gen AI: Too Much Spend, Too Little Benefit?”,
the firm projected that tech giants and other
‘good enough’ for scaling across many use cases.
companies are set to invest nearly US$1 trillion
Our survey of Indian enterprises suggests that
in AI-related expenditures over the coming years,
customer service, operations and sales & marketing
spanning data centers, specialized hardware, and
functions are already leading the way in adoption.
infrastructure upgrades. Despite these staggering
Over the next few years, as these teething issues
sums, the tangible benefits remain elusive.
are addressed, AI and GenAI models make their
Our survey of Indian enterprises suggests that 36% way into the enterprise mainstream across all
of enterprises have budgeted and started investing functions and departments.
in GenAI while another 24% are experimenting with
it. Technology sector clients have been leading
the way with Life Sciences and Financial Services AI augmented interfaces will transform
following suit. At the same time business value
consumer apps
delivered is relatively low with only 15% of Indian
enterprises report having GenAI workloads in AI-powered chat, voice and regional language
production, and just 8% being able to fully measure tools are already making an impact and this trend
and allocate AI costs. will accelerate as digital models diffuse across
the Indian consumer, enterprise and government
This is not surprising. Packaging innovation into
landscape. GenAI native interfaces will also serve
products and services that enterprises can use
as front doors to onboard less digitally savvy users
is a time-consuming process. Enterprises need
into the digital economy. Solutions like NPCI’s Hello!
clarity on ROI and guarantees around issues like
UPI and IRCTC’s AskDisha chatbot demonstrate
hallucination, data privacy and algorithmic bias as
this shift, enhancing inclusivity for underserved
they craft their digital transformation roadmaps.
populations in semi-urban and rural areas.
Rapid advancements to date have already made AI
The AIdea of India: 2025 9
Agents will transform knowledge work A rich Indic AI ecosystem will evolve to
cater to unique Indian needs
The rapid integration of AI Agents into sectors
like information technology, finance, customer There has already been a mushrooming of Indic
service and healthcare will reshape traditional LLMs that leverage open-source models fine-tuned
ways of working, presenting both opportunities with Indian language datasets. A key initiative in
and challenges for Indian professionals. Our this space is Bhashini, a government-led AI project
analysis (more on this in ‘Transforming work with aimed at creating an open-source Indic language
GenAI’) indicates potentially large productivity dataset to expand internet and digital service
improvements that will begin to manifest accessibility in Indian languages. Going forward,
themselves and companies will begin to gear up to AI will increasingly become part of the India stack
help employees manage the coming transition to and available as digital public infrastructure to build
new ways of working. next generation platforms.
A burgeoning GenAI start-up ecosystem and local
Enterprises will start to move to an
AI infrastructure will help drive adoption in
AI-embedded tech stack Indian enterprises.
Enterprises will learn to treat LLMs as but one part
of an evolving AI enabled tech stack. AI adoption
Pivoting to AI-first digital
will accelerate as enterprises integrate LLM
capabilities with classical AI techniques, new transformation
modes of automation and the emerging modern
data stack.
Similar to the transformative impact of the digital
revolution, the accelerating shift toward AI-
AI costs will continue to fall
driven platforms is poised to reshape every factor
influencing a company’s EBITDA. Across Indian
The cost of using AI models has already
enterprises, AI-first approaches are steadily taking
plummeted, making them increasingly accessible to
root, embedding themselves throughout the value
enterprises. OpenAI’s GPT API costs, for example,
chain to enhance operational efficiency and unlock
have dropped nearly 80% in two years, while
new avenues of value creation.
open-source releases like Meta’s Llama are
unlocking new capabilities. This cost is expected At a foundational level, AI automates workflows,
to fall to around INR120 per hour* or lower as detects patterns, and delivers real-time predictions,
India specific LLMs offerings become viable. creating a closed-loop system for continuous
(*Assuming that the cost is US$4 per million tokens learning. This will help companies optimize value
and the application uses 100 tokens per second chains, enhance revenue streams through improved
continuously, the enterprise would spend channels and pricing, and transform delivery with
US$1.44 per hour.) new interfaces.
10 The AIdea of India: 2025
The agenda for enterprises
Reimagine the Rethink the tech Move to AI-ready Getting your Confronting the
business and stack data people ready for AI changing frontier of
operating model risk
A new AI-powered tech stack is emerging, and workforce adaptability. Change management
combining foundational models with specialized bridges the gap between innovation and
tools. Enterprises are increasingly adopting execution, enabling organizations to thrive
SLMs for domain-specific tasks due to their cost in an AI-driven world.
efficiency, precision, and ability to run on edge
AI-first strategies introduce risks related to bias,
devices. Enterprise software providers such as
cybersecurity and explainability. Organizations
SAP, Salesforce and Oracle are embedding AI
are mitigating these by adopting automated
into their platforms, accelerating adoption with
compliance systems, real-time anomaly detection,
ready-to-deploy AI tools. Meanwhile, traditional
and explainable AI models. Regulatory frameworks
Robotic Process Automation (RPA) is evolving
like India’s Digital Personal Data Protection
into intelligent automation by integrating GenAI,
Act (DPDP Act 2023) further emphasize the
enabling systems to adapt dynamically to changes
importance of responsible AI practices, especially in
without manual intervention.
sensitive sectors like healthcare and finance.
A solid data foundation is pivotal to enterprise
AI success. Enterprises are implementing robust
governance frameworks, addressing challenges Transforming work with GenAI
related to data quality, diversity and sensitivity.
Modern data stacks, including cloud platforms
and scalable data lakes, enable real-time ingestion In India GenAI has the potential to drive
and processing, essential for AI implementation. productivity gains, impacting millions of workers
Companies that nurture proprietary datasets and redefining the future of work.
are gaining competitive advantages by achieving
EY conducted a study of over 10,000 tasks in
superior model performance.
critical industries that contribute to the Indian
Preparing people for AI is crucial to unlocking its economy. To assess GenAI’s impact on productivity,
full potential, ensuring both technological adoption tasks were analyzed based on exposure (potential
The AIdea of India: 2025 11
impact of GenAI), complementarity (human due to its higher labor share in gross output, while
oversight needed) and intensity (frequency of tasks manufacturing and construction will see smaller
analyzed in granular time units). A ‘Productivity impacts. However, even in these sectors, AI can
Uplift’ Indicator was created, to quantify drive efficiencies through better capital deployment
this potential impact in terms of Automation and resource utilization, ultimately lowering labour
(elimination of the task), Augmentation expenses and improving overall cost efficiency.
(doing the same task better using GenAI) and
Realizing this potential requires reimagining
Amplification (enhancing the nature of the task
processes, redefining workflows and reskilling
and making it richer).
the workforce. The successful adoption of GenAI
This allowed us to analyze productivity gains at requires clear strategies, piloting use cases, and
job role, functional and organizational levels. scaling solutions, alongside reimagining processes,
Our analysis reveals that 24% of tasks can be redefining KPIs, and targeted reskilling. Large-scale
fully automated, while time spent on another upskilling initiatives, supported by public-private
42% can be significantly reduced, freeing up partnerships and AI-focused training programs, are
8-10 hours per week for corporate workers. This crucial to bridging the skill gap. With investments
translates to a productivity boost of 2.61% by in skills, data and infrastructure, GenAI can drive
2030 in the organized sector affecting 38 million economic productivity and ensure a future-ready
Indian employees and an additional 2.82% in the workforce for India.
unorganized sector. The largest productivity gains
from GenAI are expected in the services sector
Productivity gains across key sectors
This graph illustrates the labor cost as a percentage of gross output on the x-axis and the percentage
productivity improvement through AI on the y-axis. The size of the bubble represents the potential labor
efficiencies created by AI for the industry.
EY India jobs study: Transforming work with GenAI
12 The AIdea of India: 2025
laitnetop
ytivitcudorP
50%
45%
IT | 19%
40%
Retail | 5%
Banking | 9%
35%
Pharma | 2%
Insurance | 8%
30%
Telecom | 5%
Automobile | 2%
25% Metals and Mining | 4%
Healthcare | 13%
20%
Media and Entertainment | 5%
15%
10%
0% 10% 20% 30% 40% 50% 60%
Labor cost by gross output
secnahne
IA
secnahne
IA
yltnacfiingis
ytivitcudorp
yllanigram
ytivitcudorp
Labor plays Labor plays a
a smaller role larger role
A policy agenda for India To ensure Responsible AI, the government has
prioritized transparency, fairness and safety
through consultations and oversight. Plans include
India’s AI policy landscape reflects a balanced
forming a National Committee on Responsible
approach to fostering innovation while ensuring
and Trustworthy AI, addressing bias, privacy and
responsible deployment. The IndiaAI Mission stands
accountability. The DPDP Act requires
at the forefront, with a financial commitment
businesses to adopt privacy-preserving AI tools,
of over INR10,000 crore to develop India’s AI
anonymization protocols, and compliant
ecosystem across seven pillars, including access
workflows, aligning AI development with evolving
to high-quality datasets, expanded compute
data protection standards.
infrastructure, and responsible AI governance. Key
initiatives include establishing the India Dataset India’s strategic AI policies, anchored in inclusivity,
Platform for organized, sector-specific data access, data sovereignty and accountability, aim to position
deploying 10,000 GPUs to scale AI research, the country as a global AI leader while mitigating
and promoting AI solutions in critical sectors like risks, promoting innovation, and ensuring ethical AI
healthcare and agriculture through R&D incentives adoption across public and private sectors.
and innovation challenges.
The AIdea of India: 2025 13
C h a p t e r 1
Generative AI:
Shaping tomorrow
14 The AIdea of India: 2025
Generative AI:
Shaping tomorrow
The AIdea of India: 2025 15
Chapter 1
Generative AI:
Shaping tomorrow
The promise still holds
Multimodal AI advancements,
agent-driven systems, and hardware Over the past few years, innovation in GenAI has
progressed at an extraordinary pace, reaffirming
advancements like NVIDIA’s Blackwell
its transformative potential across a number of
are reshaping global applications,
domains. The possibilities are vast and hold the
moving GenAI from labs to promise of profound changes on the horizon. In
the domain of healthcare, AI could accelerate
enterprise-grade solutions
breakthroughs in biology, enabling the rapid
development of cures for diseases like cancer and
The rise of open-source LLMs and the Alzheimer’s while extending human lifespans. In
neuroscience, it offers hope for understanding
success of smaller, domain-specific
and treating mental illnesses such as depression
models are addressing privacy,
and schizophrenia, while also enhancing human
efficiency, and targeted use-case needs cognition and emotional well-being. Economically,
AI promises to potentially uplift billions out of
poverty by optimizing resource distribution and
The rapidly falling costs of AI
revolutionizing industries like agriculture and
solutions, like 80% drop in the price clean energy. In governance, AI might strengthen
of OpenAI’s APIs over two years, governance by enhancing public services and
reducing corruption. Finally, in education and work,
are making advanced capabilities
AI can democratize knowledge access and redefine
increasingly accessible to enterprises meaningful human contributions, ensuring an
inclusive future where technology enriches, rather
than replaces, human purpose.
India is leveraging GenAI for
regional language accessibility,
But GenAI is not without its
digital inclusivity, and transformative
consumer apps skeptics
As Indian enterprises adopt Yet, as with all transformative technologies, GenAI
has its share of doubters. While its promise is vast,
AI-embedded tech stacks;
concerns about the pace and magnitude of its
start-ups and SaaS companies will impact linger. Goldman Sachs, for instance, has
lead the charge, driving innovation highlighted the imbalance between the massive
investments being funneled into AI and the
and integration across industries
uncertain returns. In a June 2024 report titled
in the coming years “Gen AI: Too Much Spend, Too Little Benefit?”,
the firm projected that tech giants and other
companies are set to invest nearly US$1 trillion
16 The AIdea of India: 2025
in AI-related expenditures over the coming years, Emerging
spanning data centers, specialized hardware, and
trends
infrastructure upgrades. Despite these staggering
sums, the tangible benefits remain elusive. Adding such
to the tempered outlook, MIT economist and Nobel
as Agentic AI and synthetic data
laureate Daron Acemoglu provides a cautious
generation expanded AI’s capabilities
evaluation of AI’s economic impact. His research
suggests that contrary to ambitious forecasts of by enabling autonomous, multi-step
transformative productivity gains, AI may yield
tasks and addressing data scarcity
GDP growth of a more modest 0.93% to 1.16% over
the next decade, with the possibility of reaching
1.56% under optimal conditions. These critiques
underscore the need to balance enthusiasm with
realism, tempering grand visions with practical reasoning and accuracy. Landmark achievements,
assessments of AI’s current capabilities and including Nobel-recognized contributions to
its path forward. protein structure prediction (AlphaFold2) and
industry-specific LLMs for domains like healthcare
and finance, highlighted the technology’s potential.
The year of exponential Global investment in GenAI surged, driven by
tech giants like Google, OpenAI and Microsoft.
breakthroughs
Record-breaking funding rounds and open-source
contributions from Meta and others intensified
Year 2024 proved to be one of phenomenal competition, while advancements in hardware,
advancement in the field of GenAI culminating such as Nvidia’s Blackwell platform, provided the
with the announcement of OpenAI’s o3 class of computational power to support increasingly
models, which promise to offer a quantum leap in sophisticated models. Emerging trends, such
foundational LLM capabilities and reasoning. Earlier as Agentic AI and synthetic data generation,
in the year, the transition to multi-modality allowed expanded AI’s capabilities, enabling autonomous,
seamless handling of diverse data formats, while multi-step tasks and addressing data scarcity.
advancements like expanded context windows and SLMs offered cost-effective solutions for smaller
retrieval-augmented generation (RAG) improved enterprises. Despite concerns like overfitting
and model collapse, GenAI’s strides in reasoning,
multimodality and adaptability cemented its
position as a key driver of innovation and
productivity across sectors.
Every once in a while,
We are still early in the game
a new technology, an
Despite challenges, even today’s innovations in
GenAI offer immense enterprise value. The focus
old problem, and a
is not just on GenAI but also on integrating AI,
data, and automation to build tailored solutions.
big idea turn into an Rapid advancements have made AI ‘good enough’
for scaling across many use cases. Techniques like
innovation RAG and CoT address issues like hallucination,
while guardrails secure data privacy and safety. The
cost of AI has also dropped significantly, promising
Dean Kamen returns on existing investments.
Engineer and entrepreneur
The AIdea of India: 2025 17
Human-like adaptability of AI Agents
AI Agents operate, within an enterprise context, to achieve specific goals. They can be instructed in natural
language and act autonomously on behalf of users. Users specify objectives in terms of ‘what’ or task
goals, leaving the AI agent to figure out ‘how’ this is to be accomplished using available tools. An agentic
architecture represents a fundamentally new approach to building computer systems. If successful, it
signifies a leap forward as the focus is on outcomes rather than processes.
A key innovation is that much of the control logic in an AI Agent is driven by LLMs. This approach introduces
dynamic, non-deterministic behavior – similar to human decision-making – with its associated benefits and
challenges. Decision making, with AI agents, is no longer limited to rigid programming. Agents can adapt to
contexts and improve outcomes dynamically.
Applications of AI agents across contexts
Personal assistants Reasoning Agents
Advanced personal assistants, such as Apple’s OpenAI’s O1 (and now O3) models exemplify
AI-driven assistant, showcase how AI can AI’s growing reasoning capabilities. Using
handle complex, context-dependent queries. chain-of-thought methodology, O1 formulates
For instance, when asked about a family step-by-step plans to solve problems, improving
member’s flight arrival and dinner plans, the both accuracy and transparency. Users, too,
assistant seamlessly integrates information can trace the model’s logic, identify errors and
from emails, messages, maps, calendars and make corrections. Notably, O1 has achieved over
third-party apps. These systems build a semantic 80% accuracy in solving complex mathematical
model of the user, which enables navigation problems, marking a substantial advancement
across applications to respond accurately. As over previous models. Reasoning agents
AI becomes more embedded in devices and highlight the potential for AI to bring clarity and
productivity tools, personal assistants are poised reliability to intricate problem-solving tasks.
to adeptly manage digital lives, streamlining user
interactions and enhancing productivity.
Functional Agents Agents in the real world
Salesforce’s Agentforce platform brings Anthropic’s research on AI Agents emphasizes
agentic architectures into the enterprise realm. their ability to interact dynamically with the
These autonomous AI Agents personalize world to accomplish tasks and learn from
customer interactions, streamline support and those interactions. This vision extends beyond
orchestrate actions across multiple channels. the digital realm to where agents can control
This innovation shifts traditional business physical tools, robots or laboratory equipment,
models toward outcome-based pricing – where or even design equipment for specific tasks.
costs are tied to completed tasks rather than However, such dynamic systems bring
per-user licenses. Such a model aligns software challenges in ensuring safety, reliability, and
costs more closely with business outcomes, predictability – an essential focus
offering enterprises a flexible and value-driven for developers.
approach.
18 The AIdea of India: 2025
However, adoption remains low. Our survey of 02Open source LLMs
Indian enterprises suggests that 36% of enterprises
have budgeted and started investing in GenAI
The emergence of open source LLMs (OS LLMs)
while another 24% are experimenting with it.
from organizations like Meta and Mistral intensified
Technology sector clients have been leading the
competition, prompting closed-source providers
way with Life Sciences and Financial Services
such as Anthropic and OpenAI to enhance
following suit. At the same time business value
their offerings to justify premium pricing. For
delivered is relatively low with only 15% of Indian
instance, DeepSeek v3 has been able to surpass
enterprises report having GenAI workloads in
OpenAI’s GPT-4o in performance across several
production, and just 8% being able to fully measure
industry benchmarks.
and allocate AI costs. The survey highlights the
need for packaged solutions to bridge the gap and The shift also benefited hardware providers like
accelerate adoption. As innovations mature, they NVIDIA. Demand for GPUs expanded to include
will drive a new wave of digital transformation, organizations deploying OS LLMs privately, leading
unlocking extraordinary business benefits. At them to invest in NVIDIA hardware to run models
the same time, global trends positively influence like Meta’s Llama 3.1 405B internally,
GenAI developments in India through collaboration, rather than relying on API-based access to
investment and research. closed-source models. This diversification of |
6 | ey | catalyzing-economic-growth-through-ai-investment.pdf | Catalyzing economic
growth through capital
investment in GenAI
Catalyzing economic growth through capital investment in GenAI
1
Economic impact of AI: This EY-Parthenon macroeconomic article series
provides insights on the economic potential of GenAI and actionable
considerations. Discover more
In this installment, we delve into the realm of capital investment in generative AI
(GenAI). As GenAI has emerged as one of the key components of economic impact,
business leaders today find themselves at a crossroads. The October 2023 EY CEO
survey indicates a striking dilemma: while a significant 62% of business leaders
acknowledge the urgency of acting on GenAI to prevent competitors from gaining
Gregory Daco a strategic edge, an almost equal percentage (61%) express reservations due to the
EY-Parthenon Chief Economist uncertainties surrounding the formulation and execution of an AI strategy.
New York, NY
The survey further reveals an “adoption paradox.” It highlights that two-thirds of
organizations that have successfully launched at least one AI initiative anticipate
that AI will revolutionize their entire business and operational models within a mere
two-year span. In contrast, organizations with more extensive AI experience, defined
as those having completed five or more AI-related initiatives, project a more cautious
timeline of three to five years for AI to wield similar transformative effects.
This disparity in expectations underscores the presence of ‘“unknown unknowns” in
AI adoption, particularly in determining the nature and extent of capital investment
required for laying a robust AI foundation.
Catalyzing economic growth through capital investment in GenAI
2
In assessing the potential economic impact of GenAI from a capital investment
perspective, we examined the near-term boost to growth from increased investment
in research and development, infrastructure, software creation and company
adoption. Drawing parallels with the IT revolution in the period of 1980-2000, our
two main findings are:
• Significant boost to demand: Assuming trend growth around 8.5% in
investment categories where GenAI will be most significantly captured, we
estimate that capital investment in GenAI will contribute about 0.1 percentage
points (ppt) to US GDP growth annually over the next five years. Our baseline,
however, is that business investment will likely be 25% faster, leading to an
incremental boost to short-term growth of 0.1 percentage points of GDP per
year, worth over $150bn after five years. A more optimistic scenario could see
50% faster business investment growth, leading to an incremental boost to short-
term growth of 0.2ppt of GDP per year, worth a cumulative $325bn by 2028.
• Long-term boost from supply: In our baseline where business investment
is 25% faster than the current trend growth, the potential growth rate of the
economy would rise by 0.1ppt per year in the 2028-2033 period, lifting real GDP
by nearly 1% over the baseline by 2033, or the equivalent of a $250bn boost
over a decade. Assuming capital investment in AI technology grows 50% faster
than the 2017-2022 trend pace over the next five years, the annual capital
contribution to long-term GDP growth in the 2028-2033 period would rise by
0.2ppt. This stronger tech-driven trajectory would lift real GDP by more than 2%
over the baseline by 2033, or the equivalent of a $500bn boost over a decade.
Percent Billions (USD, 2017)
US Real GDP boost from 1.4 350
GenAI investment
1.2 300
1.0 250
0.8 200
0.6 150
0.4 100
0.2 50
0.0 0
Baseline — Optimistic — Baseline — Optimistic —
Boost Boost Cumulative Cumulative
per year per year� boost by 2028 boost by 2028
Source: Bureau of Economic Analysis; EY-Parthenon
Additional chart notes: This chart shows the GDP boost from GenAI investment on an average annual basis between
2023 and 2028 as well as the cumulative boost over the same time frame; both include baseline and optimistic
scenarios. Baseline assumes business investment in categories where GenAI will be most significantly captured
is 25% faster than trend growth; optimistic assumes business investment in categories where GenAI will be most
significantly captured is 50% faster than trend growth. Data from this chart is discussed in the article
Catalyzing economic growth through capital investment in GenAI
3
Looking across major economies, the contributions from greater GenAI investment
could also be significant. While the US market is likely to remain the leader in GenAI
technologies investment, China and Europe will be following closely behind. We
estimate that the lift to global GDP could total between $300bn and $600bn over the
next five years. The boost to global potential GDP could amount to between $500bn
and $1tn over the next decade.
In this installment of our “Economic impact of AI” series, we will focus on the
business investment and capital accumulation dimension and leave the productivity
dimension of accelerating processes, optimizing operations and unlocking new
capabilities to the next article in our series.
We will discuss investment in GenAI and associated capital accumulation by taking a
deeper look at the following:
• Back to basics: demand and supply
• The demand perspective: near-term contribution of capital investment in GenAI
to GDP
• The supply perspective: a strong capital foundation to promote more sustainable
growth
1. Back to basics: demand and supply
Capital investment in GenAI can spur stronger capital
accumulation and productivity, boosting the global
economy’s growth rate.
In an era where technological innovation is the cornerstone of economic prowess,
GenAI has the potential to reshape the contours of businesses and the broader
economy. This installment delves into the burgeoning role of increased capital
investment in AI, underscoring its potential to be a significant driver of near-term
economic growth.
It’s important to consider that GenAI investment is not just a technological upgrade
but a strategic economic lever to redefine business models, markets, industries and
the very fabric of the global economy. By dissecting the dynamics of AI investment,
we aim to unveil how it can propel economic activity, observed through the dual
prisms of demand and supply.
From the demand perspective, investment in GenAI is seen as a new frontier for
capital allocation, influencing various sectors from health care to finance, and
energizing them with innovative capabilities. The investment fuels the industries it
permeates, leading to an uptick in overall economic activity and consumer demand.
On the supply side, investment in AI will be a catalyst for stronger capital
accumulation as well as productivity growth, lifting the global economy’s potential
growth rate.
Catalyzing economic growth through capital investment in GenAI
4
As we noted in the first installment of our series, prior general-purpose
technologies have had a significant impact on economic activity, but that impact
has generally lagged.
Some of the main reasons for that lag are implementation and diffusion delays,
learning and adjustment periods due to the time it takes to effectively use new
technologies and delays in the development of complementary innovations or
infrastructure for the technology to be fully effective.
To establish GenAI as a cornerstone of modern industry, substantial capital
investment may be required.
• Research and development (R&D): Building and refining AI models necessitate
a significant influx of resources. The data-intensive nature of GenAI calls
for investment in gathering, storing and processing data, as well as in the
computational power needed to train sophisticated models.
• Infrastructure providers: Investment in the physical and digital infrastructure
necessary to support AI technologies forms another cornerstone of this economic
transformation. This encompasses everything from data centers to advanced
networking capabilities and even cybersecurity. The adequacy of this infrastructure
directly impacts the efficiency and effectiveness of AI solutions.
• Software creation: The investment in AI applications across various business
sectors is perhaps the most visible aspect of AI’s economic influence. From
finance to manufacturing, AI applications are revolutionizing traditional business
processes, enhancing customer experiences and opening new revenue streams.
These investments are not merely about automating routine tasks but are
also about leveraging AI to uncover insights, predict trends and create more
personalized and efficient services.
• Corporate adoption: It’s essential for businesses to invest in integrating GenAI into
their operations. This includes not only the technology itself but also the training
of personnel and restructuring of processes to fully capitalize on AI’s potential. The
widespread adoption of AI by businesses could have a notable economic impact
as it leads to increased operational efficiencies, reduced costs and enhanced
competitive capabilities. Moreover, as AI becomes more ingrained in business
operations, it will likely drive the demand for skilled workers and AI-related
services, and, consequently, it will probably stimulate job creation and economic
activity in related sectors.
Catalyzing economic growth through capital investment in GenAI
5
2. The demand perspective: near-term contribution of
capital investment in GenAI to GDP
Rising capital investment in GenAI is positioned to
increase quickly and prompt GDP growth.
In assessing the potential economic impact of GenAI from a demand perspective, it is
instructive to draw parallels with the investment dynamics of previous technological
revolutions. In the early 1990s, business investment in information processing
equipment and software totaled about 3% of GDP, or $155 billion.
As businesses invested in the physical and human infrastructure necessary to
support, implement and reshape business processes in the computer age, that
share of investment rapidly grew to 4.5% of GDP, or $400 billion by the early 2000s.
Percentage points
US business investment in
9.0
Historical Forecast
GenAI as a share of GDP
(percent)
8.0
7.0
6.0
5.0
4.0
3.0
2.0
8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8
200 200 201 201 201 201 201 201 201 201 201 201 202 202 202 202 202 202 202 202 202
Optimistic — real Optimistic — nominal
Baseline — real Baseline — nominal
Trend — real Trend — nominal
Source: Bureau of Economic Analysis, EY-Parthenon; author’s calculation
Additional chart notes: Trend refers to trend growth around 8.5% per annum in investment categories where GenAI
will be most significantly captured. Optimistic assumes business investment is 50% faster than trend growth.
Catalyzing economic growth through capital investment in GenAI
6
We are likely on the cusp of a similar trend with GenAI, where burgeoning investment
in AI technology is poised to increase rapidly and boost GDP growth. Specifically, we
isolated the following investment categories likely to capture AI technology:
• Software
• R&D in semiconductor and other electric components manufacturing, other
computer and electronic product manufacturing, scientific services and
software publishers
• Computers and peripheral equipment
• Communication equipment
Scenario analysis
The categories where new investment in GenAI will be most significantly captured
totaled about $750 billion in 2017, or about 3.8% of real US GDP. By 2022,
investment had grown to just over $1.1 trillion, or about 5.2% of GDP.
• Trend growth: Assuming trend growth in line with economic momentum from
2017 to 2022, investment would be expected to grow around 8.8% per year from
2023 to 2028 and represent 7.6% of real GDP by 2028, or $1.9 trillion. While this
would mean that investment in AI technology would contribute about 0.4ppt to
GDP growth per year, it would not represent an increase in the growth contribution
relative to recent past.
• Baseline expectations: If, instead, we assume that nominal capital investment in
AI technology grows 25% faster than the 2017-2022 trend pace over the next five
years, then investment represents 8.1% of real GDP by 2028, or $2 trillion. This
would translate into an incremental contribution of GenAI technology investment
to GDP growth of 0.1ppt per year (for a total contribution of 0.5ppt) and, by 2028,
a boost to real GDP worth $150bn, or 0.6%.
• Reason for optimism: Still, there may be reason to be even more confident
about the outlook. Assuming capital investment in AI technology grows 50%
faster than the 2017-2022 trend pace over the next five years — which is akin
to the acceleration in business investment in information processing equipment
and software in the late 1990s — then investment would grow about 11% annually
from 2023 to 2028 and represent 8.7% of GDP by 2028, or $2.1 trillion. This
would constitute an incremental short-term contribution to GDP growth of 0.2ppt
per year (for a total contribution of 0.6ppt) and, by 2028, a boost to real GDP
worth $325bn, or 1.3%.
The potential uplift to global GDP from increased GenAI investment could also
be substantial. With the US expected to continue leading in GenAI technology
investment, closely followed by Europe, Japan and China, global GDP could see
an augmentation of between $300 billion (in our baseline scenario) and $600
billion (in the optimistic case) over the next five years. This significant boost would
reflect the accelerated adoption and integration of GenAI technologies across major
economies, underlining the transformative impact of AI.
Catalyzing economic growth through capital investment in GenAI
7
3. The supply perspective: a strong capital foundation
to promote more sustainable growth
Past tech disruptions and our scenario analysis
provide a case for optimism about GenAI’s ability to
drive long-term growth.
At the heart of AI’s transformative potential on the supply side of the economy is
its capacity to drive greater capital accumulation and stronger productivity growth.
Capital investment in AI is not just an expenditure; it’s a strategic allocation of
resources that acts as the foundation for developing and deploying AI solutions and
seeds future productivity enhancements.
While we will delineate the long-term growth implication from GenAI-driven
productivity growth in a subsequent article, we believe it is essential to dissect the
impact of greater capital accumulation first.
Capital accumulation in AI involves investing in various components such as AI
models (through building and refining), physical and digital infrastructure, software,
AI applications, and AI integration and adoption. Just like physical capital, these
investments in AI technologies act as the foundation that allows for stronger
economic potential.
Capturing longer-term impact from greater capital
investment in AI technology
The surge in business investment in information processing equipment and software
through the 1990s did not just lead to a direct boost to GDP growth, but it also led to
increased capital accumulation that then supported stronger long-term GDP growth.
To put things in perspective, the US economy’s potential GDP growth rate was
estimated to be around 2.5% from 1990 to 1995, but subsequently it accelerated
to 3.8% in the 1995-2000 period. Taking all drivers of growth into consideration,
the capital contribution to potential GDP growth nearly doubled from 0.7ppt in the
early 1990s to 1.3ppt in the 1995-2000 period. At the same time, the contribution
of productivity also rose from 1.1ppt to 1.7ppt from 1995 to 2000 and remained
elevated around 1.5ppt from 2000 to 2005.
Catalyzing economic growth through capital investment in GenAI
8
This confirms our findings from our first installment, which indicated a five- to 10-
year delay between the development of new technologies and their more sustainable
impact on productivity and growth potential.
Percentage points
US Average annual 4.0
contribution to real
3.5
potential GDP growth
3.0
2.5
2.0
1.5
1.0
0.5
0.0
1990–1995 1995–2000 2000–2005
Labor and productivity Capital Potential GDP
Source: Bureau of Economic Analysis, EY-Parthenon; author’s calculation
Additional chart notes: Trend refers to trend growth around 8.5% per annum in investment categories where GenAI
will be most significantly captured. Baseline assumes business investment is 25% faster than trend growth
Optimistic assumes business investment is 50% faster than trend growth
Scenario analysis
Using the same three scenarios, which analyzed the potential short-term economic
impact of greater capital investment in AI technologies, we can infer the likely boost
to potential GDP growth in the five years from 2028 to 2033.
• Trend growth: Assuming business investment in AI technology continues to grow
in line with its moderate 2017-2022 trend, the annual capital contribution to
long-term GDP growth in the 2028-2033 period would likely be around 0.5ppt.
• Baseline expectations: If, instead, we assume that capital investment in AI
technology grows 25% faster than the 2017-2022 trend pace over the next five
years, the capital contribution to long-term GDP growth in the 2028-2033 period
would rise from 0.5ppt annually to 0.6ppt — thereby lifting the potential growth
rate of the economy by 0.1ppt. This may appear to be a small difference, but by
lifting the economy’s potential growth rate, this stronger tech-driven trajectory
would lift GDP by nearly 1% over the baseline by 2033, or the equivalent of a
$230bn boost over a decade ($360bn in nominal terms).
• Reason for optimism: As we noted earlier, there is reason to be more confident
still about the potential capital accumulation contribution to long-term growth.
Assuming capital investment in AI technology grows 50% faster than the 2017-
2022 trend pace over the next five years — which is akin to the acceleration in
business investment in information processing equipment and software in the
late 1990s — the capital contribution to long-term GDP growth in the 2028-2033
period would rise from 0.5ppt annually to 0.7ppt, thereby lifting the potential
growth rate of the economy by 0.2ppt. This stronger tech-driven trajectory would
lift real GDP by nearly 2% over the baseline by 2033, or the equivalent of a $475bn
boost over a decade.
Catalyzing economic growth through capital investment in GenAI
9
In the long run, the potential upside to global GDP from greater capital investment
could be quite significant. How significant? Factoring stronger investment in Europe,
Japan and China and slower investment across emerging markets, we estimate a
boost to potential GDP growth worth between 0.5% and 1% by 2033, representing
between $500bn and $1tn.
Percentage points
US average annual capital 0.8
contribution to real potential 0.7
GDP growth
0.6
0.5
0.4
0.3
0.2
0.1
0.0
2020–2025 2025–2030 2030–2033
Trend Baseline Optimistic
Source: Bureau of Economic Analysis, EY-Parthenon
Additional chart notes: Trend refers to trend growth around 8.5% per annum in investment categories where GenAI
will be most significantly captured. Optimistic assumes business investment is 50% faster than trend growth.
Catalyzing economic growth through capital investment in GenAI
10
Breakdown of AI capital investment across sectors
When thinking about the sector-specific benefits from the GenAI revolution, we
often omit the investments that may be required to shift how industries operate.
By fostering innovation, enhancing productivity and creating new markets and
opportunities, the capital investments described above may be instrumental in
driving potential GDP growth.
Retail sector: AI’s role in retail is multifaceted, ranging from personalized shopping
experiences to inventory management. Capital investments in AI enable retailers to
better understand consumer behavior, optimize supply chains and enhance customer
service, leading to increased sales and market expansion. This sectoral growth is a
key contributor to overall economic development because it could boost retail sector
productivity while also stimulating consumer spending, a major component of GDP.
Health care sector: Investment in AI within health care is revolutionizing patient
care and medical research. AI-driven tools are being used to enhance diagnostic
precision, streamline patient treatment plans and personalize health care services.
This not only improves health outcomes but also helps optimize resource utilization,
reducing costs and contributing to economic growth. Additionally, AI in health care
is spearheading innovations in drug discovery and disease prediction, opening new
markets and avenues for growth.
Automotive industry: The automotive sector’s investment in AI is pivotal in
advancing the development of autonomous vehicles. This not only transforms the
concept of transportation but also stimulates investment in adjacent industries
like logistics and urban planning. The ripple effects of such advancements could
contribute significantly to GDP growth by fostering new business models, enhancing
supply chain efficiencies and creating demand in related sectors such as sensor
manufacturing and AI-driven navigation systems.
Manufacturing industry: In manufacturing, AI investment focuses on automation,
predictive maintenance and supply chain enhancement. This not only increases
production efficiency but also improves product quality, reduction of waste and
operational costs. The resultant increase in competitiveness and productivity of
the manufacturing sector could significantly contribute to GDP growth, while also
fostering an ecosystem of innovation and technological advancement.
Financial services: AI investments in financial services are reshaping banking,
insurance and investment sectors through enhanced risk assessment, fraud detection
and personalized financial planning services. This could increase the efficiency and
resilience of financial systems, supporting economic stability and growth.
Energy sector: Investment in AI within the energy sector is pivotal in transforming
how we generate, distribute and consume energy. AI technologies are being
integrated to help optimize energy production, enhance grid management and
facilitate the shift to renewable sources. Additionally, AI applications in predictive
maintenance of infrastructure may further boost economic efficiency. The
innovations driven by AI in the energy sector are crucial in supporting the transition
to a low-carbon economy, promoting sustainable economic development.
Catalyzing economic growth through capital investment in GenAI
11
Five recommendations for business leaders
By focusing on the following areas, stakeholders can better navigate the
complexities of AI capital investments and harness their full potential to drive
meaningful business transformation.
Strategic alignment with business goals
• Insight: It’s essential for AI investments to be closely aligned with the overarching
business goals and objectives. This alignment helps ensure that AI initiatives directly
contribute to the company’s strategic priorities, whether it’s improving customer
experience, optimizing operational efficiency or driving innovation.
• Recommendation: Conduct a thorough analysis to understand how AI can address
specific business challenges or opportunities. Establish clear KPIs to measure the
impact of AI initiatives on business outcomes.
Leveraging data as a strategic asset
• Insight: High-quality, relevant data is the fuel that powers AI systems. The ability of
a business to collect, process and analyze data effectively is a critical determinant
of AI success.
• Recommendation: Prioritize the establishment of a robust data infrastructure and
governance model. This may help ensure data quality, accessibility and scalability
to support AI initiatives.
Acquiring the right talent and partnering
• Insight: Successful AI implementation may require a combination of the right talent,
including data scientists, AI engineers and domain experts.
• Recommendation: Invest in building internal AI capabilities and work with
organizations that can bring the necessary professional skills and knowledge.
Continuous training and development programs are crucial to keep the team up
to date with the latest AI advancements.
Catalyzing economic growth through capital investment in GenAI
12
Fostering a culture of innovation and adaptability
Key contact
• Insight: The fast-evolving nature of AI technology makes it essential for businesses
Gregory Daco to be agile and adaptable.
EY-Parthenon Chief Economist
• Recommendation: Encourage a culture of innovation where experimentation with
New York, NY
AI is supported. This involves fostering an environment where learning from failures
is seen as a stepping stone to innovation, and where employees are encouraged to
think creatively about applying AI to solve business problems.
Understanding and managing risks
• Insight: AI projects come with their own set of risks, including data privacy
concerns, ethical considerations and potential biases in AI models.
• Recommendation: Develop a robust risk management framework that addresses
these challenges. This includes investing in data security, helping ensure compliance
with relevant regulations and implementing ethical AI practices. But for large-
scale transformation to happen, businesses may need to make significant upfront
investment in physical, digital and human capital to acquire and implement new
technologies and reshape business processes.
EY | Building a better working world
Insert brochure
About EY-Parthenon
EY exists to build a better working world, helping to create EY-Parthenon teams work with clients to navigate complexity by helping
long-term value for clients, people and society and build trust them to reimagine their ecosystems, reshape their portfolios and reinvent
title in this text
in the capital markets. themselves for a better future. With global connectivity and scale,
EY-Parthenon teams focus on Strategy Realized — helping CEOs design
Enabled by data and technology, diverse EY teams in over 150 and deliver strategies to better manage challenges while maximizing
countrieps prloavidec truest thhrouogh alssduraence rand, h elp clients grow, opportunities as they look to transform their businesses. From idea to
transform and operate. implementation, EY-Parthenon teams help organizations to build a better
working world by fostering long-term value. EY-Parthenon is a brand under
Workingd acreoss abssuirasncet, coinusultimng, law , sqtratuegy,a tax mand which a number of EY member firms across the globe provide strategy
transactions, EY teams ask better questions to find new consulting services. For more information, please visit ey.com/parthenon.
answers for the complex issues facing our world today.
Ernst & Young LLP is a client-serving member firm of Ernst & Young Global
as eritem il in
Limited operating in the US.
EY refers to the global organization, and may refer to one or more,
of the member firms of Ernst & Young Global Limited, each of which is
a separate legal entity. Ernst & Young Global Limited, a UK company © 2023 Ernst & Young LLP.
limited by guarantee, does not provide services to clients. Information All Rights Reserved.
Subtitle Ilis et volorepro quia simustis
about how EY collects and uses personal data and a description of the
rights indeivsidtuiaals sha evex upndlear ndadtaa pr odteoctliuonp letgiis,l attioonp atreu amvai laeblte SCORE No. 21894-231US
via ey.com/privacy. EY member firms do not practice law where
2311-4376751
prohibiteidp biye loncailh la wilsi. tFiour mnotre a inpfoirdma qtioun aabmout douor olreganneizaction,
ED None
please visit ey.com.
Month Year This material has been prepared for general informational purposes only and is not intended
to be relied upon as accounting, tax, legal or other professional advice. Please refer to your advisors
for specific advice. |
7 | ey | ey-how-to-ask-corporate-vendors-the-right-questions-when-it-comes-to-rai.pdf | How to ask corporate
vendors the right
questions when it comes
to responsible AI
As artificial intelligence (AI), which Most EY client vendors have probably started to embed AI
into their products and processes or are charting a roadmap
includes generative AI (GenAI) and
for an AI-powered future. Evaluating a vendor company’s AI
agentic AI, becomes part of business portfolio to assess current and future AI capabilities isn’t simple,
but it is important, especially in cases where the package
as usual, leaders are establishing and
selection, system implementation and maintenance process are
decentralized.
implementing strategies for their own
RAI inventory requires linking of data, models and use cases
organizations’ responsible AI (RAI)
for inventory and tracking purposes, which even large tech
adoption. The next phase is gaining an companies don’t necessarily have the capabilities for yet. So
vendors should be evaluated to minimize risk and facilitate
understanding of business vendor and
positive, transparent business relationships.
partner AI use, which could extend its
reach into regulatory compliance.
How to ask corporate vendors the right questions when it comes to responsible AI 1
When evaluating third-party RAI, it is a Technical documentation:
company’s responsibility to thoroughly assess:
Whether the third party provides risk-assessment
RAI framework adoption documentation at the enterprise level as well as the individual
model or system level
Risk assessment
What specific data and security regulations the AI system must
Data management
comply with, including by regulation or jurisdiction
Technical documentation
What specific metrics are used to measure AI performance
Post-production monitoring throughout the AI development lifecycle
Disclosure practices Specific limitations of the AI system and the necessary human
activities to address them
Incident response
Insurance coverage Post-production monitoring:
Responsibilities of deployer The process for post-production monitoring of AI solutions
Contractual obligations to ensure AI systems are secure, How the company will be informed when AI systems perform
compliant and ethically managed outside of the expected range
Whether logging will be available for transactions interacting
with sensitive data
What companies should consider when Disclosure and communication:
evaluating third-party vendors for responsible AI:
Whether the third party provides sufficient and specific
information on each of the AI systems to facilitate the safe
The RAI framework:
use of AI (think of food labels, included in the Singapore AI
What framework or system the vendor has adopted verification requirements)
Whether a SOC report equivalent report will be available on
Risk assessment:
the performance and compliance for AI systems
The vendor risk assessment process and criteria
Incident response and recovery:
What determines higher vs. lower risk
Communication protocol if an incident occurs, including
What governance addresses fairness, bias and accountability
threshold to disclose and resolution process
Access and data management: Third party’s incident response capability and disaster
recovery plans in case of AI system failures or security
Specific rights and data management protocols in place to
breaches, from incident management to crisis management
secure the AI system’s access to the environment
Extent of the third party’s insurance coverage
How the third party will use data and transactions to train its
models to clarify the ownership of any intellectual property
The company’s responsibilities:
that may result from the use of the AI systems, including
patents, trademarks and copyrights What specific deployer responsibilities the third party is
passing on (think of it as the CUECs (complementary user
Whether the third party has access to the vendor’s
entity controls) for a SOC report)
environment and/or data, and if so, how it is managed and
logged Any specific training and support needed to use the AI systems
How to ask corporate vendors the right questions when it comes to responsible AI 2
3
Contractual obligations: The above considerations are easier to manage in new vendor
relationships. But many existing vendors have already started
The right to audit the third-party AI systems
to embed AI into their products or plan to roll out new features
Specific data use restrictions using AI in the near future, so the picture can get murky.
Communication/escalation service-level agreements (SLAs) It’s often more challenging to evaluate a company’s current
portfolio of vendor systems and flag those that have AI
Define clear accountability and liability terms related to the AI
capabilities or will implement AI in the next six months,
solution’s performance and impact
especially in cases where the package selection, system
implementation and maintenance process is not consistently
Access and data management:
centralized.
What specific access rights and data management protocols
When evaluating third-party RAI, companies should use the
does the vendor need to put in place to secure the AI system’s
above checklist to thoroughly assess the vendor’s RAI and
access to the environment?
gain confidence that all AI systems are secure, compliant and
Will the third party use data and transactions to train its
ethically managed.
models to clarify the ownership of any intellectual property
that may result from the use of the AI systems, including
patents, trademarks and copyrights?
Will the third party have access to the vendor’s environment
and/or data? If so, how is the access managed? Is it logged?
EY contacts:
Chris Watson
Sarah Y Liang
EY Americas Risk and Supplier Services
EY Global Responsible AI Leader
Solution Leader
[email protected]
[email protected]
EY | Building a better working world
EY is building a better working world by creating new value for EY refers to the global organization, and may refer to one or more, of the member firms
of Ernst & Young Global Limited, each of which is a separate legal entity. Ernst & Young
clients, people, society and the planet, while building trust in
Global Limited, a UK company limited by guarantee, does not provide services to clients.
capital markets. Information about how EY collects and uses personal data and a description of the
rights individuals have under data protection legislation are available via ey.com/privacy.
Enabled by data, AI and advanced technology, EY teams help EY member firms do not practice law where prohibited by local laws. For more information
clients shape the future with confidence and develop answers for about our organization, please visit ey.com.
the most pressing issues of today and tomorrow. Ernst & Young LLP is a client-serving member firm of Ernst & Young Global Limited
operating in the US.
EY teams work across a full spectrum of services in assurance, © 2024 Ernst & Young LLP.
consulting, tax, strategy and transactions. Fueled by sector All Rights Reserved.
US SCORE no.
insights, a globally connected, multidisciplinary network and
2411-10227. ED none.
diverse ecosystem partners, EY teams can provide services in
This material has been prepared for general informational purposes only and is not intended to be relied
more than 150 countries and territories. upon as accounting, tax, legal or other professional advice. Please refer to your advisors for specific
advice.
All in to shape the future with confidence.
ey.com
How to ask corporate vendors the right questions when it comes to responsible AI 3 |
8 | pwc | ai_adopion_study.pdf | AI Adoption in the
Business World:
Current Trends and
Future Predictions
1
April 2023
Agenda
1 Background and focus areas
2 Current state
3 Risk and Obstacles
4 Future state
5 Key Takeaways & Implementation Guideline
2 2
Background
33
PwC | Tomorrow’s audit, 3
today
Terms & Definitions
“Artificial intelligence” - Coined by emeritus Stanford Professor John McCarthy in 1955, was defined by him as “the science and
engineering of making intelligent machines”. In other words - AI is the ability of a machine to perform cognitive functions typically
associated with human minds, such as learning, reasoning, interacting with the environment, and solving problems.
“Machine learning” Machine Learning (ML) is the part of AI studying how computer agents can improve their perception, knowledge,
thinking, or actions based on experience or data. For this, ML draws from computer science, statistics, psychology, neuroscience,
economics and control theory
“Automation” is the conversion of a work process, a procedure, or equipment to automatic rather than human operation or control.
Automation does not simply transfer human functions to machines, but involves a deep reorganization of the work process, during
which both the human and the machine functions are redefined.
“Synthetic Data” is a class of data that is artificially generated rather than obtained from direct observations of the real world. Data can
be generated using different methods, such as statistically rigorous sampling from real data, semantic approaches and generative
adversarial networks or by creating simulation scenarios where models and processes interact to create completely new datasets of
events.
“Digital Twins” is a dynamic virtual copy of a physical asset, process, system or environment that looks like and behaves identically to
its real-world counterpart. A digital twin ingests data and replicates processes so you can predict possible performance outcomes and
issues that the real-world product might undergo.
44
Sources: Professor Christopher Manning, September 2020 (Stanford University), Michael R. Lowery, Massachusetts Institute of Technology, PwC US, Gartner
Caveats
● There is a lot of hype surrounding AI, and it is crucial to approach the topic with a critical eye. AI is not a panacea for all business
problems, and it is essential to have realistic expectations about what it can and cannot do.
● Not many people and companies that claim to use AI actually use AI. Many companies do so as a marketing tactic in order to
appear innovative, even if they don’t have any actual AI technology in use, or from lack of understanding of what AI is and how it
works. We acknowledge the data presented in this study may involve the participation of such companies which could impair the
accuracy of the results.
● The study does not offer real distinction between off-the-shelf AI tools (e.g. pre-built software packages such as NLP) that comes
with pre-trained models and AI models that require extensive customization and development to work for a specific business use
case.
● The data used for this study may not be reflective of current trends, as certain tools were not available when the data was
collected (e.g. ChatGPT, Midjourney etc). Also certain trends may shift or change in the intervening years, making the data less
relevant or less reflective of the current state of the market as this industry is changing very rapidly.
● Findings from this study may not be generalizable to all contexts, as AI adoption can vary widely depending on the industry,
business size, and other factors
● It can be challenging to establish causality in a study such as this, as other factors could be influencing the outcome, so our
advice is to treat the outcomes of this study with a degree of caution.
55
Sources: PwC US, Forrester
AI is the big one. I don't think Web3 was that big or
”
that metaverse stuff alone was revolutionary but AI
Background is quite revolutionary
- Bill Gates
We are all aware of the paradigm shift in the use of AI. Examples such as Netflix recommendations systems, ChatGPT and other
chatbots, Generative Art (Text-to-Image/Video), chatbots that impersonate customer services agents online are rising and taking over
our day-to-day lives, and companies constantly looking for new ways to exploit the new paradigm. These efforts are the new value
creation engines of many leading companies in almost every industry.
The adoption of AI was low during last years because technology and infrastructure supporting technology were adequate and not
very useful. However, the tides have changed and we are witnessing increasing adoption in current days. According to Forrester’s Data
and Analytics Survey (2022) 73% of data and analytics decision makers are building AI technologies and 74% seeing a positive impact
from AI technologies in their organization. AI is definitely been starting to be adopted in a wide range of industries, including
healthcare, finance, transportation, manufacturing, marketing, education and retail.
We believe that we stand at a very important time in history where AI will play a big role in companies’ transformation and daily
operation, and the faster companies will be able to embrace the change the more advantage they will have versus their competitors.
Given the enormous potential of AI, it is not surprising that adoption of the technology is growing rapidly, so we went to find what is
the current and future state of adopting AI technology. The study aims to provide an overview of the current state of AI adoption, the
benefits and challenges, and the future trends and predictions for AI adoption.
66
Sources: PwC US, Forrester
Current State
77
PwC | Tomorrow’s audit, 7
today
Current Impact Of AI In the Business World
Data analysis efforts improvement and Streamlining processes and reducing
provision of better and faster insights the time and resources required to
that can promote strategic decision and Decision Efficiency
complete certain tasks
Making
overall performance
Current AI
Impact on
Customer Revenue
Businesses
Scaling and supporting Service Growth Business are able to develop new
companies’ customer services, products and services faster, or enter
Cost
from chatbots and virtual new markets. Companies may be
Reduction
assistants which are equipped able to upsell in more efficient ways
with NLP techniques, to with personalized offers or
predictive and sentiment suggestions
Cost reduction made available by automating
analytics
manual tasks and reducing redundant labor
costs
88
AI Adoption and Areas Of Focus
Companies that are advanced with AI (“Leaders”) Companies are more focused on leveraging
are pioneering widespread adoption of AI in AI for productivity, decision making, customer
comparison to other companies in the market experience, product/services innovation and
employee experience
Q. To what extent is your company looking to integrate AI Q. To what extent is your company looking to integrate AI
technologies into its operations? Source: PwC 2022 AI Business technologies into its operations? Source: PwC 2022 AI Business
Survey, March 2022: Leader base of 364; Other base of 631 Survey, March 2022: Leader base of 364; Other base of 631
99
Sources: PwC US
Which Industries Currently Utilize AI the most?
Companies reported they Companies reported using
42% 35%
are exploring AI AI in their business
Financial
Tech Healthcare
Services
Fraud detection, risk Machine learning, cognitive Patient diagnosis, treatment
management, and investment computing, and robotics planning, and drug
analysis development
Automotive
Retail
& Assembly
Route optimization, demand Personalized recommendations,
forecasting, and autonomous and automated inventory
vehicles management
1100
Sources: PwC US, Forrester, IBM
Adoption Rate
Industry/Function HR Manufacturing Sales & Product/service Risk Service Strategy & Supply chain
Marketing development operations corporate management
finance
Automotive & Assembly 11% 26% 20% 15% 4% 18% 6% 17%
Retail 2% 18% 22% 17% 1% 15% 4% 18%
Financial services 10% 4% 24% 20% 32% 40% 13% 8%
Healthcare/pharma 9% 11% 14% 29% 13% 17% 12% 9%
High tech/telecom 12% 11% 28% 45% 16% 34% 10% 16%
Cross Industry average 9% 12% 20% 23% 13% 25% 9% 13%
Companies that use AI are Plan/execute
motivated by three factors: the 66% applying AI for Benefits from using
ability to cut expenses, develop sustainability goals AI to automate IT,
faster, and grow profitability. 54% business or network
However, each industry’s processes, including
approach to AI applications, as Utilizing AI tools for cost savings and
well as its problems and 53% better customers efficiencies
outcomes, may differ experience 1111
Sources:
Statista 2023
AI Adoption In Practice By Categories (1/2)
Gen Z Gen X Millennials
Younger generations tend to adopt AI technology in their
29% 28% 27% professional life easier and faster
1122
Sources: Fishbowl
AI Adoption In Practice By Categories (2/2)
Key Adoption Considerations
Companies are currently or planning to apply AI to
address their sustainability goals
66%
Companies see benefits from using AI to automate
IT, business or network processes
54%
Global AI spending coming from the US
74%
AI spend out of the global total software spend by
2025
6%
1133
Sources: IBM Global AI Adoption Index 2022,
Forrester
The Global AI Index
Country Talent Infrastructure Operating Research Development Government Total
Environment Strategy Rank
USA 1 4 35 1 1 17 1
China 24 1 6 2 2 2 2
United Kingdom 3 23 24 5 11 11 3
Canada 7 15 5 10 10 1 4
Israel 5 29 14 7 9 45 5
Singapore 4 8 55 4 14 15 6
South Korea 28 6 32 12 3 7 7
The Netherlands 6 9 10 15 8 33 8
Germany 11 13 30 6 12 10 9
1144
Sources: “Israel Innovation authority”
Current availability of AI technology
Perception-based AI Cognition-based AI Customer Experience
Improved customer
Analyze and understand Analyze and interpret data
experience with faster
Computer visual data (e.g. images) to support business strategy
Decision
delivery decisions
Vision
Making
Understand and analyze Understand, learn and percept
human language (e.g. text) data to make predictions and Scale and Efficiency
NLP
Predictive trends New levels of productivity
and cost savings through
Find best solutions to
Recognize and extract text
automated processes
problems with various
from an image or scanned
OCR techniques (e.g. ML models)
document Optimization
Create and generate new New Ways of Working
Build interfaces for
information and context based
Advanced applications to understand Re-thinking of the operating
Generative on user input and large
text or speech
Recognition model to enable intelligent
datasets
delivery
1155
stfieneB
tnerruC
AI, in its current state, is primarily at the feature level rather than at the infrastructure level. AI technologies are being used to add new features to
existing products and services, such as voice recognition or image recognition. These features are built on top of existing infrastructure and use AI
algorithms to perform specific tasks. While there have been some attempts to integrate AI more deeply into the infrastructure level, such as with edge
computing, the majority of AI usage is still at the feature level.
Current Prominent Local AI Use Cases
Automation of IT Marketing and Sales Fraud Detection AI Monitoring &
processes Business Analytics or Financial Planning & Governance
Security and Threat Intelligence Analysis Conversational AI or
Detection Virtual Assistants
1166
Sources: IBM Global AI Adoption Index 2022
Risks and
Barriers
1177
PwC | Tomorrow’s audit, 17
today
Biggest Challenges when Adopting AI
Fragmented Technology Stack No AI Methodology The definition of AI's
standard for deploying AI systems. The AI proven playbooks, including designs,
community has not converged yet on best practices, and technology pipelines.
formats and interfaces across the AI/ML
stack
Misguided Strategy Performance AI-Business Alignment Clear
cannot be guaranteed on an ongoing definitions of KPIs and KRis which are
basis. Lack of clear definitions of subject to ongoing assessment,
business goals and inflated evaluation and re-design
expectations
New Business Requirements
Evolving AI Regulation The technology
Identifying new requirements and
environment is rapidly changing. Lack of
insights as they evolve. Embrace
GRC (government, risk & compliance)
uncertainty
standards
1188
Source – Data Science Group
Current Regulation Highlights
1199
dna
sutatS
sthgilhgiH
evitcejbO
➔ The focus is on ethical, legal, and technical ➔ New York joined a number of states, ➔Several states in the US have passed
aspects of its use. including Illinois and Maryland, in general data privacy legislation that goes
➔ For high-risk AI applications there are regulating automated employment into effect at various times in 2023. These
additional requirements also for a decision tools (AEDTs) that leverage AI to laws contain provisions governing
conformity assessment. However, the AI Act make, or substantially assist, candidate “automated decision-making,” which
has no specific guidelines on how such screening or employment decisions includes technology that facilitates
conformity shall be demonstrated in ➔ The Equal Opportunity Employment AI-powered decisions
practice. Commission (EEOC) launched an initiative ➔AI-focused bills have been introduced in
➔ The GDPR requires heightened compliance on “algorithmic fairness” in employment Congress
when companies use technology like AI to ➔AI regulation appear to be potentially
solely make automated decisions that emerging from the Federal Trade
produce “legal … or similarly significant” Commission (FTC)
impacts on a consumer
noitalugeR
EU AI Act / GDPR US Regulation Future Regulation
Proposed legislation, which aim to No direct legislation as of now. Initial Future regulation may emerge in
accelerate the development and uptake of approach to AI regulation emerge, focused 2023-2024, mainly pertaining to model
AI, and to ensure that its use is according on specific AI-use cases bias, user rights, transparency and AI
to EU values governance
Types of Risks
❏ Lack of
accountability
❏ Rogue AI detection
Control
❏ Adversarial attacks
❏ Privacy protection
Security Enterprise
Performance Social ❏ Reputational
❏ Financial
performance
❏ Legal compliance
Economic
❏ Missinformation
❏ Errors
❏ Public manipulation
❏ Bias & Discrimination
❏ Opaqueness / Lack of
traceability ❏ Job displacement
❏ Enhancing inequality
2200
What’s Hindering AI Adoption?
Main barriers of AI adoption reported by companies
24% 24%
25%
29%
34%
Projects are too complex or Lack of tools or platforms to Limited AI skills, expertise
Too much data complexity Price is too high
difficult to integrate and scale develop models or knowledge
Majority of organizations haven’t taken steps to ensure trustworthiness and responsible AI adoption
Can’t explain their Not tracking performance Not making enough efforts
61% 68% 74%
AI-powered decisions variations and model drift on reducing data bias
2211
Sources: IBM Global AI Adoption Index 2022
AI Risk Categorization
❏ Datasets shift/skew
❏ Patterns of Drifts
❏ Business Problem ❏ Structural Changes
❏ Formulation Anatomy of ❏ Generative Changes
DS Process
❏ Uncertain Realm ❏ Datasets versioning
❏ Experimental/Exploration ❏ Models versioning
❏ Pipeline versioning
❏ Evaluation measures
versioning
❏ Data Quality Dimensions &
Granularity ❏ Regulation
❏ Imbalanced Datasets ❏ Fairness / Bias
❏ Data Lineage & Provenance ❏ Auditability
❏ Data Preprocessing & EDA
❏ AI Cybersecurity
❏ Model
❏ Algorithm Aversion
Selection/Architecture
❏ Transparency
❏ Model Inference latency
❏ Causality
❏ Model Hyperparameters
Tuning
❏ Overfitting/Generalization Technical Debt 2222
(OOD)
Source – Data Science Group
How to Mitigate Potential Risks?
Identify unique Control your data Keep governance Validate Diversify your
vulnerabilities Pay special attention up to speed independently - team
Determine where bias to issues in historical Governance should be and continuously Building diverse teams
could creep into your data and data continuous and You can use wither an helps reduce the
datasets and acquired from third enterprise-wide. Set internal independent potential risk of bias
algorithms and where parties. This includes frameworks, toolkits team or a third party falling through the
it could cause major biased correlations and controls to help to analyze your cracks. People from
damage between variables. spot problems before algorithms for different racial and
they may proliferate. fairness. gender identities and
economic
backgrounds will
notice different biases.
2233
Sources: “Understanding algorithmic bias and how to build trust in AI” - PwC US
Auditing & QA of AI Models for Verified Development &
Deployment
AI Audit Modeling
Auditing AI models before deployment is crucial to
avoid unintended consequences. As organizations
deploy AI systems for core functions, they face new
AI Audit Process
risks due to statistical uncertainty, which can
result in dire consequences and business failures.
The AI auditing process formalizes a pipeline to
Without clear AI standards, audits, risk
minimize potential AI risks and human error in
management strategies, and GRC standards,
decision-making processes. It leverages domain
organizations can mitigate major AI disasters, as
expertise to validate AI systems, applications,
already seen in many major institutions.
technology infrastructure, and standards for quality,
reliability, and consistency. The process ensures
alignment with business and governance
standards, generating human-readable specifications
that are useful to end-users.
2244
Source – Data Science Group
Future State
2255
PwC | Tomorrow’s audit, 25
today
The Rise of Generative AI
Companies growth opportunities in the AI generative
space: what’s next?
New product and services creation
❏ Idea generation
❏ Prototyping
❏ Market Research
R ❏ Customization Faster decision making
G
CA ❏ Process Optimization
% ❏ Predictive Analytics
7
33. ❏ Customer Insights
Enhanced customer demand ❏ Risk Assessment
forecasting ❏ Processes
Automation
❏ Inventory Optimization
❏ Sales Forecasting
❏ Supply Chain Improve efficiency of marketing
Three major areas that will be deeply impacted by Optimization campaigns
generative AI in the near future ❏ Personalization
❏ Better Customer
Segmentation
❏ Ad Optimization
New Drug Material Financial
❏ Faster Content Generation
Discovery Science Services
2266
Sources: Forrester
Near-Future Value Capture Opportunities
Decision Making Simulation Data Analysis
Computer-based processes The ability to process AI nowadays can help
that uses AI to mimic and significant amount of historical automate and streamline
simulate real-world scenarios data and produce and analyze the data analysis process
or system, allowing for the future optional decision trees (e.g. cleansing) as well as
testing and optimization of scenarios. Adoption rates are significantly improve
various strategies, outcomes, significant when it comes to predictive models and
and performances. areas of technology, operations analysis of unstructured
and maintenance, and also CX data.
and strategy.
2277
Sources: PwC US
Seize Current AI Value
Subject Matter Value Capture Proposal
ML models require huge amounts of data, which simulation
Synthetic data
models can create. Synthetic data can turbocharge other AI
and analytics initiatives. Simulation
To help make sense of your various data sets in the context
Digital Twin
of your business, consider making Digital Twins a platform
capability.
Simulating real-world scenarios or systems, allowing for the
Predictions and
testing and optimization of various strategies, outcomes,
Scenario modeling
and performances.
Data Analysis
Utilize AI abilities to clean and organize your data which
Labor cost
can save you time and resources put into this effort.
Bring your data specialists (e.g. Data Scientists, Engineers)
Data Specialist together before initiating any endeavour in order to align
methodology and goals.
Decision-Making
Consider combination between AI and other immersive
Other immersive technologies and especially Blockchain related technology
technologies which can help overcome data related problems (e.g. bias,
privacy, security).
2288
Sources: PwC US
Where Will Adoption Increase Most?
2299
D a t a - c e n t r i c A I
M o d e l - c e n
pA
nec
t r i c A
tacilp
A cirt
I
oiI n s -
Fusion of AI techniques
(composite AI)
Synthetic Data
Massive increase in adoption as
Expected to reach mainstream adoption
synthetic data, mainly to tackle
in two to five years, the business benefits
cost and timing problems
of composite AI are likely to be
pertaining to ML development.
transformational, enabling new ways of
doing business across industries that will
result in major shifts in industry
dynamics.
AI trust, risk and security Improved Business Cases
management
Organizations will need to integrate digital ethics
into their AI strategies to bolster their influence
and reputation among customers, employees,
partners and society.
Sources: Gartner
H u m a n - c e n t r i c A I
Decision intelligence and edge AI are both
expected to reach mainstream adoption in
two to five years and have transformational
business benefits.
Key Takeaways &
Implementation Guideline
3300
PwC | Tomorrow’s audit, 30
today
ROI Measurement Considerations
Companies are now increasingly able to predict AI
implementation ROI thanks to new assessment methods.
Qs. How confident are you These can capture not just “hard” returns, such as increased
in your company’s ability
to Assess ROI of current AI productivity, but also “soft” costs, such as new hardware
initiatives? How confident
spending
are you in your company’s
ability to accurately
Predict ROI of AI initiatives
in the next 12 months
❏ Time Savings ❏ Better Experience
❏ Cost Savings ❏ Talent Retention Soft Returns
Hard Returns
❏ Productivity Increase ❏ Team Agility
❏ Revenue Increase Benefits / Returns (capabilities)
ROI =
❏ Data Investments
Investment Costs
❏ Licenses ❏ Compute and Storage
Hard Costs ❏ Resources ❏ SME (Subject Matter Soft Costs
Experts)
❏ Data Science training
3311
Sources: “Solving AI’s ROI problem. It’s not that easy” - PwC US
Labor Considerations – Human-Centric AI
Despite AI talent shortage, companies that take holistic approach to AI are far more advanced than those taking a
piecemeal approach. Such companies also 1.5x more likely than other companies to plan on leveraging more
third-party vendors with their scalable AI workforce.
Highest value use of AI Reducing the need for The AI talent shortage can
in the labor market rote work will make be mitigated by taking
today is to help people employees life more in-house specialists that
to do better work, easier and more possess some of the skills
reducing the press to fill engaging you need, and provide them
hard-to-fill positions with the rest
Organizations will use AI to address labor or skill shortages in three main ways
Reducing manual or Increasing employee Improving recruiting and
65% 50% 45%
repetitive tasks Learning & Development human resources
processes
3322
Sources: IBM Global AI Adoption Index 2022, PwC US
The Future of Working with AI - Key Takeaways
Trends
Ethics & Governance
❏ AI is recession-resilient and continued AI
❏ Algorithmic and data biases will likely be
investments will continue in 2023,
regulated in the near future and will
particularly among business impacted by
create uncertainty regarding usage of
economic and supply chain disruptions
certain AI models
❏ In 2023 low/no code AI tools will be more
❏ Increased AI models regulations will force
involved in the software development
change in many companies’ systems and
lifecycle
infrastructure
❏ Image editing is going to be changed
❏ Applications of AI will not be fully
dramatically
implemented into enterprises until
business cases and expected ROI will be Workforce
fully understood
❏ In the short term - AI will free up employees
❏ Industries with more consumer
to focus on value-add tasks and will improve
regulatory pressure will have lower AI
job satisfaction
adoption rates
❏ AI applications still require human
❏ AI governance will likely join
supervision and therefore it is unlikely
cybersecurity as a board-level topic
that we will see dramatic HR changes in
3333
Sources: World Economic Forum. IBM Global AI Adoption index 2022, Source:The state of Machine Learning the near future, except certain functions
at the end of 2022 (cnvrg.io)
The Future of Working with AI - Key Takeaways
Management Adoption
❏ Management’s decision making ❏ AI adoption will probably still remain
processes will not change low in 2023
significantly in the short term ❏ 10% of Fortune 500 enterprises will
generate content with AI tools in 2023
❏ 25% of tech executives (e.g. CTO/CIO) will
❏ Company’s ability to completely
report to board/committee on AI
change its processes will be hard, and
governance
therefore we expect adoption to be
slow. It will be likely to be easier for
companies to integrate AI into their
Additional Opportunities
core processes if they can spin off
certain functions or form brand new
❏ Big opportunities of utilizing AI exist in M&A, the
business units
process itself and also ESG matters which
❏ AI models still considered as black box
companies invest a vast amount of time and
for non-technological employees
resources into them both
which will require training and
upskilling
❏ AI can improve and transform the way companies
❏ AI infrastructure challenges will
manage their databases and documentation
surpass data associated issues as the
biggest challenge for scaling AI/ML 3344
Sources: Experts Interviews, PwC Israel, Forrester Predictions 2023: Artificial Intelligence, run:ao 2023 state
of AI Infrastructure
Implementation Do’s and Don'ts
AI tools tend to be highly accurate, but they are definitely not perfect and can make bizarre mistakes. Maintaining human oversight
during the implementation and afterwards is crucial to ensuring quality, both for model training and for the final correction of the
output in downstream processes. Leaders must stay vigilant about the potential risks and cognizant of the need for proper training
and corporate governance
Action Implementation Guidelines
● Relevant data requirements should be identified as a first step, then evaluate the sources currently
Define the Problem
available
● Success criteria should be clearly defined and be as measurable as possible
● Stakeholders should be involved in the process of defining the problem (inc. external stakeholders
and customers)
● The program should be focused on digital and analytic understanding, awareness and
Develop Training
understanding of the flaws and advantages of the tools
Program ● All employees will need to be upskilled (inc. CEO)
● Make sure employees understand basic concepts of AI technologies
● Companies should ensure that employees are conversant with current technologies and this
transformation will take hold only if the entire workforce is brought along
● Anyone for whom a substantial portion of daily tasks will essentially be eliminated should be
Anticipate Impact
monitored (*that is the reality of automation)
● The message to communicate to such employees is that AI will free them to focus on
3355
harder-to-solve problems which demand human judgement or creativity
Sources: PwC US
Implementation Do’s and Don'ts
Action Implementation Guidelines
● Tactical level incentives to use AI tools and the new platform can create better engagement
● Incentives are dependant on corporate culture, but should include KPIs for performance reviews,
Offer Incentives
bonuses or coupons
● Employees will be compelled when they start seeing their productivity enhanced
● Appoint top-down champions who consistently communicate the benefits of the AI
Promote Cultural implementation
● Communicate the message that using AI tools is not only good for customers but also for the
Change
company’s growth
● Build trust by focusing on competence, consistency, dependability and transparency
● Make sure compliance with relevant regulations and appropriate requirements
Ensure Safe and ● Understand the background technology behind the AI tools
● Develop ethical and user policies
Trustworthy Use
● Establish internal audit team to monitor abusive, illegal and/or inappropriate usage
● The platform should combine data management, automation tools, and AI applications, and keep
people at the loop
Establish Platform
● The platform could be enterprise-level portal, wherein data could be stored and exchanged, and
applications uploaded and downloaded
● The platform should be accessible to all employees and be receptive to employee-led innovations
● Make sure the democratization of these powerful technologies are utilized responsibly 3366
Sources: PwC US |
9 | pwc | nextgen-survey-2024.pdf | PwC’s Global NextGen Survey 2024
Vietnam report
NextGen Vietnam
Succeeding in an AI-driven world
1 | PwC’s Global NextGen Survey 2024 - Vietnam report
2 | PwC’s Global NextGen Survey 2024 - Vietnam report
Table of Contents
Foreword 5
1. Embracing Leadership in the Digital Era 6
Rising generational involvement in family businesses 7
Setting a clear vision for the digital future 8
Leading the reinvention imperative in family businesses 10
2. Exploring Generative AI (“GenAI”) and Emerging Technologies 12
Attuned to emerging technologies 13
Ambition to lead AI innovation in family businesses 14
Navigating the gap between NextGen ambition and organisational AI 15
readiness
Harnessing the advantages of AI in the next three years 16
3. Maximising NextGen’s contribution to family businesses 21
Fostering alignment between generations 22
Governance and trust as bedrock for growth and innovation 23
Next steps 24
About PwC NextGen survey 28
Contact us 30
3 | PwC’s Global NextGen Survey 2024 - Vietnam report
44 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Foreword
In the ever-evolving landscape of business and technology, the emergence
of generative artificial intelligence (“GenAI”) stands as a transformative
force, reshaping industries and redefining the very nature of leadership.
PwC’s NextGen 2024 Survey sheds light on Vietnamese NextGen’ pivotal
position in shaping the future of family businesses amidst the digital age’s
transformative tide. The NextGen in Vietnam are not mere spectators to
this paradigm shift, but are poised to step into leadership roles, armed
with a keen understanding of the significance of AI and its implications
for future strategies. More than ever, they have the capacity to shape their
family businesses and make an impact as they take up responsibilities as
stewards of their businesses.
We encourage you to share the insights from this survey with family
members, top management and peers, and join us on this exciting and
transformational journey.
Johnathan Ooi Siew Loke
Entrepreneurial and Private
Business Leader
PwC Vietnam
55 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Embracing
Leadership in the
Digital Era
66 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Rising generational involvement
in family businesses
Our ongoing analysis of family businesses Moreover, the number of respondents feeling
and the members of the next generation disengaged from their family businesses has
(“NextGen”) in Vietnam since 2019 has plummeted to just 12%, down from 34%
shown increasing generational involvement in 2022. This indicates a notable surge in
and transition within these enterprises. the contribution of NextGen to their family
enterprises.
In our latest report, the PwC Global
NextGen Survey 2022 – Vietnam’s NextGen The current business environment, post-
in Focus, we shed light on the Vietnamese pandemic, presents an opportune moment
NextGen who were emerging as leaders for NextGen to take the reins. With ever
in waiting and becoming particularly greater disruptions and complexities arising
noticeable during the pandemic. With from technological advancements and global
aspirations to lead and a readiness to shifts, there exists a wealth of opportunities
assume their roles, Vietnamese NextGen for innovation and entrepreneurship – areas
are now rising to the challenge, actively where the new generation of leaders excel.
participating in shaping the future of their
As Vietnam’s NextGen leaders step up
family businesses.
to the plate, they are poised to drive the
Two years on, now 52% of NextGen evolution of family businesses, striving for
respondents from our survey are already growth, resilience, and success in the face of
occupying leadership positions, a unprecedented challenges.
substantial increase from 29% in 2022.
Vietnam NextGen Current Job Role / Position (%)
52
Leadership role
29
15
Shareholder/beneficiary
11
15
Governance role
8
Employee/intern 12 2024
16
18 2022
Intrapreneur
5
9
Entrepreneur
16
Other 3
12
Not engaged yet
34
7 | PwC’s Global NextGen Survey 2024 - Vietnam report
Setting a clear vision for the digital
future
NextGen in Vietnam feel positive about their career opportunities and
ambitions
With a strong emphasis on personal and professional development, 76% of NextGen within
family businesses in Vietnam prioritise opportunities for learning and growth within their
companies. Moreover, they demonstrate a clear understanding of both the career aspirations set
by the current generation and their own ambitions for future roles within the family business.
NextGen’ future in the business (%)
76
I feel I have the opportunity to learn and grow within
the family business
75
73
I am clear on what the current generation’s goals
are for my career path in the family business
59
70
I have a clear idea about my personal ambitions
for a future role in the family business
70
Vietnam
Global
88 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
8
Aside from business growth priority, talent management and technology adoption are top
priorities for NextGen in the next two years
As Vietnamese NextGen step into leadership Additionally, they emphasise the importance
roles amidst the dawn of technological of strengthening the technological foundation
disruption, their focus remains steadfast (36%) and ensuring that employees possess
on securing the prosperity of their family the necessary skills to embrace new
businesses. A notable 39% prioritise growth as technologies (33%). This acute understanding
a top business imperative, underscoring their of the key ingredients for business success
commitment to driving forward momentum. demonstrates NextGen’ clear vision of what
drives success in the new era.
Recognising the vital role of human capital in
fortifying their businesses and the associated In navigating the challenges faced by
technological infrastructure, Vietnamese businesses and society today, Vietnamese
NextGen prioritise initiatives aimed at NextGen recognise the importance of
building and nurturing the talent pools of their a human-led, tech-powered approach.
businesses (39%). Their forward-thinking mindset reflects
their commitment to building resilient and
innovative businesses that can thrive in an
ever-evolving landscape.
Key priorities over the next two years (Top 3) - Vietnam
Global: Global:
Top 3 NextGen
priorities engagement
39
Achieving business growth
39 52 55
Talent management -
39
attracting/retaining the best
18 36 30
young talent
36
Adopting new technologies
39 25 33
Upskilling the digital capabilities 33
of our workforce 30 17 23
Reconsidering our asset allocation 27
and investments 18 19 25
Improving the working conditions/ 21
15 26
practices of our employees 24
Increasing our focus on investments 21
18 21
for sustainability and impact 21
Expanding into new sectors or 21
37 42
markets 15
Ensuring we offer the right
18 22 28
products and services for
24
today’s customers
9 19 21
Investing in innovation and R&D
18
Top 3 priority Engaged or likely to be engaged
9 | PwC’s Global NextGen Survey 2024 - Vietnam report
Leading the reinvention imperative
in family businesses
NextGen in Vietnam are in line with Reshaping management and
the sentiment of CEOs across the business strategy
Asia Pacific region regarding the
reinvention imperative The top areas where Vietnamese NextGen
seek to add value are in professionalising
In light of PwC’s 27th Annual Global CEO and modernising management practices.
Survey - Asia Pacific; where 69% of CEO Additionally, they want to play a key role in
respondents were from privately owned facilitating the separation of family ownership
businesses and from management. This highlights the
63% importance of external ideas and talent in the
success and longevity of family business.
Moreover, Vietnamese NextGen see
Asia Pacific CEOs expressed
themselves as better suited than their
scepticism about the economic
predecessors in developing a business
viability of their companies
strategy tailored for the digital age. With
within a decade on their current
a focus on fortifying the company’s
trajectories, technological foundation, this again
highlights the pivotal role that they are to
play in shaping the future trajectory of their
a pressing dual imperative emerges: organisations. Their proficiency, particularly
addressing immediate profitability challenges in navigating AI disruptions, is poised to be
while concurrently reinventing businesses for instrumental in ensuring the company’s long-
future sustainability. term success.
Vietnamese NextGen bring their distinct
perspectives to the forefront, identifying
avenues where they can drive substantial value
within their enterprises, alongside articulating
clear business objectives. Positioned as
catalysts for change, they recognise their key
roles in reshaping the future sustainability of
their family businesses.
Where NextGen feel they can add the most value to the business (%)
Having a business Having a clearly Separating family
strategy fit for the defined purpose, i.e. ownership from
digital age ensuring the business management
is not just about
making profits
Vietnam: 24% Vietnam: 18% Vietnam: 15%
Global: 21% Global: 10% Global: 8%
1100 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Thriving on change
The story of Biti’s
Miss Vuu Le Quyen
CEO of Biti’s
In the dynamic realm of business, where As Biti’s starts integrating emerging
technology constantly reshapes the technologies such as GenAI into its
landscape, the story of Ms. Vuu Le Quyen, operations, Ms. Quyen emphasises the
CEO of Biti’s, offers valuable insights into importance of involving the founding
navigating change and preparing for an AI- generation through sharing compelling
driven future. use cases with her parents, who founded
the company, demonstrating the tangible
While driving business growth remains the
benefits and opportunities of new
company’s top priority, Ms. Quyen is deeply
technologies, thus fostering support and
committed to a people-centric approach.
understanding.
Initiatives such as “Happy Biti’s” underscore
her dedication to fostering a positive and “Reflecting on Biti’s current early-stage
transparent work culture that prioritises adoption of technologies like GenAI, I see the
employee well-being. Recognising the imperative for action. In the ever-changing
inevitable impact of emerging technologies business and technological landscape,
on the future workforce, she emphasises the adaptation is vital for survival. By identifying
need for organisational readiness to embrace gaps, assessing risks and opportunities,
change for the company’s advancement. and investing in areas that yield competitive
advantages, we can attain sustained growth
Acknowledging the natural resistance to
and success, with our people leading the
change within organisations, Ms. Quyen
charge.” - Ms. Quyen.
highlights the importance of effective change
management. In addition to providing
processes and training, she values the
significance of shifting mindsets. Clear
communication and engagement from
leadership are vital in helping employees
grasp the benefits of adaptation. Once
employees recognise the value and benefits,
they become proactive in self-learning,
experimentation, and integrating new
knowledge into their daily tasks.
1111 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Exploring Generative AI
(“GenAI”) and Emerging
Technologies
1122 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Attuned to emerging technologies
Most NextGen in Vietnam are very interested in
GenAI
According to the 2024 PwC Asia Pacific CEO Survey,
the emergence of climate change and technological
advancements, notably led by innovations like GenAI,
82%
has intensified the call for CEOs to adapt their strategies.
An overwhelming 77% of business leaders in the region
anticipate substantial shifts in how their companies
of NextGen in Vietnam
generate, deliver and capture value within the next three
are personally
years, all due to the influence of GenAI.
interested in GenAI
Echoing this sentiment, Vietnamese NextGen are
(Global: 82%)
increasingly intrigued by the transformative potential
of GenAI. Our research reveals an impressive 82% of
Vietnamese NextGen expressing personal enthusiasm for
exploring GenAI, reflecting a widespread recognition of its
power among the younger cohort of leaders.
Vietnamese NextGen see themselves as
knowledgeable on GenAI
55%
This shows a confidence in GenAI’s ability to drive
positive change and innovation, mirroring a broader
of NextGen in Vietnam
trend of embracing cutting-edge technologies in
feel personally
Vietnam’s evolving business landscape.
knowledgeable
This knowledge on GenAI makes Vietnamese NextGen
about GenAI
well positioned to derive insights and unlock the
(Global: 53%)
creative possibilities and business potential of AI and
emerging technologies, from AI-generated content to
AI-driven analytics.
1133 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Ambition to lead AI innovation in family
businesses
67%
Personally, nearly two third (58%) also
believe that championing AI initiatives will
Vietnamese NextGen share a strong
enable them to make a name for themselves
consensus regarding GenAI’s
and allow them to become leaders within
potential as a powerful tool for
their businesses.
business transformation.
They view themselves as instrumental in
driving the adoption of GenAI, advocating
for its integration across various business
They perceive GenAI not merely as a
functions and processes. And over half (55%)
technological innovation, but as a catalyst
are keen to guide their businesses through
for redefining business operations,
the complexities of adopting these new
strategies and customer experience.
technologies.
There is widespread recognition among
Their proactive stance towards embracing
Vietnamese NextGen (67%) that AI
GenAI reflects not only their readiness to
represents a significant opportunity for
adapt but also their commitment to driving
family businesses to assume a leading
transformative change in their family
role in the responsible use of technology
businesses and the broader business
and AI. They envision their businesses not
landscape.
only adapting to the digital age but also
pioneering ethical and sustainable practices
in AI implementation.
Agreement with statements (%)
AI is a powerful force for 67
business transformation 73
There is an opportunity for family
67
businesses to take a leading role in the
responsible use of technology and AI 50
Vietnam
Being an AI champion will help me 58
Global
move into a leadership position
40
I feel I can personally help the
55
business to navigate emerging
technologies / AI 42
1144 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Navigating the gap between NextGen
ambition and organisational AI readiness
However, a significant disparity arises 76%
between the personal ambition of
Vietnamese NextGen for GenAI and the
Vietnamese NextGen respondents
readiness of organisations to implement
say that their business is likely to be
such initiatives.
involved in AI-related initiatives in the
Vietnamese family businesses are very future,
much in the early stage of adopting these
new technologies, with a majority (63%) of
family businesses in Vietnam having yet to showing an optimistic outlook towards
explore AI. the adoption of this emerging technology
within the Vietnamese business landscape.
Nevertheless, there are still promising signs
Crafting an “early-stage” GenAI strategy is
of change. Nearly one third revealed that
essential for family businesses to maintain
they are currently exploring and piloting
a competitive edge amidst the rapidly
AI-related initiatives (27%), with a smaller
accelerating imperative for business
proportion having already implemented
reinvention.
such initiatives (9%). In addition, 27% of
Vietnamese family businesses (compared to
Read more:
the global average of 14%) have dedicated
Craft an “early-stage” GenAI
personnel or teams responsible for GenAI
strategy for leading adoption
initiatives within their organisations. and success.
Business’s current level of adoption of GenAI (%)
64% 24% 3% 9%
No activity/ Exploration Test/ Pilot Implementation
Not sure (Global: 30%) (Global: 7%) in a few or many areas
(Global: 55%) (Global: 7%)
36% already exploring/implementing AI
Read more:
GenAI: Bridging the gap
between intent and adoption
15 | PwC’s Global NextGen Survey 2024 - Vietnam report
Harnessing the advantages of AI
in the next three years
When exploring about the impact of GenAI on
family businesses,
39% agree that GenAI has already
begun influencing company strategy.
However, opinions diverge on its immediate effects
such as reducing headcount (24% believe this will
NextGen expect a
happen) and increasing profitability (18%).
rising impact from
A significant consensus is found in the acknowledgment
GenAI on business
that GenAI will necessitate a fundamental shift in workforce
skills (73%). Vietnamese NextGen widely agree that
employees must develop new competencies to effectively
harness this technology. Additionally, 64% share the
understanding that GenAI will reshape how companies
operate, from value creation to delivery and capture.
Impact from GenAI on family business in the next three years
Last 12 months Next 12 months Next 3 years
39% 24% 73%
say that AI has think that GenAI will think GenAI will require most of their
already changed their result in headcount workforce to develop new skills
company strategy reduction (Global: 48%)
(Global: 15%) (Global: 18%) 64%
18%
think GenAI will significantly change
think GenAI will increase the way their companies generate,
the profitability of their deliver, and capture value
company (Global: 44%)
(Global: 21%)
1166 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Seizing opportunities presented
by AI, particularly in regard to the
workforce and skills
Vietnamese NextGen view GenAI as a catalyst Through leveraging AI-driven insights and
for business transformation, anticipating automation, businesses can effectively equip
benefits like increased employee productivity their teams with the digital skills necessary for
(39%), cost savings (39%), and enhanced success.
customer experience (36%). This highlights
These insights again highlight that Vietnamese
the strategic significance of embracing AI in
NextGen recognise the importance of a human-
today’s competitive landscape, positioning
led, tech-powered approach, where new
family businesses for success in the digital age.
technologies such as GenAI can greater power
In discussions about workforce upskilling, human potential.
Vietnamese NextGen reaffirm the critical role
of AI. Over half believe that GenAI will play a
key role in enhancing the digital capabilities of
their workforce, surpassing the global average
of 41%.
Top
opportunities or benefits
that NextGen believe AI
can/will bring to family
business
Enhanced
customer
experience
36%
Cost saving
Increased 39%
(Global: 25%)
employee
productivity (Global: 36%)
39%
(Global: 46%)
1177 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Acknowledging challenges
in AI advancements
In line with their global counterparts, Vietnamese
NextGen recognise the challenges inherent in AI
advancements. Over two thirds of them acknowledge
the rapid evolution of AI technologies, which poses a
significant challenge for businesses striving to keep
pace with these advancements. Additionally, nearly half
of Vietnamese NextGen find it challenging to capitalise
on AI, indicating the complexity involved in effectively
leveraging this technology for business purposes.
Looking ahead,
73%
Vietnamese NextGen foresee that AI will
intensify competition in the market over the
next three years, highlighting the growing
pressure to stay ahead in an increasingly
AI-driven landscape.
These findings indicate the multifaceted challenges and
competitive dynamics associated with AI innovation,
emphasising the need for strategic adaptation and
proactive measures to navigate this rapidly evolving terrain.
Agreement with statements (%)
In the next three years, AI will lead to more
73
competitor pressure (e.g., new products, entrants,
64
price changes)
Vietnam
AI seems to evolve so quickly that it’s hard 70
to keep up 66
Global
48
It’s difficult to know how to capitalise on AI
51
18 | PwC’s Global NextGen Survey 2024 - Vietnam report
Advocating for a governance
framework for Responsible AI
Over half of NextGen in
Vietnam express concerns
Consequently, Vietnamese NextGen are
about the potential increase in
increasingly acknowledging the necessity of
cybersecurity risks associated governance structures for utilising AI within
with GenAI adoption. family businesses, with 69% recognising the
imperative of defining such frameworks. Clear
governance structures will play a pivotal role
in guiding ethical AI practices, mitigating risks,
and fostering trust among stakeholders.
Within this group, only 21% have taken
This reflects a heightened awareness of tangible steps. However, a further 48%
the vulnerabilities that may arise from the believe they need to do so, signalling a
use of these new technologies, such as growing awareness of the importance of
data breaches, privacy infringements, and proactive governance in AI adoption. There
cyber attacks. As GenAI systems often rely is a need for family businesses to prioritise
on vast amounts of sensitive data, there’s the establishment of robust governance
a growing need for robust cybersecurity frameworks to deploy AI technologies ethically
measures to mitigate these risks and and effectively.
safeguard critical assets.
Agree that GenAI is likely to increase the following risks in your company in
the next 12 months
Cybersecurity risk 58
(e.g., phishing attacks, data breaches)
48
52
Spread of misinformation
33 Vietnam
Global
52
Legal liabilities and reputational risks
29
Bias towards specific groups of 39
customers or employees
25
19 | PwC’s Global NextGen Survey 2024 - Vietnam report
SAudcocpetsins gst GoreinesAI responsibly
AI has the power to greatly transform our lives and work, but
we need to manage its risks to unlock its full potential in a
secure manner. When integrating AI into business processes,
it’s crucial to understand how decision making is supported
to ensure accuracy and fairness, as well as protect privacy
while fostering growth and innovation. That’s where
Responsible AI comes in.
Responsible AI is about managing risks in AI-based
solutions. It means evaluating our current practices or
creating new ones to ensure we use AI responsibly.
Organisations worldwide recognise the importance of
Responsible AI, though they may be at different stages of
implementation. By investing in Responsible AI from the
start, we gain a competitive edge. We can actively assess
related risks and establish an effective AI governance
framework using a standardised AI risk taxonomy and
toolkit.
As AI may significantly impact current family businesses in
the near future, NextGen leaders in Vietnam should consider
how AI could disrupt their current business models. They
need to seize new opportunities that AI can offer and invest
in the right resources and expertise to foster a culture of
adaptability. By embracing Responsible AI throughout their
AI adoption journey, they can harness its transformative
power while safeguarding their core values.
With this approach, family businesses in Vietnam can
navigate and shape a sustainable future of success within
the evolving AI landscape.”
Pho Duc Giang
Director
Data Trust and Cybersecurity
Services
PwC Vietnam
20 | PwC’s Global NextGen Survey 2024 - Vietnam report
20
Maximising NextGen’
contribution to family
businesses
2211 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Fostering alignment between generations
Vietnamese NextGen seek to be agents of This highlights the barrier to adopting
change in order to bring innovation and change new ideas and innovation within family
within family businesses. However, in order for businesses, as the NextGen seek to drive
them to play their role as innovation catalysts, transformative change while encountering
there will need to be alignment between the internal resistance.
perspectives of the two generational cohorts, to
Furthermore, there is disparity in
make sure that business and family are united
perceptions regarding digital capabilities
in carrying out these transformative tasks.
between CurrentGen and NextGen.
A notable finding reveals that Interestingly,
almost half of 45% 42%
Vietnamese NextGen
perceive a lack of comprehensive a greater proportion of CurrentGen
understanding among the current have a positive view of their
generation (“CurrentGen”) company’s digital capabilities
regarding the opportunities linked
compared to NextGen (27%).
to technology transformation within
the business,
This suggests a potential gap in
a figure notably higher than the global understanding or prioritisation of digital
average (29%). initiatives between the two generational
cohorts. Closing this gap and fostering
alignment in perspectives will be crucial
Additionally, for leveraging the full potential of NextGen
as innovation accelerators within family
a substantial majority 61%
businesses.
of Vietnamese
NextGen encounter
resistance within their organisations
towards embracing change,
compared to the CurrentGen (39%).
Agree with statements - Vietnam (%) ?
There is a resistance within the 61
company
39
NextGen
27
CurrentGen
We have strong digital capabilities
42
2222 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Governance and trust as bedrock for
growth and innovation
Strengthening family governance structure Additionally, over half of NextGen (52%)
and trust within family businesses struggle to understand the criteria for family
employment and board member/executive
Strong governance and internal trust serve as
selection, indicating a transparency gap.
the bedrock for family businesses venturing
into the era of emerging technologies. Moreover, trust issues pose a significant
However, Vietnamese NextGen show less challenge, with NextGen less likely to perceive
optimism in these crucial areas compared high levels of trust between family members.
to the perspectives of the CurrentGen, as Particularly, only 27% of NextGen believe
revealed in our Family Business Survey 2023 there are high levels of trust between them
- Vietnam Report. and the CurrentGen, compared to 31% of the
CurrentGen.
45%
Addressing this “trust gap” is paramount for
Vietnamese NextGen are likely the future growth of family businesses. Our
Family Business 2023 survey emphasises the
to express their clarity on the
importance of establishing a formal family
governance structure of their
governance structure and fostering transparent
business,
communication to manage conflicts effectively
compared to 50% of the CurrentGen. and ensure the longevity of family enterprises.
Similarly, perceptions about roles and
responsibilities are less defined among
NextGen, with only 48% feeling clarity
compared to 53% of the CurrentGen.
Agree with statements - Vietnam (%) ?
There are clear roles and
48
responsibilities for those involved in
53
running the business
45
We have a clear governance structure
50
High level of trust between NextGen
27
family members and the current
generation 31
High level of trust between family
15 NextGen
members outside the business and family
members working in the business 25
CurrentGen
High level of trust between family 15
owners and non-management
28
High level of trust between family
18
members and non-family members
within the business 22
2233 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Involvement in succession
Compared to our NextGen 2022 survey, it is encouraging
to note a growing awareness among NextGen regarding
succession planning, with 72% indicating involvement
in the process (up from 58% in 2022), and 39% actively
participating in plan development (up from 26% in 2022).
72% 39%
indicating involvement actively participating in
in the process plan development
(up from 58% in 2022) (up from 26% in 2022)
Regarding succession hurdles, 36% of Vietnamese
NextGen find the readiness of the CurrentGen to retire a
difficult aspect, while 58% anticipate challenges in proving
24
themselves as new leaders or board members. However,
these figures reflect greater optimism compared to our
2022 survey results, where 42% and 61%, respectively,
expressed similar sentiments.
Awareness of succession plan - Vietnam
6
29
21
13
33
26
39
32
2024 2022
Yes, and we have developed the plan together
Yes, but I was not involved in its development
No, there is no plan
I don’t know if there is a plan
24 | PwC’s Global NextGen Survey 2024 - Vietnam report
Next steps
Turbocharging innovation in
family businesses
For
For NextGen
CurrentGen
Seek out dialogue Listen and put innovation in your
CEO and board agenda
If you feel well equipped to
understand the related opportunities Actively listen to concerns and have
and risks, don’t be afraid to talk to clear communication with NextGen
the current generation of leadership on innovation decisions. The decision
and raise your questions or concerns to implement innovation in the
about technological transformation. It business should be a debate about
will be for your mutual benefit. strategy, not about functions, tools or
technology.
Understand your business and
initiate or volunteer pilot projects Involve NextGen in AI
You need to be knowledgeable about You can start by engaging NextGen
the current business model and the in low-risk, high-return GenAI pilot
financial and organisational limits of programmes. This will support the
the company. Embrace opportunities generational transition and prepare
to learn, try and fail through pilot them for future roles in the business.
projects in order to develop your skills Treat them as a valuable resource
and talents with great passion. with which to build your AI strategy
and firm-wide AI capabilities.
2255 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Next steps
Co-managing generational transition
in an AI-driven world
For CurrentGen
For NextGen
Get your licence to earn trust Use NextGen and their enthusiasm
to strengthen the board
You want to earn recognition and
respect in your own right and not Combine NextGen’ acumen for
depend on your birthright. A solid technology with the business
education and relevant working experience of older board members.
experience outside the family Invite them as guests to your board
business will give you the confidence meetings, and allow them to listen,
to contribute and the ability to learn and contribute their fresh ideas
earn the trust necessary for future and perspectives.
leadership or board positions.
Align family values, business
Strike the right balance purpose and governance
Finding the balance among respect, Family businesses can be conscious
continuity, disruption and change adopters of GenAI, but it is important
is key to making the business for everyone in the family to
ready for a digital future. Your role understand what this means and how
is to challenge the status quo in a it aligns with the family values and
constructive and respectful manner. business purpose. Reviewing your
family and corporate governance as
well as your leadership and board
composition will help to get this right.
2266 || PPwwCC’’ss GGlloobbaall NNeexxttGGeenn SSuurrvveeyy 22002244 -- VViieettnnaamm rreeppoorrtt
Generational alignment
in digital era
Aligning NextGen and current leaders’ understanding of
digital initiatives is vital for unlocking NextGen’ innovation
potential in family businesses. Fostering governance and
trust is key.
NextGen need to learn how to combine the legacy and
values of their family business with their own ambitions, as
well as having transparent communication on innovation
ideas. Meanwhile, the current generation can help the next
generation prepare for leadership by involving them in
leadership decision-making and letting them manage lower-
stakes innovation projects where they can prove themse |
10 | pwc | the-emerging-threat-of-ai-powered-fraud_20.pdf | The emerging threat o f AI-powered fraud
Artificial Intelligence (AI) is changing the landscape in our world today. ChatGPT, DALL-E and
other GenAI tools have ushered in a new era of advancements, allowing users to boost
productivity. A 2023 survey by IBM revealed that 42% of enterprise-scale companies have
actively deployed AI into their business model with an additional 40% currently exploring and
experimenting with AI1. This tells one story— AI is poised to transform businesses and will soon
become critical for businesses.
However, the widespread adoption of AI by businesses also
“
means that the technology will attract malicious actors such as
fraudsters and cybercriminals. As legitimate businesses seek to
grow using this new technology, fraudsters are also exploring
how to use AI to advance their “business”. As a result,
understanding the strategic opportunities and the inherent fraud
risks that comes with AI is now of paramount importance for
today’s business leaders.
42% of enterprise-scale companies
have actively deployed AI into their
business model.
Source: IBM Global AI Adoption Index 2023
1. BM Newsroom. 2024. “Data Suggests Growth in Enterprise Adoption of AI is Due to Widespread Deployment by Early Adopters, But Barriers Keep 40% in the Exploration and Experimentation Phases.” IBM Newsroom.
https://newsroom.ibm.com/2024-01-10-Data-Suggests-Growth-in-Enterprise-Adoption-of-AI-is-Due-to-Widespread-Deployment-by-Early-Adopters.
2
The emerging threat o f AI-powered fraud
History of fraud and technology
Historically, adoption of technology by individuals and businesses resulted in a corresponding adoption by fraudsters.
Emails led to the rise of phishing emails and email scams, social media platforms led to the rise of fake profiles for
scamming as well as outright theft of online identity, and e-commerce and digital payment platforms resulted in high
rates of online payment fraud. A recent study estimates that global cumulative merchant losses to online payment
fraud will exceed $343 billion between 2023 and 2027.2
USSD banking introduced in Nigeria also resulted in a surge in sim swap frauds enabling fraudsters to access funds,
obtain loans and make other transactions on victims accounts. Gift cards and reward programmes have led to a
wave of scams, forcing many establishments to either scrap them entirely or implement stricter regulations. In 2022,
Bloomberg reported that PayPal shut down 4.5 million accounts linked to exploiting their incentive and rewards
program.
These examples show that technological advancements have also led to new frauds and vulnerabilities to businesses
and individuals. Consequently, the prevalent adoption of AI also means that AI-powered fraud is coming.
2. Maynard, Nick. 2022. “Online Payment Fraud Losses to Exceed $343 Billion Globally Over the Next 5 Years | Press.” Juniper Research. https://www.juniperresearch.com/press/online-payment-fraud-losses-to-
exceed-343bn/.
3
The emerging threat o f AI-powered fraud
How businesses are using GenAI
“
Companies are integrating AI into their business strategies. PwC’s
27th Annual Global CEO Survey West Africa report found that 51%
of companies have adopted GenAI across their companies and
47% believe that GenAI will improve the quality of their company’s
products and services3. Businesses are using AI to automate
customer service, screen candidates in the recruitment process,
predict market trends, optimise energy distribution etc. In Nigeria,
companies in the financial services industry have integrated GenAI
in customer service with the introduction of chatbots.
When adopting new technology, businesses need to consider the
risks adoption exposes them to. There have been instances where
researchers manipulated AI and convinced chatbot users to visit a
51% of companies have adopted GenAI
website containing malware or a phishing text in order to get credit across their companies.
card details4. Another paper on Large Language Models (LLM)
found random words that when fed to chatbots, will cause them to Source: PwC’s 27th Annual Global CEO Survey
West Africa report
ignore their boundaries, resulting in these chatbots providing
instructions for building an explosive device and manipulating
elections5.
This leads to an important question - how are companies managing the fraud risks and other threats arising from this
new technology? Business leaders should mandate their teams to conduct extensive risk assessment to ascertain
how AI exposes their business to vulnerabilities or fraud. This is not only important for entities that are adopting or
plan to adopt AI. It is equally important for those entities who are yet to embark on any AI journey. PwC’s CEO
Survey further highlights that business leaders are concerned GenAI adoption will expose their businesses to
cybersecurity and misinformation risks.
3. PwC Nigeria. 2024. “PwC's 27th Annual Global CEO Survey - West Africa.” PwC. https://www.pwc.com/ng/en/publications/pwc-ceo-survey.html.
4. Greshake, Kai, Sahar Abdelnabe, Shailesh Mishra, Christoph Endres, Thorsten Holz, and Mario Fritz. 2023. “Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect
Prompt Injection.” AISec '23: Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, (November), 79-90. https://doi.org/10.1145/3605764.3623985.
5. Zhou, Andy, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Z. Kolter, and Matt Fredrikson. 2023. Universal and Transferable Adversarial Attacks on Aligned Language Models.
https://doi.org/10.48550/arXiv.2307.15043.
4
The emerging threat o f AI-powered fraud
How fraudsters are using GenAI
The developments in artificial intelligence have the potential to increase the volume and sophistication of fraud. Here
are some possible exploitations of AI for fraud6.
Generating text and image content.
GenAI can be used to create tailored emails, instant messages and image content
as the bait to hook potential scam victims, for example, in phishing and smishing
attempts, or through fraudulent adverts. GenAI can also make these scams harder
to detect by eliminating the traditional ‘tells’ such as poor spelling and grammar.
There have been instances where AI generated images (e.g. of damaged property)
were used to support insurance claims.
AI-enabled chatbots.
Fraudsters are leveraging elements of AI in chatbots that converse with victims to
manipulate them in a scam. Chatbots have the potential to amplify fraudsters’ ability
to reach victims, delivering volumes of scams that would previously have required a
large team of individuals operating in a scam centre.
Sophisticated targeting of victims.
Other instances where AI tools may be of benefit to cybercriminals is in the review
of large volumes of data to identify potential victims and tailor scam content to an
individual’s specific vulnerabilities. For example, using online content to identify an
individual’s employment details, family circumstances, where they have recently
been on holiday etc. GenAI could make it easier for fraudsters to analyse large
sets of data for their pig-butchering scams and perform them at scale.
6. PwC UK. 2024. “Written evidence submitted by PwC.” Committees. https://committees.parliament.uk/writtenevidence/125808/pdf/
5
The emerging threat o f AI-powered fraud
Deep fake videos.
Deep fakes are now used as ‘click bait’ to direct users onto malicious websites (where
their credit card information may then be harvested) or which use a trusted persona to
encourage investment in a scam. In April 2024, a video posted on social media
featured a Channels Television news anchor and Nigerian business mogul, Aliko
Dangote. In the video, Dangote appears to be promoting a cryptocurrency investment
scheme. Channels Television subsequently released a statement where it clarified that
the video was doctored using existing footage and a generated voiceover.
Voice cloning.
Deep fake technology can copy voices to an increasingly high degree of accuracy.
Currently, voice clones potentially require as much as an hour of training data to
perfect, but that requirement is reducing all the time. Voice clones can then be used
to trick individuals into making payments and can be used to break through
systems where voice biometrics are used for ID verification. In the upcoming 2024
US election, there are growing concerns about the implications of deepfakes as AI-
imitation of Joe Biden’s voice was used to discourage voters in New Hampshire7.
7. SWENSON, ALI, and WILL WEISSERT. 2024. “Fake Biden robocall being investigated in New Hampshire.” AP News. https://apnews.com/article/new-hampshire-primary-biden-ai-deepfake-robocall-f3469ceb6dd613079092287994663db5.
6
The emerging threat o f AI-powered fraud
The key impact of AI will be to enable
fraudsters to create content at greater speed
and in greater volume, and to make scams
more believable. For example, a fraudster who
has stolen the sim or WhatsApp profile of a
business leader could clone the owner’s voice
and use it to authorise payments or use AI to
generate content and use it to defraud the
business leader’s networks etc.
In February 2024, a finance officer in Hong
Kong had a video conference call with his Chief
Financial Officer and other team members. On
the call, he was directed to pay out $25 million.
The Hong Kong police reported that after
checking with the head office, the employee
discovered that everyone on the multi-person
conference call was (deep) fake8. In May 2024,
Financial Times identified the company as UK-
based engineering group, Arup9.
In May 2024, the CEO of WPP was the target
of a deepfake scam. Fraudsters created a fake
WhatsApp account using his image and set up
a Microsoft Teams meeting with an agency
leader, impersonating the CEO and another
senior executive. They used AI voice cloning
and YouTube footage to make the scam more
convincing. The scammers attempted to trick
the agency leader into setting up a new
business and revealing sensitive information10.
WPP noted that the scam attempt was
unsuccessful.
These reports show that businesses are
vulnerable to AI fraud.
8. Chen, Heather, and Kathleen Magramo. 2024. “Finance worker pays out $25 million after video call with deepfake ‘chief financial officer.’” CNN. https://edition.cnn.com/2024/02/04/asia/deepfake-cfo-scam-hong-
kong-intl-hnk/index.html.
9. Financial Times. 2024. “Arup lost $25mn in Hong Kong deepfake video conference scam.” Financial Times. https://www.ft.com/content/b977e8d4-664c-4ae4-8a8e-eb93bdf785ea.
10. Robins, Niick. 2024. “CEO of world's biggest ad firm targeted by deepfake scam.” The Guardian. https://www.theguardian.com/technology/article/2024/may/10/ceo-wpp-deepfake-scam.
7
The emerging threat o f AI-powered fraud
How businesses can prepare for AI fraud
Perform proactive fraud risk assessment.
Businesses should conduct periodic and proactive fraud risk
assessments to protect their organisation from AI-powered fraud.
Such risk assessments should start from reviewing existing
processes and identifying how malicious actors can leverage GenAI
to exploit the processes. This would entail the business staying
updated on AI developments.
In addition to this, businesses should incorporate fraud risk
assessment into their internal frameworks and mechanisms for
launching new products or adopting a new technology. This will help
them identify how the new technology and product could create new
risks or exacerbate existing ones, giving the advancement in AI at
the time of launch.
Businesses will become aware of fraud risks they face in the light of
changes in AI and should be able to take proactive measures to
mitigate such risks.
Review and update the anti-fraud strategy and framework.
Most businesses have not updated their anti-fraud policies, despite the rapidly changing business
environment powered by an equally rapid advancement in technology. Businesses should update their
anti-fraud policies to reflect current state realities and incorporate how the organisation intends to deal
with emerging fraud risks. In defining what constitutes fraud and misconduct, each organisation’s anti-
fraud policy should detail examples of use cases of AI and GenAI that would constitute fraud by
employees, vendors and other stakeholders.
ACFE’s 2024 Anti-fraud Technology Report highlighted that 83% of organisations plan to adopt GenAI in
their anti-fraud strategy11. Similarly, 69% of respondents to PwC’s 2024 Digital Trust Insight survey noted
that they plan to use generative AI for cyber defence in 2024, and nearly half (47%) are already using it for
cyber-risk detection and mitigation12.
11. Association of Certified Fraud Examiners and SAS. 2024. “2024 Anti-Fraud Technology Benchmarking Report.” ACFE. https://www.acfe.com/-/media/files/acfe/pdfs/sas_benchmarkingreport_2024.pdf.
12. PwC. 2023. “2024 Global Digital Trust Insights Survey.” PwC. https://www.pwc.com/us/en/services/consulting/cybersecurity-risk-regulatory/library/global-digital-trust-insights.html.
8
The emerging threat o f AI-powered fraud
Businesses should adopt the use of GenAI in their fraud prevention and detection efforts. This would
involve in-depth reviews of business needs and requirements before identifying the technology/system to
adopt or deploy. This should include outlining the roles and responsibilities of AI systems and human
analysts, establishing clear protocols for handling AI-generated alerts and insights, and ensuring
compliance with relevant regulatory requirements.
The fraud awareness and training programme should be updated to include modules that educate
employees on AI-enabled fraud and the potential impact to them and the organisation as a whole. Such
sessions should provide employees with clear steps and procedures to take when they suspect or
become aware of such fraud.
9
The emerging threat o f AI-powered fraud
Empower anti-fraud teams with the right skillset and tools.
Businesses should invest in building the capacity generative AI, and creating a controlled sandbox
of their anti-fraud teams to deal with and environment where employees can freely
respond to Ai-enabled fraud. This includes experiment and test innovative ideas without risk.
providing them with access to AI training as well Government can support businesses by raising
as investing in the right tools for investigating AI- awareness among individuals and law
powered fraud. enforcement agencies. This is essential to
combat GenAI-powered fraud effectively. The
In the light of the advances in AI, every government can initiate online campaigns to
organisation’s anti-fraud team must have digital inform the public about AI-driven fraud.
forensics capabilities (i.e. training and tools)
which will serve as a foundation for investigating In addition, the government should promote
and gathering evidence related to AI-enabled collaboration between the players in public and
fraud. Earlier this year, ACFE’s Anti-fraud private sectors to address the emerging threat of
Technology Report indicated that only 29% of AI-powered fraud. By working together, these
organisations have an anti-fraud program that institutions can pool resources, share insights,
involves digital forensics or e-discovery software. and develop coordinated strategies to effectively
This number would be significantly lower in fight fraud. Governments can encourage this
Nigeria and other countries in Sub-Saharan collaboration by:
Africa.
● Providing incentives for industry-led initiatives
Business leaders should balance their aimed at strengthening and enhancing fraud
enthusiasm for GenAI with a clear understanding detection capabilities; and,
of fraud and other risks that would be involved ● Creating regulatory frameworks to enable
with its use. They should think through the information-sharing and cooperation,
controls they can implement to mitigate those ultimately creating a more fraud-resilient
unique risks. They can consider developing ecosystem.
comprehensive training programs and guidelines
to ensure the ethical and responsible utilisation of
10
The emerging threat o f AI-powered fraud
Conclusion
The increased reports of deepfake scams and attempted fraud schemes send a clear message and
warning: AI-powered fraud is here. Business executives must update their fraud framework, perform risk
assessment on areas of their businesses that are vulnerable to GenAI-enabled scams and ensure their
anti-fraud team have the right skills and tools to detect and respond to threats from AI. Additionally,
governments, industries and law enforcement should collaborate to develop a framework for preventing
and responding to AI-enabled fraud.
11
The emerging threat o f AI-powered fraud
Contact us
Habeeb Jaiyeola
Partner and Forensics S ervices Leader,
PwC Nigeria
[email protected]
+234(0)803-394-5167
Adeola Adekunle
Associate Director, Forensics Services,
PwC Nigeria
[email protected]
+234(0)806-486-3890
At PwC, our purpose is to build trust in society and solve important problems. We’re a network of
firms in 151 countries with more than 360,000 people who are committed to delivering quality in
assurance, advisory and tax services. Find out more and tell us what matters to you by visiting us at
www.pwc.com.
©2024 PwC. All rights reserved. PwC refers to the PwC network and/or one or more of its member
firms, each of which is a separate legal entity. Please see www.pwc.com/structure for further details.
The emerging threat o f AI-powered fraud |
11 | pwc | s-b_on_PwC_early-days-generative-AI-strategy.pdf | 07 DECEMBER 2023
Do you have an
“early days”
generative AI
strategy?
Organizations at the forefront of generative
AI adoption address six key priorities to set
the stage for success.
by Scott Likens and Nicole Wakefield
www.pwc.com/generative-ai-strategy
Scott Likens Nicole Wakefield
is PwC’s Global AI and Innovation is PwC’s Global Advisory Clients and
Technology Leader. He is a principal Markets Leader. She is a partner
with PwC US. with PwC UK.
In a recent conversation about generative AI with one of our colleagues, the CIO
of a major healthcare company laid out a wide range of issues that concerned
her: risk protocols, use case development, cybersecurity, ethics and bias, train-
ing and development, and many more. After a few minutes, our colleague asked
the client to take a step back: “How clear are you on what you are trying to ac-
complish, and why? In other words, do you have a strategy?” These questions
stopped the CIO, leading her to call a series of meetings with key leaders, and
ultimately the board, to create a sharper set of objectives. What emerged was
a group of priorities that collectively formed what might be termed an “early
days” AI strategy.
Early days, because—let’s face it—that’s exactly where we are with gener-
ative AI. It was only in November 2022 that the consumer release of ChatGPT
captured the world’s imagination. Since then, organizations have been strug-
gling to keep up with the pace and potential they see in this new, general-pur-
pose technology application. Some organizations are doing better than others,
and it’s not too soon to start taking stock of early leaders that are leveraging
generative AI to capture value and pull ahead. Across industries, we’re seeing
these leaders tackling a number of critical priorities:
• They’re navigating tensions between the need for prudence and risk
mitigation, and the importance of moving quickly to grab emerging
opportunities.
• They’re aligning their new generative AI strategy with their existing digi-
tal and AI strategies, building on these foundations to guide their thinking
2 | www.pwc.com/strategy-business
rather than starting from scratch.
• They’re thinking big—encouraging experimentation across their organi-
zations, with a focus on identifying use cases that can scale.
• Rather than simply looking for ways to improve productivity, they’re look-
ing strategically at their options for putting productivity gains to use.
• Relatedly, they’re considering impacts on workers, roles, and skills-build-
ing, determining how best to both prepare employees to take advantage
of the new tools available and include employees in shaping the compa-
ny’s generative AI journey.
• They’ve realized that with such a potentially disruptive technology, team-
ing up and collaborating with their ecosystems can be a truly transforma-
tive route to a radical rethink of their value chains and business models.
In many cases, these priorities are emergent rather than planned, which is
appropriate for this stage of the generative AI adoption cycle. Leaders and orga-
nizations are learning as they go.
Priority 1: Manage the AI risk/reward tug-of-war
There’s a fascinating parallel between the excitement and anxiety generated by
AI in the global business environment writ large, and in individual organiza-
tions. At the same time that surging market capitalizations for early AI leaders
are providing financial evidence of the opportunity investors and markets see
in generative AI, a number of experts in the field are voicing existential angst
about the potentially significant unintended consequences that could emerge as
the reach of AI grows. Similarly, in many companies we know, there’s a tug-of-
war going on between the executives and managers seeking to rapidly tap the
potential of generative AI for competitive advantage and the technical, legal,
and other leaders striving to mitigate potential risks. Although such tension,
when managed effectively, can be healthy, we’ve also seen the opposite—dis-
agreement, leading in some cases to paralysis and in others to carelessness, with
large potential costs.
Achieving healthy tension often starts with a framework for adopting AI re-
sponsibly. At PwC, we developed such an approach several years ago, and we
3 | www.pwc.com/strategy-business
continue evolving it with the changing nature of AI opportunities and risks.
Practical safeguards and guidelines help organizations move forward faster, and
with more confidence. Open-minded, agile leadership also is critical: risk-mind-
ed leaders deliver better, faster guidance as they internalize the momentous sig-
nificance of the generative AI revolution. Opportunity-seekers are well-served
by spending time immersing themselves in what can go wrong to avoid costly
mistakes. And both groups need a healthy dose of appreciation for the priorities
and concerns of the other.
One company we know recognized it needed to validate, root out bias, and
ensure fairness in the output of a suite of AI applications and data models that
was designed to generate customer and market insights. Given the complexity
and novelty of this technology and its reliance on training data, the only inter-
nal team with the expertise needed to test and validate these models was the
same team that had built them, which the company saw as an unacceptable con-
flict of interest. The near-term result was stasis.
Another company made more rapid progress, in no small part because of ear-
ly, board-level emphasis on the need for enterprise-wide consistency, risk-appe-
tite alignment, approvals, and transparency with respect to generative AI. This
intervention led to the creation of a cross-functional leadership team tasked with
thinking through what responsible AI meant for them and what it required. The
result was a set of policies designed to address that gap, which included a core
set of ethical AI principles; a framework and governance model for responsible
AI aligned to the enterprise strategy; ethical foundations for the technical ro-
bustness, compliance, and human-centricity of AI; and governance controls and
an execution road map for embedding AI into operational processes.
For this company, in short, addressing risk head-on helped maintain momen-
tum, rather than hold it back.
Priority 2: Align your generative AI strategy with your digital
strategy (and vice versa)
If you’re anything like most leaders we know, you’ve been striving to digitally
transform your organization for a while, and you still have some distance to go.
4 | www.pwc.com/strategy-business
The rapid improvement and growing accessibility of generative AI capabilities
has significant implications for these digital efforts. Generative AI’s primary out-
put is digital, after all—digital data, assets, and analytic insights, whose impact
is greatest when applied to and used in combination with existing digital tools,
tasks, environments, workflows, and datasets. If you can align your generative
AI strategy with your overall digital approach, the benefits can be enormous.
On the other hand, it’s also easy, given the excitement around generative AI and
its distributed nature, for experimental efforts to germinate that are disconnect-
ed from broader efforts to accelerate digital value creation.
To understand the opportunity, consider the experience of a global consumer
packaged goods company that recently began crafting a strategy to deploy gen-
erative AI in its customer service operations. Such emphasis has been common
among companies. The chatbot-style interface of ChatGPT and other generative
AI tools naturally lends itself to customer service applications. And it often har-
monizes with existing strategies to digitize, personalize, and automate custom-
er service. In this company’s case, the generative AI model fills out service tick-
ets so people don’t have to, while providing easy Q&A access to data from reams
of documents on the company’s immense line of products and services. That all
helps service representatives route requests and answer customer questions,
boosting both productivity and employee satisfaction.
As the initiative took hold, leaders at the company began wondering wheth-
er generative AI could connect with other processes they had been working to
digitize, such as procurement, accounts payable, finance, compliance, HR, and
supply chain management. It turned out that similar generative AI models, with
refinement and tailoring for specific business processes, could fill out forms, as
well as provide Q&A access to data and insights in a wide range of functions.
The resulting gains, in total, dwarfed those associated with customer service,
and were possible only because the company had come up for air and connect-
ed its digital strategy and its generative AI strategy. In this case, the alterna-
tive would have been a foregone opportunity to turbocharge existing digital ef-
forts. In the extreme, siloed digitization and generative AI efforts might even
work at cross-purposes. Given how much companies have already invested in
5 | www.pwc.com/strategy-business
digitization, and the significance of generative AI’s potential, there’s no substi-
tute for the hard work of bringing the two together.
A fringe benefit of connecting digital strategies and AI strategies is that the
former typically have worked through policy issues such as data security and
the use of third-party tools, resulting in clear lines of accountability and deci-
sion-making approaches. Such clarity can help mitigate a challenge we’ve seen
in some companies, which is the existence of disconnects between risk and legal
functions, which tend to advise caution, and more innovation-oriented parts of
businesses. This can lead to mixed messages and disputes over who has the final
say in choices about how to leverage generative AI, which can frustrate every-
one, cause deteriorating cross-functional relations, and slow down deployment
progress. These disconnects are easily avoided, though. At another financial
services company we know that was seeking to exploit generative AI in the HR
function, the CHRO, the CIO, and the CISO came together quickly to assess the
new opportunities against the company’s existing data, tech, and cybersecurity
policies, providing helpful guidance that maintained momentum.
Priority 3: Experiment with an eye for scaling
The C-suite colleagues at that financial services company also helped extend
early experimentation energy from the HR department to the company as a
whole. Scaling like this is critical for companies hoping to reap the full benefits
of generative AI, and it’s challenging for at least two reasons. First, the diversity
of potential applications for generative AI often gives rise to a wide range of pi-
lot efforts, which are important for recognizing potential value, but which may
lead to a “the whole is less than the sum of the parts” phenomenon. Second, se-
nior leadership engagement is critical for true scaling, because it often requires
cross-cutting strategic and organizational perspectives.
Experimentation is valuable with generative AI, because it’s a highly versa-
tile tool, akin to a digital Swiss Army knife; it can be deployed in various ways
to meet multiple needs. This versatility means that high-value, business-spe-
cific applications are likely to be most readily identified by people who are al-
ready familiar with the tasks in which those applications would be most useful.
6 | www.pwc.com/strategy-business
Centralized control of generative AI application development, therefore, is like-
ly to overlook specialized use cases that could, cumulatively, confer significant
competitive advantage. Certainly, our experience at PwC—where internal hack-
athons have identified value creation opportunities comprising 1 to 2% of reve-
nue in some of our service lines—has underscored the importance of engaging
individual workers and departments in experimentation and exploration.
Powerful as pilots like this are for spotting business-specific trees of opportu-
nity, they run the risk of missing the forest (at best) or (at worst) veering toward
the “pilot purgatory” state in which many corporate advanced data analytics ef-
forts found themselves a few years ago, with promising glimmers generating
more enthusiasm than value. The above-mentioned financial services company
could have fallen prey to these challenges in its HR department, as it looked for
means of using generative AI to automate and improve job postings and employ-
ee onboarding.
Fortunately, the CHRO’s move to involve the CIO and CISO led to more than
just policy clarity and a secure, responsible AI approach. It also catalyzed a re-
alization that there were archetypes, or repeatable patterns, to many of the HR
processes that were ripe for automation. Those patterns, in turn, gave rise to a
lightbulb moment—the realization that many functions beyond HR, and across
different businesses, could adapt and scale these approaches—and to broader
dialogue with the CEO and CFO. They began thinking bigger about the impli-
cations of generative AI for the business model as a whole, and about patterns
underlying the potential to develop distinctive intellectual property that could
be leveraged in new ways to generate revenue.
This same sort of pattern recognition also was important to scaling at the
consumer packaged goods company we mentioned earlier. In that case, it soon
became clear that training the generative AI model on company documenta-
tion—previously considered hard-to-access, unstructured information—was
helpful for customers. This “pattern”—increased accessibility made possible
by generative AI processing—could also be used to provide valuable insights to
other functions, including HR, compliance, finance, and supply chain manage-
ment. By identifying the pattern behind the single use case initially envisioned,
7 | www.pwc.com/strategy-business
the company was able to deploy similar approaches to help many more func-
tions across the business.
As leaders make such moves, they also need to take a hard look at them-
selves: What skills does the organization need to succeed at scale with AI, and
to what extent do those capabilities already reside somewhere in the company?
What’s the plan for filling skills gaps, and on what time frame? Failure to pose
questions like these can lead to problems down the road—and they’re much
better answered in the context of early experiments than in the abstract.
Priority 4: Develop a productivity plan
Generative AI’s ability to find relevant information, perform repetitive pattern
tasks quickly, and integrate with existing digital workflows means the increased
efficiency and productivity it can deliver can be almost instant, both within in-
dividual departments and organization-wide. Such opportunities aren’t unique
to generative AI, of course; a 2021 s+b article laid out a wide range of AI-en-
abled opportunities for the pre-ChatGPT world.
Generative AI has boosted the awareness and interest of many leaders in
AI-enabled productivity gains, which companies can do three things with:
• Reinvest them to boost the quality, volume, or speed with which goods
and services are produced, generating greater output, broadly defined,
from the same level of input.
• Keep output constant and reduce labor input to cut costs.
• Pursue a combination of the two.
PwC firms in mainland China and Hong Kong followed the first approach in
small-scale pilots that have yielded 30% time savings in systems design, 50% ef-
ficiency gains in code generation, and an 80% reduction in time spent on inter-
nal translations. When generative AI enables workers to avoid time-consuming,
repetitive, and often frustrating tasks, it can boost their job satisfaction. Indeed,
a recent PwC survey found that a majority of workers across sectors are positive
about the potential of AI to improve their jobs.
Generative AI’s ability to create content—text, images, audio, and video—
means the media industry is one of those most likely to be disrupted by this new
8 | www.pwc.com/strategy-business
technology. Some media organizations have focused on using the productivity
gains of generative AI to improve their offerings. They’re using AI tools as an
aid to content creators, rather than a replacement for them. Instead of writing
an article, AI can help journalists with research—particularly hunting through
vast quantities of text and imagery to spot patterns that could lead to interest-
ing stories. Instead of replacing designers and animators, generative AI can help
them more rapidly develop prototypes for testing and iterating. Instead of decid-
ing that fewer required person-hours means less need for staff, media organiza-
tions can refocus their human knowledge and experience on innovation—per-
haps aided by generative AI tools to help identify new ideas.
It’s also important to consider that when organizations automate some of
the more mundane work, what’s left is often the more strategic work that con-
tributes to a greater cognitive load. Many studies show burnout remains a prob-
lem among the workforce; for example, 20% of respondents in our 2023 Glob-
al Workforce Hopes and Fears Survey reported that their workload over the 12
months prior frequently felt unmanageable. Organizations will want to take
their workforce’s temperature as they determine how much freed capacity they
redeploy versus taking the opportunity to reenergize a previously overstretched
employee base in an environment that is still talent-constrained.
Other companies may focus more on cost savings, which can be substan-
tial, but which also carry with them risks—for example, worker unrest (as we
saw in Hollywood), or the hollowing out of the capabilities that companies
need to differentiate themselves from competitors. Some organizations may
decide these risks are worth taking; the right approach will obviously vary
from industry to industry, company to company, and even department to de-
partment. What’s crucial is to have a plan: What is the relative importance of
speed, quality, and cost improvements? What time horizon are you solving
for? What will you do with employees whose skills have become redundant
as a result of new generative AI capabilities? Getting clarity on the answers
to questions like these is an important starting point for focusing your plan.
9 | www.pwc.com/strategy-business
Priority 5: Put people at the heart of your generative AI strategy
Regardless of the productivity path you choose to pursue, considering its impact
on your workforce and addressing it from the start will make or break the suc-
cess of your initiatives.
Our 26th Annual Global CEO Survey found that 69% of leaders planned to
invest in technologies such as AI this year. Yet our 2023 Global Workforce Hopes
and Fears Survey of nearly 54,000 workers in 46 countries and territories high-
lights that many employees are either uncertain or unaware of these technol-
ogies’ potential impact on them. For example, few workers (less than 30% of
the workforce) believe that AI will create new job or skills development oppor-
tunities for them. This gap, as well as numerous studies that have shown that
workers are more likely to adopt what they co-create, highlights the need to put
people at the core of a generative AI strategy.
Companies are investing in AI, but most workers aren’t sure what
that means for them
69% of CEOs say their company is Impact workers expect AI to have on their career in the
investing in advanced technologies next five years
such as AI
Positive Negative Neutral
AI will help me increase my
productivity/efficiency at work 31% 52% of
respondents
AI will create opportunities for me
27% selected at least
to learn new skills
one positive
AI will create new job opportunities for me 21% statement
AI will require me to learn new skills that I’m
18% 35% of
not confident I have the capacity to learn
respondents
AI will change the nature of
14% selected at least
my work in a negative way
one negative
statement
AI will replace my role 13%
I don’t think AI will impact my job 22%
AI will impact my job in other ways not listed 11%
Don’t know 10%
Sources: PwC’s 26th Annual Global CEO Survey and Global Workforce Hopes and Fears Survey 2023
10 | www.pwc.com/strategy-business
To ensure your organization is positioned to capitalize on the promise of gen-
erative AI, prioritize steps to engage employees in the creation and selection of
AI tools, invest in AI education and training, foster a culture that embraces hu-
man–AI collaboration and data-driven decision-making, and support innova-
tion. To this end, we suggest several key strategies:
• Engage your people early and often. Continually communicate why AI is
important and how it fits into the company’s goals. Explain how AI can make
employees’ jobs better and not replace them, and highlight that amassing AI
skills will be critical for workers to succeed in their careers going forward.
But remember that communication should be a two-way street. Provide
mechanisms to gather feedback from employees about their AI experienc-
es, and use it to refine tools and training programs and address any con-
cerns or challenges.
• Offer customized training and upskilling. Assess your emploees’
current AI skills and knowledge, and provide role-specific training
programs, learning resources, and certifications to address the gaps.
Consider teaming up with educational institutions or AI training pro-
viders to offer these programs. Create mentorship opportunities that
give employees guidance on their AI journey, and provide a way for
them to get advice and feedback from AI experts within your company.
And although it’s still difficult to predict many of the new roles that
generative AI could give rise to, we know they’ll materialize. Preparing
employees for these roles and highlighting the opportunities can energize
those looking for career growth and tamp down workers’ fears of replace-
ment. Prompt engineering is a much-discussed role, though it may prove
to be a short-term one as generative tools advance. Many other emerging
roles involving AI ethics and training will become more prevalent, along
with unforeseen roles.
• Promote a growth mindset. Create a workplace where learning and
trying new things with AI is encouraged by recognizing and rewarding
those who do so. And, importantly, make it clear that, with proper guard-
rails and protections in place, failures mark innovation and are expected,
11 | www.pwc.com/strategy-business
and even celebrated. One financial services firm we know, for exam-
ple, highlights at least one instance of failure on a weekly stand-up call
among its designers to make visible that these occurrences are accept-
able and incur no punitive measures. Unfortunately, this organization
remains in the minority—in our 2023 Annual Global CEO Survey, 53%
of respondents said leaders in their company don’t often tolerate small-
scale failures (and employees think that figure is closer to two-thirds).
Fostering a growth culture also includes encouraging employees to
share their learnings with each other as they begin working with these
tools. Some companies we know are establishing prompt libraries, for
example.
• Advocate and enable ethical AI use. Provide clear guidelines that ar-
ticulate how your organization defines the ethical use of generative AI,
and ensure that employees understand the importance of fairness, trans-
parency, and responsible AI practices. At PwC, for example, we’ve created
an internal microsite articulating the generative AI tools approved for em-
ployee use, acceptable business use cases, restrictions on the nature of in-
formation employees can input into these tools, requirements for human
oversight and quality checks, and more.
• Measure impact. Knowing what’s working and what isn’t requires not
only worker feedback but also measurement. Implement key performance
indicators to assess the impact of AI on productivity, innovation, and cus-
tomer satisfaction; and actively promote the results. Some companies we
know are conducting controlled experiments, such as by having software
engineers use coding assistants, to measure productivity improvements.
By following these strategies, organizations can systematically equip and
empower their workforce to position themselves, and the organization, for suc-
cess in an AI-driven world.
Priority 6: Work with your ecosystem to unlock even bigger
benefits
Recent PwC analysis has found that companies with a clear ecosystem strategy
12 | www.pwc.com/strategy-business
are significantly more likely to outperform those without one. It’s important,
as you experiment with AI, to look outside the four walls of your company: Do
you know how your suppliers, service providers, customers, and other partners
are planning to leverage this technology to improve their service proposition?
What implications does their use of AI have for your early days strategy? Will it
impose new conditions and demands? Could closer collaboration on AI lead to
fresh opportunities to develop stronger propositions?
The holy grail of healthcare and pharmaceutical firms, for instance, is the
ability to access patient records at scale and identify patterns that could uncov-
er routes to more effective treatments. Yet information sharing between orga-
nizations has long been restricted by privacy issues, local regulations, the lack
of digitized records, and concerns about protecting intellectual property—all of
which limit the scope and power of ecosystem collaboration.
Meanwhile, the use of AI has already become widespread across the indus-
try. Medical institutions are experimenting with leveraging computer vision
and specially trained generative AI models to detect cancers in medical scans.
Biotech researchers have been exploring generative AI’s ability to help identify
potential solutions to specific needs via inverse design—presenting the AI with
a challenge and asking it to find a solution. This AI-supported treatment discov-
ery approach is already being used for both precision medicine (via genetic and
healthcare record analysis to identify the best treatments given an individual’s
specific circumstances) and drug development (via protein and chemical model
synthesis that can create custom antibodies).
Until recently, the true potential of AI in life sciences was constrained by the
confinement of advances within individual organizations. Today, organizations
can combine generative AI’s ability to help create and manage records with its
capacity for creating statistically reliable, yet fully anonymized, synthetic data-
sets to enable safe, secure, large-scale data-sharing and data-pooling among
healthcare organizations and their partners. That larger pool of information in-
creases the opportunity for medical breakthroughs by helping researchers iden-
tify commonalities that can reveal more effective treatments—as well as new
opportunities for collaboration between organizations, new business models,
13 | www.pwc.com/strategy-business
and new ways to capture value along with improved patient outcomes.
Use cases have come up several times as we’ve described these priorities. That
makes sense, because generative AI is a general-purpose technology, suitable
for an enormous range of business activities; it’s hardly surprising that emerging
leaders are emphasizing the search for smart, targeted applications. Here again,
though, it’s important to underscore that it’s still early days. To understand how
early, consider another general-purpose technology: electricity. Beginning with
lighting in the 1870s, electricity began permeating a range of industrial settings
and applications, bringing with it a variety of productivity improvements in the
decades that followed. Electricity was the force behind a key feature of Henry
Ford’s automated assembly line—the overhead monorail conveyor system that
made it possible to move parts and materials smoothly throughout the plant.
Looking back, no one talks about Ford’s “electricity strategy.” Rather, the fo-
cus is on the moving assembly line. We suspect the same will be true with gen-
erative AI, which will give rise to revolutionary business innovations that are
beyond our imagination today. That makes early days AI strategies and prior-
ities like the ones we’ve described even more important. They won’t just yield
near-term business benefits; they’ll also build muscle and generate valuable
experience that sets up today’s leaders to achieve much bigger breakthroughs
to make product, process, and service innovations that represent the assembly
lines of the future.
The authors would like to thank Lois Geraldo and Julia Lamm
for their contributions to this article.
14 | www.pwc.com/strategy-business
• strategy-business.com
• pwc.com/strategy-business
• facebook.com/strategybusiness
• linkedin.com/company/strategy-business
• twitter.com/stratandbiz
©2023 PwC. All rights reserved. PwC refers to the PwC network and/or one or more of its member firms,
each of which is a separate legal entity. Please see www.pwc.com/structure for further details.
Strategy+business is published by certain member firms of the PwC network. Articles published in
strategy+business do not necessarily represent the views of the member firms of the PwC network.
Reviews and mentions of publications, products, or services do not constitute endorsement or
recommendation for purchase. Mentions of Strategy& refer to the global team of practical strategists that
is integrated within the PwC network of firms. For more about Strategy&, see www.strategyand.pwc.com.
No reproduction is permitted in whole or part without written permission of PwC. “Strategy+business” is a
trademark of PwC. |
12 | pwc | agentic-ai-the-new-frontier-in-genai-an-executive-playbook.pdf | Agentic AI
– the new
frontier in
GenAI
An executive playbook
Harnessing AI isn’t just about
technology— it’s about unleashing
unprecedented potential.
In an era where speed, efficiency, and customer centricity dictate market leadership, organisations need to
harness every tool at their disposal. Over the past couple of years, artificial intelligence (AI) has exploded onto
the world stage, with companies and individuals across the globe rapidly adopting the technology. The GCC is
playing a lead role in the space, with business leaders in the region exploring ways of integrating this rapidly
developing technology into their operations.
Generative AI (GenAI) is being recognised as a game-changer for innovation in the region, empowering
enterprises by automating routine tasks, enhancing customer experiences and assisting in critical
decision-making processes. Insights from our 27th Annual CEO Survey: Middle East findings have shown that
73% of CEOs in the Middle East believe GenAI will significantly change the way their company creates, delivers
and captures value over the next three years1. GenAI is poised to make a significant economic impact, with
estimates indicating that it could contribute between $2.6 trillion and $4.4 trillion annually to global GDP across
various industries by 2030. In specific sectors, such as energy, investments in GenAI are expected to triple,
from $40 billion in 2023 to over $140 billion by the end of the decade. This surge in investment reflects the
transformative potential of GenAI, particularly in enhancing productivity, streamlining business processes, and
reshaping value chains across industries2.
Against this backdrop, multimodal GenAI agentic frameworks has emerged as transformative catalysts,
enabling businesses to accelerate process automation at an unprecedented scale. This technology involves
multiple AI agents working together, each specialising in different tasks or data types, to solve complex
problems and automate processes. By collaborating and constantly learning, these agents enhance
decision-making, optimise processes, and drive innovation. It combines range of advanced AI techniques to
process diverse data types and automate complex tasks.
The central question isn’t whether to adopt this technology, but how swiftly organisations can integrate it to
stay ahead of the competition. This executive playbook explores how organisations can leverage this
technology to boost operational efficiency, enhance customer experience, and drive revenue growth. It provides
real-world success stories spanning industry sectors and organisational functions, strategic insights, tactical
blueprints, and best practices to guide your journey into this revolutionary landscape.
Key insights
● Agentic AI, differentiated by its advanced human-like reasoning and interaction capabilities, is
transforming the manufacturing, healthcare, finance, retail, transportation, and energy sectors, among
others.
● Organisations’ AI strategies should leverage multimodal GenAI capabilities while ensuring ethical AI
safeguards to drive autonomous process re-engineering and enhanced decision-making across all lines
of business.
● Integrated effectively, agentic AI can enhance efficiency, lower costs, improve customer experience, and
drive revenue growth.
What is agentic AI?
Agentic AI generally refers to AI systems that
possess the capacity to make autonomous
decisions and take actions to achieve specific
goals with limited or no direct human
intervention3.
Key aspects of agentic AI
Autonomy: Agentic AI systems Goal-oriented behaviour: These Environment interaction: An
can operate independently, AI agents are designed to pursue agentic AI interacts with its
making decisions based on their specific objectives, optimising surroundings, perceiving changes
programming, learning, and their actions to achieve the and adapting its strategies
environmental inputs. desired outcomes. accordingly.
Learning capability: Many Workflow optimisation: Agentic Multi-agent and system
agentic AI systems employ AI agents enhance workflows and conversation: Agentic AI
machine learning or business processes by integrating facilitates communication
reinforcement learning techniques language understanding with between different agents to
to improve their performance over reasoning, planning, and construct complex workflows. It
time. decision-making. This involves can also integrate with other
optimising resource allocation, systems or tools, such as email,
improving communication and code executors, or search
collaboration, and identifying engines, to perform a variety of
automation opportunities. tasks.
Environment Learning
interaction capability
Workflow
Goal-oriented
optimisation
behaviour
Multi-agent
and system
Autonomy conversation
Evolution to multimodal GenAI agents
In AI, the only constant is change—embrace a culture of perpetual innovation.
The journey of agentic frameworks began as simple, rule-based systems designed to perform specific tasks. Over time,
these systems have evolved into sophisticated, multimodal agents capable of processing and integrating information from
various sources, such as text, images, and audio. Multimodality capabilities allow AI agents to understand, employ
reasoning, and interact like humans, enhancing their effectiveness and versatility to solve a wide range of business
problems4.
The evolution can be broken down into three key phases:
(20001s.) Integration of Machine Learning (ML)
○ Learning from data: The integration of ML allowed agents to learn from large datasets, improving their ability
to make decisions and perform tasks. This was a significant step forward from rule-based systems, as agents
could now adapt to new information and improve over time.
○ Natural Language Processing (NLP) enabled user interactions: Advances in NLP enabled agents to
understand and generate human language more effectively, making interactions more natural and intuitive.
(20102s.) Introduction of multimodality
○ Combining text, images, and audio: Multimodal agents emerged, capable of processing and integrating
information from various sources. For instance, an agent could analyse a text description, recognise objects in
an image, and understand spoken commands. This multimodality made agents more versatile and capable of
handling complex tasks.
○ Enhanced user interactions: Multimodal agents could interact with users in more dynamic ways, such as
providing visual aids in response to text queries or understanding context from a combination of spoken and
visual inputs.
20203s.- Advanced autonomy and real-time interactions
present ○ Advanced autonomy: Agents can operate independently, rationalise and set their own goals, develop path(s)
to attain these goals, and make independent decisions without constant human intervention, leveraging data
from multiple sources or synthetic datasets. In a multi-agentic orchestration system, the first set of agents
focus on mimicking human behaviour (e.g. ChatGPT-4o), that is, thinking fast to come up with solution
approach, while the second set of agents focus on slow reasoning (e.g. ChatGPT-1o) to come up with a vetted
solution5. Combining thinking fast and slow reasoning, agents can process information and make optimal
decisions in real-time – crucial for applications like autonomous vehicles, real-time customer service, and
various mission-critical business processes. This autonomy makes agentic AI particularly powerful in dynamic
and complex real-world environments.
○ User interactions within an ethical and responsible AI-controlled environment: With increased
capabilities, there has also been a focus on ensuring that agentic systems operate ethically and responsibly,
considering factors such as bias, transparency, and accountability.
Integration of ML (2000s)
NLP enabled user
Learning from data
interactions
Integration of Machine Learning (2000s)
Introduction of multimodality (2010s)
Natural Language Processing
LCeoamrnbiningi nfrgo mte xDta, tiamages, and (NLP) Enabled User
Enhanced user interactions
audio Interactions:
Goal-oriented
AI agent I An dte vg anra ct eio dn a o uf t oM na oc mh yin ae n L de ra er an li -n tg im (2 e0 i0 n0 tes r) actions (2020s-present)
behaviour
Natural Language Processing
User interactions within an
LHeuamrnainng-l ifkroem re Daastoaning and (NLP) Enabled User
ethical and responsible AI-
advanced autonomy Interactions:
controlled environment
Why organisations should pay attention
In the fast lane of technological evolution, missing the AI turn today means being outpaced tomorrow.
Agentic AI offers significant advantages in efficiency, decision-making, and customer interaction. By automating routine
tasks and providing intelligent insights, agentic AI can help organisations save time, reduce cost, and improve overall
productivity. Moreover, organisations who adopt an agentic AI system can gain a competitive advantage by leveraging its
capabilities to innovate and enhance their business operations. Lower cost to entry and economies of scale makes it
favourable for organisations to fully harness the capabilities it offers compared to its predecessors like traditional ML and
Robotic Process Automation (RPA)-driven automations.
Agentic AI systems can significantly enhance an organisation’s competitive edge by automating complex workflows,
reducing operational costs, and improving decision-making processes. These systems are designed to adapt to changing
business environments, driving higher productivity and enabling organisations to stay competitive. For example, agentic AI
can predict market trends and customer preferences, allowing businesses to tailor their strategies proactively. This
adaptability not only improves efficiency but also fosters innovation, giving companies a significant edge over competitors6.
Moreover, agentic AI systems can handle large volumes of data and extract actionable insights, which can be used to
optimise operations and enhance customer experiences. By automating routine tasks, these systems free up human
resources to focus on more strategic initiatives, thereby increasing overall organisational agility and responsiveness7.
Enhanced decision-making
Agentic AI systems can analyse vast amounts of data quickly and accurately, providing valuable insights to inform better
decision-making. Businesses can leverage these insights to optimise revenue and operations, identify market trends, and
make data-driven decisions. For instance, in the financial sector, AI can analyse market data to predict trends, inform
investment strategies, and boost investment ROI. In retail, it can streamline inventory management by predicting demand
and optimising stock levels.
Boosted efficiency and productivity
Agentic AI can significantly enhance business efficiency and productivity by automating routine tasks and processes. This
allows employees to focus on more strategic and creative activities. For example, in customer service, agentic AI can
handle common inquiries, freeing up human agents to tackle more complex issues. In manufacturing, AI-driven robots can
manage repetitive tasks with precision and consistency, reducing errors and increasing output.
Improved customer experience
By integrating agentic AI, businesses can offer personalised and responsive customer experiences. AI-driven chatbots and
virtual assistants can provide instant support, answer queries, and even recommend products based on customer
preferences and dynamic interactions. This improves customer satisfaction, builds loyalty, and drives sales. For example,
e-commerce platforms use AI to recommend products based on browsing history and purchase behaviour.
Agentic AI systems are redefining customer service centres and are gaining popularity as a game-changing capability
for both government entities and private sector organisations. While traditional rule-based chatbots
(software-as-a-service) provided basic 24/7 support, and Retrieval Augmented Generated (RAG)-based chatbots
enhanced human-like interactions (enhanced software-as-a-service), agentic AI surpasses both in terms of accuracy,
contextual coherence, and problem-solving ability.
In terms of accuracy, rule-based chatbots are limited to programmed responses, causing inaccuracies when queries
fall outside of predefined rules. RAG-based chatbots depend on retrieved data that may not match user intent. In
contrast, the novel approach of agentic AI allows it to understand nuances in language, generating accurate responses
even to complex or unseen queries. Its ability to learn from vast datasets enhances precision and adaptability, making
it superior for customer interactions.
One of the biggest limitations of chatbots has been contextual coherence. Rule-based chatbots struggle to maintain
context in extended interactions due to linear scripting, leading to disjointed responses that harm customer
experience. RAG-based chatbots may produce inconsistent replies if retrieval mechanisms don't consider previous
interactions. Whereas agentic AI’s orchestration capability helps it excel at tracking conversation history,
understanding dialogue flow, ensuring responses remain contextually appropriate and coherent, significantly boosting
customer engagement.
Thus far, both rule-based and RAG-based chatbots have limited autonomous problem-solving ability. The former can't
handle problems outside their scripts while the latter provide information but can't synthesise data and prepare the
human-live problem-solving logic to solve complex issues across integrated sources such as CRMs, ERP, or IVR
systems. The agentic AI performs dynamic reasoning and decision-making, leveraging a series of autonomous agents,
analysing customer issues, considering multiple factors, and applying learned knowledge to resolve problems more
efficiently. The outcome is quicker, solution-oriented, and fluid conversations that enhance customer experience and
set new standards for efficiency and responsiveness in automated customer service.
stnega-orciM
Customer support agent
Customer support agent
User Issue Feedback
Status updates
experience FAQ agent resolution collection Nth agent
agent
agent agent agent
tnega
retsaM
tnega
rotartsehcrO
How to conceptualise agentic AI
solutions for future business operations
Agentic AI business imperatives
Organisations managing day-to-day operations stand to gain significantly from agentic AI systems, embracing the
emerging "service-as-a-software" model. This innovative approach transforms manual labour into automated, AI-driven
services. Rather than purchasing traditional software licences or subscribing to cloud-based software-as-a-service
(SaaS), businesses can now pay for specific outcomes delivered by AI agents. For example, a company might employ
AI customer support agents like Sierra to resolve issues on their websites, paying per resolution rather than maintaining
a costly human support team. This model allows organisations to access a wider range of services – whether it’s legal
support from AI-powered lawyers, continuous cybersecurity testing by AI penetration testers, or automated CRM
management – at a fraction of the cost. This not only drives efficiency but also significantly reduces operational
overheads.
By leveraging the service-as-a-software model, businesses can automate both routine and highly specialised tasks that
were once time-consuming, required skilled professionals, and typically involved expensive software licences or cloud
solutions. AI applications with advanced reasoning capabilities can now handle complex tasks, from software
engineering to running customer care centres, enabling companies to scale their operations without a proportional
increase in cost. This transition expands the services available to organisations of all sizes, freeing them to focus on
strategic priorities while AI systems manage the operational burden. Adopting these AI-driven services positions
businesses to stay competitive in an ever-evolving marketplace8.
Transitioning from copilot to autopilot models
Service-as-a-software represents an outcome-focused, strategic shift, enabling organisations to transition from their
current state to operating in "copilot" and ultimately "autopilot" modes. Sierra, for instance, offers a safety net by
escalating complex customer issues to human agents when necessary, ensuring a seamless customer experience.
While not all AI solutions offer this built-in fallback, a common strategy is to initially deploy AI in a "copilot" role
alongside human workers. This human-in-the-loop approach helps organisations build trust in AI capabilities over time.
As AI systems demonstrate their reliability, businesses can confidently transition to an "autopilot" mode, where AI
operates autonomously, enhancing efficiency and reducing the need for human oversight. GitHub Copilot is a prime
example of this, assisting developers and potentially automating more tasks as it evolves.
Outsourcing work through AI services
For organisations with high operational costs, outsourcing specific tasks to AI services that guarantee concrete
outcomes is an increasingly attractive option. Take Sierra, for example: businesses integrate Sierra into their customer
support systems to efficiently manage customer queries. Instead of paying for software licences or cloud-based
services, they pay Sierra based on the number of successful resolutions. This outcome-based model aligns costs
directly with the results delivered, allowing organisations to harness AI for specific tasks and pay solely for the
outcomes achieved.
This shift from traditional software licences or cloud SaaS to service-as-a-software is transformative in several ways:
Targeting service profits: Traditional SaaS focused on selling user seats, whereas service-as-a-software taps into
service profit pools, delivering solutions that focus on specific business outcomes.
Outcome-based pricing: Instead of charging per user or seat, service-as-a-software adopts a pricing model based on
the actual outcomes achieved, directly aligning costs with results.
High-touch delivery models: Service-as-a-software offers a top-down, highly personalised approach, providing
trusted, tailored solutions that meet the specific operational needs of businesses.
Why should organisations consider early
adoption and avoid being late movers?
Early adopters Late movers
Set industry benchmarks
Market Struggle to catch up and miss out on
and gain first-mover market advantage.
position creating competitive advantage.
Leverage AI to innovate business Slow to innovate business processes and
Innovation processes, deploy the AI solutions take full advantage of AI solutions to create
effectively and create differentiation. differentiation.
Build deeper customer relationships
Customer Play catch-up to match the personalised
through personalised and newer
relationships services of early adopters.
experiences.
Operational Streamline operations and reduce Higher lost opportunity cost due to late entry
efficiency operational cost early on. and adoptions.
Benefit from the initial learning curve and Miss out on early learning opportunities and
Learning curve
shape industry standards. industry influence.
Increase market share and profitability
Market share Struggle to achieve similar market share.
through early adoption.
Barriers to Create barriers for competitors through Face higher barriers to entry due to
entry deep AI integration. established competitors.
Pay relatively higher cost of entry and
Pay relatively lower cost of entry and lower
Cost to entry iterative test-and-learn due to new AI
learning and experiments.
solutions.
Real-world success stories
Catalysing change across all industries
Manufacturing: Siemens AG
Siemens transformed its maintenance operations by deploying AI models that analyse sensor data from machinery. The
system predicts equipment failures before they occur, scheduling maintenance proactively. The multimodal framework
processes data from various sources – vibration, temperature, and acoustic signals – providing a holistic view of
equipment health and proactive maintenance orchestrated by the agentic AI models.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Regression and deep ● Savings: Reduced maintenance ● Enhanced equipment reliability
learning models costs by 20% ● Improved worker safety
● Platforms: Siemens ● Revenue growth: Increased
MindSphere9 production uptime by 15%
● Tools: Scikit-learn, TensorFlow,
Keras, IoT sensors
Healthcare: Mayo Clinic
By integrating AI into its radiology workflows, Mayo Clinic allows for quicker and more accurate diagnoses. The multimodal
AI processes imaging data alongside patient history and lab results, offering comprehensive insights that aid radiologists in
decision-making, automating documentation and process automation across the radiology value chain.
Technology stack: Financial impact: Non-financial benefits:
● AI Models: Regression and ● Efficiency gains: Reduced ● Improved diagnostic accuracy
Convolutional Neural Networks diagnostic times by 30% ● Enhanced patient outcomes
(CNNs) models ● Cost reduction: Lowered
● Frameworks: NVIDIA Clara unnecessary procedures by
platform10 15%
● Tools: Scikit-learn, PyTorch,
Medical Imaging Data
Finance: JPMorgan Chase
JPMorgan’s Contract Intelligence (COiN) platform uses AI to analyse legal documents, extracting key data points in
seconds. The multimodal framework interprets complex legal language, images, and tables, streamlining a process that
once took thousands of human hours.
Technology stack: Financial impact: Non-financial benefits:
● AI models: NLP with Generative ● Savings: Saved 360,000 hours ● Enhanced accuracy in
Pre-trained Transformers (GPT) of manual review annually document analysis
● Frameworks: COiN platform11 ● Risk mitigation: Significantly ● Improved employee productivity
● Tools: Python, Hadoop reduced compliance risk
Retail: Amazon
Amazon leverages AI to analyse browsing behaviour, purchase history, and even visual preferences. Multimodal AI models
generate personalised recommendations, orchestrate tasks across order fulfilment value chains, and enhance the
shopping experience to drive sales.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Regression and deep ● Revenue boost: Increased sales ● Enhanced customer satisfaction
learning Models by 35% through personalised ● Increased engagement time on
● Frameworks: Amazon recommendations and one-click the platform
Personalise12 and Amazon order fulfilment
Order Fulfilment ● Customer retention: Improved
● Tools: AWS SageMaker loyalty rates by 20%
Transportation and logistics: DHL
DHL utilises AI models to predict and orchestrate shipping demands, optimise routes, and manage warehouse operations.
The system processes data from various sources, including traffic patterns, weather conditions, and order volumes.
Technology stack: Financial impact: Non-financial benefits:
● AI models: ML models and route ● Cost savings: Reduced ● Enhanced customer satisfaction
optimisation algorithms operational costs by 15% ● Reduced carbon footprint
● Frameworks: DHL Resilient ● Efficiency gains: Improved
supply chain platform13 delivery times by 20%
● Tools: IoT devices, ML models
Energy: BP (British Petroleum)
BP uses AI to analyse seismic data, generating 3D models of subterranean structures. The multimodal approach combines
geological, geophysical, and historical data to identify favourable drilling sites and orchestrate drilling equipment settings
for optimal outcomes.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Regression and ● Savings: Reduced exploration ● Reduced environmental impact
GenAI models costs by 20% ● Improved safety measures
● Frameworks: Azure cloud ● Revenue growth: Increased
services14 successful drilling operations by
● Tools: Microsoft AI 15%
Education: Pearson
Pearson’s AI models tailor educational content to individual learner needs, adjusting difficulty levels and content types
based on performance and engagement data.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Adaptive learning ● Revenue increase: Boosted ● Improved student outcomes
algorithms course enrollment by 25% ● Enhanced user engagement
● Frameworks: Multimodal content ● Cost reduction: Lowered
delivery systems15 content development costs by
● Tools: Python, TensorFlow 15%
Media and entertainment: Netflix
Netflix uses AI models to recommend and orchestrate content by analysing viewing habits, ratings, and even visual
content features. The multi-modal AI ensures that users find content that resonates with their preferences, keeping them
engaged.
Technology stack: Financial impact: Non-financial benefits:
● AI models: ML and GenAI ● Subscriber growth: Increased ● Personalised user experiences
models retention rates by 10% ● Improved content strategy
● Frameworks: Netflix multimodal ● Revenue boost: Enhanced
user interaction analysis16 engagement leading to higher
● Tools: AWS, Apache Spark subscription renewals
Telecommunications: AT&T
AT&T’s AI models analyse and orchestrate network performance data and customer interactions to optimise network
operations and personalise customer service through chatbots.
Technology stack: Financial impact: Non-financial benefits:
● AI models: ML for network ● Cost savings: Reduced ● Enhanced network reliability
analytics operational expenses by 15% ● Improved customer satisfaction
● Frameworks: Edge computing ● Revenue growth: Improved
with multimodal data inputs17 upselling through personalised
● Tools: AI chatbots, data offers
analytics platforms
Government and public sector: Singapore Government
Singapore utilises AI models to orchestrate and manage traffic flow, energy consumption, and public safety. The
multi-modal system processes data from various sensors and citizen feedback mechanisms to make real-time decisions.
Technology stack: Financial impact: Non-financial benefits:
● AI models: ML and GenAI ● Efficiency gains: Reduced ● Improved public services
models administrative costs by 25% ● Enhanced quality of life
● Frameworks: Smart Nation ● Economic growth: Attracted for citizens
platform18 US$12 billion in foreign
● Tools: IoT sensors, cloud investment
computing
Real-world success stories
Innovation within business functions
Human resources: Unilever
Unilever uses AI to screen candidates by analysing video interviews and responses, allowing recruiters to focus on the
most promising applicants.
Technology stack: Financial impact: Non-financial benefits:
● AI models: NLP and facial ● Cost reduction: Saved over ● Enhanced diversity in hiring
recognition algorithms US$1 million annually in ● Improved candidate experience
● Frameworks: Multimodal recruitment costs
candidate assessment ● Efficiency gains: Reduced hiring
platforms19 time by 75%
● Tools: HireVue AI platform
Customer service: Bank of America
Erica, an AI virtual agent, handles over a million customer queries daily – including snapshots of month-to-date spending
and flagging recurring charges – providing instant assistance and freeing human agents to tackle more complex issues.
Technology stack: Financial impact: Non-financial benefits:
● AI models: GenAI for ● Cost savings: Reduced ● Improved customer satisfaction
conversational interfaces customer service costs by 10% ● 24/7 customer support
● Frameworks: Multimodal ● Revenue growth: Increased availability
customer interaction platforms20 product cross-selling by 5%
● Tools: Erica, the virtual assistant
Marketing: Coca-Cola
Coca-Cola uses AI to generate marketing content, analyse consumer trends, and personalise advertising, resulting in more
effective campaigns.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Generative ● Efficiency gains: Reduced ● Innovative marketing strategies
Adversarial Networks (GANs) content creation time by 50% ● Enhanced customer
● Frameworks: Multimodal data ● Revenue increase: Boosted engagement
analysis for consumer insights21 campaign ROI by 20%
● Tools: Custom AI platforms
Supply chain management: Walmart
Walmart employs AI to predict product demand, optimise stock levels, and streamline logistics, ensuring products are
available when and where customers need them.
Technology stack: Financial impact: Non-financial benefits:
● AI Models: Predictive analytics ● Cost Reduction: Decreased ● Reduced waste
for demand forecasting inventory costs by 15% ● Enhanced supplier relationships
● Frameworks: Multi-modal data ● Revenue Growth: Improved
integration from sales, weather, product availability leading to
and events22 higher sales
● Tools: Data lakes, Machine
Learning models
Research and development: Insilico
Medicine
Insilico Medicine, a biotechnology company focused on longevity, has developed inClinico, an AI platform that
predicts phase II clinical trial outcomes to enhance drug discovery and development.
Technology stack: Financial impact: Non-financial benefits:
● AI Models: In-house-developed ● Cost Reduction: 35% ● Accelerated drug discovery and
multimodal foundation model nine-month ROI in an clinical trials process
● Platforms: Multi-modal investment application ● 79% accuracy for clinical trials
integration of omics, text, ● Time Efficiency: Reduced drug
clinical trials, small molecule development time
properties, and disease
targets23
● Tools: Transformer-based,
in-house-trained AI model and
platform
Legal: Hogan Lovells
The AI platform analyses large sets of contracts and legal documents, extracting critical information, and identifying
risks.
Technology stack: Financial impact: Non-financial benefits:
● AI models: NLP and ML ● Efficiency gains: Increased ● Improved accuracy
● Frameworks: Kira Systems review speed by 40% ● Enhanced client satisfaction
platform with multimodal data ● Cost savings: Reduced billable
processing24 hours for clients
● Tools: Kira AI
Procurement: Coupa
Coupa’s AI-driven spend management platform optimises supplier selection, contract management, and spend analytics,
transforming procurement processes into a strategic function.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Predictive analytics, ● ROI: Achieved an impressive ● Increased compliance and risk
machine learning, and spend 276% return on investment management.
forecasting. (ROI). ● Improved supplier performance
● Frameworks: Coupa ● Efficiency gains: Reduced and relationships
Source-to-Pay, Coupa Business procurement cycle and
Spend Management (BSM).25 significantly enhancing process
● Tools: Cloud computing, speed.
advanced sourcing optimisation,
real-time spend visibility.
IT Operations: Microsoft
Microsoft uses AI to monitor IT systems, predict failures, and automate support tickets, ensuring seamless operations.
Technology stack: Financial impact: Non-financial benefits:
● AI Models: Anomaly detection ● Cost Savings: Reduced IT ● Enhanced employee productivity
and predictive maintenance support costs by 20% ● Proactive issue resolution
algorithms ● Efficiency Gains: Improved
● Frameworks: Azure AI with system uptime by 15%
multi-modal data inputs26
● Tools: AI chatbots, Monitoring
tools
Sales: Salesforce
Salesforce’s AI analyses customer interactions, market trends, and sales data to provide actionable insights for sales
teams.
Technology stack: Financial impact: Non-financial benefits:
● AI models: Predictive analytics ● Revenue growth: Increased ● Improved customer relationships
with ML sales by 15% ● Enhanced decision-making
● Frameworks: Salesforce Einstein ● Efficiency gains: Reduced sales
with multimodal data cycle times by 25%
processing27
● Tools: CRM systems
Key GenAI agentic tools and their
differentiation
Commercial solutions Open-source solutions
LangGraph28 AutoGen29
● Target audience: Startups and established ● Target audience: Developers and researchers
enterprises ● Open-source framework: Facilitates cooperation
● Support: Offers robust customer support and among multiple AI agents
professional services ● Simplification: Orchestrates, automates, and
● Integration: Seamlessly integrates with existing optimises complex LLM workflows
enterprise systems ● Human-in-the-loop: Supports human-in-the-loop
● Customisation: High level of customisation and workflows for enhanced performance
control over workflows ● Community-driven: Encourages innovation and
● Features: Advanced features like statefulness collaboration within the community
(having a perfect memory or knowledge of previous
calls or requests), streaming support, and
moderation loops
CrewAI30 AutoGPT31
● Target audience: Fortune 500 companies and large ● Target audience: AI enthus |
13 | pwc | the-pwc-malta-ai-business-survey-report.pdf | TTThhheee PPPwwwCCC MMMaaallltttaaa
AAAIII BBBuuusssiiinnneeessssss
SSSuuurrrvvveeeyyy RRReeepppooorrrttt
20
24
pwc.com/mt/digital
1 Introduction
3
2 Executive Summary
6
3 Purpose for this Report
9
4 Overview of the Thematic Insight Areas
12
5 Thematic Insights: Strategy and Adoption
14
6 Thematic Insights: Governance
18
7 Thematic Insights: Investment
21
8 Thematic Insights: Market Perspectives
25
tropeR
yevruS
ssenisuB
IA
atlaM
CwP
ehT
Table of
contents
Malta AI Business Survey Report 2024
Introduction
Introduction
Introduction
The 2024 PwC Malta AI Business Survey was an endeavour of PwC Digital Services with as generative AI, organisations can facilitate tasks like software development and system
the objective of assessing the current state of AI adoption among organisations in Malta. transformation. Furthermore, organisations that are integrating AI into their operations, can
As a means to inform this current state, the survey was designed to elicit feedback in achieve a human-led, tech-powered strategy that not only addresses current challenges
targeted thematic areas, within which several capability areas were explored. but also positions them towards future success.
This survey is grounded in extensive research and aligns with PwC’s broader studies on In fact, artificial intelligence is revolutionising modern businesses by offering unparalleled
AI’s business impacts such as PwC’s Global AI study, which found that AI has the potential value across various dimensions. From a business perspective, AI enables organisations
to contribute up to $15.7 trillion to the global economy, and an increased 26% boost in to uncover deep insights from vast quantities of data, driving operational efficiency
GDP for local economies by 2030. and transforming products and services to better meet customer needs. In terms of
experience, AI enhances customer interactions by providing personalised and seamless
Technologically, AI empowers businesses to innovate and stay competitive. According to experiences, as seen in PwC’s AI-driven solutions for contact centres that improve self-
our latest CEO Survey 2024, 45% of CEOs believe their organisation will not be viable in service and live engagements.
ten years if it remains on its current path. By leveraging advanced models and tools, such
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 4
Insight Areas
At the European Union (EU) level, we are seeing significant focus
being placed on how our approach to AI will define the world we
will eventually live in, and from the EU’s perspective, technology,
especially Artificial Intelligence, is seen as a crucial driver in sustaining
economic growth, societal well-being, and digital sovereignty. The
European AI strategy emphasises the importance of setting global
standards and strengthening digital infrastructure to ensure that Europe
remains competitive and resilient in the face of the rapidly advancing
technologies that surround us. In fact, the EU’s approach to artificial
intelligence aims to make the EU a global hub for AI by promoting
research, innovation, and industrial capacity and ensuring the safe and
ethical use of AI systems.
At a national level Malta’s AI Strategy named “Strategy and Vision for
Artificial Intelligence in Malta 2030” sets out a long-term vision aimed
at transforming the country into an AI pioneer within the European
economy, by enhancing AI education, research, and commercial
applications of AI. By design, the national AI strategy is built on
three strategic pillars focusing on boosting investment, innovation,
and adoption, with a further three enablers cutting across the
aforementioned areas. These strategic enablers being:
1) education and workforce;
2) ethical and legal; and
3) ecosystem infrastructure.
In this frame, we are excited to link the findings of the PwC Malta AI
Business Survey with such global insights, to provide a holistic view of
AI’s transformative potential and its implications for businesses in Malta.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 5
Insight Areas
Malta AI Business Survey Report 2024
Executive
ve Summar y
While it is still early days for Malta in terms of the adoption of AI technologies, we believe Executive Summary
this report underlines the need for organisations to put AI high on the agenda at a strategic
level. This can be done by ensuring they have robust governance frameworks in place, and
strategically aligning their goals and objectives, where possible, with AI enabled initiatives in
order to fully harness the mass potential AI is capable of bringing.
The below provides an executive summary that highlights the key insights and takeaways on
the thematic areas explored in this survey’s report:
Organisations are finding it challenging to 1
manage the generative AI wave
From an AI strategy and adoption perspective, 56% of organisations responded that they do
not have an individual or team dedicated to assessing potential AI use cases. This suggests a
significant gap in structured AI evaluation and implementation.
While a priority area, the set-up of governance structures
2
for the responsible implementation of AI is a key
limiting factor for organisations
Our survey showed that 75% of organisations identified themselves as having no AI
governance framework in place, indicating a substantial lack of oversight and control over
AI initiatives and related regulatory obligations. In particular, the lack of a robust governance
framework may result in ethical, legal, and operational risks, as well as misalignment with
organisational goals and standards.
Organisations view AI enablement efforts to bring the largest benefits 3
in internal-facing operations to gain operational efficiency benefits
41% of organisations view the potential for AI in having the greatest impact on their
internal operations, suggesting a focus on improving efficiency and productivity. Meanwhile,
29% are looking to enhance customer experience through AI, and 21% aim to improve their
data-driven, decision-making capabilities.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 7
Insight Areas
No AI Novices
4
None of the participants scored as an AI Novice, providing
a strong indication that all the respondents are familiar with AI
technologies where the lowest scoring firms were AI Explorers
(15% of the respondents). None of the participants scored as an AI
Novice, providing a strong indication that all the respondents are
familiar with AI technologies where the lowest scoring firms were AI
Explorers (15% of the respondents).
While the majority of respondents recognise the value 5
of AI, organisations remain early in their AI
enablement journey
More than half of the respondents fell into the Visionary category, which speaks to
the strong intent of these organisations to be actively involved in AI from design to
implementation in their respective operating models. While these firms recognise the
value of AI enablement, they find challenges in, among others, finding a dedicated
talent with subject matter expertise to support a responsible AI implementation.
Prioritising the human-in-the-loop is
6
enabling the Leaders & Trailblazers to
leverage AI ahead of their peers
Those organisations that scored among the Leaders (24%) and
Trailblazers (10%) distinguished themselves across the thematic
areas being assessed for the maturity. Here, our analysis shows
that these organisations are investing into AI technologies, while
prioritising the human-in-the-loop philosophy via: (I) pursuing internal
AI initiatives such as upskilling, and (ii) allocating internal resources
to drive adoption of the latest generative AI product offerings.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 8
Insight Areas
Malta AI Business Survey Report 2024
Purpose for
this Repor t
Purpose for this Report
The objective of the PwC Malta AI Business Survey was to assess the current state of Local businesses were invited to participate through public promotions distributed on
AI adoption in Malta, identify the key drivers and barriers organisations are facing to PwC’s website and social media platforms, through a number of published thought
AI implementation and to make aware and understand the potential benefits and risks leadership articles, as well as through an email invitation sent out by PwC Malta’s
that may emerge. The survey explores several critical areas to provide a comprehensive marketing team. Overall, 59 participants completed the survey on behalf of their
understanding of AI’s impact on businesses in Malta. Each dimension was carefully organisation, between March and September 2024. The survey targeted individuals who
chosen to address critical aspects of AI adoption and its implications for organisations, are most engaged with AI practices in their organisation, such as, but not limited to the
outlined by a number of questions spanning over four distinct aspects, all of which shall following roles: Chief Executive Officer, Chief Financial Officer, Chief Legal Officer, Chief
be further explored in the following sections. Information Officer, Chief Technology Officer, IT Manager/s, or similar. In the absence of
such a role, the person responsible for overseeing technological development was asked
The online self-administered survey consisted of 20 questions covering four AI thematic to fill in the survey.
areas, at the end of which, respondents were each provided a maturity score.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 10
Insight Areas
In interpreting the results of this survey, it is important to note
that this study is not a representative one, in that it does not
accurately represent a larger population. Furthermore, efforts
were made to directly reach out to potential participants
through email and/or phone calls.
An even share of the participants was observed to be from
organisations with a revenue stream of more than €50M
(27%) and in the €1M - €10M range (27%), with a further
20% having a revenue stream in the €10M - €50M range.
The profiles that contributed to the survey were among a
variety of business functions including C-suite (44%); IT and
Cybersecurity (31%) and Finance Professionals (8%). The
remaining 17% was made up of respondents coming from
Sales, Compliance, Human Capital, and Operations.
From an industry perspective, the respondents were from a
wide range of industries, including financial services (19%),
government and public services (15%), technology, media
and communications (15%), consumer markets, distribution
and retail (7%) and professional services (5%). The remaining
39% fell under a plethora of different industries such as food
and beverage, leasing, real estate, pharmaceutical, aviation,
logistics and mobility, and multi-sector service.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 11
Insight Areas
Malta AI Business Survey Report 2024
Overview of
of the Thematic
Insight Areas
I. Strategy and Adoption II. Governance
This thematic area examines how businesses in Malta are adopting AI Effective governance is essential for managing AI initiatives. This
technologies. It covers responses related to the usage, perception, and theme explores the structures and framework implemented by
implementation of AI solutions within organisations. By understanding how businesses to oversee AI projects. It highlights the importance of
AI is being integrated into business operations, we can gauge the current having robust governance mechanisms to ensure that AI is
state of AI adoption and identify trends and patterns in its usage. implemented ethically and responsibly, aligning with organisational goals
and regulatory requirements.
III. Investment IV. Market Perspective
The survey also investigates the financial commitment of businesses This thematic area captures the general views and benefits realisation
towards AI. This thematic area provides insights into the budget expected from the use of AI technology. It includes perspectives on the
allocations for AI efforts, reflecting the level of investment and prioritisation potential advantages AI can bring to businesses, such as increased
given to AI initiatives. Understanding the financial landscape helps in efficiency, improved decision-making, and enhanced customer
assessing the readiness and willingness of businesses to embrace AI. experiences. By analysing these views, we can better understand the
market sentiment towards AI and its perceived value.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 13
Insight Areas
Malta AI Business Survey Report 2024
Thematic Insights
Strategy and
Adoption
Strategy and Adoption
Key Insights
Use case discovery and identification remains a go-to initiative for many
organisations, and our results suggest that organisations are at different
stages in performing such a strategic exercise. The results indicate that a
significant percentage of respondents - 58% - are at the beginning of their
AI enablement journey. For these organisations, a focus may be to first
understand the business impact to be realised from AI into their organisations,
as a means to inform where a use case for AI may be explored.
To what extent is your company actively considering AI (e.g.
GenAI) technlogy as a tool (e.g. leveraging prebuilt tolls like
ChatGPT or Microsoft Copilot) in your business operations?
Not yet Using but Considering 29%
Limited Use Cases of AI 29%
Researching Internal Use Cases 19%
Integrated into Our Processes 12%
Performing Proof of Concepts 10%
0% 10% 20% 30%
% of Responses
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 15
Insight Areas
The rate of AI enablement remains dependent on the availability of specialised talent.
Currently, it is clear from our analysis that organisations view their readiness to adopt
and successfully maintain AI technology use as reliant on their internal resources. 39%
of respondents believe there is a lack of subject matter expertise available within their
firm to be able to champion AI initiatives, be that an optimisation to transformation of
operating procedures.
In your opinion, what are the main challenges your organisation anticipates
encountering in the adoption of AI technologies (e.g. GenAI)?
7% Lack of Internal Expertise or Skills
14%
Integration with Existing Systems
39%
Data Privact and Security Concerns
19%
Ethical Considerations
22% We have not adopted /
considered adopting AI
Interestingly, data privacy and security risk from AI deployment is not a leading concern
for the participants. Ethical concerns from the use of AI technologies are the lowest
barrier for adoption, with the more conventional dimensions to digital transformation
being represented in: (i) integration of AI solutions with the organisation systems and
applications; and (ii) management of data privacy and security.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 16
Insight Areas
What’s next
The below are the recommended next steps that should be taken by organisations
to enhance their AI strategy and organisational adoption:
• Establish clear AI adoption goals and a manageable timeline to ensure a
successful implementation. Furthermore, the board should encourage cross-
departmental collaboration and produce a list of potential use cases that
would align with the long-term strategic objectives of the organisation.
• Prioritise the formation of an internal team overseeing all AI initiatives, use
case formulations and ensuring accountability while driving initiatives to
upskill employees in AI usage and other integrated tools to ultimately foster a
knowledgeable workforce.
• Secure investment to enable AI initiatives within the organisation, prioritising
governance practices while ensuring employees and the end-customer
experience a meaningful impact.
• Explore generative AI tools for contract drafting and review, legal research,
claims processing and vendor management. While questions surrounding
other fields including data protection and confidentiality may subsist, the CLO
should plan ahead and assess which solution can unlock more value for their
business without compromising on the essential security and privacy aspects.
• Support the implementation and experimentation of AI pilot projects to
demonstrate the value and impact AI has on the workforce and streamlining
processes to strive for a broader approach and not segmented. The CTO/CIO
should also ensure the implementation of a robust AI governance framework
to maintain data integrity and security.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 17
Insight Areas
Malta AI Business Survey Report 2024
Thematic Insights
Gover nan
ance
Governance
Key Insights
Undoubtedly, organisations are being asked to reinvent themselves to the With an ever-increasing list of legal and regulatory obligations, keeping a finger
operating model potential of the 21st century technologies being brought on the pulse of the AI regulatory landscape can be challenging. As of August
about through AI tools such as generative AI capability. Still, businesses must 2024, the regulatory clock via the EU AI Act has started and businesses will
be mindful to set-up governance mechanisms to ensure that such disruptive be expected to begin addressing the compliance requirements. This comes as
technology implementation happens in a responsible manner, as the potential a stark realisation for a significantly large portion of our respondents who are
ramifications from sprinting to the finishing line may prove costly. More than either unaware of the regulation (56%) or have voiced their need for guidance to
70% of the respondents observe a foundational concern from having a lack interpret their regulatory obligation (29%).
of a formal AI framework to inform their AI enablement journey.
Which of the below statements best describes the governance framework Which of the statements, best describes your
your company is considering in lieu of AI (e.g. GenAI)? organisation approach to the upcoming EU AI Act?
3%
There is no AI governance framework No awareness of the EU AI Act
7%
12%
There is a champion leading the 7% Aware of the EU AI Act,
framework with weak documentation Do no understand Impact
5% 29%
of procedures
7% Assigned an internal team to
There is a general AI governance understand Impact
framework with a set of policies
75%
and procedures
Currently investing in
There are designated champions in monitoring our AI compliance
the firm responsible for various AI
governance elements 56%
There is a specific team to centralise
the AI governance framework across
the business
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 19
Insight Areas
What’s next
The below are the recommended next steps that should be taken by
organisations to enhance their AI governance approach:
• Promote awareness with the C-Suite level about compliance issues and the
overall governance challenges to be able to provide effective oversight and
maintain an active understanding of key regulations such as the EU AI Act.
• Be the connection between executives and shareholders - guiding them
on ethical and compliant AI’s ability to create value, rather than seeing
it as a cost. Establish a comprehensive AI governance framework to
ensure ethical AI use, regulatory compliance and complete alignment with
organisational goals.
• Work closely with the CLO in providing the financial resources necessary to
develop and implement an AI compliance governance strategy framework,
prioritising initiatives such as AI literacy as complementary activities.
• Develop a risk-led strategy to help the company stay ahead of the
regulation, as a means to provide guidance on the critical areas of the EU
AI Act that need to be addressed first.
• Collaborate with the CLO and compliance team to ensure that the
organisation’s transformation is not slowed down by regulatory and ethical
challenges down the line. Develop and deploy continuous monitoring
systems to further ensure AI compliance and ethical use.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 20
Insight Areas
Malta AI Business Survey Report 2024
Thematic Insights
Investme
ent
Investment
Key Insights
Only 5% of the respondents are confident in their ability to measure
their return on investment (‘ROI’) from AI initiatives, thus it is evident
that gauging the success of such technology implementation is a
significant challenge for modern businesses. Additionally, the low
confidence in ROI measurement underscores the necessity for a
robust monitoring framework to ensure the success of AI initiatives.
How confident are you in your company’s ability to assess the
Return on Investment of current AI (e.g. GenAI) initiatives?
100%
Minimal confidence 22%
Limited confidence 22%
Moderate confidence 32%
Significant confidence 19%
Optimised confidence 5%
23.1%
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 22
Insight Areas
Too few of a percentage of the respondents (18%) view awareness, Paired with the above, a byproduct is being experienced by businesses that find future-
education, and research and development as a major AI investment area. planning of AI efforts a major hurdle to overcome. Among the spread of respondents, a
In contrast, AI transformation must begin with a lens of the impact on the lack of budget (29%) and conservative planning (41%) of AI-targeted investment areas
human, where the targeted upskilling of one’s company workforce is a strong such as training programmes or performing proof-of-concept applications of AI in one’s
indicator of successful AI enablement. business, remain the defaulted approaches.
Considering your technology investment strategy for AI initiatives Over the past and next 12 Months, which of the following statements best
(e.g. GenAI), which of the following areas does your company plan to describes the approach to technology investment of your company with respect
allocate budgetary funds to in the upcoming year? to AI initiatives (e.g. GenAI)?
Budgetary Fund Allocation
No Budget Allocation 29%
Proof of Concept testing
14%
27% Partial Budget Allocation 41%
Investment into AI
Transformation initiatives
18%
Moderate Budget Allocation 10%
Awareness and Education
Research and Development 23% Dedicated Internal Technology Investment 7%
18%
Other
Yearly Budget Allocation (Internal & External) 14%
0% 10% 20% 30% 40%
% of Responses
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 23
Insight Areas
What’s next
The below are the recommended next steps that should be taken
by organisations to enhance their AI investment:
• Discuss the ROI of AI from cost-savings, productivity-
gains, and experience-enhancement to provide an informed
evaluation of continued budget allocation for AI initiatives.
• Lead from the front to integrate AI into the current business
operating model and processes by prioritising quick-win
projects such as AI business case initiatives, while promoting
an internal culture of continuous learning and innovation.
• Collaborate with the CEO, and CTO/CIO teams to establish
reasonable ROI metrics to be monitored from the effort in AI
enablement services driven internally or sourced from
external providers.
• Support the investment and trust in use of AI from a regulatory
perspective, in a manner that provides the confidence to
C-suite on the safety of AI within one’s organisation.
• Facilitate the CFO’s financial management, via the sharing
of, among others, data points that would inform the CFO on
uptake of AI tools across the business.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 24
Insight Areas
Malta AI Business Survey Report 2024
Thematic Insights
Market
Perspectives
Market Perspectives
Key Insights
In contrast to their peers, only 10% of respondents mention AI technologies with the potential for
sector-agnostic transformation - taken to mean that all sectors from financial services to shipping,
will experience positive disruption from adoption of AI into their business models.
AI as an enabler for business optimisation of internal operations was found to be the leading driver
(42%) of AI adoption. Likewise, respondents identified customer experience (27%) as a major area
for AI optimisation, where the customer is both the workforce that interacts with AI, as well as the
customer’s client that is benefiting from a service delivery that is enhanced from AI use.
From the following statements, where do you anticipate the biggest
impact of AI in your industry, in the next 24 months?
2%
Optimising internal operations 3%
Enhancing customer experiences
5%
Augmenting data driven
decision making
20%
Other 42%
Improving marketing and
advertising strategies with
personalised content generation
27%
Streamlining customer service and
support through AI-driven solutions
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 26
Insight Areas
Interestingly for 41% of the responses, the foreseen impact of AI technologies was shared to be
significant to their department processes although not viewed as transformative to their operating
model - taken to mean that while a business may foresee an optimisation within their human
resources department, it is not the expectation that conventional process will be re-engineered
completely from the use of AI tools. At the same time, it must be noted that most respondents are
still exploring how best to leverage AI technologies which may suggest further need for study and
experimentation of AI initiatives.
In your opinion, what level of impact do you foresee AI (e.g. GenAI) having in your industry,
in the next 24 months?
Overview of
Executive Purpose for Strategy Market
Introduction the Thematic Governance Investment Contact us Summary this Report and Adoption Perspectives
Insight Areas
sesnopseR
fo
%
41%
40%
29%
30%
20%
15%
10%
10%
5%
No significant Limited Moderate Transformative Sector-wide
impact impact impact organisational impact impact
27
What’s next
The below are the recommended next steps that should be taken by organisations to
enhance their adoption of AI capabilities:
• Encourage a strategic focus on AI to optimise the organisation’s internal
operations and improve its service offering to one’s client base, while promoting
AI’s potential to streamline processes and enhance decision-making.
• Design an AI strategy that prepares a route for the company to manage AI
enablement in the short, medium and long term, with a focus on supporting
departmental use of technology to create value in efficiency, cost-savings and
user experience.
• Support the AI strategy with secured funding to perform internal research and
development that will ensure the organisation remains in-tune with the latest
AI developments.
• Stay abreast with the latest technology regulatory developments to ensure a
well-governed and responsible approach to AI use by the organisation.
• Maintain a vigilance on new and upcoming AI tools, as a means to remain
competitive in the service delivery of the organisation.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 28
Insight Areas
Key Actions for Successful
AI Transformation and Adoption
1. Leverage strategy and 2. Adopting a human-led, tech- 3. Prioritise and
governance to realise benefits powered approach pilot use cases
An effective AI strategy and governance At PwC, we believe that the key to realising The new and emerging capabilities of Generative
framework is crucial for realising the full benefits meaningful change from AI, is through AI, and continued advancements in the AI field
of AI. By establishing a clear strategic vision responsible AI use that blends human will be disrupting forces for one’s modern IT
on AI coupled with the necessary guidelines experiences with the power and potential operating model system with significant potential
and frameworks, organisations can ensure of the technology. Humans bring forward across the enterprise. Its implementation should
that AI systems are developed and deployed the knowledge required, and ultimately, by be guided by clearly defined use cases that
responsibly. This can be achieved by setting combining human expertise with advanced AI provide clear business value to the company. In
the necessary policies and procedures for technology, organisations can ignite a powerful this frame, it is recommended that organisations
usage, implementation, security and ethical synergy that drives growth, enhances user prioritise and pilot use cases either in individual
considerations, which help build trust in AI experience, and addresses complex challenges business functions (e.g. Finance, Human
amongst an organisation’s stakeholders. effectively. By leveraging this approach, Resources, other) or else cross organisationally
Moreover, it is paramount that regular monitoring organisations are able to realise AI that can be through user journeys (e.g. hire-to-retire). Such
and evaluation of AI systems, to ensure such is designed to work alongside humans, enhancing prioritisation and piloting will ensure that an
functioning as intended and making unbiased their capabilities and diminishing the risk of AI organisation can gain and leverage the necessary
ethical decisions. A robust governance structure replacing the human at the workplace. insights to make an informed risk-based
in place, therefore, will ensure organisations can business decision on how to gradually scale
mitigate risks and enhance the reliability and such use cases across the enterprise.
transparency of their AI initiatives.
Overview of
Executive Purpose for Strategy Market
Introduction Summary this Report the Thematic and Adoption Governance Investment Perspectives Contact us 29
Insight Areas
Contact us
Jake Azzopardi
Andrew Schembri
Senior Manager
Partner
[email protected]
[email protected]
This publication has been prepared for general guidance on matters of interest only, and does not constitute professional advice. You should not act upon the information contained
in this publication without obtaining specific professional advice. No representation or warranty (express or implied) is given as to the accuracy or completeness of the information
contained in this publication, and, to the extent permitted by law, PricewaterhouseCoopers, its members, employees and agents do not accept or assume any liability, responsibility
or duty of care for any consequences of you or anyone else acting, or refraining to act, in reliance on the information contained in this publication or for any decision based on it.
© 2024 PricewaterhouseCoopers. All rights reserved. ‘PwC’ refers to the Malta member firm, and may sometimes refer to the PwC network. Each member firm is a separate legal
entity. Please see www.pwc.com/structure for further details. |
15 | pwc | how-to-deploy-ai-at-scale-report.pdf | How to deploy AI at scale:
A PwC and Microsoft playbook that explores the
critical role of cloud and cybersecurity
Introduction
Artificial intelligence (AI) stands poised to bring transformative changes to the way we
live and work, much like the significant technological breakthroughs of the past 10,000
years, such as agriculture, the printing press, electricity, and the internet. However, AI
differs in its potential to fundamentally enhance what individuals and businesses can
achieve, and it promises to do so with unprecedented speed and impact
AI and Generative AI (GenAI) represent a truly transformational wave of technology that
will reshape our world. AI will influence and change all areas of business and what we
can accomplish in our working lives—for the better. AI is already starting to accelerate
new innovations and automate processes in ways we would have thought unimagi-
nable only a few years ago. It is improving our productivity and helping us reimagine
the customer experience—and we are only at the very beginning of understanding
what it can deliver.
There are multiple facets to what AI is and can do: machine learning, a subset of AI,
enables algorithms to learn from data. Deep learning, another subset, also identifies
patterns. GenAI, the most recent evolution, has garnered much interest of late because
of its ability to generate novel content, such as text and images, which it is able to fulfil
by using models trained on large datasets.
There are two underlying requirements that are essential for AI use within organisa-
tions: the adoption and use of cloud technology and security. Cloud infrastructure is
the engine that helps to fully exploit AI’s capabilities. This is needed to manage and
grow with the vast sums of data that AI creates. But in consequence, it introduces
new cybersecurity challenges. Strong cybersecurity provides fundamental protections
for company data—including for AI models—and safeguards a business’s intellectual
property. Combining cloud with cybersecurity is what provides the essential building
blocks that will truly help organisations to realise the full potential of AI.
This paper seeks to explain and outline all the necessary steps and considerations that
organisations need to take to make the most of this exciting technology, one that will
revolutionise the entire world.
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 2
1. Understand AI goals and
ambitions by determining strategy
Momentum around AI has been building slowly and goals to get there, aligning them with business
surely over the past decade, with a more recent strategy. Developing a clear roadmap can help
surge in interest following the launch of GenAI businesses navigate through the transformative
tools. The tools’ inherent ease of use has placed process of AI adoption. For those just starting, the
the technology in the reach of a much wider audi- focus should be on building foundational knowledge
ence, and at the same time, highlighted the possi- and exploring pilot AI projects that align with key
bility for all businesses to transform operations. business objectives. Mid-level adopters should
work on scaling these initiatives by refining their
We are now at the GenAI inflection point:
AI infrastructure and aligning AI strategies with
businesses are moving beyond individual exper-
broader business goals. Advanced users can focus
imentation and are rolling out the technology in
on optimisation, leveraging AI to innovate and gain
a concerted attempt to derive measurable gains
a competitive edge. A clear understanding of the
across the organisation. Organisations are all at
outcomes that the organisation wants to achieve,
different stages with AI. Some are taking their first
and its level of maturity is crucial. By providing
steps, some are at the early stages of exploring its
organisations with clear steps to follow, a solid
strategic implications, while others are already into
roadmap can ensure smoother transitions and better
making development decisions.
integration of AI technologies into operations.
Many of us have used AI without being aware of
Responsible AI practices help to design trust
its existence: simple grammar and spelling checks
in from the start and ensure that the impact of
and machine translations are both AI driven. We
the technology is broadly positive. This requires
are now witnessing a significant leap in what AI
developing a code of conduct that supports the
and the latest generation of AI tools can do. We
transparent, accountable and fair use of AI. We will
are seeing products such as the Microsoft Azure
cover this topic in more depth later in this paper.
OpenAI Service, which can be customised to
cater for specific use cases, but also off-the shelf Once AI goals have been aligned with business
GenAI tools, such as Microsoft Copilot1, which are strategy, you need to achieve a thorough under-
proving to be truly transformative for end users. standing of your organisation’s s capabilities,
Microsoft Copilot, for example, can help streamline assess your IT infrastructure and build in trust
a wide range of daily business activities, helping measures. Then the next step is to ensure the use
to cut down the production time needed for key of generative AI can be deployed effectively across
deliverables from days to perhaps a single hour. the organisation. The key: a robust and supportive
cloud architecture.
Business leaders are more than aware of GenAI’s
abilities and of its potential. Fully 70% of CEOs
believe that GenAI will transform the way they
create, deliver and capture value over the next
three years, according to PwC’s 27th Annual
70%
Global CEO Survey2. But before businesses
rush to start integrating GenAI into day-to-day
operations, several factors need to be considered.
The most important start point for every business
leader is in understanding the organisation’s AI of CEOs
maturity. This is crucial in determining readiness to
adopt and scale AI use for any new initiative. believe that GenAI will transform the
way they create, deliver and capture
Organisations should then define all the outcomes
value over the next three years2
they wish to achieve with GenAI and set out clear
1 PwC and Microsoft Copilot for Microsoft 365 | 2 PwC’s 27th Annual Global CEO Survey
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 3
2. Assess your cloud infrastructure
Adopt an effective cloud strategy
Cloud is the fuel of AI. Cloud offers scalability to Hybrid cloud combines public cloud services with
harness vast computing resources and helps busi- existing on-premises data centres and private
nesses be more agile and flexible, qualities which cloud infrastructures. This enables the seamless
are essential to the effectiveness of all AI roll outs. movement of workloads between the two environ-
Organisations should assess where they are on ments without compromises to performance.
their cloud journey and consider what steps they
need to take to support and enable their use of AI.
“There are many reasons why hybrid cloud
makes good sense for businesses getting
PwC’s recent Cloud and AI Business survey3
started with AI. It offers the best of both
identified a small number (12%) of businesses—
worlds by protecting existing investment but
named “Top Performers”—that have already
adding cloud scalability and flexibility. We’ve
begun to reap the rewards of their investment also pioneered the ability to manage both
in AI and the cloud. The report notes that 72% on-premises and cloud assets with cloud
of these Top Performers are far more likely to tools, which makes hybrid more attractive
have achieved “all-in cloud adoption” when it and simpler to adopt for many organisations.”
comes to modernising data, versus 33% of other
Joao Couto, EMEA VP and COO Cloud
companies. By moving their data to the cloud and
Commercial Solutions, Microsoft
making it more easily ingestible by large language
models (LLMs), Top Performers are more readily
able to unlock new value from their data as they The set-up is also useful to support the regulatory
integrate new AI capabilities. compliance and data sovereignty needs of highly
regulated industries where sensitive data must be
The use of cloud also requires a strategy that
processed within a country’s borders.
suits an organisation’s individual needs. There are
several options and each company must decide A multi-cloud approach refers to the simultaneous
what works best for them. The public cloud use of multiple cloud service providers (CSPs). As
is perhaps the best known. A simple internet Couto points out, when organisations opt for this
connection allows any business to run all or parts model, it is mostly because they perceive a risk
of their IT infrastructure in the cloud, rent storage of being reliant on one vendor: “Some customers
and servers and use a variety of services. Public want the option of using multiple cloud providers.
cloud offers unlimited access to IT resources What we find is that they eventually choose one of
giving businesses a flexible IT usage model, one two models: either the use of a sole provider or a
that is ideal for training LLMs. main cloud provider with another one as back-up.”
72%
have achieved “all-in cloud adop-
tion” when it comes to modern-
ising data, versus 33% of other
companies.
of “Top Performers”
3 PwC US report: 2024 Cloud and AI Business Survey
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 4
Use cloud to provide the Address data privacy issues
necessary infrastructure for AI
Whether a business is at the starting gate or has
Making the wheels of AI turn productively will already begun to use AI, it is essential to assess
require a robust cloud architecture. Building and the organisation’s processes and policies and
maintaining a wholly owned IT infrastructure is adapt these to govern the use of the technology.
expensive and can invariably place limits on a Cloud helps classify data access, for example,
company’s ability to scale. providing permissions for employees to access
data at the right time, when they need it, and only
if they need it. With stringent access controls,
“AI systems involve lots of data and that
organisations can more easily meet data protec-
data needs to be accessible. The cloud is a
tion regulation compliance and overcome data
scalable resource and it’s reliable—you need
privacy issues.
that if you are serious about bringing AI into
your business.”
Security is essential to AI because of the huge
data volumes involved. A strong security posture
Sebastian Paas, Partner, EMEA Cloud
helps ensure that all data used within AI systems
Leader, PwC Germany.
are not misused. Cybersecurity is foundational to
successful AI implementation.
Cloud service providers, such as Microsoft Azure4,
offer scalable resources that help control and
minimise the cost of AI development and deploy-
ment. Cloud resources also facilitate collaboration
across a company and among individual teams
helping users to seamlessly share real-time
insights and resources.
PwC’s 2024 Cloud Business and AI Survey5
showed that while most companies rather their
CSPs favourably, there are opportunities to get
even more value out of cloud by evolving their
relationships. At the top of the list: monitoring and
managing security and compliance, where more
than half of companies are looking to change their
relationships with their CSPs. More than two-fifths
of companies are also evaluating the types of
services provided and looking to collaborate on
future-state capabilities.
Streamline access to data
while making AI and machine
learning more accessible
Cloud’s operational agility is essential in supporting
AI systems and is also providing access to
specialised tools and services that are designed
for developing, deploying and enhancing GenAI
applications. One notable example is the Microsoft
Azure OpenAI Service, which delivers access to
powerful language models, such as GPT-4 and
DALL-E. Furthermore, Microsoft also provides
data management tools that help clean, organise
and prepare unstructured and structured data, to
increase its usability for those applications.
4 PwC and Microsoft generative AI | 5 PwC US report: 2024 Cloud and AI Business Survey
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 5
3. Secure your data to power
AI solutions
Like any technology system, artificial intelligence
systems need to be protected from potential “Organisations need to ensure they have
threats and vulnerabilities. AI systems handle policies and processes in place to mitigate
huge amounts of data that include both personal high levels of risk in their AI systems, such as
and proprietary information, making them anything that is harmful to an individual. Not
appealing cyberattack targets. only do companies need to implement strong
cybersecurity, but they also need to ensure AI
When designing a new AI system, organisations
outputs are monitored and managed.”
should take care to build in strong security meas-
ures from the start to counter the rising number of Neil Redmond, Director, Cybersecurity and
attacks, which are continually growing in their levels Privacy, Competency Lead, PwC Ireland
of sophistication. Unsurprisingly, organisations
believe cyber risk to be only second in importance
for businesses after inflation, according to PwC’s
A secure cloud platform, such as Microsoft Azure,
2023 Global Risk Survey6, with many respondents
helps protect AI data from the additional risk
feeling they are “highly or extremely exposed”
of cloud vulnerabilities because of the greater
to them. The same survey notes that digital and
visibility it offers in security monitoring. This also
technology risks are also of high concern.
helps minimise data breaches and unintentional
CSPs offer the most highly advanced security user input. Implementing robust governance
controls with continuous monitoring and encryp- structures supports data integrity further by
tion. A ‘zero trust’ security architecture adds addi- ensuring data is validated and monitored, along
tional protection with superior access controls, with processes that can quickly detect and correct
ensuring that every access request is verified any additional errors in the AI data.
regardless of its origin. This helps to maintain AI
Authorised GenAI business tools also reinforce
system integrity and data confidentiality. These
security, avoiding what is termed ‘shadow GenAI’.
measures also work to prevent unauthorised
In the absence of a company-authorised chatbot
access and malicious actors from compromising
tool and associated policy, employees are likely
the AI system, so it remains available to users.
to use unauthorised tools, which increases the
LLMs are complex pieces of software, which are risk of data breaches. When companies block
open to multiple security risks that threaten their GenAI tools, they can also inadvertently push
integrity. The way LLM data is trained can lead to staff to transfer sensitive data to less-secure
biased or erroneous outputs that raise either legal personal devices. Having an approved tool used
and ethical concerns or erode trust in AI systems, in the cloud environment and blocking access to
so it’s vital to include human oversight throughout browser-based or consumer GenAI tools helps to
the training process and beyond. Continuous reduce the risk of shadow GenAI practices.
model training and bias mitigation measures help
Building trust in AI system accuracy is vital in
identify and eliminate problematic output.
protecting organisational reputation and credibility.
Fine tuning models through continued validation Customers feel more assured and users more
of inputs and outputs, along with anomaly detec- confident in AI outputs when robust security meas-
tion processes, help to achieve fair and reliable ures and governance frameworks7 are in place.
results, too.
6 PwC Global Risk Survey 2023 | 7 PwC report: GenAI is here to stay: What it means for cyber security
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 6
4. Streamline cyber defences
Security teams, under constant pressure from
attacks and hackers, can strengthen and stream- “AI can be extremely helpful in maintaining
line their cybersecurity using GenAI8. The three security costs, while increasing cybersecurity
principal ways organisations are prioritising the protections and managing the constantly
use of GenAI for cyber defences, according to changing security threat landscape. GenAI
PwC’s latest Global Digital Trust Insights report9, tools help organisations execute routine
are: monitoring more efficiently, freeing up analyst
time to focus on more complex tasks.”
1. Threat detection and response
2. Threat intelligence
Aleksei Resetko, Partner, Cybersecurity &
3. Malware/phishing detection
Privacy, PwC Germany
Automating security using GenAI protects AI
systems because of the ability to constantly
Because PwC works closely with Microsoft, its
monitor for vulnerabilities in networks, applica-
security experts are well placed to tailor the tools
tions, platforms, systems and cloud.
to meet specific organisational needs. PwC’s
global reach provides an additional layer of
A good example of automation is in the use of
understanding in addressing complex security
Microsoft Copilot for Security for continuous
challenges across different regions and sectors.
monitoring of network traffic and threat identifi-
cation in real time. Not only does this mean that
GenAI can also be employed to review code for
threats can be mitigated expeditiously, but also
security flaws or for penetration testing to identify
the burden of repetitive and time-consuming tasks
IT system vulnerabilities. In addition to making
is greatly reduced.
these processes faster, GenAI can also provide
much more precise analyses and support lower-
This not only increases productivity, but it can
level work, such as recognising threat patterns,
also help companies retain skilled employees who
drafting incident reports and general management
appreciate a more varied and challenging workload.
reporting. While GenAI tools won’t replace human
While Security Copilot significantly boosts cyber- analysts, the tech can significantly boost efficiency
security defences, organisations can improve its for security teams, enabling them to more easily
use further with expert help. monitor, report and respond rapidly to incidents.
8 PwC report: GenAI is here to stay: What it means for cyber security | 9 PwC 2025 Global Digital Trust Insights: Bridging the gaps to cyber
resilience: The C-suite playbook
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 7
5. Keep up with changing
regulatory environments
Regulatory compliance is an important consid- involved for all AI-driven activity. Under the Act,
eration, as regulators are responding to the AI systems that pose an unacceptable risk to the
rapid development of GenAI and the growing safety, livelihood or rights of individuals, or that are
use of other forms of AI and organisations must seen to manipulate the behaviour of humans or
comply with an increasing number of regulatory exploit their vulnerabilities are not permissible.
requirements. While CEOs have a higher level of
GenAI can be employed to achieve compliance
confidence in the ability of their organisation to
with the Act. For example, PwC has developed
comply with regulations, CISOs, at the front line
its own AI-based processes to test and validate
of cybersecurity are less optimistic. For example,
use cases against the EU legislation. This helps to
while 67% of CEOs in a recent survey reported
determine what is acceptable, what is prohibited
a high level of confidence in their organisation’s
under the Act, and how a particular use case
ability to be in compliance with AI regulations, just
54% of CISO/CSOs were equally confident10. The aligns with an organisation’s responsibilities and
recent enactment of the EU AI Act11 in Europe— compliance obligations. AI can also help address
which came into force in August 2024—is the first other types of regulatory compliance, for example
legislation to govern AI use. It is aimed at ensuring by using GenAI to help achieve compliance on
the safe and ethical development and deployment data protection rules or other types of legislation.
of AI within the European Union.
“The Act represents a vital first step in creating
67%
safe digital markets. It is expected to be the first
of many and similar legislations are already in
development in other global regions.”
Mona de Boer, Partner, Data and Artificial of CEOs
Intelligence, PwC Netherlands
reported a high level of confidence
The EU Act will require developers of GenAI foun-
in their organisation’s ability to be
dation models to be transparent about the data
in compliance with AI regulations
they use for model training and demonstrate how
models are developed to highlight the levels of risk
10 PwC 2025 Global Digital Trust Insights: Bridging the gaps to cyber resilience: The C-suite playbook | 11 European Parliament: EU AI Act
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 8
6. Operationalise responsible AI
practices
AI systems need to be implemented responsibly AI still nascent and growing in its use in organisa-
to ensure their lawful, ethical and robust use. tions, trust is critical to engender acceptance of AI
PwC’s Responsible AI methodology12 helps use and the overall success of AI projects.
support the development of robust governance
frameworks to ensure AI use is transparent,
“There are still challenges in getting people
fair and accountable. This helps to manage
to use available AI tools in organisations.
AI risks effectively through the institution of
‘Employees’ tolerance levels will diminish
comprehensive policies and procedures, meaning
if AI tools don’t work or are perceived to
organisations can overcome potential ethical
be biased. We have to acknowledge that
violations and mitigate legal risks. To operation-
especially in regulated industries such as
alise responsible AI, businesses should implement
financial services, accuracy is key and it’s
governance frameworks that monitor AI’s use
absolutely critical to ensure that client data is
in real time, ensuring continuous oversight and
well-protected.”
immediate response to any issues that may arise.
Conducting regular audits to prevent biases or Prafull Sharma, Partner, Technology and
unintended consequences should also be an inte- Data Leader, PwC Switzerland
gral part of the process. “When approaching AI for
the first time, risk is often a key client concern,”
adds Mona de Boer. “It’s essential to show how a While responsible AI practices provide the back-
high-level responsible AI strategy translates to an bone for GenAI use, it is critical to design trust in
operational procedure level so they can see how from the outset, not only for AI applications in use,
risks are managed.” but also for supporting infrastructure such as with
the cloud platform.
Responsible AI deployment also means aligning AI
investment with clearly defined ethical standards
that cover items such as privacy and bias preven-
tion, to maintain stakeholder trust. With GenAI and
12 PwC: The responsible AI framework
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 9
7. Build strategic partnerships
For organisations wanting to successfully develop PwC now has one of the largest implementations
secure AI solutions, it is imperative to bring in a of Azure OpenAI in the world, and our AI Factory13
strong technology partner with the right capabili- operating model supports the rapid scaling of
ties, industry knowledge and functional expertise. models for use in other areas of a client’s busi-
It is equally essential to tap into proven industry ness. A good illustration of this is an automated
expertise and knowledge to overcome barriers to invoice processing solution we developed using a
implementation. This helps to smooth the journey Microsoft GenAI model for a global manufacturing
to AI and jump-start its adoption. client. This solution can automatically approve,
deny or send invoices for human review and
PwC has taken a 360-degree approach to AI.
greatly reduces tedious and repetitive work. The
First, we embarked on our own AI journey by
AI Factory model is helping to scale the model for
adopting and using GenAI across the entire PwC
document review and analysis across the entire
organisation. This is helping us thoroughly test
finance function. “PwC is a pioneer in our entire
and refine the technology and ensure that any
partner ecosystem and is leading by example,”
GenAI offering could deliver the most client value.
adds Joao Couto. “Because PwC adopted
Our significant investment in deploying these solu-
Microsoft GenAI tools across its business, it can
tions internally, for example through our strategic
quickly and reliably demonstrate the business
partnership with Microsoft, is also helping us to
impact to customers based on its own experi-
deliver more tailored AI solutions.
ences. It’s a unique position to be in.“
Microsoft is a leader in secure generative AI tech-
“Our partnership with Microsoft enables pilot nology with more than 60,00014 customers using
projects that help us to demonstrate the impact Azure AI today. And this sophisticated technology
and potential of AI. Because we can rely on a is backed by the stringent security tools and
full range of AI, GenAI, machine learning and controls of the Azure Cloud Platform. By tapping
deep learning solutions from Microsoft, we into the PwC and Microsoft relationship, compa-
believe we can quickly help our clients gain that nies can use AI to drive growth. The Microsoft
all-important first mover advantage.” OpenAI Service integrates several powerful foun-
dation models into its products. It also offers an
Mauro Xavier, Partner, EMEA Microsoft Application Programming Interface (API) service
Alliance Leader, PwC Spain for developers to integrate the models it uses into
their own applications.
13 Why you need an AI factory: A CIO’s guide to generative AI | 14 Press Release Webcast - FY 2024 Q4
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 10
8. Empower and upskill your
people on AI
As AI continues to evolve, it’s impact on the Both will contribute significantly to gaining more
workforce will be increasingly far-reaching. Using confidence and adopting AI in the organisation.
AI has the potential to help the workforce be far If this succeeds, it can both increase employee
more productive. PwC’s 2024 AI Jobs Barometer productivity and help employers retain talent
notes an almost five-fold increase in labour within the company. PwC’s 2024 AI Jobs
productivity in business sectors exposed to AI15. Barometer shows that these capabilities are
already highly valued; employers in the countries
To achieve this impressive level of impact,
surveyed are willing to pay a 14% wage premium
organisations need to proactively prepare their for people skilled in the technology16. PwC will
employees for the AI revolution by providing explore this topic in greater depth in one of a
training opportunities and a safe space for series of forthcoming AI whitepapers.
employees to experiment with the technology.
15, 16 PwC’s 2024 AI Jobs Barometer
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 11
Closing: monitor and adapt to new
business issues
We are on the cusp of great change. AI and GenAI are showing how we can transform
what we can achieve. And we are only at the very beginning of the seismic effect
that AI will bring to the efficiency of businesses and their ability to compete and grow
by accomplishing goals much faster17. Starting the AI journey correctly is crucial.
Collaborating with experienced business and technology partners yields better, more
positive results and motivates organisations to keep progressing.
A strong cloud partner is of equal importance. As we have stated: for AI projects to be
successful, they need the scalability of a robust cloud infrastructure. This removes the
brakes that traditional wholly-owned IT infrastructures can place on development and
enables AI applications to be deployed rapidly.
Those organisations that don’t adopt AI now may find themselves pushed out of their
markets very quickly. And once the technology has been adopted, organisations
should keep an eye on the future. The possibilities of AI are constantly evolving and
growing. To maintain the competitive edge that AI and GenAI can deliver, it is essential
for every business to focus on continually improving its AI capabilities and keep pace
with industry trends.
We believe that AI has the potential to help organisations fuel innovation, make great
advances in productivity and reinvent how they operate. A new dawn of possibilities is
emerging—one that helps businesses solve their most important challenges and build
the trust they need to achieve a better tomorrow.
17 PwC The Leadership Agenda: Gen AI is a tool for growth, not just efficiency
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 12
Contacts
Joao Couto Mauro Xavier Mona de Boer Sebastian Paas
EMEA VP & COO Partner, Partner, Data Partner,
Cloud Commercial EMEA Microsoft & Artificial EMEA Cloud
Solutions Aliance Leader Intelligence Transformation
Microsoft PwC Spain PwC Netherlands Leader
PwC Germany
Aleksei Resetko Prafull Sharma Neil Redmond
Partner, Partner, Director,
Cybersecurity Technology & Cybersecurity
& Privacy Data Leader and Privacy,
PwC Germany PwC Switzerland Competency Lead
PwC Ireland
How to deploy AI at scale: A PwC and Microsoft playbook that explores the critical role of cloud and cybersecurity 13
© 2024 PwC. All rights reserved. Not for further distribution without the permission of PwC. ‘PwC’
refers to the network of member firms of PricewaterhouseCoopers International Limited (PwCIL), or,
as the context requires, individual member firms of the PwC network. Each member firm is a separate
legal entity and does not act as agent of PwCIL or any other member firm. PwCIL does not provide any
services to clients. PwCIL is not responsible or liable for the acts or omissions of any of its member firms
nor can it control the exercise of their professional judgment or bind them in any way. No member firm is
responsible or liable for the acts or omissions of any other member firm nor can it control the exercise of
another member firm’s professional judgment or bind another member firm or PwCIL in any way. |
16 | capgemini | Everest_Group_-_Artificial_Intelligence__AI__Services_PEAK_Matrix_Assessment_2023_-_Focus_on_Capgemini.pdf | Everest Group Artificial Intelligence (AI) Services PEAK Matrix® Assessment 2023
Focus on Capgemini
January 2024
Copyright © 2024 Everest Global, Inc.
This document has been licensed to Capgemini
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Introduction
Artificial Intelligence (AI) has been a transformative technology since its inception. Increasing advances in AI, bolstered by the recent developments in generative AI (gen AI), are pushing
organizations to actively invest in a strong AI strategy to achieve business-oriented outcomes and improve customer experience. Despite these developments, organizations are failing to
achieve the full benefit, because they are adopting AI in pockets, rather than across the organization. Providers with innovative solutions, accelerators, and strong advisory capabilities can
efficiently help enterprises to navigate the fast-evolving AI landscape and successfully implement it.
In this research, we present an assessment and detailed profiles of 26 AI service providers featured on the Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023. Each profile
offers a comprehensive picture of its service focus, key Intellectual Property (IP) / solutions, domain investments, and case studies. The assessment is based on Everest Group’s annual
RFI process for calendar year 2023, interactions with leading AI service providers, client reference checks, and an ongoing analysis of the AI services market.
The full report includes the profiles of the following 26 leading AI service providers featured on the Artificial Intelligence (AI) Services PEAK Matrix:
⚫ Leaders: Accenture, Capgemini, Cognizant, Deloitte, IBM, TCS, and Wipro
⚫ Major Contenders: DXC Technology, EPAM, Eviden –an Atos business, EXL, EY, Genpact, Globant, HCLTech, Infosys, KPMG, LTIMindtree, NTT DATA, PwC, Sopra Steria, and
Tech Mahindra
⚫ Aspirants: Kyndryl, Stefanini, UST, and Virtusa
Scope of this report
Geography Providers Services
Global 26 AI service providers AI services (refer to page
10 for scope of research)
Note: Everest Group has refrained from identifying Star Performers for this AI Services PEAK Matrix report due to change in the scope of this research
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 2
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
AI services PEAK Matrix® characteristics
Leaders
Accenture, Capgemini, Cognizant, Deloitte, IBM, TCS, and Wipro
⚫ Leaders have displayed a strong vision focused on driving business outcomes through AI services for their customers
⚫ They are at the forefront of innovation and driving change with thought leadership, partnerships, and internal investments in emerging themes such as gen AI, sustainability, responsible
AI, MLOps, no-code/low-code solutions, AIOps, and edge AI
⚫ Leaders have invested heavily in acquisitions as well as building structured internal talent development programs to ensure the availability of skilled talent to solve complex problems.
They have also focused on the breadth of skills, enabling full services play by developing a range of certification programs that help them stay ahead as technology evolves
⚫ Leaders have developed a range of integrated platforms along with industry-and use case-specific accelerators to cut down the trial and run phase to achieve faster outcomes
⚫ Domain focus and willingness to share risk and returns through value-based pricing models have further differentiated them in stakeholder partnerships
Major Contenders
DXC Technology, EPAM, Eviden – an Atos business, EXL, EY, Genpact, Globant, HCLTech, Infosys, KPMG, LTIMindtree, NTT DATA, PwC, Sopra Steria, and Tech Mahindra
⚫ Major Contenders have shown high confidence in their sweet spots within the AI stack. They have a strong base of satisfied clientele within these areas
⚫ Major Contenders have the vision to develop full services play and are investing in talent development programs, acquisitions, IP building, and a partnership ecosystem to enable
the same
⚫ They need to supplement their vision and investments with effective communication of success on transformative end-to-end AI deals to enhance their market perception
Aspirants
Kyndryl, Stefanini, UST, and Virtusa
⚫ Aspirants are focused on developing expertise in their preferred AI value chain segments with most investments directed toward upgrading and improving the features of these flagship
solutions
⚫ Aspirants try to differentiate themselves through cost-effectiveness, innovation, personalized services, and agility or quick turnaround time
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 3
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Everest Group PEAK Matrix®
Artificial Intelligence (AI) Services PEAK Matrix® Assessment 2023 |
Capgemini is positioned as a Leader
Everest Group Artificial Intelligence (AI) Services PEAK Matrix®Assessment 20231,2
High
Leaders
Major Contenders
Aspirants
Low
Low High
Vision & capability
Measures ability to deliver services successfully
1 Assessments for EPAM, Eviden–an Atos business, EY, Infosys, KPMG, PwC, and UST exclude service provider inputs on this study, and are based on Everest Group’s estimates that leverage its proprietary Transaction Intelligence (TI) database,
ongoing coverage of service providers’ public disclosures, and interaction with buyers. For these companies, Everest Group’s data for assessment may be less complete
2 Assessment for Deloitte is based on partial inputs provided by service provider and is also based on Everest Group’s estimatesthat leverage its proprietary Transaction Intelligence (TI) database, ongoing coverage of service providers’ public disclosures,
and interaction with buyers. For this company, Everest Group’s data for assessment may be less complete
Source: Everest Group (2023)
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 4
tcapmi
tekraM
tekram
eht
ni
detaerc
tcapmi
serusaeM
Leaders
Accenture
Major Contenders Deloitte
Capgemini
IBM
Infosys
TCS
Genpact HCLTech Wipro
EY Cognizant
PwC
KPMG
EXL
Globant Tech Mahindra
LTIMindtree
NTT DATA
DXC Technology
EPAM
Eviden
Virtusa Sopra Steria
UST
Kyndryl Stefanini
Aspirants
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Capgemini profile (page 1 of 5)
Overview
Company overview Low (<10%) Medium (10-25%) High (>25%)
Capgemini, headquartered in Paris, is a prominent global corporation delivering consulting, technology,
engineering, professional, and outsourcing services. Capgemini operates in more than 50 countries and is Adoption by industry
particularly strong in Europe, North America, Asia-Pacific, and the Middle East. The company caters to a
Banking, Financial Electronics, hi-tech, Healthcare and
diverse clientele across sectors such as Banking, Financial Services, and Insurance (BFSI), retail, Services, and Insurance and technology life sciences
manufacturing, and technology while specializing in digital transformation, cloud services, cybersecurity,
AI, and analytics. Retail, distribution, Telecom Media
and CPG and entertainment
Manufacturing Public sector Others
Headquarters: Paris, France Website: www.capgemini.com
Key leaders Adoption by geography
⚫ AimanEzzat: Chief Executive Officer North America UK Rest of Europe
⚫ Niraj Parihar: CEO, Insights and Data GBL
⚫ Anne-Laure Thibaud(THIEULLENT):Data, AI, and Analytics Group Offer Leader APAC South America MEA
AI practice overview
⚫ Capgemini's AI Services business is organized based on two dimensions: group portfolio and Global Adoption by buyer group
Business Lines (GBL)
Small-market Mid-market Large-market Very large-market
⚫ The Data and AI global portfolio team coordinates and manages the entire group response for data and
(Annual revenue (Annual revenue (Annual revenue (Annual revenue
AI, ensuring alignment and coordination across the group portfolio
<US$1 billion) US$1-5 billion) US$5-25 billion) >US$25 billion)
⚫ Capgemini has invested in generative AI to scale up its capabilities and build industry-focused solutions
to cater the specific needs of its clients, with an additional investment of EUR2 billion in AI over the next
three years
AI practice fact sheet 2021 (Jan-Dec) 2022 (Jan-Dec) 2023 (Jan-Jun)
Number of active clients 2,000-2,500 3,000-3,500 3,000-3,500
Number of FTEs 28,000-30,000 30,000-35,000 32,000-36,000
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 5
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Capgemini profile (page 2 of 5)
Solutions
IP overview
⚫ Capgemini’s portfolio brings the foundations: AI & data strategy, AI analytics & data science, intelligent process automation, and AI & data engineering. It enables Capgemini to bring new data & AI approaches. Recently, it has
introduced offers as part of the Generative AI portfolio spanning from strategy definition through to practical development and implementation of generative AI at scale, by bringing together years of experience and leading-
edge generative AI work and augmenting it with industrialization around foundation models
⚫ Capgemini has a unified portfolio of assets and solutions that it leverages to deliver business outcomes to its clients. It follows a Data and AI-powered transformation strategy for the industrialization of its data platforms into
managed business assets. It serves its clients with Data & AI solutions to deliver customer experiences, transform to intelligent & sustainable products and industrial operations
Proprietary IP/solutions/frameworks/accelerators/tools developed internally to deliver AI services
Solution name Solution type Year launched Details
AI @Scale Framework N/A It is a platform designed to help organizations achieve enterprise-wide AI adoption and scalability. It addresses the challenges
that businesses face when modernizing its AI journey and centralizing AI capabilities. The framework encompasses
processes, reference architectures, data strategy, governance, ethical AI principles, and accelerators.
Edge AI Framework/Accelerator 2021 It is a framework designed to enable the deployment of advanced AI solutions securely on edge devices. It addresses
challenges by optimizing power and compute resources to maintain model performance and accuracy. It also enhances
availability while prioritizing data privacy and security, ensuring that sensitive information remains protected.
Artificial Data Amplifier (ADA) –powered Product 2018 It is a data augmentation and synthetic data generation platform powered by AI and ML techniques. It is designed to address
by gen AI the challenges associated with data scarcity, privacy concerns, and the need for diverse and representative datasets in AI and
ML projects.
Generative Testing Product N/A It leverages Large Language Models (LLMs) and synthetic data for the discovery of code to test case, specification to test
case, and defect report to test case and then the generation of the test cases for the monitoring and prediction of defect rate.
Privacy Preserving AI (PPAI) Solution N/A It is a suite of solutions designed to enhance current privacy techniques and explore novel approaches to safeguard sensitive
data utilized across the AI life cycle.
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 6
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Capgemini profile (page 3 of 5)
Partnerships
Key partnerships (top 10)
Partner name Details
AWS It is a premier consulting partner with an aim to leverage the capabilities of AWS's cloud infrastructure and AI services to drive innovation and transformation for clients. Capgemini’s
Custom Generative AI for Enterprise is available on AWS as well.
Azure It is a Microsoft gold partner to combine Capgemini's AI expertise and industry knowledge with Azure's advanced AI capabilities including ML, cognitive services, and data analytics.
Capgemini and Microsoft have also partnered to launch Azure Intelligent App Factory, a product that aims to help businesses quickly and responsibly deploy gen AI capabilities.
GCP It is a premium Google partner with an aim to leverage GCP's cloud-based AI and ML services to drive innovation and transformation for clients. Capgemini has also created a global gen
AI CoE in partnership with Google.
Salesforce Capgemini is global strategic partner and has introduced genAI for CX Foundry for clients using Salesforce that helps in hyper-personalization and data-driven CX.
Dataiku Capgemini is a platinum partner and offers a collaborative platform that powers both self-service analytics and the operationalization of ML models in production.
DataRobot Capgemini is a service partner to DataRobotand has collaborated to leverage DataRobot’splatform for its initiatives around next-generation demand themes.
Databricks Capgemini has a strategic partnership and has collaborated to build gen AI capabilities and cater to the growing demand.
H2O.ai Capgemini is a global System Integrator (SI) partner to H2O.ai helping clients with investments in AI, cloud, and digital.
Other partnerships (logos)
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 7
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Capgemini profile (page 4 of 5)
Investments and market success
Other investments to enhance AI services capabilities, e.g., setting up of new delivery centers / CoEs / innovation labs, trainings/certifications, etc.
Investment Details
Innovation lab ⚫ Introduced a dedicated genAI practice relying on a network of experts globally to support its clients’ gen AI solutions adoption and implementation
⚫ Established a gen AI lab with a dedicated team of AI experts. The lab's primary focus is on researching gen AI use cases, confidentiality, privacy, multi-modal models, and technology readiness. It
explores the challenges of context-aware AI and consists of a core team of experts and additional members across global Capgemini offices
⚫ Launched gen AI Google Cloud CoEto help enterprises realize the full potential of AI technologies. The new CoEaims to help clients advance its business transformation goals, enhance engagement
with customers, and accelerate value creation from AI investments
⚫ Established a Quantum Lab in collaboration with IBM, which is dedicated to assisting clients in exploring the prospects of quantum technologies. Its primary focus is on shaping the organization's
strategy and capabilities to transform the potential of quantum computing into practical reality
⚫ It also utilized a wide network of delivery and solutioning centers supported by innovation centers and dedicated advanced technology labs such as 5G Lab, IPA AI Lab, and Global AI CoEnetwork to
enable the best solution capability for its clients
Talent development ⚫ Launched gen AI campus on the data and AI learning platform (NEXT) to enhance gen AI skillset and build solutions for clients and partners
⚫ Launched a solution development lab, GenZArena, a hub for skill development, employee engagement, and IP solution creation. It is designed to actively involve and quickly onboard new talent,
particularly recent graduates, harnessing its millennial mindset. It places a strong emphasis on advanced visualization, DevOps,and ML solution development using cutting-edge technologies and tools
Acquisitions ⚫ Acquired Quantmetry, an independent consulting firm specializing in mathematical data modeling and AI technological solutions. The acquisitions aims to strengthen the capabilities of Capgemini in
France to deliver data transformation at scale and in the development of innovative, high-impact products and services powered by trusted AI
⚫ Acquired Braincourt, a German firm that specializes in business intelligence and data science services
Recent AI engagements (non-exhaustive)
Client Year of signing Geography Engagement details
Multinational consumer N/A N/A Built a cohesive AI suite with the help of GPT-3 model to generate content that reduces the content creator’s time, increases product visibility, and increases
goods company purchase conversion for the target product
Global academic publisher N/A N/A GPT-enabled semantic search enabling reduced support cost and enhanced customer experience through integrations of various platforms to provide
personalized content
A pharmaceutical company N/A N/A Enabled a trusted data and AI platform to speed up drug development and improve the success rate of clinical trials by 30%
A healthcare major N/A N/A Established an AI-powered touchless forecasting accelerator with 20+ forecasting models resulting in enhanced processing time by 80%
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 8
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Capgemini profile (page 5 of 5)
Everest Group assessment – Leader
Measure of capability: Low High
Market impact Vision & capability
Market Portfolio Value Vision and Scope of Innovation and Delivery
adoption mix delivered Overall strategy services offered investments footprint Overall
Strengths Limitations
⚫ Broad industry coverage:Capgemini has extensive expertise in serving clients spanning ⚫ Talent concerns: while Capgemini has invested in different upskilling programs such as
different industries including banking, manufacturing, life sciences, and retail, distribution, Millennial Garage (Gen Z Arena) and Data & AI Campus, referenced clients have highlighted
and CPG. Referenced clients value Capgemini’s ability to deliver tailored solutions suiting that there is scope for improvement in the depth of Capgemini’s technical expertise. Some
their requirements clients also raised concerns around project delays due to attrition
⚫ Strong gen AI focus:referenced clients also appreciated Capgemini’s extensive investments ⚫ Potential for elevating consulting and advisory skills:Capgemini’s consulting and
in gen AI research. It offers privacy preserving gen AI through federated learning, augmented advisory capabilities are limited, as highlighted by the referenced clients. They believe
masking, etc., and has also invested in strategic partnerships such as a gen AI CoEwith Capgemini finds it difficult to act as a strategic partner and proactively introduce new
Google and Azure Intelligent App Factory with Microsoft technologies and innovative off-the-shelf solutions in engagements
⚫ Proficient data-centric competencies:Capgemini has a strong data for AI foundation with ⚫ Limited exposure in small and mid-market segment:while Capgemini has significant
its synthetic data generation, document extraction, and data labelling capabilities, supported expertise in catering to large enterprises, its experience in serving midsize and small size
by a large data engineering talent base enterprises is relatively limited
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 9
Appendix
10
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Everest Group PEAK Matrix® is a proprietary framework for assessment of
market impact and vision and capability
Everest Group PEAK Matrix
High
Leaders
Aspirants
Low
Low High
Vision and capability
Measures ability to deliver services successfully
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 11
tcapmi
tekraM
tekram
eht
ni
detaerc
tcapmi
serusaeM
Major Contenders
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Services PEAK Matrix® evaluation dimensions
Measures impact created in the market –
captured through three subdimensions
Market adoption
Number of clients, revenue base,
YoY growth, anddeal value/volume
Portfolio mix
Diversity of client/revenue base across
geographies and type of engagements
Value delivered
Value delivered to the client based
on customer feedback and
transformational impact
Measures ability to deliver services successfully.
This is captured through four subdimensions
Vision and strategy Scope of services offered Innovation and investments Delivery footprint
Vision for the client and itself; future Depth and breadth of services portfolio Innovation and investment in the enabling Delivery footprint and global sourcing mix
roadmap and strategy across service subsegments/processes areas, e.g., technology IP, industry/domain
knowledge, innovative commercial
constructs, alliances, M&A, etc.
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 12
tcapmi
tekraM
Leaders
Major Contenders
Aspirants
Vision and capability
FAQs
Does the PEAK Matrix®assessment incorporate any subjective criteria?
Everest Group’s PEAK Matrix assessment takes an unbiased and fact-based approach that leverages provider / technology vendor RFIs and Everest Group’s proprietary databases containing providers’ deals
and operational capability information. In addition, we validate/fine-tune these results based on our market experience, buyer interaction, and provider/vendor briefings.
Is being a Major Contender or Aspirant on the PEAK Matrix, an unfavorable outcome?
No. The PEAK Matrix highlights and positions only the best-in-class providers / technology vendors in a particular space. There are a number of providers from the broader universe that are assessed and do
not make it to the PEAK Matrix at all. Therefore, being represented on the PEAK Matrix is itself a favorable recognition.
What other aspects of the PEAK Matrix assessment are relevant to buyers and providers other than the PEAK Matrix positioning?
A PEAK Matrix positioning is only one aspect of Everest Group’s overall assessment. In addition to assigning a Leader, Major Contender, or Aspirant label, Everest Group highlights the distinctive capabilities
and unique attributes of all the providers assessed on the PEAK Matrix. The detailed metric-level assessment and associated commentary are helpful for buyers in selecting providers/vendors for their specific
requirements. They also help providers/vendors demonstrate their strengths in specific areas.
What are the incentives for buyers and providers to participate/provide input to PEAK Matrix research?
⚫ Enterprise participants receive summary of key findings from the PEAK Matrix assessment
⚫ For providers
– The RFI process is a vital way to help us keep current on capabilities; it forms the basis for our database –without participation, it is difficult to effectively match capabilities to buyer inquiries
– In addition, it helps the provider/vendor organization gain brand visibility through being in included in our research reports
What is the process for a provider / technology vendor to leverage its PEAK Matrix positioning?
⚫ Providers/vendors can use their PEAK Matrix positioning or Star Performer rating in multiple ways including:
– Issue a press release declaring positioning; see our citation policies
– Purchase a customized PEAK Matrix profile for circulation with clients, prospects, etc. The package includes the profile as well as quotes from Everest Group analysts, which can be used in PR
– Use PEAK Matrix badges for branding across communications (e-mail signatures, marketing brochures, credential packs, client presentations, etc.)
⚫ The provider must obtain the requisite licensing and distribution rights for the above activities through an agreement with Everest Group; please contact your CD or contact us
Does the PEAK Matrix evaluation criteria change over a period of time?
PEAK Matrix assessments are designed to serve enterprises’ current and future needs. Given the dynamic nature of the global services market and rampant disruption, the assessment criteria
are realigned as and when needed to reflect the current market reality and to serve enterprises’ future expectations.
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 13
Artificial Intelligence (AI) Services PEAK Matrix®Assessment 2023
Everest Group is a leading research firm helping business leaders make confident decisions. We guide clients through
today’s market challenges and strengthen their strategies by applying contextualized problem-solving to their unique
situations. This drives maximized operational and financial performance and transformative experiences. Our deep
expertise and tenacious research focused on technology, business processes, and engineering through the lenses of
talent, sustainability, and sourcing delivers precise and action-oriented guidance. Find further details and in-depth content
at www.everestgrp.com.
NOTICE AND DISCLAIMERS
IMPORTANT INFORMATION. PLEASE REVIEW THIS NOTICE CAREFULLY AND IN ITS ENTIRETY.
Stay connected
THROUGH YOUR ACCESS, YOU AGREE TO EVEREST GROUP’S TERMS OF USE.
Dallas (Headquarters) Website Everest Group’s Terms of Use, available at www.everestgrp.com/terms-of-use/, is hereby incorporated by
[email protected] everestgrp.com reference as if fully reproduced herein. Parts of these terms are pasted below for convenience; please refer
+1-214-451-3000 to the link above for the full version of the Terms of Use.
Social Media Everest Group is not registered as an investment adviser or research analyst with the U.S. Securities and
Bangalore @EverestGroup Exchange Commission, the Financial Industry Regulatory Authority (FINRA), or any state or foreign securities
[email protected] regulatory authority. For the avoidance of doubt, Everest Group is not providing any advice concerning securities
@Everest Group
+91-80-61463500 as defined by the law or any regulatory entity or an analysis of equity securities as defined by the law or any
@Everest Group
regulatory entity.
Delhi @Everest Group All Everest Group Products and/or Services are for informational purposes only and are provided “as is” without
[email protected]
any warranty of any kind. You understand and expressly agree that you assume the entire risk as to your use
+91-124-496-1000 Blog and any reliance upon any Product or Service. Everest Group is not a legal, tax, financial, or investment advisor,
everestgrp.com/blog and nothing provided by Everest Group is legal, tax, financial, or investment advice. Nothing Everest Group
London provides is an offer to sell or a solicitation of an offer to purchase any securities or instruments from any entity.
[email protected] Nothing from Everest Group may be used or relied upon in evaluating the merits of any investment. Do not base
+44-207-129-1318 any investment decisions, in whole or part, on anything provided by Everest Group.
Products and/or Services represent research opinions or viewpoints, not representations or statements of fact.
Toronto
Accessing, using, or receiving a grant of access to an Everest Group Product and/or Service does not constitute
[email protected]
any recommendation by Everest Group that recipient (1) take any action or refrain from taking any action or
+1-214-451-3000
(2) enter into a particular transaction. Nothing from Everest Group will be relied upon or interpreted as a promise
or representation as to past, present, or future performance of a business or a market. The information contained
in any Everest Group Product and/or Service is as of the date prepared, and Everest Group has no duty or
obligation to update or revise the information or documentation. Everest Group may have obtained information
that appears in its Products and/or Services from the parties mentioned therein, public sources, or third-party
sources, including information related to financials, estimates, and/or forecasts. Everest Group has not audited
such information and assumes no responsibility for independently verifying such information as Everest Group
has relied on such information being complete and accurate in all respects. Note, companies mentioned in
Products and/or Services may be customers of Everest Group or have interacted with Everest Group in some
other way, including, without limitation, participating in Everest Group research activities.
Proprietary © 2024, Everest Global, Inc. | this document has been licensed to Capgemini 14 |
17 | capgemini | Clara-Shih-23Oct2024-Conversations-for-tomorrow_Edition_9_Report.pdf | Gener(AI)ting
the future
Quarterly review
N°9 — 2024
Gener(AI)ting the future
Executive Conversations
CLARA SHIH
Chief Executive Officer
Salesforce AI
64
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
A PLATFORM FOR
GENERATIVE AI
Clara Shih is the CEO of Salesforce AI. In her role,
Clara oversees artificial intelligence (AI) efforts
across the organization, including product, go-
to-market, growth, adoption, and ecosystem for
Salesforce’s AI customer relationship management
(CRM) platform. Clara also served on the Starbucks
board of directors for 12 years and serves as
Executive Chair of Hearsay Systems, a digital
software firm she founded in 2009 that is merging
with Yext (NYSE:YEXT).
65
Gener(AI)ting the future Capgemini Research Institute
Executive Conversations
SALESFORCE AND AI
What led to the development of Salesforce AI?
We have been working on AI for a long time. In 2014, we
established our Salesforce AI Research Group, and in 2016,
we introduced the first predictive AI for CRM, Einstein.
Salesforce Research has been developing large language
models (LLMs) for many years. The popularity of ChatGPT
and increased demand for enterprise AI led us to productize
our generative AI applications and platform.
Agentforce, our suite of customizable autonomous agents
and low-code tools – powered by our Customer 360
applications, Data Cloud, and Salesforce Platform – makes
Clara Shih
deploying and getting value from trusted agents easier than
Chief Executive Officer
ever. It’s the next generation of our Einstein AI solutions.
Salesforce AI
Every agent request runs through our Einstein Trust layer
to ensure data privacy, data security, ethical guardrails,
observability, and monitoring. We know customers don’t
want to be locked-in to a specific model, especially given the
rapid advancement and growth in model options, so we’ve
architected Agentforce to work with any model.
To help customers see value fast, we offer over 100 out-
of-the-box (OOTB) AI use cases and Agentforce agents,
including service agent, sales development representative
agent, commerce agent, merchandiser, buyer agent,
personal shopper, and campaign optimizer. These OOTB
agents make it easy to get started and are easy to customize.
Agentforce agents can be set up in minutes, scale easily,
and work 24/7 on any channel (Salesforce offers digital
messaging, messaging over in-app and web (MIAW), email,
and now voice natively).
Our customers and partners can easily customize and build
trusted agents on Agentforce using our low-code tools such
as agent builder, prompt builder, and model builder.
66
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
Can you expand on why you chose the platform approach?
Agents have to be customized and grounded in trusted data and role- and
industry-based context in order to be production-ready for the enterprise.
Salesforce has always offered a user-friendly platform for customers and
partners to easily build and customize, and from the beginning, we designed
Salesforce Platform to be used even by non-programmers.
Our customers want to customize their own AI apps, and we give them
options to do this either with no code, low code, or pro code. Rather than
every organization having to build their own data cloud, trust layer, and
API management, we make it easy by offering Salesforce Data Cloud,
the Einstein Trust Layer, and Mulesoft as part of the Salesforce Platform.
Customers and partners tell us all the time how much they appreciate how
the Einstein Trust Layer takes care of data masking, citations, audit trail,
toxicity filters, zero retention prompts, and
prompt defense to mitigate cybersecurity
risks.
From the beginning, Prompt builder and agent builder allow
customers to take our out of the box (OOTB)
we designed
use cases and customize them with their
Salesforce Platform own brand voice, company policies and
procedures, and reference organization-
to be used even by
specific custom data. For example, an
non-programmers." automotive company can directly reference
specific custom fields to guide their agents,
such as the make, model, and warranty SLA.
A retail customer would have a different set of custom fields and business
processes. Customers can reference any structured or unstructured data
from across their organization, whether it is in Salesforce or an external data
lake or data warehouse such as Snowflake, Databricks, or Big Query, by using
our Data Cloud.
Agentforce is about deploying autonomous agents to help drive human
productivity. It follows all of the data-sharing rules in each Salesforce
organization and is personalized to every user. For example, if two different
sales reps within the same company ask the same question of Agentforce
– such as “What are my top sales deals this quarter?” – they will each get a
customized answer based on each individual rep’s territory, customers, and
open opportunities.
67
Gener(AI)ting the future Capgemini Research Institute
Executive Conversations
GENERATIVE AI – A POTENTIAL ECONOMIC IMPACT OF TRILLIONS OF DOLLARS
What kind of impact do you
envisage generative AI having on
large organizations globally?
Gucci used Salesforce
AI to transform their
Generative AI offers a tremendous
opportunity with a potential economic service representatives
impact of trillions of dollars from both
into sellers."
productivity gains and cost savings.
Agentforce customers like Wiley and
OpenTable are finding tremendous
success, increasing the number of routine support issues they can use AI
to resolve autonomously 24/7 while increasing employee engagement and
customer satisfaction.
But change cannot happen overnight. Companies need support in the form
of trusted software systems and partners who can guide them through
the transformation. In the current scenario, even the most forward-
looking customers want AI automation to allow employees to work in
more productive and efficient ways. Then, the priority shifts to reshaping
departments. For example, Gucci used Salesforce AI to transform their
service representatives into sellers. In addition to resolving customer
support problems faster, our AI tools also helped teach them how to help
customers find additional products to buy and to complete e-commerce
transactions. The third phase is enterprise transformation. Just as with the
internet, generative AI and agents will enable new pricing models, business
models, and organization models.
"Generative AI offers a tremendous
opportunity with a potential economic
impact of trillions of dollars from both
productivity gains and cost savings."
68
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
Is there any specific industry
in which you see the most
enthusiasm?
We offer 15 different industry clouds
at Salesforce and there has been AI
demand and customer success in every
industry. For example, Santander Bank,
"90% TIME
in the financial services industry, uses
Agentforce to visualize its international
SAVINGS
trade trends and customer insights in
real time to guide customers towards the
BY USING
right products. L’Oréal, in the consumer
products industry, uses Agentforce to
GENERATIVE
boost direct-to-consumer revenue with
AI-powered product recommendations.
AI TO RESPOND
Iron Mountain, an information
management and storage company,
TO CUSTOMER
turned to Salesforce for customer
service, and their service representatives
EMAILS."
use Agentforce to create a connected
experience across email, chat, and
voice. Simplyhealth, a leading health
insurance provider in the UK deployed
our Agentforce for their customer
service team. They saw 90% time savings
by using generative AI to respond to
customer emails, and they were able
to resolve over one-third of their cases
using conversational AI.
69
Gener(AI)ting the future Capgemini Research Institute
Executive Conversations
Which generative AI use cases do you think are the most popular?
Each industry has specific use cases. For example, in communications, customers want
organizations to address billing inquiries promptly. In consumer goods, the focus is
on crafting AI-driven personalized product descriptions and marketing campaigns.
In healthcare, it is on optimizing patient appointment scheduling and reminders in a
compliant way.
This is why we were so thrilled recently to launch over 100 new out-of-the-box
Agentforce for Industries features, now available in our Salesforce AI Use Case Library.
Customers can easily customize and deploy this new ready-to-use AI to automate
time-consuming tasks such as matching patients to clinical trials, generating proactive
maintenance alerts for industrial machinery, and
delivering government program benefits. These
use cases are tailored by role and to each of our 15
Industries clouds for accelerated time to value. They
In customer service,
are easily customizable with prompt builder, agent
emphasis is on builder, and model builder.
delivering solutions
Many companies trying to "DIY" their AI tech stack
rapidly, addressing are finding they've wasted a lot of time and money
finetuning models and building data pipelines without
questions quickly and
much to show for their efforts. In contrast, customers
accurately, and closing from AAA Insurance and Air India to Wyndham Hotels
& Resorts are finding rapid value in a matter of weeks
the case promptly."
using these out-of-the-box Salesforce AI features.
Horizontally, across functions and sales, we place importance on streamlining account
research and meeting preparation, and gaining a thorough understanding of all the
open support cases and marketing engagement. In customer service, emphasis is on
delivering solutions rapidly, addressing questions quickly and accurately, and closing
the case promptly. It also enables better formulation of draft cases and incident
summaries to help service representatives to allocate their time to more strategically
significant tasks. In marketing, use cases include generating personalized emails and
campaigns, segments, landing pages, auto-populating contact forms, and rapidly
understanding insights from large-scale customer surveys.
In e-commerce, the focus is on the creation of digital storefronts, promotions, product
descriptions, and outlining e-commerce strategies. From a developer standpoint, it's
boosting productivity with AI-driven code generation and test generation.
70
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
CHALLENGES WITH GENERATIVE AI
"When we meet with
the Gucci customer
service representatives
who are using
Agentforce Service
Agents from Salesforce,
they're so fired up."
How do you envision the future balance between human-led and
AI-led customer services?
There's going to be a need for both. ATM
machines did not replace tellers. There are
more tellers today than ATMs, but now they
are personal bankers and focus on forging
personal relationships and upselling. AI will allow
ATM machines did not
workers to move away from repetitive tasks
replace tellers. There are to focus on doing what humans do best, which
is building relationships, unlocking creativity,
more tellers today than
making connections, and addressing higher-order
ATMs, but now they are problems. When we meet with the Gucci customer
service representatives who are using Agentforce
personal bankers."
Service Agents from Salesforce, they're so fired
up. They feel like we are empowering them to do
the best work of their careers.
71
Gener(AI)ting the future Capgemini Research Institute
Executive Conversations
"ORGANIZATIONS MUST TAKE
AN ETHICS-FIRST, TRUST-BASED
APPROACH TO AI PRODUCT
DEVELOPMENT."
What worries you the most about generative AI?
Any powerful new technology has a range of different applications. The
majority of them are good, but there can also be some nefarious use cases.
I think educating law enforcement professionals, government leaders, and
voters on the risks of misinformation and disinformation, including fake AI-
generated images, is of utmost importance.
Salesforce has joined the Business for America coalition supporting the
bipartisan Protect Elections from Deceptive AI Act. This legislation would
ban the use of AI to generate materially deceptive content that falsely
depicts candidates in political ads with the intention of influencing federal
elections.
How do you think organizations can create representative
and inclusive datasets?
Organizations must take an ethics-first, trust-based approach to AI product
development. Trust is the most crucial element engineered into any
Salesforce product. We have also enabled responsible AI practices across the
organization.
For example, to protect consumer and employee privacy, we disallow the
use of facial recognition AI within Salesforce products. Another aspect of
our AI acceptable use policy is that when one of our customer's customers
is using an AI agent, we require the agent to self-identify as an AI versus
masquerading as a human. This is to ensure trust and transparency remain
paramount.
72
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
We’ve open-sourced our
trusted AI principles around
five pillars:
1. Being responsible,
safeguarding human
rights, and protecting the
data with which we're
entrusted
2. Being accountable,
seeking feedback,
and acting on it for
continuous improvement
from all stakeholders
3. Developing a transparent
user experience to guide
users through any AI-
driven recommendations
4. AI is here to empower
people – not replace
them
5. AI should be inclusive
"We disallow the use of
facial recognition AI within
Salesforce products."
73
Gener(AI)ting the future Capgemini Research Institute
Executive Conversations
What are your views on the climate impact of LLMs?
Sustainability is among our core values. LLMs expend a tremendous amount
of energy on both training and running the models. At Salesforce, we
envision that, because of climate impact, as
well as for cost and performance reasons, the
future of AI will be a combination of LLMs
and small models.
The future of AI will be
Currently, small language models (SLMs),
a combination of LLMs
even ones that run locally on laptops, could
and small models." accomplish similar results to those that LLMs
produce. Salesforce AI Research Group is
developing these small and medium-sized
fine-tuned models, which are industry- and use-case-specific. Over time, we
will help our customers figure out the right model mix for them.
GENERATIVE AI REGULATORY LANDSCAPE
What are your thoughts on generative AI regulation?
The power of generative AI justifies strict regulation. The smartest approach
involves broadening the scope of existing laws to encompass elements
particular to AI usage. A great example is the Telephone Consumer
Protection Act (TCPA) in the US. That requires organizations to obtain
customer consent before robocalling or text messaging the consumer.
Recently, the TCPA was extended to include the use of AI-generated voices.
It makes a lot of sense to take existing laws and ensure that they are
updated to capture the new risks that AI has introduced.
74
Capgemini Research Institute Gener(AI)ting the future
Executive Conversations
Clara Shih
Chief Executive Officer
Salesforce AI
“The power of generative AI
justifies strict regulation.”
75
Gener(AI)ting the future Capgemini Research Institute
www.capgemini.com |
18 | capgemini | CRI_Gen-AI-in-Mgmt_Final_web-compressed-2.pdf | Gen AI at work: Shaping the future of organizations
Gen AI at work
Shaping the future of organizations
#GetTheFutureYouWant
fo
elbaT
stnetnoc
2
Gen AI at work: Shaping the future of organizations
Executive summary Gen AI has the potential Gen AI could
to transform the world re-engineer
of work for employees organizational
structures
Who should read this
report and why? How could Gen AI To harness Gen AI
impact management effectively, organizations
and leadership? must upskill across
the workforce
Capgemini Research Institute 2024
3
Gen AI at work: Shaping the future of organizations
How to build a Gen
AI-augmented workforce
Research
methodology
Conclusion Appendix
Capgemini Research Institute 2024
evitucexE
yrammus
4
Gen AI at work: Shaping the future of organizations
Generative AI (Gen AI) is transforming the way we work. In our • At manager level, roles are expected to become more
research, we asked leaders, managers, and employees to share strategic, focusing on AI-enhanced decision-making, and
how they project themselves into the future and how they performing tasks that require a high level of emotional
expect the world of work to change with Gen AI. intelligence. Leaders and managers also think that, within
three years, due to advancements in Gen AI, manager-
Employees predict that, at entry level, Gen AI will facilitate
level positions will evolve from generalists to specialists.
a third of tasks over the next 12 months. In the longer run,
Moreover, managers will be critical in assuaging fears and
collaboration between humans and AI will create greater value
skepticism in the workforce in relation to new technologies.
and new job roles, streamlining organizational structures and
As human-AI teams become the new reality, managers will
operating models and creating a new ontology of work:
play a key role in defining rules and responsibilities on how
Gen AI is expected to reshape roles and responsibilities human and AI will collaborate, ensuring accountability and
adapting workflows, practices, processes, and operating
• In the next three years, at entry level, roles will become
models to a human-centered approach.
more autonomous and progressively evolve from creation
to review, as Gen AI streamlines the generation process • At leadership level, roles will focus on redesigning the
allowing individuals to focus on critical analysis, quality organization of the future, redefining the nature of roles
assurance and innovation. Gen AI could also accelerate the across levels, and reimagining the ways of working. Nearly
career progress of entry-level workers, as suggested by three in four (70%) of leaders and managers also believe
leaders and managers in our research. This shift requires that leaders will focus on establishing robust frameworks
organizations to prepare junior employees to take up and guardrails for responsible and ethical development and
these responsibilities. deployment of Gen AI systems.
Capgemini Research Institute 2024
evitucexE
yrammus
5
Gen AI at work: Shaping the future of organizations
Gen AI could transform organizational structures managers transition from traditional coordination roles to
AI-enhanced specialized, skilled and strategic roles.
The impact of Gen AI on organizational structures and
operating models has been the subject of extensive debate. There is no clear consensus among experts on which
Among various possible organizational structures (classic organizational model will dominate. And future organizational
pyramid, inverse pyramid, diamond, hourglass, pillar, etc.), structures may differ significantly from current expectations.
most experts suggest two distinct organizational frameworks However, the leaders and managers in our survey sample lean
could emerge: towards the diamond model (see figure below) and expect the
proportion of managers in their teams to expand from 44% to
• The hourglass model with a small strategic leadership, a
53% in the next three years. It is also critical to note that this
lean middle-management layer, and a broad base of highly
middle layer will not be just composed of people managers or
skilled entry-level talent, augmented by Gen AI. In this
generalists but also technical or functional leads, specialists
model, technology enables entry-level employees to act
and subject matter experts (SMEs).
with more autonomy based on real-time data. This reduces
the need for intensive managerial supervision and quality This trend is consistent across organizations of all sizes,
control, flattening managerial hierarchies while widening industries and functions. Only 18% of leaders and managers
managerial span. believe that Gen AI will reduce middle management and
only 21% anticipate that, with Gen AI, they will have higher
• The diamond model with critical top leadership, a broader
shares of employees in entry-level and non-managerial roles.
middle layer, and a smaller entry-level layer that is partially
In this context, organization will need to reevaluate current
automated with Gen AI. This concentrated and skilled junior
roles, outline new roles, and establish clear career paths
layer focuses on high-value specialist tasks as opposed
across levels. Experimenting with flatter, more agile, and
to manual and repetitive work. Work is delivered with
collaborative organizational structures along with retaining
a combination of human-AI teams. In these structures,
strategic fluidity is key.
Capgemini Research Institute 2024
evitucexE
yrammus
6
Gen AI at work: Shaping the future of organizations
Expected team structures in the
Current team structures
next three years, impacted by Gen AI
Leaders and
upper 12% 15%
managers
Middle- and Middle managers: 19% Middle managers: 24%
frontline 44% 53%
managers Frontline managers: 25% Frontline managers: 29%
Entry-level
employees 44% 32%
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,500 leaders and managers.
Capgemini Research Institute 2024
evitucexE
yrammus
7
Gen AI at work: Shaping the future of organizations
Gen AI has the potential to unlock significant benefits • Complexity in integrating Gen AI tools into existing
workflows
Employees see Gen AI’s benefits in boosting their creativity,
complementing their skills, and reducing work-related stress. • Lack of skills to effectively drive outputs from Gen AI.
It can assist in complex managerial tasks, acting as a “thought
For instance, only 16% of employees say they receive ample
partner” for leaders and managers. A two-thirds majority
support from their organization to develop Gen AI skills, and
(65%) believes Gen AI can serve as a co-thinker in value-
only 46% of leaders/managers have been through formal Gen
adding activities such as strategic planning, evaluating risks
AI training.
and opportunities and augmenting decision-making.
To build a Gen AI-augmented workforce, organizations
However, key challenges remain
should:
Currently, only 15% of leaders and managers and 20% of
• Reevaluate strategic workforce planning, roles
employees use Gen AI tools daily. Respondents see the top
and career pathways for the new, agile and flatter
hurdles to Gen AI adoption as:
organizational structures
• Low confidence around the accuracy, logical soundness,
• Optimize practices, processes, workflows, and operating
security, and respect for IP/copyright and data privacy
models for human-AI collaboration
of Gen AI tools in connection with concerns regarding
inaccuracies, false logic, bias, IP/copyright issues, privacy,
and security
• Lack of clear guidelines from organizations regarding
usage
Capgemini Research Institute 2024
evitucexE
yrammus
8
Gen AI at work: Shaping the future of organizations
• Equip workforces with technology in a well-governed Gen AI thrives best as part of a broader AI ecosystem.
environment, helping them to evolve into an This hybrid AI approach – combining traditional AI, Gen
augmented force AI, automation, and other technologies – can unlock
unparalleled intelligence and efficiency tailored to specific
• Integrate existing business applications and workflows
business challenges.
with Gen AI to boost adoption
Please note, the study findings reflect the views of the
• Establish robust data foundations and governance
respondents and are aimed at providing directional guidance.
principles to harness the potential of Gen AI
Please contact one of the Capgemini experts listed at the end
• Empower people with the required technical (data of the report to discuss specific implications.
management and machine conversation) and soft (critical
thinking, emotional intelligence, risk management, and
ethical judgment) skills to use and trust Gen AI
• Create a culture of continuous learning and
experimentation, focusing on the most visible aspect of
organizational culture: adapting behaviors and habits
• Emphasize the role of Gen AI in augmenting and
empowering, and not replacing, human intelligence.
Capgemini Research Institute 2024
9
Gen AI at work: Shaping the future of organizations
Who should read this report and why?
Gen AI is poised to influence the future of work, AI-augmented workforce? In this report, we as 1,000 employees (entry-level individual contributors) at
transforming roles, organizational frameworks, explore these areas in depth. organizations with annual revenue above $1 billion in 15
and the skills required at all levels. As Gen AI countries: Australia, Canada, France, Germany, India, Italy,
Business leaders across functions including
augments and assists tasks, leader, manager, Japan, the Netherlands, Norway, Singapore, Spain, Sweden,
corporate strategy, finance and risk, human
and employee roles are shifting toward more Switzerland, the UK, and the US. The survey spans 11 key
resources, marketing and sales, IT, sustainability,
strategic, creative, and problem-solving industries and sectors: aerospace and defense, automotive,
innovation/R&D, product design/development,
responsibilities. This shift demands a workforce banking and capital markets, consumer products, energy and
sourcing, manufacturing/operations, and supply
as agile as the technology driving it. utilities, insurance, life sciences, manufacturing, public sector/
chain will find it useful.
government, retail, and telecom, media, and high tech. The
How can organizations and business leaders
The report draws on a comprehensive analysis of report also includes qualitative findings from 15 industry
thrive in the dynamic environment of human-AI
a survey of 1,500 leaders and managers (CxOs, leaders.
collaboration? And how should they build a Gen
directors, managers, team leaders, etc.), as well
Capgemini Research Institute 2024
1100
GGeenn AAII aatt wwoorrkk:: SShhaappiinngg tthhee ffuuttuurree ooff oorrggaanniizzaattiioonnss
01
Gen AI has the potential
to transform the world
of work for employees
CCaappggeemmiinnii RReesseeaarrcchh IInnssttiittuuttee 22002244
1111
Gen AI at work: Shaping the future of organizations
Gen AI is expected to into their service centers, enhancing problem resolution,
and creating cross-selling opportunities. Rather than
reshape roles and displacing roles, AI has the potential to reshape them.”2
A few key trends are emerging:
responsibilities
• Entry-level roles are expected to evolve from creation
to review
Gen AI is transforming the way we work: 56% of leaders
More than 6 in 10 leaders and managers expect entry-
and managers and 54% of employees in our research
level roles to evolve in the next three years, from creation
agree. The technology is expected to unlock new levels
(of content/code, etc.) to critically reviewing and refining
of productivity, adaptability, and innovation, creating
outputs generated by Gen AI. Moreover, 71% of employees
synergies between human and machine intelligence,
agree with this. Steven Matt, a marketing executive at a
while redefining and reshaping traditional roles and
global professional services firm, adds: “You don’t need
structures. Polish spirits company, Dictador, has even
typical copywriters, but rather “copy reviewers” to check
appointed “Mika,” the first Gen AI CEO.1
whether AI-generated content matches the voice and tone
% • Eric Loeb, Executive Vice President, Government of the company, is free of hallucinations, and if it follows
56
Affairs at Salesforce, says: “As with any industrial brand guidelines. This concept extends to other creative
revolution, Gen AI will change the nature of jobs. fields, such as video editing. Instead of spending hours on
Imagine the transformative impact of AI on customer tasks like synchronizing clips and perfecting transitions,
service, for example. Gen AI will handle calls and video editors can now rely on Gen AI to automate these
streamline processes with unprecedented efficiency. processes. I believe that the future of many roles will be
of leaders and managers and 54% Customer service agents can use Gen AI prompts to centered around reviewing and verifying AI-generated
of employees agree that Gen AI is identify opportunities during interactions, upskilling work, rather than creating [content] from scratch.”
transforming the way we work
them to hybrid service-sales roles. Some of our
global customers have already integrated Gen AI
CCaappggeemmiinnii RReesseeaarrcchh IInnssttiittuuttee 22002244
1122
GGGeeennn AAAIII aaattt wwwooorrrkkk::: SSShhhaaapppiiinnnggg ttthhheee fffuuutttuuurrreee ooofff ooorrrgggaaannniiizzzaaatttiiiooonnnsss
Figure 1.
With the advent of Gen AI, most respondents expect entry-level roles to transition from creation to review and refinement.
Percentage of respondents who agree with the statement: "In the next three years,
entry-level roles will primarily evolve from creation (of content, code, etc.) to review
and refinement of outputs generated by Gen AI”.
71%
64% 64%
61%
Leaders Middle Frontline Employees
managers managers
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,500 leaders and managers, N=1,000
employees.
Capgemini Research Institute 2024
13
Gen AI at work: Shaping the future of organizations
• Entry-level roles will progressively become more Figure 2.
autonomous
Entry-level roles will become more autonomous due to Gen AI in the next three years.
As Gen AI becomes more integrated into the workplace,
entry-level roles are expected to gain greater autonomy –
52% of leaders and managers predict this (see Figure 2).
Percentage of leaders and managers who agree with the statement: "In the next three years,
entry-level roles will become more autonomous due to Gen AI," categorized by sector.
57% 56% 56%
54% 54%
52% 51% 51% 51% 50%
46%
44%
Aerospace Public sector Energy Automotive Consumer Telecom, media
and defense and utilities products and high tech
Banking and
Manufacturing Life sciences Overall Insurance Retail
capital markets
Source: : Capgemini Research Institute, Gen AI for management research, July 2024, N=1,500 leaders and managers.
Capgemini Research Institute 2024
14
Gen AI at work: Shaping the future of organizations
• Gen AI could accelerate career progress of entry-level skills and readiness of junior employees as part of a clear
employees roadmap for employees’ journeys to people leadership or
A recent LinkedIn survey revealed that 52% of millennials functional/technical leadership. This requires proactive
and 48% of Gen Z globally believe that AI will help advance steps around talent acquisition, development, skilling, and
their careers by providing faster access to work-related review and reward mechanisms.
knowledge and insights.3
As Figure 3 shows, most leaders and managers from
In our research, over half (51%) of leaders and managers supply chain, risk management, and human resources
anticipate that numerous entry-level roles will evolve functions agree. For example, in supply chain roles, Gen
into frontline managerial roles within the next three AI virtual assistants can handle routine tasks such as
years, as the integration of Gen AI into existing workflows inventory management, order processing, and tracking
accelerates. It should be noted that this shift depends on shipments. This shift will enable junior analysts to progress
several factors: clarity on skills requirements at higher to supply chain coordinator roles, overseeing AI operations
levels; the ability of junior employees to develop these and tackling strategic responsibilities such as refining
skills (often tied to experience, which cannot be fast- logistics networks, managing supplier relationships, and
tracked); and the availability of opportunities available coordinating large-scale inventory projects.
for the shift. Organizations must prioritize building the
Capgemini Research Institute 2024
15
Gen AI at work: Shaping the future of organizations
Figure 3.
Leaders and managers anticipate entry-level employees to assume responsibilities previously held by their supervisors.
Percentage of leaders and managers who agree with the statement:
“With Gen AI, in the next three years, many entry-level roles will transition to frontline manager roles," categorized by function.
67%
63%
59%
57%
54% 53% 52% 51% 51% 51% 47%
42%
31%
Supply chain Product design/ Innovation/R&D Manufacturing/ Marketing and Finance and Sourcing
development operations communications risk management
Human resources IT/engineering Sustainability Sales Overall Corporate strategy
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,500 leaders and managers.
Capgemini Research Institute 2024
16
Gen AI at work: Shaping the future of organizations
Gen AI is likely to augment
roles
At entry level, employees expect Gen AI to assist with 32% of
tasks over the next 12 months (see Figure 4). Archisman
Munshi, co-founder of a senior citizen care company that is
tackling financial fraud issues using AI, adds: “It is imperative
to educate people to view AI as an “assistant” that will make
it easier and faster to complete their day-to-day tasks. Also,
people won’t be replaced; it is the tasks that will be
replaced.” 4
%
32
of employee work is expected to be
augmented or assisted by Gen AI in
the next 12 months
Capgemini Research Institute 2024
17
Gen AI at work: Shaping the future of organizations
Figure 4.
Gen AI has the potential to assist with nearly one-third of tasks across functions in the next 12 months.
Percentage share of employee work that can be augmented or assisted by Gen AI in the next 12 months, categorized by function.
36% 36%
34%
32% 32% 32% 32% 32% 31% 31% 30%
29%
24%
Sustainability Innovation/R&D Marketing and Overall Sourcing Supply chain Human resources
communications
Product design/ IT/engineering Finance and Manufacturing/ Corporate strategy Sales
development risk management operations
Note: Low base for employees from human resources, sustainability, and sourcing functions.
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,000 employees.
Capgemini Research Institute 2024
18
Gen AI at work: Shaping the future of organizations
Gen AI has the potential
Figure 5.
Gen AI enhances employee creativity, reduces work-related stress, and complements human skills by filling knowledge gaps.
to unlock significant
benefits Percentage of employees who agree with the statements below
Gen AI yields significant productivity improvements at entry
level. Employees believe that, over the next 12 months, Gen
AI tools could lead to an average time saving of Gen AI has helped me reduce
72%
18% implying there could be significant productivity my work-related stress.
improvements. While the anticipated productivity gains
from Gen AI tools are promising, careful consideration of
their implementation costs is crucial to ensure a net positive
impact on overall efficiency. Gen AI effectively complements my skills 64%
and fills in my knowledge gaps.
A majority (64%) of the workforce today is already using Gen
AI tools for their work – with 78% using them for text/content
creation (summarization, automation or translation of text/
content). However, only 20% of employees use Gen AI tools Gen AI has helped me be more
52%
daily. Users see benefits including boosting their creativity, creative in my work.
reducing their work-related stress, and complementing their
skills (see Figure 5).
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=641 employees using Gen AI for their work.
Capgemini Research Institute 2024
1199
GGeenn AAII aatt wwoorrkk:: SShhaappiinngg tthhee ffuuttuurree ooff oorrggaanniizzaattiioonnss
“You don’t need typical copywriters, but rather “copy reviewers” to check whether AI-generated content matches the
voice and tone of the company, is free of hallucinations, and if it follows brand guidelines. This concept extends to
other creative fields, such as video editing. Instead of spending hours on tasks like synchronizing clips and perfecting
transitions, video editors can now rely on Gen AI to automate these processes. I believe that the future of many roles
will be centered around reviewing and verifying AI-generated work, rather than creating [content] from scratch.”
Steven Matt
A marketing executive at a
global professional services firm
Capgemini Research Institute 2024
2200
GGeenn AAII aatt wwoorrkk:: SShhaappiinngg tthhee ffuuttuurree ooff oorrggaanniizzaattiioonnss
02
How could Gen AI impact
management and
leadership?
CCaappggeemmiinnii RReesseeaarrcchh IInnssttiittuuttee 22002244
21
Gen AI at work: Shaping the future of organizations
Gen AI is amplifying the
Figure 6.
Gen AI is transitioning leadership and managerial roles towards strategy, innovation and AI augmented decision-making.
strategic scope of
managerial and leadership
Percentage of respondents who agree with the statement:
roles "Using Gen AI, my role as a manager has become more strategic, focusing on
decision-making and innovation."
Leaders and managers currently spend more than one-third
(38 percent) of their time on administrative and project 57%
management tasks. With Gen AI, they anticipate a greater 52%
focus on strategic decision-making and people-centric 46% 46%
42%
leadership: “With Gen AI helping in operational tasks,
leaders and managers will have more time for strategy,
quality, and team management,” says Stephane Dupont,
Head of Operations and Business Improvement, Sustainability
and Communications at Airbus.
In fact, within organizations that are advanced in Gen AI
implementation, 57% of leaders and managers report that
Overall Organizations Organizations Organizations Organizations
Gen AI has already made their roles more strategic (see that have enabled that have enabled that have begun that have started
Figure 6). Isabel Baque, Senior Director at Stellantis, agrees: Gen AI capabilities Gen AI capabilities working on exploring
“Gen AI is creating new opportunities for middle managers in most in some Gen AI pilots Gen AI's potential
function/locations functions/locations
by changing them from task leaders to strategic leaders.
So, instead of focusing on the day-to-day operational
tasks, middle management are increasingly shifting their
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,456 leaders and managers who have
focus to strategic planning, problem-solving, and to social
experimented with Gen AI in leadership/managerial tasks.
interactions and relationship building.”
Capgemini Research Institute 2024
22
Gen AI at work: Shaping the future of organizations
“Gen AI is creating new opportunities In the next three years:
for middle managers by changing
• Three-quarters (78%) of leaders and managers predict
them from task leaders to strategic that Gen AI will augment their problem-solving and
leaders. So, instead of focusing on decision-making.
the day-to-day operational tasks,
• Over half (52%) of leaders and managers expect that their
middle management are increasingly roles will shift toward tasks that require a high level of
shifting their focus to strategic emotional intelligence.
planning, problem-solving, and to
social interactions and relationship Most managers could
building.”
become specialists and be
more critical than ever
Most leaders and managers (51%) believe that, owing to
advancements in Gen AI, within three years, manager-level
positions will evolve towards specialization or move into top-
tier strategic roles. For instance, HR roles may transition from
HR generalists to talent analytics specialists or employee
experience designers, while IT might see a move from
Isabel Baque
project management to niche areas such as AI strategy or
Senior Director at Stellantis
data science. As Figure 7 highlights, most respondents from
supply chain, HR, manufacturing, and IT believe that Gen AI
will lead managers to move toward specialization.
Capgemini Research Institute 2024
23
Gen AI at work: Shaping the future of organizations
Managers will play a
Figure 7.
Managerial roles will move toward niche expertise areas or strategic roles.
critical role as catalysts
for Gen AI-driven change
Percentage of leaders and managers who agree with the statement:
"With Gen AI, in the next three years, many managerial roles will transition
to either specialist/subject matter expert or top strategic leadership." Managers are crucial to addressing workforce fears and
skepticism associated with new technologies – 53% of leaders
in our research agree. Our employee research shows that
64% 63% nearly 4 in 10 (39%) employees say they are apprehensive
58% 57% 57% about the introduction of Gen AI. One in three (35%) also
54% 54% 53% 51% 50% 48% expresses concern about job security and the potential
45%
43% obsolescence of their role.
A majority (54%) of leaders believe that, in this context,
the significance of managerial roles will intensify as they
will play a critical role as catalysts for Gen AI change. Isabel
Baque adds: “Middle managers need to take the role of
facilitators and coaches who lead and manage the change,
by advocating for the use of Gen AI and leading by example.”
Supply chain IT/engineering Sustainability Marketing and Overall Sales Manufacturing
communications /operations
Moreover, as Gen AI integration between teams becomes
Human Product design/ Sourcing Innovation/R&D Finance and Corporate the new reality, managers will be critical to re-bundling tasks
resources development risk management strategy for Gen AI-augmented workforces. Half (50%) of leaders in
our research believe that managers must rethink the balance
of task allocation to avoid over- and under-delegation and
Source: Capgemini Research Institute, Gen AI for management research, July 2024, N=1,500 leaders and managers.
manage other risks. The manager needs to:
Capgemini Research Institute 2024
24
Gen AI at work: Shaping the future of organizations
• Ensure each team member is equipped with the skills Gen AI adoption will require a strong risk management • When used as a co-pilot, Gen AI becomes an efficient
and knowledge to fulfill their specific role approach to mitigate potential risks around IP/copyright, collaborator with the leader or manager, handling a wide
security, bias, accountability etc. Leadership’s role becomes range of administrative, communication, and operational
• Define rules and responsibilities on how humans and
critical in establishing robust frameworks and guardrails for tasks. Co-pilot interaction is best suited to tasks where the
Gen AI will collaborate
ensuring responsible and ethical Gen AI systems are built leader or manager’s main contribution is initial guidance,
and used. In fact, 7 in 10 leaders and managers agree that curation, final review, and approval of the output.
• Ensure accountability when Gen AI systems make
in the next three years, the role of leaders will shift towards
mistakes • When used as a co-thinker, Gen AI becomes the leader
managing risks and creating responsible Gen AI.
or manager’s thought partner, engaging in discussion,
• Adapt workflows, practices, processes, and operating
Valentin Marguet, Powertrain Project Lead in the automotive suggesting new perspectives, and challenging assumptions
models with a human-centric approach.
industry, says: “As AI becomes integral to business operations, or ideas. Co-thinker interaction is best suited to tasks that
organizations should establish dedicated AI Centers of require methodological guidance and structured reflection
As stated by a large bank’s global head of sales training: Excellence (COEs) led by C-suite executives. These COEs (such as weighing options, assessing risks, or considering
“The manager needs to make sure that, firstly, [employees] should be staffed with a diverse team of AI specialists, different points of view).
are given better or different work that activates what
domain experts, and program managers. The key is to deploy
they're good at. And secondly, make them feel valued for Harvard Business Review’s forthcoming book, authored by
a lean, cross-functional team that can create and enforce
that work.” experts from Capgemini6 explores both modes across the
guidelines for AI tool usage, data governance, and risk
most common managerial tasks. Our research highlights that
management frameworks.”
a two-thirds majority (65%) of leaders and managers think
Leadership roles will
Gen AI can serve as a co-thinker in value-adding activities
Gen AI has the potential such as strategic planning (see Figure 8). As we move toward
encompass the
the co-thinker end of the spectrum, the necessity for human
to assist with complex engagement and interaction with Gen AI increases.
responsible and ethical
managerial tasks
deployment of Gen AI
systems There are two primary modes of interacting with Gen AI:
“co-pilot” and “co-thinker.”5
Capgemini Research Institute 2024
222555 2255
GGeenn AAII aatt wwoorrkk:: SShhaappiinngg tthhee ffuuttuurree ooff oorrggaanniizzaattiioonnss
“Gen AI can provide targeted training and coaching based on your profile and skill gaps. Also, today, with continuously
evolving learning and training requirements, Gen AI can revolutionize learning by enabling tailor-made, short, and
targeted trainings.”
Anna Kopp
Senior director at Microsoft
Capgemini Research Institute 2024
26
Gen AI at work: Shaping the future of organizations
Figure 8.
More than 6 in 10 leaders and managers view Gen AI as a strategic thought partner to consider risks, evaluate opportunities, and hone decision-making.
Co-pilot Co-thinker
Project Team-and people Business-and
Administrative tasks management-related tasks management-related tasks strategy-related tasks
▪ Time approvals ▪ Project planning/scheduling ▪ Recruitment ▪ Innovation
Examples of ▪ Claims approvals ▪ Task delegation ▪ Onboarding ▪ Planning
tasks ▪ Meetings management ▪ Workflow optimization ▪ Goal setting ▪ Forecasting
▪ Meetings summarization ▪ Knowledge management ▪ Performance evaluation ▪ Market intelligence
▪ Drafting emails ▪ Compliance monitoring ▪ Training and development ▪ Evaluating risks and opportunities
▪ Mentoring ▪ Decision-making
▪ Retention
Percentage of
leaders and
managers who
see high 48% 44% 57% 65%
potential in Gen
AI to add value in
this area
Continued to the next page
Capgemini Research Institute 2024
27
Gen AI at work: Shaping the future of organizations
Project Team-and people Business-and
Administrative tasks management-related tasks management-related tasks strategy-related tasks
Meeting summarization Project planning Performance review Insight and recommendation generation
Morgan Stanley is piloting an AI program Procore, a US-based construction Managers at Valera, an established credit union PepsiCo harnesses Gen AI to analyze customer
called Debrief, which automatically management software organization, has service organization, are using feedback, which it uses to refine the shape
summarizes client meetings and generates recently launched Procore Copilot AI, which Gen AI to generate constructive, unbiased design and flavor of its Cheetos branded snack,
follow-up emails, enhancing advisor integrates with Microsoft Teams, allowing feedback for employees, resulting in resulting in market penetration deepening by
Case examples productivity and customer engagement.7 project managers to monitor and query 67% higher-quality feedback and halving 15%.11
project management and receive review-writing time.9
comprehensive summaries and relevant
links to project documentation.8 Personalized L&D Decision-making
Team leaders and managers at Siemens Energy Portfolio managers at Morgan Stanley use
use Gen AI to create targeted learning paths Gen AI as a “virtual coach” to enhance
for personalized, streamlined skill building.10 decision-making processes and improve
investment outcomes.12
A senior risk model manager at a leadi |
19 | capgemini | Final-Web-Version-Report-Harnessing-the-Value-of-Gen-AI.1.pdf | HHAARRNNEESSSSIINNGG
TTHHEE VVAALLUUEE OOFF
GGEENNEERRAATTIIVVEE AAII
Top use cases across industries
#GetTheFutureYouWant
evitucexE
yrammuS
2
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Generative artificial intelligence (AI) is rapidly becoming restructuring of business models. Globally, about one-
an integral part of our private and professional lives. fifth (21 percent) of executives surveyed say generative
While the technology has been in existence for a number AI will significantly disrupt their industries. Executives in
of years, it has gained widespread consumer interest high tech and industrial manufacturing – two industries
only recently and has emerged as a critical strategic that have long been shaped by AI technologies and have
consideration. Our latest industry-focused research been at the forefront of generative AI – are most likely to
reveals that generative AI is on the boardroom agenda agree with this statement.
at 96 percent of organizations surveyed globally. While
The potential of generative AI to drive innovation and
generative AI is in its infancy in terms of scaled adoption
improve efficiency and productivity extends to nearly all
and implementation, nearly 60 percent of executives
functions and has applications across all industries. Use
globally say their leadership is a strong advocate for
cases are wide-ranging, from creating unique content
generative AI and only 39 percent are taking a “wait-and-
and automating and accelerating tasks, to creating
watch” approach to adoption.
personalized experiences and generating synthetic data.
Many organizations already see generative AI as a Our research reveals that generative AI has the greatest
powerful tool that can accelerate growth, enhance potential within IT, sales and customer service, and
capabilities, and unlock new opportunities without drastic marketing functions. The high tech sector leads the way,
Capgemini Research Institute 2023
with the greatest share of ongoing generative AI pilots. adverse impact of generative AI on the environment.
Executives in our survey also project efficiencies from Nevertheless, the net impact of generative AI on an
generative AI in the next three years in the range of 7–9 organization’s Scope 1, 2, and/or 3 emissions is currently
percent. difficult to forecast.
As with any new technology, generative AI is not without We conclude this report with a look at how organizations
risk. However, with proper planning and guardrails in can start and/or accelerate their generative AI journeys.
place, there is potential to transform business operations, First, they must create a robust generative AI strategic
product and service development, and customer and operational architecture. Organizations must also
interaction. Nearly three-quarters of executives in our establish internal and external guidelines around the
survey (74 percent) agree that the benefits of generative use of generative AI, adopt a human-centric approach
AI outweigh the risks. Given the carbon-intensive nature to scaling the technology, and build user and consumer
of training new generative AI models, it will also be trust in the AI system. Given the high carbon emissions
important to weigh environmental considerations. The associated with generative AI trainings and queries,
good news is that executives in our survey are aware sustainable development and use of the technology
of this dynamic and understand how to mitigate the should also be a high priority.
evitucexE
yrammuS
3
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Capgemini Research Institute 2023
noitcudortnI
4
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Generative artificial intelligence (generative AI) is rapidly innovating of organizations; highlighting the function-
transforming the way we interact with technology. and industry-specific use cases we believe to have the
Machines are beginning to mimic creative human thought greatest potential; and comparing adoption rates across
processes, synthesizing tailored content with significant industries.
implications for organizations and consumers.
To gauge executives’ perceptions of generative AI and
This report is the second in a series of reports we adoption of use cases, we conducted a global survey of
have created around this topic. Our first report, Why 1,000 organizations across Australia, Canada, France,
consumers love generative AI, explored consumer Germany, Italy, Japan, the Netherlands, Norway,
perceptions of generative AI; consumer use of generative Singapore, Spain, Sweden, the UK, and the US. We
AI; and how the technology is shaping the future of questioned executives from multiple industries, including
customer experience. automotive, consumer products, retail, financial services,
telecom, energy and utilities, aerospace and defense,
In this report, we delve into the transformative potential
high tech, industrial manufacturing, and pharma and
of generative AI for organizations across industries,
healthcare. For more details on the survey sample, please
asking how the technology could kick-start the
refer to the research methodology.
Capgemini Research Institute 2023
noitcudortnI
5
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The report explores five broad themes:
1 2 3 4 5
Organizations view Organizations see Generative AI High tech leads How organizations
generative AI not as more gain than pain packs the most in implementing can kick-start their
a disruptor but as an in generative AI punch for IT, sales, generative AI generative AI
accelerator and marketing journeys
Capgemini Research Institute 2023
6
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Who should read this
report and why?
This report offers a comprehensive introduction to the transformative
impact that Generative AI holds for large businesses in industries such
as automotive, consumer products, retail, financial services, telecom,
energy and utilities, aerospace and defense, high tech, industrial
manufacturing, and pharma and healthcare. The report will help
business executives identify use cases that will illustrate the pragmatic
applications of Generative AI in IT, sales, and marketing, for example.
The report leverages a comprehensive analysis of 1,000 industry leaders
(ranked Director and above) across 13 countries, each at varying stages
of Generative AI implementation. The report also offers actionable
recommendations for business leaders to kick-start their organizations’
generative AI journeys. This report is the second in our series of reports
on Generative AI. Read the first report focusing on consumer reactions to
Generative AI at
https://www.capgemini.com/insights/research-library/
creative-and-generative-ai/
Capgemini Research Institute 2023
7
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.1
Generative AI applications across multiple formats
Selected generative AI applications Indicative examples
Defining Text Summarizing and translating into multiple OpenAI’s GPT-4, Jasper1
languages
generative AI
Images and video Analyzing existing images/video to generate new Adobe Firefly,2 Stable
generation content (e.g., video games, VR, animation) Diffusion, Midjourney
Generative AI has the capability to learn and reapply the
Music generation and remixing, speech synthesis, Sonix.ai (a cloud-based audio
properties and patterns of data for a wide range of
Audio sound effects, voice conversion, audio and video-transcription
applications, from creating text, images, and videos in enhancement solution)3
different styles to generating tailored content. It enables
machines to perform creative tasks previously thought
exclusive to humans. The following table summarizes the Chatbots to provide automated customer service Google Bard,4 OpenAI’s
Chatbots
top generative AI applications reported in our research and and advice ChatGPT
gives some indicative examples.
Enhanced search functions using natural
Search Perplexity AI5
language processing and machine learning
Source: 1. TechTarget, “What is generative AI? Everything you need to know,” March 5, 2023.
2. Adobe, "Adobe unveils Firefly, a family of new creative generative AI," March 21, 2023.
3. Sonix.ai, "Sonix releases the world’s first automated transcription and generative AI summarization tool," December 14, 2022.
4. Cointelegraph, "What is Google’s Bard, and how does it work?" May 10, 2023.
5. Kevin-Indig, "Early attempts at integrating AI in Search," January 10, 2023.
Capgemini Research Institute 2023
8
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
01
ORGANIZATIONS VIEW GENERATIVE
AI NOT AS A DISRUPTOR, BUT AS AN
ACCELERATOR
Capgemini Research Institute 2023
9
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.2
Generative AI is a topic for boardroom discussion at nearly all organizations
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
Generative AI is a top STATEMENT BY SECTOR
agenda item in boardrooms
96% 100% 98% 98% 97% 96% 95% 94% 93% 93% 93%
Nearly all executives (96 percent) in our survey cite
generative AI as a hot topic of discussion in their
respective boardrooms (see Figure 2), making it probably
the fastest new technology to garner such high-level
interest. Pat Geraghty, CEO of GuideWell, a US-based
mutual insurance organization, comments: “Every single
board meeting we’ve had this year has had a standing
agenda item of AI and ChatGPT. We want to make sure we’ve
got our board with us as we’re thinking about where we’re
going.” 1 Average Financial Industrial Energy Aerospace Consumer
services manufacturing and utilities and defense products
High tech Pharma Telecom Automotive Retail
and healthcare
Generative AI is a topic of discussion in our boardroom
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
10
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.3
The leaders of most organizations are strong advocates of generative AI
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
STATEMENT BY SECTOR
2% 1% 1% 1% 1% 4% 2% 5% 3% Top leaders are strong
16%
32% advocates for generative AI
39% 39% 39% 41% 37% 39%
57% 45% 50%
Among the 96% of organizations that discuss generative
AI in their boardrooms, over half (59 percent) of
84%
executives say their leadership are strong advocates for
59% 67% 60% 60% 59% 59% 58% generative AI only six months after the technology hit
51%
43% 57% the mainstream. This rises to 84 percent in the high-tech
sector. Thirty-nine percent of executives say their leaders
are taking a “wait-and-watch” approach to the technology
Average Aerospace Telecom Retail Industrial Consumer
and defense manufacturing products and only 2 percent of executives globally say their leaders
High tech Financial Energy Pharma Automotive are not convinced or are divided by the potential of
services and utilities and healthcare generative AI (see Figure 3).
Our leadership is a strong advocate of generative AI
Our leadership is taking a "wait-and-watch" approach to generative AI
Our leadership is not convinced of / is divided on the potential of generative AI
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 766 organizations that cite generative AI
as a topic of discussion in their respective boardrooms.
Capgemini Research Institute 2023
11
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
96%
organizations say generative AI
is a topic of discussion in their
boardrooms
Capgemini Research Institute 2023
12
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.4
Majority of consumers use generative AI tools for generating content
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
Most organizations do not
STATEMENT BY SECTOR
view generative AI as a
52%
48% disruptor
While twenty-one percent of executives anticipate a
significant disruption in their respective industries from
21% 21% 21% 20% 19% 18% 18% generative AI, 67 percent of executives disagree. That
12% is, a majority of the executives do not see generative
AI significantly disrupting their business models.
3%
However, executives within the high-tech and industrial
Average Industrial Pharma Consumer Aerospace Retail manufacturing sectors expect significant disruption at
manufacturing and healthcare products and defense 52 percent and 48 percent, respectively (see Figure 4).
While this may be reflective of these executives’ superior
High tech Energy Financial Automotive Telecom
and utilities services understanding of the technology’s potential, the figures
underline the widespread expectation that generative AI
will boost business overall.
Generative AI can significantly disrupt our industry
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
13
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.5
Relevance of generative AI platforms for organizations across different domains
PERCENTAGE OF ORGANIZATIONS THAT FIND GENERATIVE AI
Organizations are finding
PLATFORMS RELEVANT TO THEIR BUSINESS
generative AI platforms
Chatbots (automating customer service and improving
83%
knowledge management: e.g., ChatGPT)
increasingly relevant
Data (designing, collecting, or summarizing data:
75%
e.g., Jasper’s Text Summarizer)
Chatbots emerge as the most relevant generative AI Text (summarizing, automating, or translating content: e.g., ChatGPT) 71%
application, with 83 percent of organizations citing it.
Organizations can use generative-AI-driven chatbots Search (AI-powered insights: e.g., Bing) 70%
to improve their customer service and also to enable
Generating synthetic data (Capgemini's Artificial Data Amplifier) 61%
improved internal knowledge management. Seventy-five
percent of executives say that data applications can be ML platforms (applications of machine learning: e.g., Slai) 54%
used effectively in their organizations, and 71 percent
Code (testing and coding assistant e.g.,GitHub Copilot, converting code
believe this to be true of text-generating platforms such 50%
from one language to another e.g., Codex, Capgemini's A2B Translator)
as ChatGPT (see Figure 5).
Images (generating images: e.g., DALL-E) 48%
Audio (summarizing, generating or converting text in audio: e.g., Sonix) 34%
Video (generating or editing videos: e.g., Pictory, Synthesys) 26%
Gaming (generative AI gaming studios or applications: e.g., Ludo AI) 4%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
14
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
US financial services organization Morgan Stanley's
vast library of investment strategies, market research,
and analyst insights can be time-consuming and
cumbersome for wealth-management advisors to
sift through. To address this, Morgan Stanley is using
GPT-4 to power an internal chatbot that provides
instant access to any area of the archive. Jeff McMillan,
Head of Analytics, Data, and Innovation, adds: “You
essentially have [access to] the knowledge of the most
knowledgeable person in wealth management – instantly.
Think of it as having our chief investment strategist, chief
global economist, global equities strategist, and every other
analyst around the globe on call for every advisor, every
day. We believe that is a transformative capability for our
company.”2
Capgemini Research Institute 2023
15
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
“You essentially have [access to] the knowledge of the
most knowledgeable person in wealth management
– instantly. Think of it as having our chief investment
strategist, chief global economist, global equities
strategist, and every other analyst around the globe
on call for every advisor, every day. We believe that is a
transformative capability for our company.”
Jeff McMillan
Head of Analytics,
Data, and Innovation,
Morgan Stanley.
Capgemini Research Institute 2023
16
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The impact of Fig.6
Most executives agree that generative AI will augment knowledge work
generative AI on
the workforce
PERCENTAGE OF ORGANIZATIONS THAT AGREE WITH THE STATEMENTS
Generative AI has the potential to Generative AI will augment the roles of knowledge
70%
workers and reduce their workloads
transform work
Our consumer research on generative AI reveals that
most consumers (70 percent) believe it will make As generative AI algorithms begin to provide concepts
them more efficient at work and will free them from and initial designs, employees may shift from 69%
routine tasks to explore more strategic aspects of their traditional ideation and creation to review and refinement
jobs.3 Most executives concur with these consumer
sentiments, with 70 percent agreeing the technology
will allow organizations to widen the scope of the
roles of knowledge workers (see Figure 6). Over half
Generative AI will completely revolutionize the way we work 60%
(60 percent) also mentioned that generative AI would
completely revolutionize their way of working.
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
17
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The rise of generative AI will create new roles 60%
In our current survey, 69 percent of executives believe generative AI will lead to the emergence of new roles. In
addition to prompt engineers, we may also see new roles such as AI auditors and AI ethicists emerge as the
believe that generative AI will completely
initiatives scale.
revolutionize the way we work
Fig.7
Most executives believe new roles will emerge from generative AI
Generative AI will demand upskilling
and training initiatives
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENT
As well as opening up new job roles and requirements,
as 68 percent of executives in our survey say will happen,
the integration of generative AI into the workforce will
require a significant investment in upskilling and cross-
skilling of talent. In April 2023, in response to growing
demand, Coursera, a large-scale US-based open online
69% Generative AI will lead to the course provider, launched multiple new generative AI
emergence of new job roles (e.g., prompt
training courses, including ChatGPT Teach-Out from the
engineer)
University of Michigan, which introduces learners to large
language models (LLMs) and chatbots and discusses
the ethical use of generative AI and how the technology
might be harnessed and regulated moving forward.4
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N=800 organizations.
Capgemini Research Institute 2023
18
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
02
ORGANIZATIONS SEE MORE GAIN
THAN PAIN IN GENERATIVE AI
Capgemini Research Institute 2023
19
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.8
Most executives across industries say that the benefits of generative AI outweigh potential risks
Most organizations believe
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENT BY SECTOR
the benefits of generative AI
outweigh the risks Average 74%
High tech 84%
Our survey reveals that the majority of executives (74
percent) believe the benefits that generative AI brings Aerospace and defense 82%
outweigh the associated risks. The executives most
strongly convinced that generative AI is a power for Pharma and healthcare 80%
good work within the high-tech sector (84 percent); even
Industrial manufacturing 77%
at the other end of the list, a substantial 69 percent of
executives within the energy and utilities and telecom Retail 76%
sectors would bet on generative AI (see Figure 8).
Financial services 74%
Consumer products 70%
74% Energy and utilities 69%
Telecom 69%
believe the benefits of generative AI Automotive 66%
outweigh the associated risks
The benefits of utilizing generative AI outweigh the associated risks
Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
20
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.9
Most executives say that generative AI will improve products/services and customer service
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENTS
Anticipated benefits of
generative AI extend to
Generative AI will allow the design process to be
78% product design and
more efficient and streamlined
customer experience
Generative AI can enable us to create products and services
that are more accessible and inclusive, serving a wider 76%
range of customers with diverse needs and preferences Generative AI brings numerous transformative benefits
to organizations, including enhanced decision-making,
improved efficiency, personalized experiences, cost
Generative AI can enable us to create more
71% reductions, augmented innovation capacity, risk
interactive and engaging experiences for our customers
management, and predictive analytics. Most executives
in our survey (78 percent) believe that generative AI will
make product and service design more efficient and
Generative AI can be used to improve customer
service by providing automated and personalized support 67% that it will help them design more inclusive, accessible
products and services (76 percent). Seven in ten
executives believe generative AI will help them improve
Generative AI can improve internal operations the customer experience (see Figure 9).
65%
and enhance facility maintenance
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
21
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.10
Generative AI implementation is expected to yield operational and customer benefits
Executives are positive but EXPECTED FUTURE BENEFITS OF GENERATIVE AI IN THREE YEARS FROM TODAY,
AVERAGE % PROJECTED INCREASE
realistic in their expectations
of generative AI
Improved customer engagement and satisfaction
9%
(i.e., increase in Net Promoter Score)
We asked executives which organizational benefits they
expect to see from generative AI within three years.
Executives expect to see improvements of 7–9 percent
Increase in operational
across all industries (see Figure 10). Recent research from 9%
efficiency (e.g., improved quality)
Stanford and MIT on the applications of generative AI
in the workplace found that the productivity of tech-
support agents who used conversational scripts improved
as much as 14 percent at one organization,5 suggesting Increase in sales 8%
such an estimate is realistic, if not conservative.
Decrease in costs 7%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
22
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
• Customer engagement and skills in the Korean language using LLMs – machine
learning (ML) algorithms that can recognize,
satisfaction: Organizations can use generative
understand, predict, and generate human speech
AI for personalization; real-time insights; intelligent
based on huge text datasets.6
customer service; predictive analytics; continuous
improvement; and optimized customer journeys. • Operational efficiency: Organizations
These benefits ultimately lead to improved customer
are already reporting significant efficiencies from
engagement, satisfaction, and loyalty.
generative AI; German biotech firm Evotec announced
a phase-one clinical trial for a novel anti-cancer
KT telecom (South Korea’s leading mobile operator)
compound it developed with Exscientia, a UK
has built billion-parameter LLMs trained on the NVIDIA
organization that uses AI for small-molecule-drug
DGX SuperPOD platform and NeMo framework to
discovery. By using Exscientia’s Centaur Chemist AI
power smart speakers and customer call centers. Its
design platform, the organizations identified the
AI voice assistant, GiGA Genie, can control TVs, offer
drug candidate in only eight months. For context, the
real-time traffic updates, and complete a range of
average traditional discovery process takes 4–5 years.7
other home-assistance tasks when prompted by voice
commands. It has developed advanced conversational
Capgemini Research Institute 2023
23
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
• Sales: By using generative AI to produce • Costs: By using generative AI to automate
personalized marketing, pricing optimization, demand processes, optimize resources, implement predictive
forecasting, improved customer experience, enhanced maintenance, optimize the supply chain, mitigate
sales support, and data-driven decision-making, risks, and improve decision-making, organizations
organizations can attract more customers, drive can achieve cost savings and enhance overall financial
life-long content-driven conversations, and boost performance.
conversions.
Germany-based Claudius Peters produces processing
In an attempt to increase its sales, Italian consumer- equipment for cement, coal, alumina, and gypsum
products organization Ferrero worked with brand plants. Working with technology partner Autodesk, it
20–60% designer Ogilvy Italy to customize jars for its popular used the Scrum project-management framework to
Nutella chocolate spread. Data scientists fed a reduce costs and product weights while shortening the
database of patterns and colors to a generative AI engineering process. The generative design produced
algorithm, which rapidly produced 7 million distinct components with a remarkable 20–60 percent weight
reduction in weight achieved through jar designs. These unique jars, branded as Nutella reduction while meeting performance requirements.
Unica, were sold all across Italy, reportedly selling out Additionally, the design served as a re-engineering
generative design by German-based
within a month. The design relied on the brand's highly template for conventional manufacturing, resulting
Claudius Peters recognizable lettering, around which other elements in a 30 percent lighter final design that lowered
were customized.8 component costs.9
Capgemini Research Institute 2023
24
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.11
Organizations are prioritizing dedicated generative AI teams
Four in 10 organizations have
CURRENT LEVEL OF INTEGRATION OF GENERATIVE AI INTO FUTURE
already established teams PRODUCT/SERVICE DEVELOPMENT PLANS
and budget for generative AI
3% We have already established a dedicated
In just a few months of the public getting to know 8% team and budget for its implementation
about the technology through the launch of ChatGPT in
November 2022, nearly all (97 percent) of organizations
in our survey have plans for generative AI. Our research We are looking at establishing a dedicated
40%
reveals that 40 percent of organizations have established team and budget for its implementation
dedicated teams and budgets for generative AI, while in this year
another half (49 percent) are contemplating doing the
same within 12 months. Only 8 percent of organizations
We have not yet developed a concrete
are yet to develop a firm strategy for integration, and
plan for integration
as little as 3 percent are currently unsure if or how they 49%
will integrate generative AI into their product- or service-
development plans (see Figure 11). We are currently unsure if or how we
will integrate generative AI into our
product/service development plans
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
25
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.12
High tech and retail show the strongest commitment to integrating generative AI
PERCENTAGE OF ORGANIZATIONS THAT HAVE ESTABLISHED A DEDICATED
TEAM AND BUDGET TO INTEGRATE GENERATIVE AI INTO FUTURE
The majority (74 percent) of executives in the high tech
PRODUCT/SERVICE DEVELOPMENT PLANS BY SECTOR sector say they have established dedicated teams and
budgets for generative AI. Over 60 percent of executives
Average 40% from retail and 52 percent of executives from aerospace
and defense say the same (see Figure 12). Within retail,
High tech 74% while only 3 percent of executives believed generative
AI to be disruptive to their industry (refer to Figure 4),
Retail 62%
62 percent of retail executives say their organization has
Aerospace and defense 52% established a dedicated team and budget. This suggests
that while the retail industry does not see this technology
Pharma and healthcare 42%
as a disruptor, organizations realize they will lose out if
Financial services 42% they fail to implement it.
Energy and utilities 39%
Telecom 36%
Automotive 30%
Consumer products 23%
Industrial manufacturing 19%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations
Capgemini Research Institute 2023
26
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
40%
of organizations have already established
teams and budget for generative AI, while
another half (49 percent) are contemplating
doing the same within 12 months
Capgemini Research Institute 2023
27
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Governing Fig.13
Most organizations are working/prefer to work with developers and IT vendors for their generative AI initiatives
generative AI
PARTNERS THAT ORGANIZATIONS ARE ALREADY WORKING WITH/PREFER
TO WORK WITH TO DRIVE MORE VALUE FOR GENERATIVE AI INITIATIVES
Centralized funding for generative
AI initiatives is currently the favored Developers (e.g., OpenAI, Stability AI) 69%
model
Of the 40 percent of organizations in our survey (320 IT vendors/C&SI (consulting and system integrators) 66%
companies) that have a dedicated budget for generative
AI initiatives, 78 percent source it from their central
budget, 16 percent from their overall AI budget, and 6
Academic institutions 55%
percent from their IT/digital department.
Organizations expect to partner
Big tech (e.g., Microsoft, Google) 35%
with developers and IT vendors
The preferred partners for generative AI initiatives are
Peer companies 22%
developers (69 percent); IT vendors and consulting firms
(66 percent); academic institutions (55 percent); and big
tech (35 percent) (see Figure 13).
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
28
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
03
GENERATIVE AI PACKS THE MOST
PUNCH FOR IT, SALES, AND
MARKETING
Capgemini Research Institute 2023
29
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.14
67 percent of executives see the most potential for generative AI in the IT function
PERCENTAGE OF ORGANIZATIONS THAT SEE THE MOST POTENTIAL FOR
The greatest potential for GENERATIVE AI MODELS TO DRIVE INNOVATION AND CREATE VALUE FOR THEIR
ORGANIZATION ACROSS BUSINESS FUNCTIONS
generative AI lies in the IT
IT (e.g., driving innovation in other
function 67%
functions, testing and coding assistant)
Sales and customer service
54%
(e.g., optimizing support chatbots/self-service)
Nearly 70 percent of executives see generative AI
bringing the most potential value to IT within its role Marketing and communications 48%
(e.g., creating personalized marketing campaigns)
as an enabler for driving innovation across functions.
Over half (54 percent) also see generative AI driving Manufacturing (e.g., 3D modeling) 31%
innovation for sales and 48 percent for marketing and
Product design/research and development
communications (see Figure 14). (e.g., generating new design, faster drug discovery) 31%
Operations (e.g., optimizing supply chain) 26%
67%
Risk management (e.g., drafting
22%
and reviewing legal and regulatory documents)
Finance (e.g., processing invoices) 13%
of executives see generative AI bringing
Logistics (e.g., optimizing routes) 9%
the most potential value to IT within its
role as an enabler for driving innovation
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
across functions
Question asked: In which business functions do you see the most potential for generative AI models to drive innovation and create
value for your organizatio |
20 | capgemini | Build-a-GenAI-data-powered-enterprise.pdf | Build success as a
Gen AI data-powered
enterprise
Here’s why and how to make it happen
2
Business leaders are increasingly recognizing generative Data is an asset that requires investment, management,
AI’s value as an accelerator for driving innovation and and governance as Gen AI applications need a solid
revenue growth. An amazing 91 per cent of organizations foundation of clean, accurate, and usable data to deliver
are experimenting with or investing in Gen AI, and 88 per meaningful results. A data-powered enterprise has a
cent of organizations plan to focus on AI – including Gen strong foundation that reduces the complexity of the
AI – in the next 12 to 18 months. ecosystem, understands the difference between proof
of concept and scaled projects, connects data processes
But the majority of organizations that manage to scale
and policy, and supports the agility needed to move
up their Gen AI initiatives subsequently struggle to
quickly.
extract significant value from their investments. And
often that’s because of issues with their data and data-
management practices.
Build success as a Gen AI data-powered enterprise
3
Data-powered
defined
We identified nine key attributes in the Capgemini report
Data-powered enterprises: The path to data mastery. These
dimensions collectively empower organizations to create,
process, and leverage data to achieve business objectives,
increase operational excellence, improve customer
experience, and drive innovation.
Build success as a Gen AI data-powered enterprise
Defining the data-powered enterprise 4
Data-powered enterprises: The path to data mastery, Capgemini Research Institute 2024
Build success as a Gen AI data-powered enterprise
5
The same report found that, over the past four years, data executives are aware of the data trust and guiding
almost two-thirds of executives state their organizations principles required to succeed with AI adoption. That
use activated data, which is information that has been means the majority of organizations that manage to
embedded within core business processes. However, the scale up their Gen AI initiatives subsequently struggle to
data maturity progress made to unlock the value of data extract significant value from their investments. That’s
in these nine areas indicates otherwise. often because issues with data and data-management
practices impede success.
While 80 percent of global organizations increased
their Gen AI investment this year, only 54 percent of
Only In 2024,
54% 80%
of data executives are aware of of global organizations increased
the data foundations required to their investment in Gen AI from
win in the AI era last year
Build success as a Gen AI data-powered enterprise
6
The irrefutable value of data
Enterprise businesses already understand the emails, videos, images, social media posts, organization is hampered by limited access
value of information, as leaders who say their and HTML content. These data types make to the right technology skills to effectively
organization is cashing in on data has doubled identifying, collating, analyzing, and extracting leverage it, they won’t be able extract the most
since 2020 – up to two-thirds in 2024. But data insights a challenge. If an organization’s data is value from Gen AI.
quality is often an issue in achieving AI at scale, low quality, poorly governed, siloed in disparate
as much of it typically consists of unstructured systems, or laden with security issues, or if an
Build success as a Gen AI data-powered enterprise
7
Here’s how organizations can effectively unlock and supercharge their data.
Start strong Avoid excessively complex ecosystem
1
Build a data foundation that can unlock timely, accurate, Data is often siloed into disparate technologies and
2
and relevant insights to drive real outcomes. This is the first software products. Much of the data is unstructured or
step toward becoming a data-powered enterprise. low quality, and vetting it and restructuring it to analyze,
compare, and generate insights requires time, skill, and
budget.
Create the ability to scale
Remove obstacles to efficient delivery
Companies often see success with proof-of-concept Gen
AI products but success rates can drop dramatically when 4
3 Organizations must move fast and keep costs down
they move to production. The key is quality data and the
to deliver on their commitment. Without managing
capacity to create a clear, shared enterprise-wide data
complexity and scalability, this becomes challenging and
taxonomy. Engineering teams need strong, coordinated
costly.
data security and compliance policies and procedures
as well as the capacity to orchestrate a multiple-vendor
purchasing strategy. Ultimately, driving results and returns means data must be accessible, structured,
trustworthy, and mature.
Build success as a Gen AI data-powered enterprise
8
Working together on
data enablement to create
an advantage
Most Gen AI maturity journeys start in the same place: Capgemini RAISE, our Reliable AI Solution Engineering
businesses want ChatGPT-like experiences and they solution, includes key capabilities from Databricks:
encounter thousands of open- and closed-sourced Gen training and serving (Mosaic AI and AI/BI), data
AI models. Accessing trust, cost, and scale controls in a warehousing Databricks SQL and UniForm) and machine
single toolkit is therefore invaluable. learning (MLflow) capabilities, all using open standards
and complemented by key Informatica capabilities
including data integration, data quality, no-code AI
application development and trusted master data;
That’s why Capgemini is working with Databricks
comprehensive data governance is provided by the
and Informatica to provide a solution for enterprise
combined solution of Databricks Unity Catalog and
organizations that enables them to mature and leverage
Informatica’s Cloud Data Governance and Catalog. This
data more effectively to drive business results. Our
makes data usable on multiple clouds across hybrid
approach looks at data as a product hub. By combining
environments and reduces the complexity of managing
the best capabilities of enterprise data management
an end-to-end platform. And it’s available to be deployed
platforms on the cloud, along with the capabilities
on existing data platforms including Microsoft Azure,
of the best Gen AI solutions and capabilities from
AWS, and Google Cloud Platform.
the Databricks Data Intelligence Platform, and with
Informatica’s Intelligent Data Management Cloud, we’re
simplifying the data-management process within one
tool as an efficient, interoperable, and scalable Gen AI
development platform and framework.
Build success as a Gen AI data-powered enterprise
9
Capgemini RAISE works on multiple platforms including
Microsoft Azure, AWS, and Google Cloud Platform. Pilot, scale, and industrialize
Gen AI to deliver business
benefits.
Working seamlessly with existing infrastructure, Capgemini
RAISE also enhances data synergy and democratization
across the business with the data foundation necessary
to implement and scale Gen AI and other innovations
powered by data. The accelerator can identify and
As a Gen AI value cases operational accelerator, Capgemini
industrialize data products for AI models consumption,
RAISE delivers tangible business results, enabling
and ensure democratization of data through a data mesh,
organizations to industrialize custom Gen AI projects with
which is a decentralized data architecture designed to
the right guardrails, and addresses the issues of data
improve data access, security, and scalability by distributing
complexity, trust readiness, and scalability by creating the
ownership and management across business domains.
unified data governance and AI risk framework required
This effectively gives data-powered organizations an
for Gen AI data pilots. It equips organizations for Gen AI
advantage, and the ability to pilot, scale, and industrialize
scaling with a focus on business priorities.
their Gen AI applications and services to achieve the
Capgemini RAISE is not a one-size-fits-all product. It can be desired results.
built in modules, with the flexibility to meet unique needs
while delivering an end-to-end value chain for enterprise-
wide data management for Gen AI.
Generative AI holds great promise for enterprises in any
sector but there are substantial challenges to building
effective systems at scale. Capgemini RAISE and our
partnership with Databricks and Informatica solve those
issues today. Contact us to learn more.
Build success as a Gen AI data-powered enterprise
10
Authors
Please reach out with questions or to schedule a
conversation about this paper’s content and our
capabilities to assist your organization.
Eric Reich Rik Tamm-Daniels Ryan Simpson
Offer Leader and Global Head of GVP Ecosystems & Alliances Managing Technical Alliance Lead,
AI & Data Engineering, Insights & Informatica Databricks
Data, Capgemini
Build success as a Gen AI data-powered enterprise
11
About Databricks
Databricks is the Data and AI company. More than 10,000
organisations worldwide — including Block, Comcast,
Condé Nast, Rivian, Shell and over 60% of the Fortune
500 — rely on the Databricks Data Intelligence Platform
to take control of their data and put it to work with AI.
Databricks is headquartered in San Francisco, with offices
around the globe, and was founded by the original creators
of Lakehouse, Apache Spark™, Delta Lake and MLflow. To
learn more, follow Databricks on LinkedIn, X and Facebook.
About Informatica
Informatica (NYSE: INFA), a leader in enterprise AI-powered
cloud data management, brings data and AI to life by
empowering businesses to realize the transformative
power of their most critical assets. We have created a
new category of software, the Informatica Intelligent
Data Management Cloud™ (IDMC). IDMC is an end-to-
end data management platform, powered by CLAIRE® AI,
that connects, manages and unifies data across any multi-
cloud or hybrid system, democratizing data and enabling
enterprises to modernize and advance their business
strategies. Customers in approximately 100 countries,
including over 80 of the Fortune 100, rely on Informatica to
drive data-led digital transformation. Informatica. Where
data and AI come to life.
Build success as a Gen AI data-powered enterprise
About Capgemini
Capgemini is a global business and technology transformation partner, helping organizations to
accelerate their dual transition to a digital and sustainable world, while creating tangible impact for
enterprises and society. It is a responsible and diverse group of 340,000 team members in more than
50 countries. With its strong over 55-year heritage, Capgemini is trusted by its clients to unlock the
value of technology to address the entire breadth of their business needs. It delivers end-to-end
services and solutions leveraging strengths from strategy and design to engineering, all fueled by
its market leading capabilities in AI, cloud and data, combined with its deep industry expertise and
partner ecosystem. The Group reported 2023 global revenues of €22.5 billion.
www.capgemini.com
© 2024 Capgemini. All rights reserved. |
21 | capgemini | Generative-AI-in-Organizations-Refresh.pdf | Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Harnessing the value
of generative AI
2nd edition: Top use cases across sectors
#GetTheFutureYouWant
fo
elbaT
tnetnoC
2
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Capgemini Research Institute 2024
3
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Capgemini Research Institute 2024
evitucexE
yrammuS
4
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Increased maturity and investment: Organizations are Moreover, generative AI adoption among employees is robust
embracing generative AI, which is reflected in an uptick in in most organizations, with the majority allowing its use. Only
investment levels. The vast majority (80%) of organizations 3% of surveyed organizations enforce a complete ban on
in our survey have increased their investment in generative public generative AI tools in the workplace.
AI from 2023, 20% have maintained their investment level,
Tangible benefits and strategic shifts: Early adopters
and not one organization decreased their investment from
of generative AI are are seeing benefits in areas in which
last year. Larger enterprises lead the charge, and overall,
generative AI has been piloted or deployed, from improved
nearly one-quarter (24%) of organizations have integrated
operational efficiency to enhanced customer experience.
this technology into some or most of their operations, an
For example, on average, organizations realized a 7.8%
acceleration from 6% reported just 12 months ago. This
improvement in productivity and a 6.7% improvement
increase in generative AI adoption since 2023 spans all
in customer engagement and satisfaction, over the past
sectors. For example, in retail, implementation increased to
year. Organizations anticipate that generative AI will drive
40%, more than doubling from 17% in 2023.
adjustments to their strategic approaches and business
Pervasive integration across functions: Generative AI models. With a belief that the technology will be a key
permeates organizations, catalyzing a shift in operational driver of revenue growth and innovation, organizations are
paradigms. In the past year, there has been an increase in exploring new ways of harnessing its capabilities.
its adoption across all organizational domains, from sales
The rise of AI agents: The emergence of AI agents marks a
and marketing to IT, operations, R&D, finance, and logistics.
shift, with potential to enhance automation and productivity
across sectors, business processes, and along the entire
value chain. These AI agents have evolved from supportive
Capgemini Research Institute 2024
evitucexE
yrammuS
5
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
tools to autonomous entities capable of executing tasks Empower your generative AI journey: Organizations should:
independently. Organizations are eager to adopt AI agents,
with a strong majority (82%) intending to integrate them Establish a robust framework for data governance
within 1–3 years. There is a level of trust in AI agents for and management
specific tasks, such as generating work emails, coding, and
data analysis. However, organizations are also mindful of the Strengthen the data platform and cultivate trust to
need to establish guardrails to validate AI-made decisions, ensure reliable outcomes
ensuring transparency and accountability.
Cultivate expertise through strategic training and
talent development
Acquire understanding and expertise of the generative
AI ecosystem
Deploy a generative AI platform to manage use cases
at scale
Fortify against cybersecurity threats
Embrace emerging trends such as AI agents to boost
competitiveness and innovation.
Capgemini Research Institute 2024
6
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
This report is a part of Capgemini Research Institute’s series on Generative AI
Gen AI in organizations - annual research
Gen AI for management*
Gen AI in supply chain* Gen AI for marketing Gen AI for software Gen AI in R&D
engineering and engineering*
Gen AI and
consumers
Gen AI and Gen AI and Gen AI and
Gen AI in business operations* Gen AI in manufacturing* Gen AI in customer service* sustainability* ethics/ cybersecurity*
trust*
Data mastery*
Special edition of our premium journal Conversations for tomorrow on Gen AI*
To find out more, please go to https://www.capgemini.com/insights/research-institute/ *Upcoming reports
Capgemini Research Institute 2024
7
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Who should This report offers an overview of the transformative The report will help business executives identify use cases
potential of generative AI for large organizations that illustrate the applications of generative AI across
across sectors such as automotive, consumer functions, including IT, sales, marketing, and product design/
read this
products, retail, financial services, telecom, energy R&D. The report draws on the comprehensive analysis of a
and utilities, aerospace and defense, high tech, survey of 1,100 leaders (director level and above) across 14
report and industrial manufacturing, pharma and healthcare, countries. Finally, it offers recommendations for business
and the public sector/government. It is the second leaders to accelerate their organizations’ generative AI
installment in an annual research series and identifies journeys.
why? shifts in trends from 2023.
Capgemini Research Institute 2024
noitcudortnI
8
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI is rapidly transforming the way we interact with organizations are now integrating generative AI into some
technology. Machines are now capable of mimicking creative or most of their locations or functions, up from just 6% in
human thought processes and synthesizing tailored content 2023. In this year’s report, we analyze shifts in generative
of increasingly high quality. This has significant implications AI adoption and take a closer look at the investment levels
for driving innovation, operational efficiency, and growth. and benefits organizations have realized. We also turn the
spotlight on AI agents, a quickly evolving technology with
This report is the second in the Capgemini Research
potential to drive innovation.
Institute’s annual research series that examines generative
AI trends and use cases. In the first report of this series, To gauge perceptions of generative AI, we conducted a
“Harnessing the value of generative AI: Top use cases global survey of 1,100 executives at organizations with
across industries,” we explored the transformative potential annual revenue above $1 billion. We invited public-sector
of generative AI, highlighting the function- and sector- organizations and government entities with an annual
specific use cases with the greatest potential, and comparing budget of at least $50 million to participate. Organizations
adoption rates across sectors. In our 2023 research, we are headquartered in 14 countries: Australia, Canada, France,
discovered that, while still in its infancy in terms of scaled Germany, India, Italy, Japan, the Netherlands, Norway,
adoption and implementation, generative AI was on the Singapore, Spain, Sweden, the UK, and the US. Organizations
agenda in 96% of boardrooms globally. We found that nearly surveyed operate across 11 key sectors: aerospace and
60% of organizations said their leaders are strong advocates defense, automotive, consumer products, energy and
of generative AI, and only 39% were taking a “wait-and- utilities, financial services, high tech, pharma and healthcare,
watch” approach. industrial manufacturing, retail, telecom, and the public
sector/government. For more details on the survey sample,
This year’s research highlights a quickening of the pace
please refer to the research methodology.
of implementation. Notably, nearly one-quarter (24%) of
Capgemini Research Institute 2024
noitcudortnI
9
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
This report comprises five sections:
1 2 3 4 5
Organizations are Generative AI Generative AI is AI agents: The new How organizations
deploying generative is pervading already driving technology frontier can accelerate
AI at pace organizations benefits their generative AI
journeys
Capgemini Research Institute 2024
10
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
01
Organizations are deploying
generative AI at pace
Capgemini Research Institute 2024
11
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Investment in generative AI Dave Chen, Head of Global Technology Investment Banking
at Morgan Stanley, says:“Though cost savings and operational
is increasing efficiencies remain a priority for large enterprises, they are also
showing a willingness to spend, especially on generative AI and
traditional AI hardware and software that may [in the medium
According to our research, 80% of organizations have
to long term] help reduce costs and increase productivity and
increased their investment in generative AI from last year.
revenue.” 1 Recently, The Coca-Cola Company committed
Remarkably, not a single organization decreased their
$1.1 billion over a five-year period to accelerate cloud and
investment, while the remaining 20% maintained the same
generative AI initiatives.2
investment level. This trend echoes across all sectors and
organization sizes in the research. For example:
• In aerospace and defense, almost nine in 10 organizations
have (88%) boosted their investment in generative AI;
80%
• Within retail, the lowest proportion among all sectors in
our survey, 66% have invested in generative AI;
• 73% of organizations with $1–5 billion in annual
of organizations have increased their revenue have increased their investment, and 89% of
investment in generative AI from last year organizations with over $20 billion in revenue have
done so.
Capgemini Research Institute 2024
12
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
In the past year, Figure 1.
More organizations have increased their maturity in generative AI
implementation of
generative AI has
% of organizations who agree with the statement on generative AI maturity
accelerated
Across our total survey sample of 1,100 organizations, 2023
only 6% of organizations are yet to begin exploring 53% 41% 6%
generative AI. Out of those who have at least begun to do
so (n=1,031), nearly one-quarter (24%) are now integrating
this technology into some or most of their locations or
functions. This marks an increase from just 6% reported last 2024
year, indicating widespread recognition of the benefits (see 27% 49% 18% 6%
Figure 1).
Only 10% of smaller organizations in our research, We have started exploring the We have begun working on some
with annual revenue of $1–5 billion, have implemented potential of generative AI pilots of generative AI initiatives
generative AI across some or most of their locations We have enabled generative AI capabilities in
We have enabled generative AI capabilities
and functions. In contrast, 49% of organizations with most/all of our functions/locations
in some of our functions/locations
annual revenue surpassing $20 billion have implemented
the technology.
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI
Jack Forestell, Chief Product and Strategy Officer at Visa,
executive survey, May–June 2024, N = 940 organizations that are at least exploring generative AI capabilities.
says: “While much of generative AI so far has been focused on
*In the 2024 data points respondents from India and the public sector/government are excluded as they were not
tasks and content creation, this technology will soon not only
included in the 2023 research.
reshape how we live and work, but it will also meaningfully
change commerce in ways we have yet to fully understand.” 3
Capgemini Research Institute 2024
13
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
All sectors have progressed Generative AI integration has increased across all sectors (see Figure 2). For a detailed listing of use cases by sector and
since 2023. For example, 40% of organizations in the retail associated implementation data, please refer to Appendix.
in their implementation of sector have implemented generative AI across some or most
functions/locations, more than doubling from 17% in 2023
generative AI
Figure 2.
Over the past year, there has been an increase in the maturity of generative AI across sectors
% of organizations who agree with the statement on generative AI maturity, by sector
4% 5% 4% 6% 3% 3% 4% 2% 3% 2% 2%
6% 16 8% % 17% 22% 45% 32% 35% 26% 28% 17 9% % 18% 19 5% % 21% 33% 1 10 4% % 1 11 1% % 7% 20% 11% 10% We have started exploring the
41% 18% 47% 49% 37% 44% potential of generative AI
48%
24% 40% 51% 48% 68% 68% We have begun working on some
49% 30% 53% 68% 54% 53% pilots of generative AI initiatives
53% 49% 55% 45% 61% 68% 47% 64% 47% 53% 53% W cae p ah ba iv lie ti ee sn a inb l se od m g ee on fe ora ut rive AI
27% 34% 11% 39% 21% 14% 22% 24% 35% 27% 30% 19% 20% functions/locations
We have enabled generative AI
capabilities in most/all of our
2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2024*
functions/locations
Average Retail Industrial Consumer Automotive High tech Financial Energy and Telecom Pharma and Aerospace Public
manufacturing products services utilities healthcare and defense sector
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities; N varies per sector use case ranging from 50 to 189. *Respondents from the public sector were not included in the 2023 research. **Excluded from Figure 2 is the percentage of
organizations that have started exploring the potential of generative AI.
Capgemini Research Institute 2024
14
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
David M. Reese, Executive Vice-president and Chief Highlighting the gradual scaling of generative AI in financial
Technology Officer at Amgen, a US biopharmaceutical services, Asim Tewary, former Chief AI Officer, PayPal,
company, says: "Generative AI is transforming drug discovery comments: "You have to be able to explain why certain decisions
by allowing us to build sophisticated models and seamlessly were made — why a credit limit was set at that amount, for
integrate AI into the antibody design process.'' 4 Natarajan example. There’s an absoluteness that’s expected from regulators
Chandrasekaran, Chairperson of Tata Group, states: “In about being able to explain how the decision was made. Anytime
e-commerce, generative AI is being used to generate product you impact the consumer or introduce a system risk, regulators
catalogs, deliver conversational shopping experiences, and get very concerned.” Also concerning to the financial sector is
provide personalized offers.” 5 Michael Smith, Chief Information the increased sophistication of deepfakes which can deceive
Officer at The Estée Lauder Companies, says: “The generative customers into transferring funds to seemingly legitimate
AI chatbot developed with [a partner] helps us quickly find accounts, whether virtual or human agent mimicked. This
products that address concerns relevant to specific regions and underscores the imperative of ensuring both accuracy in
emerging markets. We will continue to explore other ways we customer-facing AI products and robust security measures in
can harness the wealth of data across products, ingredients, and customer interactions.7
more, in tandem with the power of generative AI.” 6
Capgemini Research Institute 2024
15
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Investment in generative AI
Figure 3.
increases with organization size
Investment in generative AI trends upward with organization size
On average, organizations surveyed have $20 billion believe that failing to adopt generative
allocated around $110 million to generative AI AI will place them at a considerable disadvantage
for the current fiscal year. Thirty-four percent of relative to their competitors. This sentiment is lower Average investment dedicated to generative AI,
organizations in our survey have allocated $50 among organizations with annual revenues under $5 by annual revenue, 2024
million or less to generative AI, while 11% have billion (56%)8.
allocated $250 million or more.
Our average investment of $110 million is higher than $157.7
The amount of generative AI investment increases some recently published analyst reports and likely
$131.5
with company size. For example, on average, reflects the broad categories of enterprise spend
$109.8
organizations with annual revenue of $1–5 billion including hardware, software, licensing, training, $99.5
allocate $85 million and those with more than $20 among others. According to Gartner, software $85.2
billion allocate $158 million (see Figure 3). development is the function with the highest rate
of investment in generative AI, followed closely by
Given that the amount of investment allocated
marketing and customer service.8 Additionally, a
to generative AI increases with organization size,
significant majority of organizations are investing in
larger organizations widely agree that generative
partnerships with external providers of generative
AI is more than just a passing trend, serving as a
AI applications. According to our research, 70%
pivotal cornerstone in their enterprise evolution. Average $1 bn– $5 bn– $10 bn– More than
Large organizations are increasingly embracing of organizations are exclusively using external $4.9 bn $9.9 bn $19.9 bn $20 bn
applications or a combination of external and
the transformative potential of generative AI
in-house solutions. Commonly used tools include
technology more fervently than perhaps other Source: Capgemini Research Institute, AI executive survey, May–June
OpenAI’s ChatGPT, GitHub Copilot, Scribe, Microsoft
recent technological advancement. A striking 71% 2024, N = 981 organizations who are at least exploring generative AI
Copilot, and AWS Gen AI.
of organizations with annual revenues exceeding capabilities, excluding the public sector.
Capgemini Research Institute 2024
16
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
02
Generative AI is pervading
organizations
Capgemini Research Institute 2024
17
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI makes Figure 4.
Over the past year, adoption of generative AI has grown across functions
inroads across functions
% of organizations implementing generative AI use cases, by function
Our research indicates an increase in generative AI
adoption across all facets of organizations over the past 12
4%
months. Examining individual functions, in the IT domain IT 27%
for example, the adoption rate has increased to 27% from Risk management 4%
4% the previous year (see Figure 4). Hitachi successfully 26%
integrated generative AI tools by leveraging its detailed Logistics 2%
26%
system-design knowledge with Microsoft’s AI services,
Sales/customer operations 4%
achieving a 70%–90% success rate in generating application 25%
source code.9 For a detailed listing of use cases by function Finance 5%
and associated implementation data, please refer to 25%
the Appendix. Human resources* 24%
ESG/sustainability* 22%
3%
Product design/R&D
19%
2%
Marketing
19%
2023 2024
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI executive survey,
May–June 2024, N = 1,031 organizations that are at least exploring generative AI capabilities; N varies per functional use case, ranging
from 499 to 716.
*ESG/sustainability and human resources were excluded from the 2023 research.
** “Implementation” refers to organizations that have partially scaled the functional use case in question.
***In the 2024 averages, respondents from the public sector and India are excluded, as they were not included in the 2023 research.
Capgemini Research Institute 2024
18
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI is used by Figure 5.
97% of organizations allow employees to use generative AI in some capacity
employees in most
organizations
% of organizations who agree with the statements
The majority of organizations allow employees to use
generative AI in some capacity. Over half of organizations We allow all our employees to use generative AI tools but have set up
54%
(54%) require employees to follow specific guidelines when guardrails/principles
using these tools, rather than imposing a complete ban.
Three percent of surveyed organizations report a ban on We allow only a carefully chosen group of skilled employees, primarily
36%
public generative AI tools in the workplace. However, 7% of those in specialized/technical roles, to use generative AI tools
organizations permit unrestricted use of such tools, which
may pose future risks to the organization (see Figure 5). We allow all our employees to use generative AI tools at will 7%
We have banned all our employees from using public generative AI
3%
tools in the workplace
2024
Source: Capgemini Research Institute, Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities.
Capgemini Research Institute 2024
19
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Despite the implementation of guardrails and policies to workplace. Amazon has prohibited employees from using In the table that follows, we highlight recent
regulate the use of generative AI, unauthorized usage among third-party generative AI tools, such as OpenAI's ChatGPT, generative AI use cases across sectors and functions:
employees is still relatively common. Among the 39% of particularly for handling confidential data. This policy is
organizations with a ban or limitation policy, half of them intended to prevent data-ownership issues and protect
say there is still unauthorized usage of generative AI in the sensitive company information.10
Sector Company Function Example
Has transformed its operations and innovation processes with generative AI. AI assistants
Aerospace Airbus Manufacturing
provide aircraft manufacturing instructions, enhancing accessibility to technical data, and
facilitating precise task guidance.11
Uses generative AI to incorporate engineering constraints into vehicle design, and
Automotive Toyota Product design/R&D
optimizing metrics such as aerodynamic drag, enhancing efficiency of electric-vehicle
(EV) design.12
Leverages generative AI in its “Hey Mercedes” feature, which is in beta with 900,000
Automotive Mercedes-Benz Customer experience/
users. It offers personalized, screen-free interactions, enhancing driving experience with
service
dynamic adjustments and real-time safety support.13
Consumer products General Mills Customer experience/ Launched MillsChat, a generative AI tool, to streamline customer service. This enhances
service efficiency, provides personalized assistance, and encourages customer engagement.14
Harnesses generative AI to analyze customer feedback, which it uses to refine shape design
Marketing and
Consumer products PepsiCo and flavor of its Cheetos branded snack, boosting market penetration by 15%. This strategy
branding
has also shortened product launch cycles and increased profitability.15
Continue to the next page...
Capgemini Research Institute 2024
20
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Uses generative AI to streamline legal processes, including research, drafting, and
Consumer product Unilever Legal
contract reviews. This allows legal teams to focus on strategic tasks, enhancing
operational effectiveness.16
Energy British Human resources – Leverages generative AI to assist employees with daily tasks such as email management.
Enhances employee productivity and transforms business workflows.17
Petroleum (BP) employee productivity
Used GPT-4 to create an AI tool for financial advisors, allowing rapid access to internal
Financial services Morgan Stanley Customer
research. This enhances advisor efficiency and client service, simulating top investment
experience/service
experts on call.18
Uses generative AI to reduce carbon footprint of commercial buildings. Uses historical data
High tech BrainBox AI ESG/sustainability
to predict interior building temperatures, cutting heat, ventilation and air-conditioning
(HVAC) energy costs by up to 25% and greenhouse gas (GHG) emissions by 40%.19
Added generative AI into FactoryTalk Design Studio to help engineers generate code using
Industrial manufacturing Rockwell Automation IT – coding/software natural language prompts, automating routine tasks and improving design efficiency. It will
development also empower experienced engineers to accelerate development and mentor newcomers
more effectively.20
Continue to the next page...
Capgemini Research Institute 2024
21
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Integrated generative AI into Finance Advisor, a conversational assistant for financial
Industrial manufacturing Schneider Electric Finance and accounting
analysts in global finance, ensuring precise, compliant, and timely decision-making across
accounting and related functions.21
Logistics UPS Marketing Developed the Message Response Automation (MeRA) system in-house using publicly
available large language models (LLMs), to automate routine customer interactions,
reducing email handling times by 50% and allowing human agents to focus on more
complex issues. It also streamlines operations and improves customer satisfaction by
ensuring prompt, accurate responses.22
Pharmaceutical Insilico Product design/R&D Identified a new drug candidate, MYT1, using its generative AI platform in each step of its
and biotech Medicine preclinical drug-discovery process, offering more effective, safer treatments for breast and
gynecological cancers.23
Pharmaceutical Moderna Research and Uses generative AI tools, including the company's Dose ID GPT, which uses ChatGPT
Enterprise's Advanced Data Analytics feature to further evaluate the optimal vaccine dose
and biotech development
selected by the clinical study team.24
Continue to the next page...
Capgemini Research Institute 2024
22
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Plans to use generative AI to analyze traffic data to improve road safety, reduce
Public sector California Department of Citizen services
call-center wait times, aid non-English speakers, and streamline healthcare-facility
Transportation and
inspections.25
Department of Tax and
Fee Administration
Public sector State of Pennsylvania Employee operations Runs a generative AI pilot program for state employees, integrating the technology into
government operations. Supports crafting/editing copy, updating policy language,
drafting job descriptions, and generating code.26
Retail ASOS Sales Uses generative AI to make fashion recommendations, customer-service interactions, and
trend analysis, enhancing user engagement, personalizing customer experiences, and
optimizing retail strategies.27
Uses generative AI to reduce food waste by helping employees make quick decisions.
Retail Walmart ESG/sustainability
Employees scan a product such as produce or apparel, and a digital dashboard makes
suggestions on what to do with the product based on its characteristics (e.g., ripeness,
whether its seasonal). Suggested actions could include a price change, putting it on sale,
sending the item back, or donating it.28
Continue to the next page...
Capgemini Research Institute 2024
23
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Uses generative AI, in its Seoul, South Korea, store to develop innovative ice-cream
Retail Baskin Robbins Product design/R&D
flavors. Supported the introduction of a monthly exclusive flavor, and personalized
experience offered through an ice-cream docent program.29
Telecom AT&T Employee productivity Employs generative AI capabilities in its Ask AT&T tool to support employees by
enhancing productivity and creativity, translating documents, optimizing networks, and
summarizing meetings. This leads to improved efficiency and greater innovation.30
Voxi by Vodafone, a generative AI self-service experience, enhances interactions, provides
Telecom Vodafone Customer
personalized assistance, and optimizes customer support services, fostering satisfaction
experience/service
and engagement.31
Capgemini Research Institute 2024
24
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Organizations must
Figure 6.
carefully scale generative 36% of organizations are currently tracking carbon emissions from generative AI use
AI initiatives with a focus
% of organizations currently tracking and measuring the
on environmental
below metrics in the use of generative AI
sustainability
30% 29%
Organizations must assess technological 36%
advancements in generative AI alongside their
environmental consequences. They should
Yes
evaluate the business value, considering
implementation complexity and costs, while No
also scrutinizing environmental impacts such 54% 57% 62% Unsure/ don’t know
as GHG emissions, electricity usage, and water
consumption. Our research indicates that, roughly
a third of organizations are currently monitoring
energy and water consumption, as well as carbon 10% 13% 9%
emissions, associated with their generative AI
Carbon Energy Water
initiatives (see Figure 6).
emission utilization consumption
Source: Capgemini Research Institute, Generative AI executive survey, May–June
2024, N = 1,031 organizations that are at least exploring generative AI capabilities.
Capgemini Research Institute 2024
25
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Furthermore, our research explored the
Figure 7.
measures organizations are implementing
to mitigate the environmental impact Half of organizations are currently developing guidelines for generative AI use
of generative AI. Slightly over half of
organizations (54%) are developing guidelines
for responsible use of generative AI, and % of organizations currently trying to mitigate the carbon footprint from using generative AI
47% are transitioning to more energy-
efficient hardware. However, the proportion
of organizations undertaking additional
Developing guidelines for responsible use 54%
actions such as investing in renewable energy,
offsetting emissions through carbon credits,
and optimizing training algorithms remains Using more energy-efficient hardware 47%
low (see Figure 7).
Offsetting through carbon credits 37%
Investing in renewable energy 36%
Only a third of organizations are
currently monitoring energy and water
Optimizing our training algorithms 31%
consumption, as well as carbon emissions,
associated with their generative AI
initiatives.
Source: Capgemini Research Institute, Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities.
Capgemini Research Institute 2024
26
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
03
Generative AI is already
driving benefits
Capgemini Research Institute 2024
27
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Organizations have Figure 8.
Generative AI yielded benefits in the past year in the areas in which the technology has been piloted or deployed
achieved benefits
Average benefits realized from generative AI within the past year
Our current research evaluates the benefits that generative
AI has brought at organizational level in the past year in the
areas in which generative AI has been piloted or deployed. 7.8%
For example, on average, organizations realized a 7.8%
6.7%
improvement in productivity and a 6.7% improvement in
5.4%
customer engagement and satisfaction over the past year
4.4%
(see Figure 8).
3.6%
Generative AI |
22 | capgemini | Setting-the-pace-for-intelligent-transformation-weblocked.pdf | Setting the pace for
intelligent transformation
Four steps banks can take to build a roadmap to AI adoption success
Seemingly overnight, AI in the banking industry has
catapulted from limited adoption to a competitive
imperative. This is particularly true of generative
AI, which 80% of bank CXOs who participated in
Capgemini’s World Retail Banking Report 2024
believe is a significant leap with a potential that no
one can ignore.
In brief
• AI in the banking industry has catapulted from
limited adoption to a competitive imperative, but
impediments remain.
• To help overcome the hurdles, banks should develop an AI
adoption roadmap that includes cloud, data-as-a-product,
data mesh, LLM selection, and effective governance.
• The benefits of building a holistic AI roadmap are
considerable as enterprise-wide AI is a steppingstone to
autonomous and intelligent banking, which takes banks
beyond consuming AI to wielding it for competitive
advantage.
Industry optimism for AI is in no small part due
to the inefficiencies facing banks every day. In
quantitative terms, 70% of bank employee time
is allocated to operational activities and only
30% to customer interactions, leaving substantial
opportunities for AI.1
Still, significant impediments to intelligent
transformations remain. These include legacy
systems, fragmented data, regulatory challenges,
skill shortages, and return on investment concerns.
In this article we explore how banks overcome such
barriers by developing an appropriate plan to guide
AI adoption initiatives in order to positively benefit
the bottom line.
2 Setting the pace for intelligent transformation
Building a strategic AI roadmap
Only 6% of
As discussed in Capgemini’s World required for building an intelligent
banks have an
Retail Banking Report 2024, transformation roadmap. We
leading CXOs worldwide have recommend using a bottom-up appropriate plan for
already identified three pivotal approach (Figure 1) to create a plan
horizontal processes, spanning the that addresses data, model, and establishing an AI
entire retail banking spectrum, business layers using the following
adoption roadmap.
as focal points for the intelligent steps:
transformations: intelligent
document automation, intelligent 1. Build a cloud foundation
call centers, and workforce
2. Develop a modern data-
productivity co-pilots.
as-a-product estate using
However, the report also revealed data mesh
that 96% of banks score low on
3. Select the right Large
the AI readiness scale, as measured
Language Model (LLM)
from both a technology and a
approach
business perspective. On a key
readiness factor, establishing an 4. Establish
AI adoption roadmap, only 6% of effective governance
banks have an appropriate a plan.
For a greater understanding of
To help banks catch up, this what each element entails, let’s
article discusses the elements discuss each in depth.
Figure 1: Four strategic essentials for an intelligent transformation roadmap
Source: Capgemini Research Institute for Financial Services Analysis, 2024
3
1. Build a cloud foundation for agility and scalability
As the most appropriate Gaining the desired benefits from
“A key variable [in
infrastructure for providing high- AI initiatives requires accelerating
performance scalable computing cloud migration efforts and developing our AI roadmap]
resources, cloud technologies lie at establishing a sufficiently robust, is to allocate cloud
the heart of enterprise AI adoption. agile, and secure foundation
computing resources to
for meeting AI’s computing
Although 91% of financial services
capacity, speed, and data generative AI use cases.
firms have embarked on their
protection requirements. The convergence of
cloud journey,3 adoption has been
uneven. For example, industry generative AI and cloud
experts and analysts suggest that
economics offer a path to
less than 30% of banks have moved
reduced costs and scaled
their core business applications to a
cloud platform.4 adoption.”
- Vincent Kolijn, Head of Strategy
and Transformation, Retail,
Rabobank, Netherlands2
4 Setting the pace for intelligent transformation
2. Develop a modern data-as-a-product estate using data mesh
Exacerbated by legacy consumption by multiple business As noted in the Capgemini World
infrastructure, departmental lines and AI applications. Retail Banking Report 2024, leading
database ownership, and banks like JP Morgan Chase and
Simplify data ownership
regulatory demands, data silos Fifth Third Bank in the US, Saxo
and management.
remain a significant challenge for Bank in Denmark, ABN AMRO in
banks. Fortunately, data mesh Enables each banking domain to the Netherlands, and numerous
architecture now offers a solution continue organizing, owning, and others have successfully adopted
by providing technology layers that managing data while improving data mesh architectures.
work across data silos (Figure 2). data access, utilization, and data-
driven innovation across a bank’s
Data mesh treats data as a stand- “Banks facing the
entire enterprise, without requiring
alone offering with a value challenge of legacy
significant overhauls to existing
proposition that is called data-as-
data infrastructure. systems must strategize
product. With this approach, data
management is decentralized and Ensure well-governed on how to adopt and scale
occurs within business silos, but is data diversity. AI effectively. It’s about
unified by standards, governance,
Enables making data FAIR crafting a roadmap that
and extraction technologies
(findable, accessible, interoperable,
that make data available to AI navigates the hurdles
and reusable) while applying
applications on demand. Use data legacy systems pose.”
appropriate key performance
mesh to:
indicators (KPIs) to govern and
Provide real-time data access. protect data, which helps assure its - Steven Cooper, CEO, Aldermore
integrity for use by AI applications. Bank, UK5
Enables creating a data
marketplace for collaborative data
Figure 2: Modern data-as-a-product estate using data mesh
Source: Capgemini Research Institute for Financial Services Analysis, 2024.
5
3. Select the right Large Language Model (LLM) approach
Shaping the algorithm layer for an calibrated using a bank’s internal and compliance considerations,
AI initiative starts with selecting data, enabling fine-tuning for the and cost analysis. Once an AI
the right large language model delivery of superior, customized application is rolled out, monitoring
(LLM). Typically, the decision is human interactions. it for continuous improvement and
shaped by the phase of an AI course corrections are also critical
Industrialization phase.
journey (Figure 3). for achieving desired business
Although only about 10% of CXOs results and goals.
Exploratory phase.
survey for World Retail Banking
Many banks purchase off-the Report 2024 have chosen to build
“Banks navigating the
shelf solutions such as chatbots, a custom LLM from scratch, this
evolving generative AI
fraud detection platforms, and industrialization phase option
others that cater to specific needs provides the greatest ownership landscape should weigh
when exploring AI. Off-the-shelf and customization. Unsurprisingly,
three approaches: building
solutions provide immediate this path also requires substantial
a custom LLM, considering
availability but limited control. resource investments.
off-the-shelf generative
AI scaling phase. Regardless of which route a bank
chooses, success requires a long- AI, and partnering with
Banks most frequently partner with
term strategic vision. This includes specialists.”
LLM specialists during scaling as a
a comprehensive assessment
balanced approach to accelerating
of specific needs, available
AI development and gaining - Pierre Ruhlmann, Chief
resources, model capabilities, risk
domain expertise. This nets an AI Operating Officer, BNP Paribas,
France6
Figure 3: Three typical approaches to LLM development
Source: Capgemini Research Institute for Financial Services Analysis, 2024; World Retail Banking Report CXO survey.
6 Setting the pace for intelligent transformation
4. Establish effective governance
As AI applications evolve rapidly, results, privacy intrusions, and
“Explainable AI (XAI)
they quickly exceed the limits malicious use.
of human understanding and in banking is essential
Naturally, developing and
make decisions that are difficult to mitigate bias risks
continuously evolving a robust
for humans to interpret, much
and comprehensive set of KPIs is and enhance trust. It
less govern. Mitigating this
necessary for effectively governing
phenomenon requires diligently accelerates AI adoption,
AI and generative AI applications.
managing and monitoring AI ensuring transparent
Here, banks are significantly
applications to ensure decisions are
lagging. Capgemini’s World Retail decisions, compliance,
explainable. Explainable AI ensures
Banking Report 2024 discovered
humans can quickly understand and collaborative industry
only 6% of banks have established
outputs and course correct as implementation.”
KPIs to measure generative AI
necessary.
impact and maintain continuous
Beyond explainability, it’s vital monitoring (Figure 4). Clearly, - Cormac Flanagan, Global Head
for banks to monitor and manage focusing greater attention on KPI of Product Management,
several other categories of development and implementation Temenos, Ireland7
AI-associated risks. These include is necessary for minimizing risks
biased and discriminatory outputs, and unintended consequences.
hallucinations with inaccurate
Figure 4: Banks are lagging KPIs for governing AI and generative AI
Source: Capgemini Research Institute for Financial Services Analysis, 2024; World Retail Banking Report CXO survey.
7
In conclusion
Take a holistic road mapping approach
Although each of the roadmap elements discussed here Be certain to address factors like change management,
have technology in common, developing a holistic plan upskilling, and cultural readiness as they are
also requires including human-centric aspects within often the make-or-break activities for successful
each for the four elements. transformations.8
Achieving the ultimate AI goal: autonomous banking
Although today’s fledgling AI initiatives are already To begin achieving your bank’s AI goals, start with a
generating considerable benefits, enterprise-wide comprehensive roadmap for navigating the AI journey.
AI is a steppingstone to autonomous and intelligent By embracing modern technology approaches,
banking. When banks reach this level of maturity, addressing key data hurdles, and establishing effective
they move beyond consuming AI to wielding it for governance, banks can successfully complete their
competitive advantage. intelligent transformation journeys and ultimately
leverage AI to redefine the industry’s future. It’s an
Current examples of self-driving offerings include
exciting time in banking for all.
BBVA’s “Bconomy” and Santander Bank’s partnership
with Personetics, which demonstrate how hyper-
personalized customer journeys and omnichannel
engagement can deliver true customer centricity.
8 Setting the pace for intelligent transformation
Endnotes
¹ Capgemini. “World Retail Banking Report 2024;” March 5, 2024
² Ibid.
³ Capgemini. “World Cloud Report – Financial Services 2023,” November 16, 2023
⁴ Ibid.
⁵ Capgemini. “World Retail Banking Report 2024;” March 5, 2024
⁶ Ibid.
⁷ Ibid.
⁸ Capgemini. “Unleashing confidence in AI: A playbook by Capgemini Generative AI Lab”; March, 2024
Meet our experts
Ashvin Parmar Chandramouli Venkatesan
Global Head of Financial Services Portfolio Development Lead - Digital
Insights & Data Portfolio Front Office Transformations | Banking
and Capital Markets
9
About Capgemini
Capgemini is a global business and technology transformation partner, helping organizations to accelerate
their dual transition to a digital and sustainable world, while creating tangible impact for enterprises and
society. It is a responsible and diverse group of 340,000 team members in more than 50 countries. With
its strong over 55-year heritage, Capgemini is trusted by its clients to unlock the value of technology to
address the entire breadth of their business needs. It delivers end-to-end services and solutions leveraging
strengths from strategy and design to engineering, all fueled by its market leading capabilities in AI, cloud
and data, combined with its deep industry expertise and partner ecosystem. The Group reported 2023
global revenues of €22.5 billion.
www.capgemini.com
Copyright © 2024 Capgemini. All rights reserved.
hcuaMB_4202
yaM_UBSSF |
23 | capgemini | Generative-AI-in-Organizations-Refresh_25112024.pdf | Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Harnessing the value
of generative AI
2nd edition: Top use cases across sectors
#GetTheFutureYouWant
fo
elbaT
tnetnoC
2
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Capgemini Research Institute 2024
3
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Capgemini Research Institute 2024
evitucexE
yrammuS
4
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Increased maturity and investment: Organizations are Moreover, generative AI adoption among employees is robust
embracing generative AI, which is reflected in an uptick in in most organizations, with the majority allowing its use. Only
investment levels. The vast majority (80%) of organizations 3% of surveyed organizations enforce a complete ban on
in our survey have increased their investment in generative public generative AI tools in the workplace.
AI from 2023, 20% have maintained their investment level,
Tangible benefits and strategic shifts: Early adopters
and not one organization decreased their investment from
of generative AI are seeing benefits in areas in which
last year. Larger enterprises lead the charge, and overall,
generative AI has been piloted or deployed, from improved
nearly one-quarter (24%) of organizations have integrated
operational efficiency to enhanced customer experience.
this technology into some or most of their operations, an
For example, on average, organizations realized a 7.8%
acceleration from 6% reported just 12 months ago. This
improvement in productivity and a 6.7% improvement
increase in generative AI adoption since 2023 spans all
in customer engagement and satisfaction, over the past
sectors. For example, in retail, implementation increased to
year. Organizations anticipate that generative AI will drive
40%, more than doubling from 17% in 2023.
adjustments to their strategic approaches and business
Pervasive integration across functions: Generative AI models. With a belief that the technology will be a key
permeates organizations, catalyzing a shift in operational driver of revenue growth and innovation, organizations are
paradigms. In the past year, there has been an increase in exploring new ways of harnessing its capabilities.
its adoption across all organizational domains, from sales
The rise of AI agents: The emergence of AI agents marks a
and marketing to IT, operations, R&D, finance, and logistics.
shift, with potential to enhance automation and productivity
across sectors, business processes, and along the entire
value chain. These AI agents have evolved from supportive
Capgemini Research Institute 2024
evitucexE
yrammuS
5
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
tools to autonomous entities capable of executing tasks Empower your generative AI journey: Organizations should:
independently. Organizations are eager to adopt AI agents,
with a strong majority (82%) intending to integrate them Establish a robust framework for data governance
within 1–3 years. There is a level of trust in AI agents for and management
specific tasks, such as generating work emails, coding, and
data analysis. However, organizations are also mindful of the Strengthen the data platform and cultivate trust to
need to establish guardrails to validate AI-made decisions, ensure reliable outcomes
ensuring transparency and accountability.
Cultivate expertise through strategic training and
talent development
Acquire understanding and expertise of the generative
AI ecosystem
Deploy a generative AI platform to manage use cases
at scale
Fortify against cybersecurity threats
Embrace emerging trends such as AI agents to boost
competitiveness and innovation.
Capgemini Research Institute 2024
6
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
This report is a part of Capgemini Research Institute’s series on Generative AI
Gen AI in organizations - annual research
Gen AI for management*
Gen AI in supply chain* Gen AI for marketing Gen AI for software Gen AI in R&D
engineering and engineering*
Gen AI and
consumers
Gen AI and Gen AI and Gen AI and
Gen AI in business operations* Gen AI in manufacturing* Gen AI in customer service* sustainability* ethics/ cybersecurity*
trust*
Data mastery*
Special edition of our premium journal Conversations for tomorrow on Gen AI*
To find out more, please go to https://www.capgemini.com/insights/research-institute/ *Upcoming reports
Capgemini Research Institute 2024
7
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Who should This report offers an overview of the transformative The report will help business executives identify use cases
potential of generative AI for large organizations that illustrate the applications of generative AI across
across sectors such as automotive, consumer functions, including IT, sales, marketing, and product design/
read this
products, retail, financial services, telecom, energy R&D. The report draws on the comprehensive analysis of a
and utilities, aerospace and defense, high tech, survey of 1,100 leaders (director level and above) across 14
report and industrial manufacturing, pharma and healthcare, countries. Finally, it offers recommendations for business
and the public sector/government. It is the second leaders to accelerate their organizations’ generative AI
installment in an annual research series and identifies journeys.
why? shifts in trends from 2023.
Capgemini Research Institute 2024
noitcudortnI
8
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI is rapidly transforming the way we interact with organizations are now integrating generative AI into some
technology. Machines are now capable of mimicking creative or most of their locations or functions, up from just 6% in
human thought processes and synthesizing tailored content 2023. In this year’s report, we analyze shifts in generative
of increasingly high quality. This has significant implications AI adoption and take a closer look at the investment levels
for driving innovation, operational efficiency, and growth. and benefits organizations have realized. We also turn the
spotlight on AI agents, a quickly evolving technology with
This report is the second in the Capgemini Research
potential to drive innovation.
Institute’s annual research series that examines generative
AI trends and use cases. In the first report of this series, To gauge perceptions of generative AI, we conducted a
“Harnessing the value of generative AI: Top use cases global survey of 1,100 executives at organizations with
across industries,” we explored the transformative potential annual revenue above $1 billion. We invited public-sector
of generative AI, highlighting the function- and sector- organizations and government entities with an annual
specific use cases with the greatest potential, and comparing budget of at least $50 million to participate. Organizations
adoption rates across sectors. In our 2023 research, we are headquartered in 14 countries: Australia, Canada, France,
discovered that, while still in its infancy in terms of scaled Germany, India, Italy, Japan, the Netherlands, Norway,
adoption and implementation, generative AI was on the Singapore, Spain, Sweden, the UK, and the US. Organizations
agenda in 96% of boardrooms globally. We found that nearly surveyed operate across 11 key sectors: aerospace and
60% of organizations said their leaders are strong advocates defense, automotive, consumer products, energy and
of generative AI, and only 39% were taking a “wait-and- utilities, financial services, high tech, pharma and healthcare,
watch” approach. industrial manufacturing, retail, telecom, and the public
sector/government. For more details on the survey sample,
This year’s research highlights a quickening of the pace
please refer to the research methodology.
of implementation. Notably, nearly one-quarter (24%) of
Capgemini Research Institute 2024
noitcudortnI
9
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
This report comprises five sections:
1 2 3 4 5
Organizations are Generative AI Generative AI is AI agents: The new How organizations
deploying generative is pervading already driving technology frontier can accelerate
AI at pace organizations benefits their generative AI
journeys
Capgemini Research Institute 2024
10
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
01
Organizations are deploying
generative AI at pace
Capgemini Research Institute 2024
11
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Investment in generative AI Dave Chen, Head of Global Technology Investment Banking
at Morgan Stanley, says:“Though cost savings and operational
is increasing efficiencies remain a priority for large enterprises, they are also
showing a willingness to spend, especially on generative AI and
traditional AI hardware and software that may [in the medium
According to our research, 80% of organizations have
to long term] help reduce costs and increase productivity and
increased their investment in generative AI from last year.
revenue.” 1 Recently, The Coca-Cola Company committed
Remarkably, not a single organization decreased their
$1.1 billion over a five-year period to accelerate cloud and
investment, while the remaining 20% maintained the same
generative AI initiatives.2
investment level. This trend echoes across all sectors and
organization sizes in the research. For example:
• In aerospace and defense, almost nine in 10 organizations
have (88%) boosted their investment in generative AI;
80%
• Within retail, the lowest proportion among all sectors in
our survey, 66% have invested in generative AI;
• 73% of organizations with $1–5 billion in annual
of organizations have increased their revenue have increased their investment, and 89% of
investment in generative AI from last year organizations with over $20 billion in revenue have
done so.
Capgemini Research Institute 2024
12
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
In the past year, Figure 1.
More organizations have increased their maturity in generative AI
implementation of
generative AI has
% of organizations who agree with the statement on generative AI maturity
accelerated
Across our total survey sample of 1,100 organizations, 2023
only 6% of organizations are yet to begin exploring 53% 41% 6%
generative AI. Out of those who have at least begun to do
so (n=1,031), nearly one-quarter (24%) are now integrating
this technology into some or most of their locations or
functions. This marks an increase from just 6% reported last 2024
year, indicating widespread recognition of the benefits (see 27% 49% 18% 6%
Figure 1).
Only 10% of smaller organizations in our research, We have started exploring the We have begun working on some
with annual revenue of $1–5 billion, have implemented potential of generative AI pilots of generative AI initiatives
generative AI across some or most of their locations We have enabled generative AI capabilities in
We have enabled generative AI capabilities
and functions. In contrast, 49% of organizations with most/all of our functions/locations
in some of our functions/locations
annual revenue surpassing $20 billion have implemented
the technology.
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI
Jack Forestell, Chief Product and Strategy Officer at Visa,
executive survey, May–June 2024, N = 940 organizations that are at least exploring generative AI capabilities.
says: “While much of generative AI so far has been focused on
*In the 2024 data points respondents from India and the public sector/government are excluded as they were not
tasks and content creation, this technology will soon not only
included in the 2023 research.
reshape how we live and work, but it will also meaningfully
change commerce in ways we have yet to fully understand.” 3
Capgemini Research Institute 2024
13
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
All sectors have progressed Generative AI integration has increased across all sectors (see Figure 2). For a detailed listing of use cases by sector and
since 2023. For example, 40% of organizations in the retail associated implementation data, please refer to Appendix.
in their implementation of sector have implemented generative AI across some or most
functions/locations, more than doubling from 17% in 2023
generative AI
Figure 2.
Over the past year, there has been an increase in the maturity of generative AI across sectors
% of organizations who agree with the statement on generative AI maturity, by sector
4% 5% 4% 6% 3% 3% 4% 2% 3% 2% 2%
6% 16 8% % 17% 22% 45% 32% 35% 26% 28% 17 9% % 18% 19 5% % 21% 33% 1 10 4% % 1 11 1% % 7% 20% 11% 10% We have started exploring the
41% 18% 47% 49% 37% 44% potential of generative AI
48%
24% 40% 51% 48% 68% 68% We have begun working on some
49% 30% 53% 68% 54% 53% pilots of generative AI initiatives
53% 49% 55% 45% 61% 68% 47% 64% 47% 53% 53% W cae p ah ba iv lie ti ee sn a inb l se od m g ee on fe ora ut rive AI
27% 34% 11% 39% 21% 14% 22% 24% 35% 27% 30% 19% 20% functions/locations
We have enabled generative AI
capabilities in most/all of our
2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2023 2024 2024*
functions/locations
Average Retail Industrial Consumer Automotive High tech Financial Energy and Telecom Pharma and Aerospace Public
manufacturing products services utilities healthcare and defense sector
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities; N varies per sector use case ranging from 50 to 189. *Respondents from the public sector were not included in the 2023 research. **Excluded from Figure 2 is the percentage of
organizations that have started exploring the potential of generative AI.
Capgemini Research Institute 2024
14
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
David M. Reese, Executive Vice-president and Chief Highlighting the gradual scaling of generative AI in financial
Technology Officer at Amgen, a US biopharmaceutical services, Asim Tewary, former Chief AI Officer, PayPal,
company, says: "Generative AI is transforming drug discovery comments: "You have to be able to explain why certain decisions
by allowing us to build sophisticated models and seamlessly were made — why a credit limit was set at that amount, for
integrate AI into the antibody design process.'' 4 Natarajan example. There’s an absoluteness that’s expected from regulators
Chandrasekaran, Chairperson of Tata Group, states: “In about being able to explain how the decision was made. Anytime
e-commerce, generative AI is being used to generate product you impact the consumer or introduce a system risk, regulators
catalogs, deliver conversational shopping experiences, and get very concerned.” Also concerning to the financial sector is
provide personalized offers.” 5 Michael Smith, Chief Information the increased sophistication of deepfakes which can deceive
Officer at The Estée Lauder Companies, says: “The generative customers into transferring funds to seemingly legitimate
AI chatbot developed with [a partner] helps us quickly find accounts, whether virtual or human agent mimicked. This
products that address concerns relevant to specific regions and underscores the imperative of ensuring both accuracy in
emerging markets. We will continue to explore other ways we customer-facing AI products and robust security measures in
can harness the wealth of data across products, ingredients, and customer interactions.7
more, in tandem with the power of generative AI.” 6
Capgemini Research Institute 2024
15
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Investment in generative AI
Figure 3.
increases with organization size
Investment in generative AI trends upward with organization size
On average, organizations surveyed have $20 billion believe that failing to adopt generative
allocated around $110 million to generative AI AI will place them at a considerable disadvantage
for the current fiscal year. Thirty-four percent of relative to their competitors. This sentiment is lower Average investment dedicated to generative AI,
organizations in our survey have allocated $50 among organizations with annual revenues under $5 by annual revenue, 2024
million or less to generative AI, while 11% have billion (56%)8.
allocated $250 million or more.
Our average investment of $110 million is higher than $157.7
The amount of generative AI investment increases some recently published analyst reports and likely
$131.5
with company size. For example, on average, reflects the broad categories of enterprise spend
$109.8
organizations with annual revenue of $1–5 billion including hardware, software, licensing, training, $99.5
allocate $85 million and those with more than $20 among others. According to Gartner, software $85.2
billion allocate $158 million (see Figure 3). development is the function with the highest rate
of investment in generative AI, followed closely by
Given that the amount of investment allocated
marketing and customer service.8 Additionally, a
to generative AI increases with organization size,
significant majority of organizations are investing in
larger organizations widely agree that generative
partnerships with external providers of generative
AI is more than just a passing trend, serving as a
AI applications. According to our research, 70%
pivotal cornerstone in their enterprise evolution. Average $1 bn– $5 bn– $10 bn– More than
Large organizations are increasingly embracing of organizations are exclusively using external $4.9 bn $9.9 bn $19.9 bn $20 bn
applications or a combination of external and
the transformative potential of generative AI
in-house solutions. Commonly used tools include
technology more fervently than perhaps other Source: Capgemini Research Institute, AI executive survey, May–June
OpenAI’s ChatGPT, GitHub Copilot, Scribe, Microsoft
recent technological advancement. A striking 71% 2024, N = 981 organizations who are at least exploring generative AI
Copilot, and AWS Gen AI.
of organizations with annual revenues exceeding capabilities, excluding the public sector.
Capgemini Research Institute 2024
16
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
02
Generative AI is pervading
organizations
Capgemini Research Institute 2024
17
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI makes Figure 4.
Over the past year, adoption of generative AI has grown across functions
inroads across functions
% of organizations implementing generative AI use cases, by function
Our research indicates an increase in generative AI
adoption across all facets of organizations over the past 12
4%
months. Examining individual functions, in the IT domain IT 27%
for example, the adoption rate has increased to 27% from Risk management 4%
4% the previous year (see Figure 4). Hitachi successfully 26%
integrated generative AI tools by leveraging its detailed Logistics 2%
26%
system-design knowledge with Microsoft’s AI services,
Sales/customer operations 4%
achieving a 70%–90% success rate in generating application 25%
source code.9 For a detailed listing of use cases by function Finance 5%
and associated implementation data, please refer to 25%
the Appendix. Human resources* 24%
ESG/sustainability* 22%
3%
Product design/R&D
19%
2%
Marketing
19%
2023 2024
Source: Capgemini Research Institute, Generative AI executive survey, April 2023, N = 800 organizations; Generative AI executive survey,
May–June 2024, N = 1,031 organizations that are at least exploring generative AI capabilities; N varies per functional use case, ranging
from 499 to 716.
*ESG/sustainability and human resources were excluded from the 2023 research.
** “Implementation” refers to organizations that have partially scaled the functional use case in question.
***In the 2024 averages, respondents from the public sector and India are excluded, as they were not included in the 2023 research.
Capgemini Research Institute 2024
18
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Generative AI is used by Figure 5.
97% of organizations allow employees to use generative AI in some capacity
employees in most
organizations
% of organizations who agree with the statements
The majority of organizations allow employees to use
generative AI in some capacity. Over half of organizations We allow all our employees to use generative AI tools but have set up
54%
(54%) require employees to follow specific guidelines when guardrails/principles
using these tools, rather than imposing a complete ban.
Three percent of surveyed organizations report a ban on We allow only a carefully chosen group of skilled employees, primarily
36%
public generative AI tools in the workplace. However, 7% of those in specialized/technical roles, to use generative AI tools
organizations permit unrestricted use of such tools, which
may pose future risks to the organization (see Figure 5). We allow all our employees to use generative AI tools at will 7%
We have banned all our employees from using public generative AI
3%
tools in the workplace
2024
Source: Capgemini Research Institute, Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities.
Capgemini Research Institute 2024
19
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Despite the implementation of guardrails and policies to workplace. Amazon has prohibited employees from using In the table that follows, we highlight recent
regulate the use of generative AI, unauthorized usage among third-party generative AI tools, such as OpenAI's ChatGPT, generative AI use cases across sectors and functions:
employees is still relatively common. Among the 39% of particularly for handling confidential data. This policy is
organizations with a ban or limitation policy, half of them intended to prevent data-ownership issues and protect
say there is still unauthorized usage of generative AI in the sensitive company information.10
Sector Company Function Example
Has transformed its operations and innovation processes with generative AI. AI assistants
Aerospace Airbus Manufacturing
provide aircraft manufacturing instructions, enhancing accessibility to technical data, and
facilitating precise task guidance.11
Uses generative AI to incorporate engineering constraints into vehicle design, and
Automotive Toyota Product design/R&D
optimizing metrics such as aerodynamic drag, enhancing efficiency of electric-vehicle
(EV) design.12
Leverages generative AI in its “Hey Mercedes” feature, which is in beta with 900,000
Automotive Mercedes-Benz Customer experience/
users. It offers personalized, screen-free interactions, enhancing driving experience with
service
dynamic adjustments and real-time safety support.13
Consumer products General Mills Customer experience/ Launched MillsChat, a generative AI tool, to streamline customer service. This enhances
service efficiency, provides personalized assistance, and encourages customer engagement.14
Harnesses generative AI to analyze customer feedback, which it uses to refine shape design
Marketing and
Consumer products PepsiCo and flavor of its Cheetos branded snack, boosting market penetration by 15%. This strategy
branding
has also shortened product launch cycles and increased profitability.15
Continue to the next page...
Capgemini Research Institute 2024
20
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Uses generative AI to streamline legal processes, including research, drafting, and
Consumer product Unilever Legal
contract reviews. This allows legal teams to focus on strategic tasks, enhancing
operational effectiveness.16
Energy British Human resources – Leverages generative AI to assist employees with daily tasks such as email management.
Enhances employee productivity and transforms business workflows.17
Petroleum (BP) employee productivity
Used GPT-4 to create an AI tool for financial advisors, allowing rapid access to internal
Financial services Morgan Stanley Customer
research. This enhances advisor efficiency and client service, simulating top investment
experience/service
experts on call.18
Uses generative AI to reduce carbon footprint of commercial buildings. Uses historical data
High tech BrainBox AI ESG/sustainability
to predict interior building temperatures, cutting heat, ventilation and air-conditioning
(HVAC) energy costs by up to 25% and greenhouse gas (GHG) emissions by 40%.19
Added generative AI into FactoryTalk Design Studio to help engineers generate code using
Industrial manufacturing Rockwell Automation IT – coding/software natural language prompts, automating routine tasks and improving design efficiency. It will
development also empower experienced engineers to accelerate development and mentor newcomers
more effectively.20
Continue to the next page...
Capgemini Research Institute 2024
21
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Integrated generative AI into Finance Advisor, a conversational assistant for financial
Industrial manufacturing Schneider Electric Finance and accounting
analysts in global finance, ensuring precise, compliant, and timely decision-making across
accounting and related functions.21
Logistics UPS Marketing Developed the Message Response Automation (MeRA) system in-house using publicly
available large language models (LLMs), to automate routine customer interactions,
reducing email handling times by 50% and allowing human agents to focus on more
complex issues. It also streamlines operations and improves customer satisfaction by
ensuring prompt, accurate responses.22
Pharmaceutical Insilico Product design/R&D Identified a new drug candidate, MYT1, using its generative AI platform in each step of its
and biotech Medicine preclinical drug-discovery process, offering more effective, safer treatments for breast and
gynecological cancers.23
Pharmaceutical Moderna Research and Uses generative AI tools, including the company's Dose ID GPT, which uses ChatGPT
Enterprise's Advanced Data Analytics feature to further evaluate the optimal vaccine dose
and biotech development
selected by the clinical study team.24
Continue to the next page...
Capgemini Research Institute 2024
22
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Plans to use generative AI to analyze traffic data to improve road safety, reduce
Public sector California Department of Citizen services
call-center wait times, aid non-English speakers, and streamline healthcare-facility
Transportation and
inspections.25
Department of Tax and
Fee Administration
Public sector State of Pennsylvania Employee operations Runs a generative AI pilot program for state employees, integrating the technology into
government operations. Supports crafting/editing copy, updating policy language,
drafting job descriptions, and generating code.26
Retail ASOS Sales Uses generative AI to make fashion recommendations, customer-service interactions, and
trend analysis, enhancing user engagement, personalizing customer experiences, and
optimizing retail strategies.27
Uses generative AI to reduce food waste by helping employees make quick decisions.
Retail Walmart ESG/sustainability
Employees scan a product such as produce or apparel, and a digital dashboard makes
suggestions on what to do with the product based on its characteristics (e.g., ripeness,
whether its seasonal). Suggested actions could include a price change, putting it on sale,
sending the item back, or donating it.28
Continue to the next page...
Capgemini Research Institute 2024
23
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Sector Company Function Example
Uses generative AI, in its Seoul, South Korea, store to develop innovative ice-cream
Retail Baskin Robbins Product design/R&D
flavors. Supported the introduction of a monthly exclusive flavor, and personalized
experience offered through an ice-cream docent program.29
Telecom AT&T Employee productivity Employs generative AI capabilities in its Ask AT&T tool to support employees by
enhancing productivity and creativity, translating documents, optimizing networks, and
summarizing meetings. This leads to improved efficiency and greater innovation.30
Voxi by Vodafone launched a generative AI self-service experience, which enhances
Telecom Vodafone Customer
interactions, provides personalized assistance, and optimizes customer support services,
experience/service
fostering satisfaction and engagement.31
Capgemini Research Institute 2024
24
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Organizations must
Figure 6.
carefully scale generative 36% of organizations are currently tracking carbon emissions from generative AI use
AI initiatives with a focus
% of organizations currently tracking and measuring the
on environmental
below metrics in the use of generative AI
sustainability
30% 29%
Organizations must assess technological 36%
advancements in generative AI alongside their
environmental consequences. They should
Yes
evaluate the business value, considering
implementation complexity and costs, while No
also scrutinizing environmental impacts such 54% 57% 62% Unsure/ don’t know
as GHG emissions, electricity usage, and water
consumption. Our research indicates that, roughly
a third of organizations are currently monitoring
energy and water consumption, as well as carbon 10% 13% 9%
emissions, associated with their generative AI
Carbon Energy Water
initiatives (see Figure 6).
emission utilization consumption
Source: Capgemini Research Institute, Generative AI executive survey, May–June
2024, N = 1,031 organizations that are at least exploring generative AI capabilities.
Capgemini Research Institute 2024
25
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Furthermore, our research explored the
Figure 7.
measures organizations are implementing
to mitigate the environmental impact Half of organizations are currently developing guidelines for generative AI use
of generative AI. Slightly over half of
organizations (54%) are developing guidelines
for responsible use of generative AI, and % of organizations currently trying to mitigate the carbon footprint from using generative AI
47% are transitioning to more energy-
efficient hardware. However, the proportion
of organizations undertaking additional
Developing guidelines for responsible use 54%
actions such as investing in renewable energy,
offsetting emissions through carbon credits,
and optimizing training algorithms remains Using more energy-efficient hardware 47%
low (see Figure 7).
Offsetting through carbon credits 37%
Investing in renewable energy 36%
Only a third of organizations are
currently monitoring energy and water
Optimizing our training algorithms 31%
consumption, as well as carbon emissions,
associated with their generative AI
initiatives.
Source: Capgemini Research Institute, Generative AI executive survey, May–June 2024, N = 1,031 organizations that are at least exploring
generative AI capabilities.
Capgemini Research Institute 2024
26
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
03
Generative AI is already
driving benefits
Capgemini Research Institute 2024
27
Harnessing the value of generative AI: 2nd edition Top uses cases across sectors
Organizations have Figure 8.
Generative AI yielded benefits in the past year in the areas in which the technology has been piloted or deployed
achieved benefits
Average benefits realized from generative AI within the past year
Our current research evaluates the benefits that generative
AI has brought at organizational level in the past year in the
areas in which generative AI has been piloted or deployed. 7.8%
For example, on average, organizations realized a 7.8%
6.7%
improvement in productivity and a 6.7% improvement in
5.4%
customer engagement and satisfaction over the past year
4.4%
(see Figure 8).
3.6%
Gene |
24 | capgemini | GENERATIVE-AI_-Final-Web-1-1.pdf | HHAARRNNEESSSSIINNGG
TTHHEE VVAALLUUEE OOFF
GGEENNEERRAATTIIVVEE AAII
Top use cases across industries
#GetTheFutureYouWant
evitucexE
yrammuS
2
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Generative artificial intelligence (AI) is rapidly becoming restructuring of business models. Globally, about one-
an integral part of our private and professional lives. fifth (21 percent) of executives surveyed say generative
While the technology has been in existence for a number AI will significantly disrupt their industries. Executives in
of years, it has gained widespread consumer interest high tech and industrial manufacturing – two industries
only recently and has emerged as a critical strategic that have long been shaped by AI technologies and have
consideration. Our latest industry-focused research been at the forefront of generative AI – are most likely to
reveals that generative AI is on the boardroom agenda agree with this statement.
at 96 percent of organizations surveyed globally. While
The potential of generative AI to drive innovation and
generative AI is in its infancy in terms of scaled adoption
improve efficiency and productivity extends to nearly all
and implementation, nearly 60 percent of executives
functions and has applications across all industries. Use
globally say their leadership is a strong advocate for
cases are wide-ranging, from creating unique content
generative AI and only 39 percent are taking a “wait-and-
and automating and accelerating tasks, to creating
watch” approach to adoption.
personalized experiences and generating synthetic data.
Many organizations already see generative AI as a Our research reveals that generative AI has the greatest
powerful tool that can accelerate growth, enhance potential within IT, sales and customer service, and
capabilities, and unlock new opportunities without drastic marketing functions. The high tech sector leads the way,
Capgemini Research Institute 2023
with the greatest share of ongoing generative AI pilots. adverse impact of generative AI on the environment.
Executives in our survey also project efficiencies from Nevertheless, the net impact of generative AI on an
generative AI in the next three years in the range of 7–9 organization’s Scope 1, 2, and/or 3 emissions is currently
percent. difficult to forecast.
As with any new technology, generative AI is not without We conclude this report with a look at how organizations
risk. However, with proper planning and guardrails in can start and/or accelerate their generative AI journeys.
place, there is potential to transform business operations, First, they must create a robust generative AI strategic
product and service development, and customer and operational architecture. Organizations must also
interaction. Nearly three-quarters of executives in our establish internal and external guidelines around the
survey (74 percent) agree that the benefits of generative use of generative AI, adopt a human-centric approach
AI outweigh the risks. Given the carbon-intensive nature to scaling the technology, and build user and consumer
of training new generative AI models, it will also be trust in the AI system. Given the high carbon emissions
important to weigh environmental considerations. The associated with generative AI trainings and queries,
good news is that executives in our survey are aware sustainable development and use of the technology
of this dynamic and understand how to mitigate the should also be a high priority.
evitucexE
yrammuS
3
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Capgemini Research Institute 2023
noitcudortnI
4
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Generative artificial intelligence (generative AI) is rapidly innovating of organizations; highlighting the function-
transforming the way we interact with technology. and industry-specific use cases we believe to have the
Machines are beginning to mimic creative human thought greatest potential; and comparing adoption rates across
processes, synthesizing tailored content with significant industries.
implications for organizations and consumers.
To gauge executives’ perceptions of generative AI and
This report is the second in a series of reports we adoption of use cases, we conducted a global survey of
have created around this topic. Our first report, Why 1,000 organizations across Australia, Canada, France,
consumers love generative AI, explored consumer Germany, Italy, Japan, the Netherlands, Norway,
perceptions of generative AI; consumer use of generative Singapore, Spain, Sweden, the UK, and the US. We
AI; and how the technology is shaping the future of questioned executives from multiple industries, including
customer experience. automotive, consumer products, retail, financial services,
telecom, energy and utilities, aerospace and defense,
In this report, we delve into the transformative potential
high tech, industrial manufacturing, and pharma and
of generative AI for organizations across industries,
healthcare. For more details on the survey sample, please
asking how the technology could kick-start the
refer to the research methodology.
Capgemini Research Institute 2023
noitcudortnI
5
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The report explores five broad themes:
1 2 3 4 5
Organizations view Organizations see Generative AI High tech leads How organizations
generative AI not as more gain than pain packs the most in implementing can kick-start their
a disruptor but as an in generative AI punch for IT, sales, generative AI generative AI
accelerator and marketing journeys
Capgemini Research Institute 2023
6
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Who should read this
report and why?
This report offers a comprehensive introduction to the transformative
impact that Generative AI holds for large businesses in industries such
as automotive, consumer products, retail, financial services, telecom,
energy and utilities, aerospace and defense, high tech, industrial
manufacturing, and pharma and healthcare. The report will help
business executives identify use cases that will illustrate the pragmatic
applications of Generative AI in IT, sales, and marketing, for example.
The report leverages a comprehensive analysis of 1,000 industry leaders
(ranked Director and above) across 13 countries, each at varying stages
of Generative AI implementation. The report also offers actionable
recommendations for business leaders to kick-start their organizations’
generative AI journeys. This report is the second in our series of reports
on Generative AI. Read the first report focusing on consumer reactions to
Generative AI at
https://www.capgemini.com/insights/research-library/
creative-and-generative-ai/
Capgemini Research Institute 2023
7
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.1
Generative AI applications across multiple formats
Selected generative AI applications Indicative examples
Defining Text Summarizing and translating into multiple OpenAI’s GPT-4, Jasper1
languages
generative AI
Images and video Analyzing existing images/video to generate new Adobe Firefly,2 Stable
generation content (e.g., video games, VR, animation) Diffusion, Midjourney
Generative AI has the capability to learn and reapply the
Music generation and remixing, speech synthesis, Sonix.ai (a cloud-based audio
properties and patterns of data for a wide range of
Audio sound effects, voice conversion, audio and video-transcription
applications, from creating text, images, and videos in enhancement solution)3
different styles to generating tailored content. It enables
machines to perform creative tasks previously thought
exclusive to humans. The following table summarizes the Chatbots to provide automated customer service Google Bard,4 OpenAI’s
Chatbots
top generative AI applications reported in our research and and advice ChatGPT
gives some indicative examples.
Enhanced search functions using natural
Search Perplexity AI5
language processing and machine learning
Source: 1. TechTarget, “What is generative AI? Everything you need to know,” March 5, 2023.
2. Adobe, "Adobe unveils Firefly, a family of new creative generative AI," March 21, 2023.
3. Sonix.ai, "Sonix releases the world’s first automated transcription and generative AI summarization tool," December 14, 2022.
4. Cointelegraph, "What is Google’s Bard, and how does it work?" May 10, 2023.
5. Kevin-Indig, "Early attempts at integrating AI in Search," January 10, 2023.
Capgemini Research Institute 2023
8
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
01
ORGANIZATIONS VIEW GENERATIVE
AI NOT AS A DISRUPTOR, BUT AS AN
ACCELERATOR
Capgemini Research Institute 2023
9
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.2
Generative AI is a topic for boardroom discussion at nearly all organizations
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
Generative AI is a top STATEMENT BY SECTOR
agenda item in boardrooms
96% 100% 98% 98% 97% 96% 95% 94% 93% 93% 93%
Nearly all executives (96 percent) in our survey cite
generative AI as a hot topic of discussion in their
respective boardrooms (see Figure 2), making it probably
the fastest new technology to garner such high-level
interest. Pat Geraghty, CEO of GuideWell, a US-based
mutual insurance organization, comments: “Every single
board meeting we’ve had this year has had a standing
agenda item of AI and ChatGPT. We want to make sure we’ve
got our board with us as we’re thinking about where we’re
going.” 1 Average Financial Industrial Energy Aerospace Consumer
services manufacturing and utilities and defense products
High tech Pharma Telecom Automotive Retail
and healthcare
Generative AI is a topic of discussion in our boardroom
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
10
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.3
The leaders of most organizations are strong advocates of generative AI
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
STATEMENT BY SECTOR
2% 1% 1% 1% 1% 4% 2% 5% 3% Top leaders are strong
16%
32% advocates for generative AI
39% 39% 39% 41% 37% 39%
57% 45% 50%
Among the 96% of organizations that discuss generative
AI in their boardrooms, over half (59 percent) of
84%
executives say their leadership are strong advocates for
59% 67% 60% 60% 59% 59% 58% generative AI only six months after the technology hit
51%
43% 57% the mainstream. This rises to 84 percent in the high-tech
sector. Thirty-nine percent of executives say their leaders
are taking a “wait-and-watch” approach to the technology
Average Aerospace Telecom Retail Industrial Consumer
and defense manufacturing products and only 2 percent of executives globally say their leaders
High tech Financial Energy Pharma Automotive are not convinced or are divided by the potential of
services and utilities and healthcare generative AI (see Figure 3).
Our leadership is a strong advocate of generative AI
Our leadership is taking a "wait-and-watch" approach to generative AI
Our leadership is not convinced of / is divided on the potential of generative AI
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 766 organizations that cite generative AI
as a topic of discussion in their respective boardrooms.
Capgemini Research Institute 2023
11
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
96%
organizations say generative AI
is a topic of discussion in their
boardrooms
Capgemini Research Institute 2023
12
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.4
About one-fifth of organizations anticipate significant disruption from generative AI
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE
Most organizations do not
STATEMENT BY SECTOR
view generative AI as a
52%
48% disruptor
While twenty-one percent of executives anticipate a
significant disruption in their respective industries from
21% 21% 21% 20% 19% 18% 18% generative AI, 67 percent of executives disagree. That
12% is, a majority of the executives do not see generative
AI significantly disrupting their business models.
3%
However, executives within the high-tech and industrial
Average Industrial Pharma Consumer Aerospace Retail manufacturing sectors expect significant disruption at
manufacturing and healthcare products and defense 52 percent and 48 percent, respectively (see Figure 4).
While this may be reflective of these executives’ superior
High tech Energy Financial Automotive Telecom
and utilities services understanding of the technology’s potential, the figures
underline the widespread expectation that generative AI
will boost business overall.
Generative AI can significantly disrupt our industry
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
13
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.5
Relevance of generative AI platforms for organizations across different domains
PERCENTAGE OF ORGANIZATIONS THAT FIND GENERATIVE AI
Organizations are finding
PLATFORMS RELEVANT TO THEIR BUSINESS
generative AI platforms
Chatbots (automating customer service and improving
83%
knowledge management: e.g., ChatGPT)
increasingly relevant
Data (designing, collecting, or summarizing data:
75%
e.g., Jasper’s Text Summarizer)
Chatbots emerge as the most relevant generative AI Text (summarizing, automating, or translating content: e.g., ChatGPT) 71%
application, with 83 percent of organizations citing it.
Organizations can use generative-AI-driven chatbots Search (AI-powered insights: e.g., Bing) 70%
to improve their customer service and also to enable
Generating synthetic data (Capgemini's Artificial Data Amplifier) 61%
improved internal knowledge management. Seventy-five
percent of executives say that data applications can be ML platforms (applications of machine learning: e.g., Slai) 54%
used effectively in their organizations, and 71 percent
Code (testing and coding assistant e.g.,GitHub Copilot, converting code
believe this to be true of text-generating platforms such 50%
from one language to another e.g., Codex, Capgemini's A2B Translator)
as ChatGPT (see Figure 5).
Images (generating images: e.g., DALL-E) 48%
Audio (summarizing, generating or converting text in audio: e.g., Sonix) 34%
Video (generating or editing videos: e.g., Pictory, Synthesys) 26%
Gaming (generative AI gaming studios or applications: e.g., Ludo AI) 4%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
14
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
US financial services organization Morgan Stanley's
vast library of investment strategies, market research,
and analyst insights can be time-consuming and
cumbersome for wealth-management advisors to
sift through. To address this, Morgan Stanley is using
GPT-4 to power an internal chatbot that provides
instant access to any area of the archive. Jeff McMillan,
Head of Analytics, Data, and Innovation, adds: “You
essentially have [access to] the knowledge of the most
knowledgeable person in wealth management – instantly.
Think of it as having our chief investment strategist, chief
global economist, global equities strategist, and every other
analyst around the globe on call for every advisor, every
day. We believe that is a transformative capability for our
company.”2
Capgemini Research Institute 2023
15
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
“You essentially have [access to] the knowledge of the
most knowledgeable person in wealth management
– instantly. Think of it as having our chief investment
strategist, chief global economist, global equities
strategist, and every other analyst around the globe
on call for every advisor, every day. We believe that is a
transformative capability for our company.”
Jeff McMillan
Head of Analytics,
Data, and Innovation,
Morgan Stanley.
Capgemini Research Institute 2023
16
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The impact of Fig.6
Most executives agree that generative AI will augment knowledge work
generative AI on
the workforce
PERCENTAGE OF ORGANIZATIONS THAT AGREE WITH THE STATEMENTS
Generative AI has the potential to Generative AI will augment the roles of knowledge
70%
workers and reduce their workloads
transform work
Our consumer research on generative AI reveals that
most consumers (70 percent) believe it will make As generative AI algorithms begin to provide concepts
them more efficient at work and will free them from and initial designs, employees may shift from 69%
routine tasks to explore more strategic aspects of their traditional ideation and creation to review and refinement
jobs.3 Most executives concur with these consumer
sentiments, with 70 percent agreeing the technology
will allow organizations to widen the scope of the
roles of knowledge workers (see Figure 6). Over half
Generative AI will completely revolutionize the way we work 60%
(60 percent) also mentioned that generative AI would
completely revolutionize their way of working.
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
17
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
The rise of generative AI will create new roles 60%
In our current survey, 69 percent of executives believe generative AI will lead to the emergence of new roles. In
addition to prompt engineers, we may also see new roles such as AI auditors and AI ethicists emerge as the
believe that generative AI will completely
initiatives scale.
revolutionize the way we work
Fig.7
Most executives believe new roles will emerge from generative AI
Generative AI will demand upskilling
and training initiatives
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENT
As well as opening up new job roles and requirements,
as 68 percent of executives in our survey say will happen,
the integration of generative AI into the workforce will
require a significant investment in upskilling and cross-
skilling of talent. In April 2023, in response to growing
demand, Coursera, a large-scale US-based open online
69% Generative AI will lead to the course provider, launched multiple new generative AI
emergence of new job roles (e.g., prompt
training courses, including ChatGPT Teach-Out from the
engineer)
University of Michigan, which introduces learners to large
language models (LLMs) and chatbots and discusses
the ethical use of generative AI and how the technology
might be harnessed and regulated moving forward.4
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N=800 organizations.
Capgemini Research Institute 2023
18
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
02
ORGANIZATIONS SEE MORE GAIN
THAN PAIN IN GENERATIVE AI
Capgemini Research Institute 2023
19
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.8
Most executives across industries say that the benefits of generative AI outweigh potential risks
Most organizations believe
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENT BY SECTOR
the benefits of generative AI
outweigh the risks Average 74%
High tech 84%
Our survey reveals that the majority of executives (74
percent) believe the benefits that generative AI brings Aerospace and defense 82%
outweigh the associated risks. The executives most
strongly convinced that generative AI is a power for Pharma and healthcare 80%
good work within the high-tech sector (84 percent); even
Industrial manufacturing 77%
at the other end of the list, a substantial 69 percent of
executives within the energy and utilities and telecom Retail 76%
sectors would bet on generative AI (see Figure 8).
Financial services 74%
Consumer products 70%
74% Energy and utilities 69%
Telecom 69%
believe the benefits of generative AI Automotive 66%
outweigh the associated risks
The benefits of utilizing generative AI outweigh the associated risks
Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
20
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.9
Most executives say that generative AI will improve products/services and customer service
PERCENTAGE OF ORGANIZATIONS WHO AGREE WITH THE STATEMENTS
Anticipated benefits of
generative AI extend to
Generative AI will allow the design process to be
78% product design and
more efficient and streamlined
customer experience
Generative AI can enable us to create products and services
that are more accessible and inclusive, serving a wider 76%
range of customers with diverse needs and preferences Generative AI brings numerous transformative benefits
to organizations, including enhanced decision-making,
improved efficiency, personalized experiences, cost
Generative AI can enable us to create more
71% reductions, augmented innovation capacity, risk
interactive and engaging experiences for our customers
management, and predictive analytics. Most executives
in our survey (78 percent) believe that generative AI will
make product and service design more efficient and
Generative AI can be used to improve customer
service by providing automated and personalized support 67% that it will help them design more inclusive, accessible
products and services (76 percent). Seven in ten
executives believe generative AI will help them improve
Generative AI can improve internal operations the customer experience (see Figure 9).
65%
and enhance facility maintenance
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
21
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.10
Generative AI implementation is expected to yield operational and customer benefits
Executives are positive but EXPECTED FUTURE BENEFITS OF GENERATIVE AI IN THREE YEARS FROM TODAY,
AVERAGE % PROJECTED INCREASE
realistic in their expectations
of generative AI
Improved customer engagement and satisfaction
9%
(i.e., increase in Net Promoter Score)
We asked executives which organizational benefits they
expect to see from generative AI within three years.
Executives expect to see improvements of 7–9 percent
Increase in operational
across all industries (see Figure 10). Recent research from 9%
efficiency (e.g., improved quality)
Stanford and MIT on the applications of generative AI
in the workplace found that the productivity of tech-
support agents who used conversational scripts improved
as much as 14 percent at one organization,5 suggesting Increase in sales 8%
such an estimate is realistic, if not conservative.
Decrease in costs 7%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
22
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
• Customer engagement and skills in the Korean language using LLMs – machine
learning (ML) algorithms that can recognize,
satisfaction: Organizations can use generative
understand, predict, and generate human speech
AI for personalization; real-time insights; intelligent
based on huge text datasets.6
customer service; predictive analytics; continuous
improvement; and optimized customer journeys. • Operational efficiency: Organizations
These benefits ultimately lead to improved customer
are already reporting significant efficiencies from
engagement, satisfaction, and loyalty.
generative AI; German biotech firm Evotec announced
a phase-one clinical trial for a novel anti-cancer
KT telecom (South Korea’s leading mobile operator)
compound it developed with Exscientia, a UK
has built billion-parameter LLMs trained on the NVIDIA
organization that uses AI for small-molecule-drug
DGX SuperPOD platform and NeMo framework to
discovery. By using Exscientia’s Centaur Chemist AI
power smart speakers and customer call centers. Its
design platform, the organizations identified the
AI voice assistant, GiGA Genie, can control TVs, offer
drug candidate in only eight months. For context, the
real-time traffic updates, and complete a range of
average traditional discovery process takes 4–5 years.7
other home-assistance tasks when prompted by voice
commands. It has developed advanced conversational
Capgemini Research Institute 2023
23
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
• Sales: By using generative AI to produce • Costs: By using generative AI to automate
personalized marketing, pricing optimization, demand processes, optimize resources, implement predictive
forecasting, improved customer experience, enhanced maintenance, optimize the supply chain, mitigate
sales support, and data-driven decision-making, risks, and improve decision-making, organizations
organizations can attract more customers, drive can achieve cost savings and enhance overall financial
life-long content-driven conversations, and boost performance.
conversions.
Germany-based Claudius Peters produces processing
In an attempt to increase its sales, Italian consumer- equipment for cement, coal, alumina, and gypsum
products organization Ferrero worked with brand plants. Working with technology partner Autodesk, it
20–60% designer Ogilvy Italy to customize jars for its popular used the Scrum project-management framework to
Nutella chocolate spread. Data scientists fed a reduce costs and product weights while shortening the
database of patterns and colors to a generative AI engineering process. The generative design produced
algorithm, which rapidly produced 7 million distinct components with a remarkable 20–60 percent weight
reduction in weight achieved through jar designs. These unique jars, branded as Nutella reduction while meeting performance requirements.
Unica, were sold all across Italy, reportedly selling out Additionally, the design served as a re-engineering
generative design by German-based
within a month. The design relied on the brand's highly template for conventional manufacturing, resulting
Claudius Peters recognizable lettering, around which other elements in a 30 percent lighter final design that lowered
were customized.8 component costs.9
Capgemini Research Institute 2023
24
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.11
Organizations are prioritizing dedicated generative AI teams
Four in 10 organizations have
CURRENT LEVEL OF INTEGRATION OF GENERATIVE AI INTO FUTURE
already established teams PRODUCT/SERVICE DEVELOPMENT PLANS
and budget for generative AI
3% We have already established a dedicated
In just a few months of the public getting to know 8% team and budget for its implementation
about the technology through the launch of ChatGPT in
November 2022, nearly all (97 percent) of organizations
in our survey have plans for generative AI. Our research We are looking at establishing a dedicated
40%
reveals that 40 percent of organizations have established team and budget for its implementation
dedicated teams and budgets for generative AI, while in this year
another half (49 percent) are contemplating doing the
same within 12 months. Only 8 percent of organizations
We have not yet developed a concrete
are yet to develop a firm strategy for integration, and
plan for integration
as little as 3 percent are currently unsure if or how they 49%
will integrate generative AI into their product- or service-
development plans (see Figure 11). We are currently unsure if or how we
will integrate generative AI into our
product/service development plans
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
25
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.12
High tech and retail show the strongest commitment to integrating generative AI
PERCENTAGE OF ORGANIZATIONS THAT HAVE ESTABLISHED A DEDICATED
TEAM AND BUDGET TO INTEGRATE GENERATIVE AI INTO FUTURE
The majority (74 percent) of executives in the high tech
PRODUCT/SERVICE DEVELOPMENT PLANS BY SECTOR sector say they have established dedicated teams and
budgets for generative AI. Over 60 percent of executives
Average 40% from retail and 52 percent of executives from aerospace
and defense say the same (see Figure 12). Within retail,
High tech 74% while only 3 percent of executives believed generative
AI to be disruptive to their industry (refer to Figure 4),
Retail 62%
62 percent of retail executives say their organization has
Aerospace and defense 52% established a dedicated team and budget. This suggests
that while the retail industry does not see this technology
Pharma and healthcare 42%
as a disruptor, organizations realize they will lose out if
Financial services 42% they fail to implement it.
Energy and utilities 39%
Telecom 36%
Automotive 30%
Consumer products 23%
Industrial manufacturing 19%
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations
Capgemini Research Institute 2023
26
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
40%
of organizations have already established
teams and budget for generative AI, while
another half (49 percent) are contemplating
doing the same within 12 months
Capgemini Research Institute 2023
27
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Governing Fig.13
Most organizations are working/prefer to work with developers and IT vendors for their generative AI initiatives
generative AI
PARTNERS THAT ORGANIZATIONS ARE ALREADY WORKING WITH/PREFER
TO WORK WITH TO DRIVE MORE VALUE FOR GENERATIVE AI INITIATIVES
Centralized funding for generative
AI initiatives is currently the favored Developers (e.g., OpenAI, Stability AI) 69%
model
Of the 40 percent of organizations in our survey (320 IT vendors/C&SI (consulting and system integrators) 66%
companies) that have a dedicated budget for generative
AI initiatives, 78 percent source it from their central
budget, 16 percent from their overall AI budget, and 6
Academic institutions 55%
percent from their IT/digital department.
Organizations expect to partner
Big tech (e.g., Microsoft, Google) 35%
with developers and IT vendors
The preferred partners for generative AI initiatives are
Peer companies 22%
developers (69 percent); IT vendors and consulting firms
(66 percent); academic institutions (55 percent); and big
tech (35 percent) (see Figure 13).
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
Capgemini Research Institute 2023
28
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
03
GENERATIVE AI PACKS THE MOST
PUNCH FOR IT, SALES, AND
MARKETING
Capgemini Research Institute 2023
29
HARNESSING THE VALUE OF GENERATIVE AI: TOP USE CASES ACROSS INDUSTRIES
Fig.14
67 percent of executives see the most potential for generative AI in the IT function
PERCENTAGE OF ORGANIZATIONS THAT SEE THE MOST POTENTIAL FOR
The greatest potential for GENERATIVE AI MODELS TO DRIVE INNOVATION AND CREATE VALUE FOR THEIR
ORGANIZATION ACROSS BUSINESS FUNCTIONS
generative AI lies in the IT
IT (e.g., driving innovation in other
function 67%
functions, testing and coding assistant)
Sales and customer service
54%
(e.g., optimizing support chatbots/self-service)
Nearly 70 percent of executives see generative AI
bringing the most potential value to IT within its role Marketing and communications 48%
(e.g., creating personalized marketing campaigns)
as an enabler for driving innovation across functions.
Over half (54 percent) also see generative AI driving Manufacturing (e.g., 3D modeling) 31%
innovation for sales and 48 percent for marketing and
Product design/research and development
communications (see Figure 14). (e.g., generating new design, faster drug discovery) 31%
Operations (e.g., optimizing supply chain) 26%
67%
Risk management (e.g., drafting
22%
and reviewing legal and regulatory documents)
Finance (e.g., processing invoices) 13%
of executives see generative AI bringing
Logistics (e.g., optimizing routes) 9%
the most potential value to IT within its
role as an enabler for driving innovation
Source: Capgemini Research Institute, Generative AI Executive Survey, April 2023, N = 800 organizations.
across functions
Question asked: In which business functions do you see the most potential for generative AI models to drive innovation and create
value for |
25 | capgemini | Generative_AI_for_Business_Operations_POV.pdf | Generative AI –
built for business
The disruptive power of GenAI
for business operations
Table of contents
GenAI – a fast-moving technology 03
Going beyond the hype 04
GenAI – context for business operations 06
Disrupting business operations with GenAI 08
Applying GenAI across key business areas 12
Innovating or reinventing – is one step at the time the right approach? 15
Critical considerations for implementing GenAI 17
Companionship on the road ahead 19
2 Generative AI – built for business
GenAI – a fast-moving
technology
In recent years, businesses have
been promised many revolutionary
technologies, ranging from blockchain
to redefine how we share data, non-
fungible tokens (NFT) to empower
digital asset ownership, and the
metaverse, which was supposed
to disrupt how we perceive what
constitutes the workplace.
Generative AI – or GenAI – is also
regarded as transformative. It’s
a technology that can handle
activities that until recently we
thought only humans could do, such
as brainstorming and generating
content.
But is it more than simply the latest
craze? In this paper, we’re going to
look at what it is, what it does, and
how it helps.
We’ll explore how it genuinely disrupts
operations in the main horizontal
business functions – and finally, we’ll
consider the key factors in a strategic,
enterprise-wide implementation.
This is a field that’s moving fast – and
as we’ll see, organizations need to
keep pace.
“Generative AI is a
96%
technology that can handle of 51%
of consumers
activities that until recently executives cite GenAI
are aware of the latest
as a hot topic of
we thought only humans
trends in GenAI
discussion
could do.”
Source: Harnessing the value of generative AI. Source: Why consumers love generative AI.
Capgemini Research Institute Capgemini Research Institute
3 Generative AI – built for business
Going beyond the hype
GenAI is a ground-breaking technology
that is part of a wider AI and data science
toolkit designed to analyze and replicate
the characteristics and patterns found
within large sets of data.
It can be used for a range of
applications, from creating text,
images, and videos in different styles to
generating tailored content.
And it enables automated business
systems to perform tasks previously
reserved exclusively for humans –
particularly those requiring creativity,
empathy, and experience (see Figure 1).
The technology can be conceived as
a highly skilled assistant or artist that
acts on requests or “prompts,” and
uses a broad scale of information
and experience gathered from open
data sources (such as the internet), as
well as from closed data sources and
experiences, such as those gleaned
from within the enterprise.
Like an artist who is inspired by events GenAI applications Examples
or environments and takes advantage
of styling experiments and available
Generating new text/reports,
tools, GenAI creates new ideas, summarizing and translating in to Open AI’s GPT-4, Google Palm 2,
Scribe, Claude
solutions, and content. multiple languages
Text
It’s worth noting that some GenAI tools
such as large language models (LLMs),
Generating new images/videos, Adobe Firefly, Stability AI,
which are used to power chat-based self- analyzing existing images/video Midjourney, Nvidia, Dell-E2,
service systems, do not possess their (e.g., video games, VR, animation) Synthesia, Runway ML
own knowledge, but augment their text Im ga eg ne es r & at v ioid neo
generation capabilities with patterns
Generating music and remixing,
found in supplied data sources.
speech synthesis, sound effects, Synthesia, Amazon Polly,
GenAI is not about replacing human voice conversation, audio Sonix.ai
creativity or skills, but is rather a means Audio enhancement
of enhancing or augmenting what
we do, carrying out tasks that are Generate human-like contextually
relevant text responses in OpenAI’s ChatGPT, Amazon Lex.
predefined and automated.
real-time to expand and improve Google Bard
customer service and advice
Chatbots
“GenAI is not about replacing
Enhanced search functions,
human creativity or skills, but adding language capabilities to Google Bard, Landing AI, Azure,
is rather a means of enhancing search e.g., retrieval augmented Facebook Liama 2, Perplexity AI
Search generation (RAG)
or augmenting what we do,
carrying out tasks that are
Figure 1. Generative AI applications across multiple formats
predefined and automated.”
Source: Capgemini Research Institute, Generative AI and the evolving role of marketing: A CMO’s Playbook, 2023
4 Generative AI – built for business
For business processes, this means Data access and data quality are key
the ability to offer new experiences and require investments to leverage
and more innovative services and operationally AI and GenAI but 74%
products, tailored to the specific large-scale implementation of GenAI of
needs and interests of customers and requires organizations to make three executives believe
augmented by data owned by an distinctive decisions: the benefits of GenAI
enterprise. outweigh the risks
• The strategic direction in which it will
play a part
The sudden rise of GenAI-enabled
products and services shows that
concepts previously regarded as • How to equip the workforce to take Source: Harnessing the value of generative AI.
advantage of it Capgemini Research Institute
futuristic are now growing in number
and scale, and are frequently becoming
• How to execute it iteratively and
a part of reinvented business processes
move towards scaled value.
or even of industry standards.
But, even with GenAI’s enormous “The sudden rise of GenAI-
Use cases include automating routine
tasks such as analyzing data hidden transformative potential, there are enabled products and services
areas of concern that need to be
within databases, automating answers shows that concepts
addressed, including consumer trust in
to client queries, and generating new
the technology, which can sometimes previously regarded as
multi-lingual training manuals.
be misplaced and leave people futuristic are becoming a part
vulnerable to threats in areas such as
More importantly, GenAI is not of reinvented business
security, privacy, and misinformation.
about making a business process
processes or even of industry
“cutting-edge,” but applying the next
generation of “smart” in a business Despite these potential downsides, standards.”
the impact of GenAI will clearly be
toolkit to improve client experience,
massive, maybe the most important
generate more value, and stay ahead
one in decades.
of the competition.
5 Generative AI – built for business
The context for
implementation
One of the most well-known Moreover, Generative AI facilitates the these domains, businesses can unlock
implementations of GenAI is, of creation of synthetic data for training unprecedented insights, drive innovation,
course, ChatGPT. However, a wide models, overcoming data scarcity issues. and achieve sustainable growth in an
range of other dedicated solutions increasingly competitive landscape.”
could provide even more efficient By harnessing Generative AI across
results depending on the specificities
and data ecosystem used for training.
Trust remains the first piece of the
puzzle to be addressed to avoid any
misunderstanding or even a complete
disconnection from reality.
How can GenAI transform business
operations? Here’s a brief overview:
“Generative AI presents a transformative
force across various business operations,
revolutionizing efficiency and
effectiveness.
In finance operations, it enables
predictive analytics for risk assessment,
fraud detection, and personalized
financial advice.
Supply chain operations benefit from
“
AI-driven demand forecasting, inventory
Capgemini’s Business Services has been at the
optimization, and real-time logistics
management, enhancing agility and forefront to leverage AI and GenAI to transform enterprise
reducing costs. process and drive significant efficiency improvements.
However, the value for the enterprise goes far beyond cost
Client operations leverage Generative
AI for personalized marketing savings. I strongly believe that through the use of these
campaigns, sentiment analysis, and new technologies we can unleash the power of data to
customer service automation, fostering
eliminate frictions, drive insights, and generate tangible
deeper engagement and loyalty.
business outcomes which impact our clients’ top and
HR operations are streamlined through bottom line.”
AI-powered recruitment processes,
talent management, and employee Oliver Pfeil
feedback analysis, facilitating better
CEO, Capgemini’s Business Services
decision-making and employee
satisfaction.
6 Generative AI – built for business
Good summary, don’t you think? In finance operations, it promises to
Oh, what a time to be alive in this brave
predict the unpredictable, like a crystal
new world of automation!”
This was not written by the authors ball that never fails to dazzle with its
of this paper, but was automatically inaccuracies.
While these two summaries may perhaps
generated with ChatGPT in less than
Supply chain operations? Ah yes, be a bit generic, they provide a fair
2 seconds! The original request was
because nothing says efficiency like and simple overview – and they were
simply this:
algorithms guessing wildly about produced very fast indeed.
demand while your shelves gather dust
“You are an expert in business
or overflow with excess inventory.
operations and intelligent
automation. Please generate a point Client operations? Let’s automate those
of view of 150 words on what are heartfelt customer interactions and
the capabilities of Generative AI to replace them with robotic responses that
transform business operations in the scream “we care... about cutting costs.” 51%
of consumers
fields of finance operations, supply
And HR operations, well, who needs are aware of the latest
chain operations, client operations
human judgment when you have trends in the GenAI space
and HR operations.”
algorithms to sift through resumes and
When the app was asked to perform churn out soulless hiring decisions?
the same task but with a sarcastic
tone of voice, the result was also Generative AI, the answer to all our Source: Why consumers love generative AI.
impressive: prayers – if those prayers involve Capgemini Research Institute
relinquishing control to glitchy
“Oh, Generative AI, the magical solution algorithms and praying for mercy from
to all our business woes! the inevitable mess they’ll make.
7 Generative AI – built for business
Disrupting business
operations with GenAI
Much of the excitement around GenAI Expected future benefits of generative AI in three years from today,
is the result of ChatGPT, which was average % projected increase
developed by OpenAI. It became hugely
popular because it enabled users
Improved customer engagement
to interact with it in an easy, natural
and satisfaction (i.e., increase in Net 9%
way, and to see the results of their
Promoter Score)
interactions with it almost immediately
– just as we’ve seen with the two
summaries above. It’s no surprise that
Increase in operational
business is exploring its potential. 9%
efficiency (e.q., improved quality)
In fact, 96% of organizations say GenAI
is on their boardroom agenda. Their
outlook is quite optimistic: executives Increase in sales 8%
predict productivity improvements of
7–9% resulting from GenAI adoption
in just the next three years, and about
one-fifth of executives surveyed
globally say it will significantly disrupt Decrease in costs 7%
their industries.
Indeed, there are some use cases
Figure 2. Expected future benefits of generative AI in three years from today, average
where the benefit potential is for
% projected increase
efficiency improvements of 60–80%
or more (see Figure 2). Source: Capgemini Research Institute, Generative AI Executive Summary, April 2023, N=800 organizations
7–9%
improvement in
productivity from GenAI
adoption in the next
three years
Source: Harnessing the value of generative AI.
Capgemini Research Institute
20%
of executives
say GenAI will
significantly disrupt
their industries
Source: Why consumers love generative AI.
Capgemini Research Institute
8 Generative AI – built for business
Consumer
expectations of
GenAI
According to a study conducted by the
Capgemini Research Institute in April
2023, over 40% of surveyed consumers
would like to see GenAI implemented
as a part of their interactions with
organizations – mainly as a part of
automating customer service (self-
service), AI-powered search and insights,
and new forms of content creation
across text, video, images and audio.
In the same report, 70% of consumers
say that GenAI tools such as ChatGPT
are becoming the new go-to when it
comes to seeking product or service
recommendations, replacing traditional
methods such as search.
There are three specific areas in
Innovative business
which clients and customers have
expectations. solutions with factual 40%
of consumers
proactiveness
would like to see GenAI
Enhanced service/product
implemented as a part
personalization and The rising awareness of GenAI among of their interactions
experience consumers also suggests that they with organizations
are increasingly looking for innovative
solutions that bring value to them. For
Clients today are not merely seeking Source: Why consumers love generative AI.
years, global businesses have been
new products or services with GenAI Capgemini Research Institute
talking about growing closer to clients
built in for its own sake. Rather, they
and becoming more proactive – not
are looking for more personalized
just to increase client satisfaction,
experiences tailored to their specific
but also to reduce the operating
context (location, time, socio-economic 70%
costs associated with solving ad-hoc
situation and personal needs) and of consumers
queries.
preferences. say that GenAI tools are
the new go-to for
GenAI opens new opportunities for
GenAI is a rising transformative tool product or service
businesses to reinvent their operating
that can provide these experiences on recommendations
procedures, products, and services.
demand by employing various case-
By taking advantage of the ability of
specific fine-tuned large foundation
AI-based systems to analyze large Source: Why consumers love generative AI.
models (LFM) connected to new or Capgemini Research Institute
quantities of unstructured data and
existing experiences.
act on identified patterns, businesses
can predict client needs and offer
Furthermore, the efficiencies delivered
solutions – even before the client “Clients are not merely seeking
by AI in the contact-focused part of the
business through AI-driven self-service realizes the need. new products or services with
experiences (contact center, marketing, GenAI built in for its own sake.
or on-demand products) ensure that This gives organizations that adopt
clients have both prompt and relevant GenAI opportunities not just to meet, Rather, they are looking for
responses available to them 24/7 – but to exceed, client expectations more personalized experiences
without the need to “wait for the next and position themselves as forward- tailored to their specific
available agent” that interrupts this thinking and client-centric leaders in
experience. their respective industries. context and preferences.”
1Generative AI in organizations, Capgemini (2023), https://www.capgemini.com/insights/research-library/generative-ai-in-organizations/
9 Generative AI – built for business
Trust through transparency
and responsibility
As businesses increasingly integrate
GenAI into their processes and
solutions, it is vital to maintain
transparency and responsibility –
especially in how client data is used to
make an automated decision.
Clients are more likely to trust such
automated services from a company
that not only fulfils legislative
requirements (such as the European
Union’s AI Act) but also is able to
demonstrate practical guardrails
and considerations such as ethical
AI (including the ethical sourcing of
data), respecting privacy and data
security, and also by being completely
transparent on how systems will be
updated in future.
This may mean not only ensuring the
technical transparency of GenAI-
based systems but also providing
business-related safeguards including
• “Happy to help. Here are step-by- from a fully manual process to the
a Code of Ethics for AI, which is what
step instructions on how to create option of an automated one, while
we have developed here at Capgemini.
your invoice in the XYZ Procurement still giving users the opportunity to
System” … followed by a long list gain the requisite knowledge for
Being more up-front with clients
of steps generated by AI retrieved themselves.
should raise their trust in GenAI-based
from the software manual. While
systems, and in effect build a more
the organization is significantly
satisfied and loyal customer base.
improving the search and learning
71%
experience of the employee, it’s still
Automating processes of executives
a fully manual process.
believe GenAI will
and improving enable them to create
The second scenario is derived from
more interactive
customer experience an automation ecosystem enhanced
experiences for their
with GenAI. Here, the response could
customers
be something like this:
GenAI shouldn’t be seen as a bolt-on.
It’s true transformative potential is
• “Happy to help. I’ll send you step-by-
realized if combined with automation Source: Harnessing the value of generative AI.
step instructions on how to create your
as well as with the organization’s data Capgemini Research Institute
invoice in the XYZ Procurement System
and its enterprise systems.
so you will know for the future. But
“As businesses increasingly
I can also walk you through it while you
Let’s consider two scenarios where in
try it out for yourself. Alternatively, I’m integrate GenAI into their
each case, a relatively new employee
happy to do it for you. Just drag and
is asking a digital business process processes and solutions, it is
drop the file to the chat window. In
assistant: “How do I raise an invoice in vital to maintain transparency
fact, I can even automate this process
the procurement system?”
for you for the next time.” and responsibility –
In the first scenario, the response especially in how client data is
This is a very different experience
is created by a standalone GenAI used to make an automated
for users, with a new level of value
implementation:
generated for the business – moving decision.”
10 Generative AI – built for business
With permission, the most advanced
automated implementation would
pull the relevant file from an inbound
“
email, automate the business
We’ve been
process, and send a notification to
the employee: “I have resolved this applying automation to
case for you, so you can focus on the make our services
client.”
radically more efficient
The key limitation of GenAI is for a while. With GenAI
obtaining a sufficient level of we’re taking the next
confidence in its results, the
step and reimagining all
knowledge base that is used to train
the model can’t be verified. Obviously, our services with an
the more data that can be obtained innovative and
on the required scope of work, the
responsible approach.”
more relevant and accurate the
results will be, but this isn’t always
Lalitha Kompella
a straightforward proposition,
especially in a business context. Head of the Analytics and
Intelligent Automation Practice,
One problem is knowing which data Capgemini’s Business Services
is necessary: if that’s unclear, the only
option is to gather, store and update
vast quantities that will never be used,
which is not only costly but also has
an impact on sustainability. Getting efficiency for basic processes the necessary data resources can be
the right balance between too much involving documents, slides, email, a challenge.
data and not enough for the individual and more with significant quality
needs of an enterprise can be a real improvements Whatever the approach, there will
challenge. be significant costs – either direct (to
• Innovating and creating value implement the solution) or indirect
By implementing intelligent process – developing services, products (cloud consumption for example) – and
automation into the core of its clients’ or even processes that were not there will also be too many temptingly
transformation journeys, Capgemini possible before. shiny targets to pursue.
has built the necessary foundation
needed to accelerate into its near Companies will of course want to Organizations will need to consolidate
future with GenAI. pursue both these opportunities, the full scope of possibilities for each
so they can lower their costs and domain of their activities and prioritize
Companies who initiated this data- optimize their time to market while the most relevant ones, considering
driven transformation with generating also generating new revenues. the sustainability implications and the
new insights based on data that expected business outcomes. Not that
is powered by automation and AI To do so, they can implement an off- simple, when the opportunities are
are currently the most advanced the-shelf solution, create their own almost limitless.
organizations accelerating with GenAI. customized model, or adopt a hybrid
approach. The first of these options will
be generic, but efficient enough and will
Improving the now certainly be cost effective, based on pre- “By implementing intelligent
trained models with global data, which is process automation into the
– and creating the
the case with ChatGPT.
core of its clients’
future
transformation journeys,
The bespoke option will generate
concrete outcomes specific to Capgemini has built the
There are two main types of activity
industry or market needs and will
necessary foundation needed
to which GenAI can be applied in the
be a distinctive and competitive
enterprise: to accelerate into its near
proposition, but it will need
a dedicated data ecosystem and future with GenAI.”
• Current daily tasks – GenAI can
specific models or LLMs – and as we’ve
optimize productivity and
seen, establishing and maintaining
11 Generative AI – built for business
Applying GenAI across
key business areas
We have analyzed several main
possibilities in four key business
areas: human resources, finance and
accounting, supply chain, and contact
centers – looking at the expected
impacts per use case.
Human resources
The introduction of GenAI in HR
is transforming every aspect of
moments that matter to employees
– from recruitment, through
development, to retirement.
Enhancing efficiency and precision
in recruitment processes by
utilizing AI-powered tools. This is not
a technological novelty and there
are many enterprise-grade systems
fulfilling this promise. But with
advances in GenAI, companies can
move swiftly through large volumes
of candidate profiles, identifying the
most suitable candidates based on
actual skills, experience, and cultural
fit, while providing a seamless and automating most routine tasks such
proactive experience to each. as year-end performance reporting,
60%
or boosting morale with individually of executives
Even the best candidates may have customized communications. say that GenAI would
learning and experience gaps that
completely revolutionize
need to be addressed to ensure they Enhancing engagement and well- their way of working
reach their potential, and GenAI will being by providing anonymized
identify these potential deficiencies. insights from employee feedback and
The enhanced recruitment process implementation recommendations,
will also look more appealing, digitally enabling HR teams to make data-driven
inclusive, and attractive to a more decisions that improve the working
70%
diverse pool of applicants. environment, directly impacting the
of consumers
satisfaction, productivity, and loyalty of
believe GenAI will
Tailoring the employee experience employees.
augment their roles and
by reinventing HR business
reduce their workloads
processes so they are specific to “Reinventing HR business
each employee’s career aspirations,
processes enables them to be
experience, and individual strengths
and needs. GenAI makes this tailored to each employee’s
a reality as part of augmented self- career aspirations, experience, Source: Harnessing the value of generative AI.
service for employees, providing Capgemini Research Institute
and individual strengths and
recommendations, creating bespoke
development content, proactively needs.”
12 Generative AI – built for business
Finance and accounting kinds of analysis support to inform their • Planning optimization – optimizing
strategic or operational level decisions. demand, supply, and inventory
Transforming the finance and GenAI will also enhance footnotes planning much more efficiently by
accounting function from a purely and comments sections in financial analyzing multiple data sources to
operational focus on delivering timely reports, making them more readable for propose new solutions and concrete
reports and transactional record stakeholders and third parties. decisions; simulating various scenarios
keeping to something of much more to provide intuitive and interactive
value. GenAI can serve the strategic Rethinking the management of risk recommendations; predicting lead
intelligence unit of the business by and compliance by providing advanced times for POs; improving production
improving the automation ratio of analytics and predictive capabilities and transit lead times; generating
data preparation and analysis tasks. with comprehensible simulations, summaries from dashboards and
explanations and recommendations – complex information; automatic
With its ability to understand not only detecting financial anomalies, benchmarking of equipment/materials,
documents, to generate but also aggregating information about and more
recommendations, and act as market trends, news and evolving
a proactive analytical assistant on regulations.
demand, it can support and enhance 69%
the work of specialists within This increases the organization’s of executives
dedicated functions. proactive ability to manage expectations believe generative AI
and safeguard financial health, while will lead to the
Automating F&A for accuracy reinforcing its transparency, integrity, emergence of new roles
and insight to improve business and reliability as a business partner.
processes beyond productivity, capacity,
and automation quick wins such as Supply chain 68%
document processing. This brings the of executives say
next level of precision and insight gained Globally, the supply chain will benefit the integration of GenAI will
from the contextual understanding of from GenAI by reducing working capital, require significant
emails, notes, and policies – thereby increasing automation at scale, and investment in up- and cross-
enhancing financial reporting, increasing revenue. skilling of talent
budgeting, forecasting, and analytical
commentary. Let’s focus on six main areas: Source: Harnessing the value of generative AI.
Capgemini Research Institute
By expanding the scope of automation,
• Master data management –
the business can not only gain deeper
automatic verification for duplicates; “GenAI can serve the strategic
insight into contextualized financial
merges of similar records; automatic
performance, but can also enable more intelligence unit of the business
extractions from complex documents;
persona-driven insights. relationships and dependencies by improving the automation
between entities; and more ratio of data preparation and
Why? Because analysts and CFOs will
require different levels and different analysis tasks.”
13 Generative AI – built for business
• Fulfillment – understanding
unstructured documents; enabling
users to participate in conversation-
based learning; identifying the
root cause of the delays/risks;
automating reports with multilingual
GenAI-powered conversational AI;
optimizing inventory management
and efficient order fulfilment at scale;
providing early warnings for erratic
order identification; and generating
automatic responses for query
resolution
• Sourcing/category management –
providing real-time market insights
from multiple platforms; generating
automatic recommendations
• Product lifecycle management –
automating data analysis and fuzzy
matching to achieve coherence and
quality; detecting anomalies with
automated quality control; recognizing
patterns and features
with efficient knowledge bases that All enquiries will be handled with
are specific to their conditions and speed and accuracy, but responses
• Procurement – quickly analyzing
treatments – just like a dedicated will also be personalized, unscripted,
complex business activities
specialist in a hospital. and in line with your operating
and predicting future market
procedures, policies, strategy, and
developments; unlocking unmatched
Redefining the customer center so it brand values.
insights and efficiency; assisting
becomes the client’s favorite part of
in supplier selection by evaluating
doing business with the organization Tailor customer engagement by
multiple factors (such as cost, quality,
by switching the focus from average anticipating customer needs and
reliability, and performance history);
handling time (AHT) to actionable net offering proactive solutions, ensuring
continuously monitoring supplier
promoter score (NPS). GenAI-powered that everyone feels understood
performance and flagging potential
solutions in contact centers can and valued for their business, while
issues before they arise, thereby
not only improve handling inbound maintaining standardization and
strengthening vendor relationships.
queries but automate the whole optimization of business processes on
process end-to-end in a self-service a global scale.
Contact centers
model, creating unparalleled client
experience along the way. By analyzing global patterns in
The customer ecosystem will be
communication and preferences,
completely reinvented with GenAI,
Advanced self-service systems GenAI can provide an unparalleled
providing new, dedicated, and highly
powered by LFMs can understand, capacity to foster deeper relationships
customized insights to every client via
respond, and trigger the automation and greater loyalty – and without
human avatars or augmented agents.
needed by clients with degrees of increasing operating costs.
precision, personalization and scale
Digital humans will be able to interact in
that are unmatched by humans –
any language, 24/7, reproducing human
making every interaction feel uniquely
elements such as tone of voice, body “The customer ecosystem will
tailored to the client context.
language, facial expressions, emotions,
be completely reinvented
and lifelike conversations to make
interaction more natural. Elevating customer Interactions with GenAI, providing new,
by giving the business a friendly
dedicated, and highly
face through a digital avatar that
For example, Capgemini created
provides multilingual, multi-channel, customized insights to every
a custom digital avatar solution for
context-driven emotion, and empathy,
a global life science company to client via human avatars or
regardless of when or how clients
support patients’ day to day needs, augmented agents..”
make contact.
14 Generative AI – built for business
Innovating or reinventing
– is one step at the time
the right approach?
When it comes to implementation,
the most important question is not
just about whether GenAI should
be treated as another technological
approach to business process
re-engineering, but rather about how
to realize its potential in reinventing
the very DNA of work.
GenAI capabilities shouldn’t be
considered as a series of isolated
decisions or small-scale automation
projects to address process
inefficiencies, but should rather be
seen as an opportunity to take step
back, holistically assess the value
that the business process should
create, and reinvent it by redefining
experiences from the ground up. only for efficiency or performance but
for top-line growth. 40%
Selecting the right use cases for GenAI of organizations
is crucial. It needs to be aligned to Moreover, immediate focus on have already established
organizational objectives and strategy, large-scale deployments from the teams and budget for GenAI
identifying areas where its application very beginning is essential to ensure
will make the most significant long-term business value, cost, and
Source: Harnessing the value of generative AI.
difference, both for the organization process controls. While it might be Capgemini Research Institute
and the process stakeholders, tempting to test the water with
internally and externally. smaller |
26 | capgemini | 2024_Capgemini_Invent_Benchmark_Report_AI_in_Energy_Trading(1).pdf | A RTIFICIA L INTE L L IG ENCE IN
ENERGY TRADING
A benchmark on how Artificial Intelligence is used among European Energy Traders
A study by Capgemini Invent, March 2024
Management Summary and Key Facts
We observe a 22% increase of perceived disruptiveness of AI in Energy Trading since 2021:
1
Study participants categorize AI as highly disruptive. That score increased significantly since our last survey conducted in
2021.
87% of participants are engaged in AI, up from 72% in 2021:
2
The majority of the surveyed energy trading companies is actively participating in AI. Nevertheless, participation differs
significantly between municipalities (72%) and pure energy tradingcompanies (100%).
Only 30% of participants show strong AI governance structure:
3
More than 50% of participants show significant AI capabilities according to our AI maturity matrix assessment, while only
around30% show strong AI governance.
More than 60% of 102 actually implemented use cases of our participants are Front Office related:
4 Across the different maturity clusters Trade Execution, Trade Capturing and Physical Operations represent more than
60% of all implemented use cases of the participants, whereas Middle Office and Back Office represent only ~17% of all
implementeduse cases.
Mature AI traders use “make” or “hybrid” systems for more than 90% of their use cases:
5
Beginners are highly reliant on buy solutions for AI applications with a 44% buy rate, while masters are much more reliant
on self-built or hybrid solutions (90%).
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 2
Agenda
01
Understanding AI’s role in Energy Trading
(pages 4-7)
02
Study methodology and participant insights
(pages 8-10)
03
Maturity assessment of Energy Trading companies
(pages 11-14)
04
Use case landscape in Energy Trading
(pages 15-17)
05
In-depth evaluation of use cases and their methodologies
(pages 18-20)
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 3
Trends on the energy market make trading more complex and
faster and are the foundation of enhanced AI considerations
1
GREENIFICATION DIGITALIZATION
The transition to cleaner and more sustainable energy sources
Digitalization of the overall energy value chain leads to
lead to new structured products and increased spot
increased automation and machine-to-machine
market relevance paired with increased short-term
interactions.
deal-counts.
2
CHANGING DEMAND BEHAVIOR ELECTRIFICATION AND E-MOBILITY
European energy
3 Smart meters, integrated decentralized
trends make Increased adoption of EVs and
renewable assets, dynamic pricing and
electricity-driven heating increases volatilities
flexibility requirements and values lead to trading more
and requires rapid data-driven decision
shifts and increased volatilities of demand complex than
making in trading and energy procurement.
behaviors of different customer segments. ever before
4
REGULATORY CHANGES AND POLICY SHIFTS DECENTRALIZATION & DEMOCRATIZATION
Regulatory changes to secure the integrity of energy The integration of scaled energy storage solutions and
5 markets and control and restrict market abuses changing balancing revenues allow for new business
impact the necessity of End-to-End data and models like aggregators and virtual power plants (VPPs)
and lead to complex orchestration requirements.
decision oversight.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 4
Participants view AI as more disruptive than in 2021 but still
have not reached “Plateau of productivity”
1 AI Disruption Score & Hype Cycle
Study participants seem to value AI as highly disruptive and
significantly higher than in our last survey conducted in 2021; from
10
5,4 to 6,6.
2 In general we observe that the peak of inflated expectations
e
r towards AI in Trading is left behind and focus is put on implementing
o
c
scalable and practical strucutures, processes and governance
S 6,6
n models.
o
i
t
p
3 u GenAI only represents a subelement of this study and can be
r
s 5,4 individually considered to be on a different part of the hype cycle
i
D
currently.
I
A
e
g
a
4 r
e
v
A
Capgemini AI in Energy
2021
1 2021 2024
5
Peak of inflated Plateau of
Innovation trigger Trough of disillusionment Slope of enlightenment
expectations productivity
Time
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 5
AI requires a nuanced definition and can be largely categorized
in two overarching methodologies
1
Artificial Intelligence (AI)
Machine Learning Deep Learning
2
• Empowering systems to automatically learn & improve • Transforming representation at one level into a
from experience without being explicitly programmed representation at a higher & more abstract level
• Employing algorithms to analyze data, identify patterns • Advantage in ability to process vast amounts of bigdata
& make informed predictions
3 Supervised Learning Unsupervised Learning Reinforcement Learning
• Processes unlabeled data to identify
• Trained on labeled datasets with known • Decision-making through trial and error
patterns or relationships
outcomes • It learns by receiving rewards or
• Does not rely on predefined outcomes
• Learns patterns and relationships penalties based on its actions
• Methods: Clustering & user segmentation
between inputs and outputs • Methods: Automated agents
4
• Methods: Linear regression & classification
Examples in Energy Trading:
• Uses historical data with labeled energy • Analyzes unlabeled data like market • Executestrades of energy assets based
prices & relevant features to predict behavior & consumption patterns to gain on market conditions, refining strategies
future prices insights over time through continuous feedback
5
AI provides powerful tools that can be strategically deployed in energy trading, unlocking lucrative opportunities
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 6
Machine Learning and Deep Learning methods offer a wide
tool set for AI use cases in Energy Trading
1
Tool Description
Ensemble learning method used for predicting Struggling with
Random Forests for Capturing nonlinear
energy prices by combining multiple decision overfitting on small
Price Prediction relationships
trees datasets
2 Efficient ensemble learning algorithm often Handling missing Challenging
Ensemble Learning
applied to optimize energy market predictions data & offering high interpretability of
with XGBoost
by combining multiple models predictive accuracy model
Modeling decision-making processes over time,
Accurate modeling
Markov Decision Comprehensive
making them suitable for optimizing energy
of transition
Processes (MDP) management
trading portfolios
3 portfolio approach probability required
Long Short-Term Part of Recurrent Neural Networks, effective in Modeling complex Struggling with
Memory (LSTM) capturing sequential dependencies for time patternsin energy abrupt changes in
Networks series forecasting in energy markets market trends market conditions
4 Transformer Models Capturing & handling Requiring large
Analyzing historical energy market data to predict
for Time Series global, long-range amount of data for
future trends and price movements
Forecasting dependencies in data effective training
Employing generative algorithms to simulate and Enhancing Requiring careful
GenAI propose diverse trading strategies based on adaptabilityto scrutiny and testing
5 historical market data dynamic markets before implementing
The AI toolset is vast and proves highly beneficial for numerous use cases within the realm of energy trading, addressing a wide
range of potentialchallenges.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 7
Our 2024 survey analyzed 22 Energy Trading companies in
Europe to identify trends and patterns in AI approaches
1
Company Type by Survey Year
22 Participants 22 Participants
The goal of this study is to identify the trends of AI adoption
2
within the energy trading industry enriched by a trend analysis
based on our last AI inEnergy TradingSurvey in2021.
8
9
3
7
Capgemini Invent surveyed 22 energy traders in Europe with a
8
focus on Central Europe.
4
7
5
Our guiding question is: What is the current and changed picture
2021 2024
of AI-maturity, relevant use case maturity, and technology Survey Year
adoption strategy in the Central European energy trading
5 Fully integrated energy company
industry?
Municipal utility company
Pure energy trading company
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 8
Throughout all company types AI participation in the Energy
Trading industry is high and increased from 73% to 87%
1 87
%
AI Participation Rate in Energy Trading
AI participation rate (current and planned implementation), group averages, %
of energy trading organizations participate in AI
2
100
PURE ENERGY TRADING COMPANIES: With a 100%
90
87 88 adoption rate in this year’s survey pure energy trading
companiesstandoutintheAIadoptiondegree.
3 73 72
70 FULLY INTEGRATED ENERGY COMPANIES: 9 out of 10
fully integrated energy companies use AI in their trading
operations. 3 years after our first survey fully integrated
energy companies have the same adoption rate as pure
50
energytradersin2021.
4
MUNICIPAL UTILITY COMPANIES: Municipal utility
companies continue to represent the lowest degree of AI
adoption. With an almost 50% increase municipal
utilities witnessed the relatively spoken biggest increase
ofAIadoption acrossallsegments.
5
All Respondents Fully integrated energy Municipal utility Pure energy trading
companies companies companies
2021 2024
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 9
Perceiving AI as a competitive advantage is highly correlated
with the AI understanding in the surveyed companies
1
High perceived AI understanding
significantly influences the energy
Organization’s Self-Rated AI Understanding vs. AI Competitiveness
trader's competitive edge.
10
Unlocking AI competitiveness through
2
understanding
9
8 In our survey, a compelling correlation emerges:
Perceiving AI as a competitive advantage is highly
7 correlated with the AI understanding in the surveyed
s
s
e companies. This relationship underscores the pivotal
3 n 6
v roleofAILiteracy inbolsteringmarketadvantage.
i
t
i
t 5
e
To gain a competitive advantage, enhancing AI
p
m
understanding or AI Literacy is vital. This often stems
o 4
c from hands-on experience with AI use cases. Notably,
I
A companies excelling in perceived AI understanding have
4 3
alreadycapitalized onthesepracticalapplications.
2
1
0
5
0 1 2 3 4 5 6 7 8 9 10
AI understanding
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 10
More than 50% of participants have built up significant AI
capabilities, while less than 30% show strong AI governance
AI Maturity Matrix (AIMM)
1 Company Type
%
0 EXPLORER
0
1
4 MASTER S Integrated
t
r
o
n Trader
g
2
c Municipal
“ r
o
2 pa utilities
r a
r
e b
d i
n il Attitude
a t
y l ia ei
t i r T s “AI disruptive”
3 l „
i
b
a “AI not disruptive”
p BEGINNER
a
MANAGER
C
3
Trading
4 “Power trader”
(10.000
transactions
NO ACTIVITY & prop. trading)
1 Strong governance
Company cluster
5
Organizational structure: „Rules before action“
5
1 Cluster 1 to 5
Governance
0% 100%
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 11
Based on the AI governance and AI capabilities 4 different
maturity groups can be differentiated
1
AI Maturity Matrix BEGINNER –What’s in it for me?
“Beginners”arejustgettingataste of things,hardlyusingany formofAI.Theyhavearelatively low
level of governance structures, organize AI in a largely decentralized manner, mostly do not employ
AI experts, and are implementing their first AI projects, which are usually intended to prove the
EXPLORER MASTER
viability of AI. With their first projects, they gain initial experience and prepare the organization for
furthersteps.
2 y
t
i EXPLORER –Trial and error.
l
i
b
“Explorers” are feeling their way forward. They have a relatively low level of governance
a
p a BEGINNER MANAGER s e g structures, organize AI in a largely decentralized manner, employ only a few AI experts, and have
C
a initial scaled AI projects that represent isolated organizational solutions. With their projects, they
t
S
continue to expand their know-how in specific domains and thus increase personal skills and
y
3 r a organizationallearning.
Governance i d
e MANAGER –Rules before action.
m
“Managers” rely on an organizational framework. They show a high degree of governance
r
e
t structures,usuallyorganizeAI inacentralunit,andmayalready havehiredAI experts.Onthisbasis,
n
No activity
I they planand develop thefirstAI projects. Witheachadditionalproject,structuresgrowfirst,before
experienceandknow-howcomeintoplay.
4
Capability MASTER –AI is in my DNA.
”AI Masters” know what they are doing. They show a high degree of governance structures,
How skilled are employees and how developed is organize AI in a central unit, employ experts, and engage in very mature AI projects that require a
the AI pipeline infrastructure? high level of organizational embedding. With their numerous and diversified use cases, they have
perfectedtheirexperienceandbuiltreliableprogrammingskills.
5 Governance
NO ACTIVITY –AI is nothing for me.
ThesecompanieshavenoAIinitiatives.OrganizationalstructuresremainunaffectedbyAIsofarand
How well is AI structured into the organization and
thecompaniesarenotbuildingupexperienceinthisarea.
progressing with a clear strategy?
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 12
In comparison to 2021, Explorers & Masters double while
a structural trend towards more governance can be observed
1
Maturity Cluster Evolution
Maturity Cluster Evolution from 2021 to 2024 Trend: 2024 vs. 2021 results
1
BEGINNERS
Experienced a substantial decline, as many companies have
+100%
2
begun to actively involve themselves with AI.
4
2
EXPLORERS
+100%
There has been a stronger focus on governance, as many
2
companies have already built a solid knowledge base.
3 y 3
t MANAGERS
i
l i Experienced a decline as they successfully advanced to
b
a master level, driven by the establishment of essential
p 3
a capabilities.
C 4
MASTERS
2024 1
4 Substantial increase as maturity advances within the
-20%
industry, leading to initial master-level entities.
5
-17%
5
NO ACTIVITY
-50%
Drastic decrease, since many companies have started
dealing with AI. The remaining are mostly municipal utilities.
5
Learn how Capgemini recommends to become an AI
Governance master on the next slides
2021
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 13
To ensure a capability-driven development we recommend a
“Use Case First” approach on the road to AI mastery
1 Road to AI Master What does this mean?
Capgemini recommends an N-shaped
In the pursuit of AI mastery, prioritize developing AI
path to AI mastery, to ensure a
capability-drivendevelopment. capabilities before establishing governance. This
2 acknowledges that creating governance structures often incurs
highercostsandsettingthemupwithoutclearneedscanresult
4
inunfitting frameworks.
2
For Beginners, skill enhancement begins by experimenting
with use cases. Prioritizing personal AI capabilities before
3 y institutionalizing governance, facilitates swift evaluation of
t
i l potential cases and clearer identification of high-value
i
b
opportunities.
a 3
p
a 1
C Explorers with advanced AI skills should concentrate on
establishing AI governance for their capabilities to yield
4
desired impacts. However, this process might temporarily slow
downusecasedevelopment.
Managers equipped with robust AI governance should
prioritize high-impact use cases, scaling them up to maximize
theirvalue.
5
Governance
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 14
Use case application differs widely between maturity clusters,
while Front Office represents the most active application area
Established Use Case Categories Popularity
1 Maturity Cluster Capgemini Interpretation
Trading Area Use Cases Beginner Explorer Manager Master
Automated Trading
1 Trade execution remains the most
Decision supporting
actively pursued use case across
Trade
Execution Trade timing optimization 1 differentmaturityclusters.
Algorithmic trading in financial markets (derivatives)
2
Algorithmic trading in short-term physical markets 2 Only Masters & Explorers venture
Price forecasting into the Middle- & Backoffice use
Financial Cash flow forecasting cases.
Forecasting Revenue and cost forecasting
Generation of custom-made financial plans and investment strategies 3 Explorers are heavily active in
physical operations, which can be
Information Extraction
3
Trade partially explained by the fact that
Automated trade capturing via voice-to-text recognition
Capturing 5 4
the majority are integrated energy
Automated trade capturing via text-to-text recognition
companies.
Predictive load forecasting
Physical
Scheduling and balancing optimization 3
Operations 4 Managers have the most
Automated nomination on a continuous real-time basis
concentrated/limited range of use
4
Anomaly detection
cases, focusing on trade execution,
Fraud detection
trade capturing & physical
Risk
Liquidity risk forecasting
Management operations.
Predictive credit scoring
Predicting risk assessment (market, price, operational, etc.) 2 5 Beginners experiment in all
Supply chain monitoring application areas and lack a common
5 Compliance
Trade Surveillance focusarea.
Automated Report Generation
Billing &
Intelligent and automated reconciliation
Settlement % of companies within
Intelligent invoice processing via Optical Character Recognition 0% 100%
maturity-cluster
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 15
All maturity clusters tend to focus and expand on known use
case areas in Front Office before extending into new areas
1
% of overall
Number of use cases per mariurity cluster & trading area
Front Office
use cases
Trade Execution 3 13 4 11 30,4%
2
Financial Forecasting 3 12 0 6 20,6%
Trade Capturing 2 5 4 5 15,7%
3
Physical Operations 5 9 3 0 16,7%
4 Risk Management 3 3 0 4 9,8%
Beginner
Compliance 2 0 0 2 3,9%
Explorer
5 Manager
Billing & Settlement 0 0 0 3 2,9%
Master
Back Office
It is a self-propellingsituation:Tradingareas inwhichuse cases are establishedare being further expanded!
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 16
Only beginners are strongly reliant on exclusive buy solutions,
whereas more mature participants use make or hybrid systems
1
EXPLORER MASTER
We have not only assessed the use cases but also
considered the decision between making or buying the
use case:
35,5%
2 42,9% 45,2% BEGINNERS
Beginners exhibit disproportionately high buy activities
58,1%
in all trading areas.
y
6,5%
t
i
l 11,9% EXPLORERS
3 i b
Explorersare planning use cases in nearly every trading
a
p BEGINNER MANAGER area; the make/buy decision is driven by use cases.
a
C
22,2% MANAGERS
4 33,3% 36,4% Managers focus on a few specific trading areas and use
45,5%
cases due to a higher emphasis on governance; the
make/buy decision is driven by use cases.
Exclusively Make
44,4% Exclusively Buy MASTERS
18,2%
Masters tackle challenging Middle- & Backoffice use
Make and Buy
5
cases and seek assistance when needed.
Governance
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 17
The study shows that every maturity cluster has a different
recommended next use case
1
Value Add when Implemented
Maturity
Next Use Case Top Benefit Top Cost Reduction Interpretation
cluster
Top recommended use case for each Top benefits and cost reduction based on responses concerning These recommendations, rooted in the survey
2 maturity cluster existing use cases insights, guide toward strategic success
• Enhanced decision- • Resource optimization In AI adoption, novices explore proven price
No Activity Price forecasting making • Operational efficiency forecasting for its widespread use and simple
• Risk mitigation implementationwithexternalexpertise.
3
• Optimized liquidity • Process efficiency and error No Beginner has dealt with automated trading
Beginner Trade Execution
management reduction →Closegaptoexplorer,easytoimplement.
Explorers prioritize building governance,
No use case recommendation, main goal:
Explorer ensuring scalable deployment of diverse use
4 Focus on Governance
cases.
• Enhanced decision- • Resource optimization Managers enhance governance to fill the gap in
Financial forecasting
Manager making • Operational efficiency financial forecasting, crafting resilient
& Trade Execution
• Risk mitigation strategies.
5
Masters innovate in Middle- and Backoffice
• Early risk detection • Automated monitoring
edge cases and gain a distinctive market
Master Trade Surveillance
• Improved compliance • Labor cost savings
advantage.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 18
Capgemini’s expertise: Understanding top use cases and
offering qualified implementation recommendations
1
Use Case Assumption Methodical Implementation Effort Score Interpretation
2
• Historical data available • Precise predictions to enhance
• Linear regression
Price Forecasting • Adequate computing resources trading decisions
• Neural networks with ensemble
• … • …
learning
• Detailed financial records • Accurate insights for optimized
3 • Time series analysis
Cash flow forecasting • Adequate computing resources financial planning (liquidity etc.)
• Neural networks with ensemble
• … • …
learning
• Real-time market data • Automated trading for structured
Algorithmic trading in • Moving averages
• High-speed trading systems and faster trading activities
4 financial markets • … • Reinforcement learning • …
• Structured data sources • Extracting valuable insights
• Natural language processing
Information Extraction • Adequate data processing tools from textual data
• Transformer networks
• … • …
5
• Comprehensive risk factors • Improved risk assessment for
• Decision trees
Risk Prediction • Statistical modeling skills informed decisions
• Random forests
• … • …
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 19
Shaping the future: Each trader’s current AI maturity status
sets the stage for next focus areas
What’s next?
1
Use Cases First - Governance second
1
The N-shape approach shows that exploring use cases first and governance second is
2 the most efficient way towards AI mastery. AI applications seem to be self-propelling,
hence active measures to spread applications are required to create cross department
value.
3
Diversifying Beyond Front Office Use Cases
2
Beyond the market-centric applications, companies poised for progress should explore promising
Middle- & Backoffice use cases. Despite being seemingly distant from direct revenue generation,
these initiatives play an essential role regarding efficiency and insights. The challenge lies in aligning
BackOfficeoperationswiththeaccelerated paceofFrontOfficeactivities.
4
Anticipating the Future: A Vision for Traders in the Next 3 Years?
3
In the face of reduced human involvement, the main challenge for energy trading will be to enable
5 and upskill professionals – a “Trader 2.0” - a hybrid of a traditional Front-/Middle-/Backoffice
employee and a data scientist. This convergence aims to blend the strengths of the data and energy
tradingworldsforamoreadaptiveandproficientfuture.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 20
Empower your Energy Trading Skills: Connect with us to
master AI!
Torben Schuster Alexander Krüger Harmanvir Singh
Vice President Senior Manager Senior Consultant
Energy Transition & Utilities Data-driven Energy & Utilities AI Garage
Löffelstraße 46 Mainzer Landstraße 180 Deutzer Allee 4
70597 Stuttgart, Germany 60327 Frankfurt am Main, Germany 50679 Köln, Germany
Phone: +49 (0)151 4025 2143 Phone: +49 (0)151 1137 4087 Phone: +49 (0)151 277 292 89
E-Mail: [email protected] E-Mail: [email protected] E-Mail: [email protected]
Thomas Gebetsroither Khaled Khalil
Senior Director Manager Contributers:
Head of Data-driven Energy & Utilities Data-driven Energy & Utilities
Olof-Palme-Straße14 Potsdamer Platz 5 Dr. Markus Jahn – AI Capability Lead
81829 Munich, Germany 10785 Berlin, Germany
Tighe Clough
Phone: +49 (0)151 4025 1167 Phone: +49 (0)151 544 766 31 Finn Fromberg
E-Mail: [email protected] E-Mail: [email protected]
Lennard Knorr
© Capgemini Invent 2024. All rights reserved.
About Capgemini Invent
As the digital innovation, design and transformation brand of the Capgemini Group,
Capgemini Invent enables CxOs to envision and shape the future of their businesses.
Located in over 30 studios and more than 60 offices around the world, it comprises a
12,500+ strong team of strategists, data scientists, product and experience designers,
brand experts and technologists who develop new digital services, products, experiences
andbusinessmodelsforsustainablegrowth.
Capgemini Invent is an integral part of Capgemini, a global business and technology
transformationpartner,helpingorganizationstoacceleratetheirdualtransitiontoadigital
and sustainable world, while creating tangible impact for enterprises and society. It is a
responsibleanddiversegroupof340,000teammembersinmorethan50countries.With
itsstrongover 55-yearheritage, Capgeminiistrustedbyitsclientstounlockthevalue of
technology to address the entire breadth of their business needs. It delivers end-to-end
services and solutions leveraging strengths from strategy and design to engineering, all
fueled by its market leading capabilities in AI, cloud and data, combined with its deep
industry expertise and partner ecosystem. The Group reported 2023 global revenues of
€22.5billion.
Get The Future You Want |www.capgemini.com/invent
This presentation contains information that may be privileged or confidential
and is the property of the Capgemini Group.
Copyright © 2024 Capgemini. All rights reserved. |
27 | capgemini | 2024_Capgemini_Invent_Benchmark_Report_AI_in_Energy_Trading.pdf | A RTIFICIA L INTE L L IG ENCE IN
ENERGY TRADING
A benchmark on how Artificial Intelligence is used among European Energy Traders
A study by Capgemini Invent, March 2024
Management Summary and Key Facts
We observe a 22% increase of perceived disruptiveness of AI in Energy Trading since 2021:
1
Study participants categorize AI as highly disruptive. That score increased significantly since our last survey conducted in
2021.
87% of participants are engaged in AI, up from 72% in 2021:
2
The majority of the surveyed energy trading companies is actively participating in AI. Nevertheless, participation differs
significantly between municipalities (72%) and pure energy tradingcompanies (100%).
Only 30% of participants show strong AI governance structure:
3
More than 50% of participants show significant AI capabilities according to our AI maturity matrix assessment, while only
around30% show strong AI governance.
More than 60% of 102 actually implemented use cases of our participants are Front Office related:
4 Across the different maturity clusters Trade Execution, Trade Capturing and Physical Operations represent more than
60% of all implemented use cases of the participants, whereas Middle Office and Back Office represent only ~17% of all
implementeduse cases.
Mature AI traders use “make” or “hybrid” systems for more than 90% of their use cases:
5
Beginners are highly reliant on buy solutions for AI applications with a 44% buy rate, while masters are much more reliant
on self-built or hybrid solutions (90%).
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 2
Agenda
01
Understanding AI’s role in Energy Trading
(pages 4-7)
02
Study methodology and participant insights
(pages 8-10)
03
Maturity assessment of Energy Trading companies
(pages 11-14)
04
Use case landscape in Energy Trading
(pages 15-17)
05
In-depth evaluation of use cases and their methodologies
(pages 18-20)
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 3
Trends on the energy market make trading more complex and
faster and are the foundation of enhanced AI considerations
1
GREENIFICATION DIGITALIZATION
The transition to cleaner and more sustainable energy sources
Digitalization of the overall energy value chain leads to
lead to new structured products and increased spot
increased automation and machine-to-machine
market relevance paired with increased short-term
interactions.
deal-counts.
2
CHANGING DEMAND BEHAVIOR ELECTRIFICATION AND E-MOBILITY
European energy
3 Smart meters, integrated decentralized
trends make Increased adoption of EVs and
renewable assets, dynamic pricing and
electricity-driven heating increases volatilities
flexibility requirements and values lead to trading more
and requires rapid data-driven decision
shifts and increased volatilities of demand complex than
making in trading and energy procurement.
behaviors of different customer segments. ever before
4
REGULATORY CHANGES AND POLICY SHIFTS DECENTRALIZATION & DEMOCRATIZATION
Regulatory changes to secure the integrity of energy The integration of scaled energy storage solutions and
5 markets and control and restrict market abuses changing balancing revenues allow for new business
impact the necessity of End-to-End data and models like aggregators and virtual power plants (VPPs)
and lead to complex orchestration requirements.
decision oversight.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 4
Participants view AI as more disruptive than in 2021 but still
have not reached “Plateau of productivity”
1 AI Disruption Score & Hype Cycle
Study participants seem to value AI as highly disruptive and
significantly higher than in our last survey conducted in 2021; from
10
5,4 to 6,6.
2 In general we observe that the peak of inflated expectations
e
r towards AI in Trading is left behind and focus is put on implementing
o
c
scalable and practical strucutures, processes and governance
S 6,6
n models.
o
i
t
p
3 u GenAI only represents a subelement of this study and can be
r
s 5,4 individually considered to be on a different part of the hype cycle
i
D
currently.
I
A
e
g
a
4 r
e
v
A
Capgemini AI in Energy
2021
1 2021 2024
5
Peak of inflated Plateau of
Innovation trigger Trough of disillusionment Slope of enlightenment
expectations productivity
Time
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 5
AI requires a nuanced definition and can be largely categorized
in two overarching methodologies
1
Artificial Intelligence (AI)
Machine Learning Deep Learning
2
• Empowering systems to automatically learn & improve • Transforming representation at one level into a
from experience without being explicitly programmed representation at a higher & more abstract level
• Employing algorithms to analyze data, identify patterns • Advantage in ability to process vast amounts of bigdata
& make informed predictions
3 Supervised Learning Unsupervised Learning Reinforcement Learning
• Processes unlabeled data to identify
• Trained on labeled datasets with known • Decision-making through trial and error
patterns or relationships
outcomes • It learns by receiving rewards or
• Does not rely on predefined outcomes
• Learns patterns and relationships penalties based on its actions
• Methods: Clustering & user segmentation
between inputs and outputs • Methods: Automated agents
4
• Methods: Linear regression & classification
Examples in Energy Trading:
• Uses historical data with labeled energy • Analyzes unlabeled data like market • Executestrades of energy assets based
prices & relevant features to predict behavior & consumption patterns to gain on market conditions, refining strategies
future prices insights over time through continuous feedback
5
AI provides powerful tools that can be strategically deployed in energy trading, unlocking lucrative opportunities
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 6
Machine Learning and Deep Learning methods offer a wide
tool set for AI use cases in Energy Trading
1
Tool Description
Ensemble learning method used for predicting Struggling with
Random Forests for Capturing nonlinear
energy prices by combining multiple decision overfitting on small
Price Prediction relationships
trees datasets
2 Efficient ensemble learning algorithm often Handling missing Challenging
Ensemble Learning
applied to optimize energy market predictions data & offering high interpretability of
with XGBoost
by combining multiple models predictive accuracy model
Modeling decision-making processes over time,
Accurate modeling
Markov Decision Comprehensive
making them suitable for optimizing energy
of transition
Processes (MDP) management
trading portfolios
3 portfolio approach probability required
Long Short-Term Part of Recurrent Neural Networks, effective in Modeling complex Struggling with
Memory (LSTM) capturing sequential dependencies for time patternsin energy abrupt changes in
Networks series forecasting in energy markets market trends market conditions
4 Transformer Models Capturing & handling Requiring large
Analyzing historical energy market data to predict
for Time Series global, long-range amount of data for
future trends and price movements
Forecasting dependencies in data effective training
Employing generative algorithms to simulate and Enhancing Requiring careful
GenAI propose diverse trading strategies based on adaptabilityto scrutiny and testing
5 historical market data dynamic markets before implementing
The AI toolset is vast and proves highly beneficial for numerous use cases within the realm of energy trading, addressing a wide
range of potentialchallenges.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 7
Our 2024 survey analyzed 22 Energy Trading companies in
Europe to identify trends and patterns in AI approaches
1
Company Type by Survey Year
22 Participants 22 Participants
The goal of this study is to identify the trends of AI adoption
2
within the energy trading industry enriched by a trend analysis
based on our last AI inEnergy TradingSurvey in2021.
8
9
3
7
Capgemini Invent surveyed 22 energy traders in Europe with a
8
focus on Central Europe.
4
7
5
Our guiding question is: What is the current and changed picture
2021 2024
of AI-maturity, relevant use case maturity, and technology Survey Year
adoption strategy in the Central European energy trading
5 Fully integrated energy company
industry?
Municipal utility company
Pure energy trading company
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 8
Throughout all company types AI participation in the Energy
Trading industry is high and increased from 73% to 87%
1 87
%
AI Participation Rate in Energy Trading
AI participation rate (current and planned implementation), group averages, %
of energy trading organizations participate in AI
2
100
PURE ENERGY TRADING COMPANIES: With a 100%
90
87 88 adoption rate in this year’s survey pure energy trading
companiesstandoutintheAIadoptiondegree.
3 73 72
70 FULLY INTEGRATED ENERGY COMPANIES: 9 out of 10
fully integrated energy companies use AI in their trading
operations. 3 years after our first survey fully integrated
energy companies have the same adoption rate as pure
50
energytradersin2021.
4
MUNICIPAL UTILITY COMPANIES: Municipal utility
companies continue to represent the lowest degree of AI
adoption. With an almost 50% increase municipal
utilities witnessed the relatively spoken biggest increase
ofAIadoption acrossallsegments.
5
All Respondents Fully integrated energy Municipal utility Pure energy trading
companies companies companies
2021 2024
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 9
Perceiving AI as a competitive advantage is highly correlated
with the AI understanding in the surveyed companies
1
High perceived AI understanding
significantly influences the energy
Organization’s Self-Rated AI Understanding vs. AI Competitiveness
trader's competitive edge.
10
Unlocking AI competitiveness through
2
understanding
9
8 In our survey, a compelling correlation emerges:
Perceiving AI as a competitive advantage is highly
7 correlated with the AI understanding in the surveyed
s
s
e companies. This relationship underscores the pivotal
3 n 6
v roleofAILiteracy inbolsteringmarketadvantage.
i
t
i
t 5
e
To gain a competitive advantage, enhancing AI
p
m
understanding or AI Literacy is vital. This often stems
o 4
c from hands-on experience with AI use cases. Notably,
I
A companies excelling in perceived AI understanding have
4 3
alreadycapitalized onthesepracticalapplications.
2
1
0
5
0 1 2 3 4 5 6 7 8 9 10
AI understanding
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 10
More than 50% of participants have built up significant AI
capabilities, while less than 30% show strong AI governance
AI Maturity Matrix (AIMM)
1 Company Type
%
0 EXPLORER
0
1
4 MASTER S Integrated
t
r
o
n Trader
g
2
c Municipal
“ r
o
2 pa utilities
r a
r
e b
d i
n il Attitude
a t
y l ia ei
t i r T s “AI disruptive”
3 l „
i
b
a “AI not disruptive”
p BEGINNER
a
MANAGER
C
3
Trading
4 “Power trader”
(10.000
transactions
NO ACTIVITY & prop. trading)
1 Strong governance
Company cluster
5
Organizational structure: „Rules before action“
5
1 Cluster 1 to 5
Governance
0% 100%
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 11
Based on the AI governance and AI capabilities 4 different
maturity groups can be differentiated
1
AI Maturity Matrix BEGINNER –What’s in it for me?
“Beginners”arejustgettingataste of things,hardlyusingany formofAI.Theyhavearelatively low
level of governance structures, organize AI in a largely decentralized manner, mostly do not employ
AI experts, and are implementing their first AI projects, which are usually intended to prove the
EXPLORER MASTER
viability of AI. With their first projects, they gain initial experience and prepare the organization for
furthersteps.
2 y
t
i EXPLORER –Trial and error.
l
i
b
“Explorers” are feeling their way forward. They have a relatively low level of governance
a
p a BEGINNER MANAGER s e g structures, organize AI in a largely decentralized manner, employ only a few AI experts, and have
C
a initial scaled AI projects that represent isolated organizational solutions. With their projects, they
t
S
continue to expand their know-how in specific domains and thus increase personal skills and
y
3 r a organizationallearning.
Governance i d
e MANAGER –Rules before action.
m
“Managers” rely on an organizational framework. They show a high degree of governance
r
e
t structures,usuallyorganizeAI inacentralunit,andmayalready havehiredAI experts.Onthisbasis,
n
No activity
I they planand develop thefirstAI projects. Witheachadditionalproject,structuresgrowfirst,before
experienceandknow-howcomeintoplay.
4
Capability MASTER –AI is in my DNA.
”AI Masters” know what they are doing. They show a high degree of governance structures,
How skilled are employees and how developed is organize AI in a central unit, employ experts, and engage in very mature AI projects that require a
the AI pipeline infrastructure? high level of organizational embedding. With their numerous and diversified use cases, they have
perfectedtheirexperienceandbuiltreliableprogrammingskills.
5 Governance
NO ACTIVITY –AI is nothing for me.
ThesecompanieshavenoAIinitiatives.OrganizationalstructuresremainunaffectedbyAIsofarand
How well is AI structured into the organization and
thecompaniesarenotbuildingupexperienceinthisarea.
progressing with a clear strategy?
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 12
In comparison to 2021, Explorers & Masters double while
a structural trend towards more governance can be observed
1
Maturity Cluster Evolution
Maturity Cluster Evolution from 2021 to 2024 Trend: 2024 vs. 2021 results
1
BEGINNERS
Experienced a substantial decline, as many companies have
+100%
2
begun to actively involve themselves with AI.
4
2
EXPLORERS
+100%
There has been a stronger focus on governance, as many
2
companies have already built a solid knowledge base.
3 y 3
t MANAGERS
i
l i Experienced a decline as they successfully advanced to
b
a master level, driven by the establishment of essential
p 3
a capabilities.
C 4
MASTERS
2024 1
4 Substantial increase as maturity advances within the
-20%
industry, leading to initial master-level entities.
5
-17%
5
NO ACTIVITY
-50%
Drastic decrease, since many companies have started
dealing with AI. The remaining are mostly municipal utilities.
5
Learn how Capgemini recommends to become an AI
Governance master on the next slides
2021
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 13
To ensure a capability-driven development we recommend a
“Use Case First” approach on the road to AI mastery
1 Road to AI Master What does this mean?
Capgemini recommends an N-shaped
In the pursuit of AI mastery, prioritize developing AI
path to AI mastery, to ensure a
capability-drivendevelopment. capabilities before establishing governance. This
2 acknowledges that creating governance structures often incurs
highercostsandsettingthemupwithoutclearneedscanresult
4
inunfitting frameworks.
2
For Beginners, skill enhancement begins by experimenting
with use cases. Prioritizing personal AI capabilities before
3 y institutionalizing governance, facilitates swift evaluation of
t
i l potential cases and clearer identification of high-value
i
b
opportunities.
a 3
p
a 1
C Explorers with advanced AI skills should concentrate on
establishing AI governance for their capabilities to yield
4
desired impacts. However, this process might temporarily slow
downusecasedevelopment.
Managers equipped with robust AI governance should
prioritize high-impact use cases, scaling them up to maximize
theirvalue.
5
Governance
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 14
Use case application differs widely between maturity clusters,
while Front Office represents the most active application area
Established Use Case Categories Popularity
1 Maturity Cluster Capgemini Interpretation
Trading Area Use Cases Beginner Explorer Manager Master
Automated Trading
1 Trade execution remains the most
Decision supporting
actively pursued use case across
Trade
Execution Trade timing optimization 1 differentmaturityclusters.
Algorithmic trading in financial markets (derivatives)
2
Algorithmic trading in short-term physical markets 2 Only Masters & Explorers venture
Price forecasting into the Middle- & Backoffice use
Financial Cash flow forecasting cases.
Forecasting Revenue and cost forecasting
Generation of custom-made financial plans and investment strategies 3 Explorers are heavily active in
physical operations, which can be
Information Extraction
3
Trade partially explained by the fact that
Automated trade capturing via voice-to-text recognition
Capturing 5 4
the majority are integrated energy
Automated trade capturing via text-to-text recognition
companies.
Predictive load forecasting
Physical
Scheduling and balancing optimization 3
Operations 4 Managers have the most
Automated nomination on a continuous real-time basis
concentrated/limited range of use
4
Anomaly detection
cases, focusing on trade execution,
Fraud detection
trade capturing & physical
Risk
Liquidity risk forecasting
Management operations.
Predictive credit scoring
Predicting risk assessment (market, price, operational, etc.) 2 5 Beginners experiment in all
Supply chain monitoring application areas and lack a common
5 Compliance
Trade Surveillance focusarea.
Automated Report Generation
Billing &
Intelligent and automated reconciliation
Settlement % of companies within
Intelligent invoice processing via Optical Character Recognition 0% 100%
maturity-cluster
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 15
All maturity clusters tend to focus and expand on known use
case areas in Front Office before extending into new areas
1
% of overall
Number of use cases per mariurity cluster & trading area
Front Office
use cases
Trade Execution 3 13 4 11 30,4%
2
Financial Forecasting 3 12 0 6 20,6%
Trade Capturing 2 5 4 5 15,7%
3
Physical Operations 5 9 3 0 16,7%
4 Risk Management 3 3 0 4 9,8%
Beginner
Compliance 2 0 0 2 3,9%
Explorer
5 Manager
Billing & Settlement 0 0 0 3 2,9%
Master
Back Office
It is a self-propellingsituation:Tradingareas inwhichuse cases are establishedare being further expanded!
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 16
Only beginners are strongly reliant on exclusive buy solutions,
whereas more mature participants use make or hybrid systems
1
EXPLORER MASTER
We have not only assessed the use cases but also
considered the decision between making or buying the
use case:
35,5%
2 42,9% 45,2% BEGINNERS
Beginners exhibit disproportionately high buy activities
58,1%
in all trading areas.
y
6,5%
t
i
l 11,9% EXPLORERS
3 i b
Explorersare planning use cases in nearly every trading
a
p BEGINNER MANAGER area; the make/buy decision is driven by use cases.
a
C
22,2% MANAGERS
4 33,3% 36,4% Managers focus on a few specific trading areas and use
45,5%
cases due to a higher emphasis on governance; the
make/buy decision is driven by use cases.
Exclusively Make
44,4% Exclusively Buy MASTERS
18,2%
Masters tackle challenging Middle- & Backoffice use
Make and Buy
5
cases and seek assistance when needed.
Governance
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 17
The study shows that every maturity cluster has a different
recommended next use case
1
Value Add when Implemented
Maturity
Next Use Case Top Benefit Top Cost Reduction Interpretation
cluster
Top recommended use case for each Top benefits and cost reduction based on responses concerning These recommendations, rooted in the survey
2 maturity cluster existing use cases insights, guide toward strategic success
• Enhanced decision- • Resource optimization In AI adoption, novices explore proven price
No Activity Price forecasting making • Operational efficiency forecasting for its widespread use and simple
• Risk mitigation implementationwithexternalexpertise.
3
• Optimized liquidity • Process efficiency and error No Beginner has dealt with automated trading
Beginner Trade Execution
management reduction →Closegaptoexplorer,easytoimplement.
Explorers prioritize building governance,
No use case recommendation, main goal:
Explorer ensuring scalable deployment of diverse use
4 Focus on Governance
cases.
• Enhanced decision- • Resource optimization Managers enhance governance to fill the gap in
Financial forecasting
Manager making • Operational efficiency financial forecasting, crafting resilient
& Trade Execution
• Risk mitigation strategies.
5
Masters innovate in Middle- and Backoffice
• Early risk detection • Automated monitoring
edge cases and gain a distinctive market
Master Trade Surveillance
• Improved compliance • Labor cost savings
advantage.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 18
Capgemini’s expertise: Understanding top use cases and
offering qualified implementation recommendations
1
Use Case Assumption Methodical Implementation Effort Score Interpretation
2
• Historical data available • Precise predictions to enhance
• Linear regression
Price Forecasting • Adequate computing resources trading decisions
• Neural networks with ensemble
• … • …
learning
• Detailed financial records • Accurate insights for optimized
3 • Time series analysis
Cash flow forecasting • Adequate computing resources financial planning (liquidity etc.)
• Neural networks with ensemble
• … • …
learning
• Real-time market data • Automated trading for structured
Algorithmic trading in • Moving averages
• High-speed trading systems and faster trading activities
4 financial markets • … • Reinforcement learning • …
• Structured data sources • Extracting valuable insights
• Natural language processing
Information Extraction • Adequate data processing tools from textual data
• Transformer networks
• … • …
5
• Comprehensive risk factors • Improved risk assessment for
• Decision trees
Risk Prediction • Statistical modeling skills informed decisions
• Random forests
• … • …
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 19
Shaping the future: Each trader’s current AI maturity status
sets the stage for next focus areas
What’s next?
1
Use Cases First - Governance second
1
The N-shape approach shows that exploring use cases first and governance second is
2 the most efficient way towards AI mastery. AI applications seem to be self-propelling,
hence active measures to spread applications are required to create cross department
value.
3
Diversifying Beyond Front Office Use Cases
2
Beyond the market-centric applications, companies poised for progress should explore promising
Middle- & Backoffice use cases. Despite being seemingly distant from direct revenue generation,
these initiatives play an essential role regarding efficiency and insights. The challenge lies in aligning
BackOfficeoperationswiththeaccelerated paceofFrontOfficeactivities.
4
Anticipating the Future: A Vision for Traders in the Next 3 Years?
3
In the face of reduced human involvement, the main challenge for energy trading will be to enable
5 and upskill professionals – a “Trader 2.0” - a hybrid of a traditional Front-/Middle-/Backoffice
employee and a data scientist. This convergence aims to blend the strengths of the data and energy
tradingworldsforamoreadaptiveandproficientfuture.
Artificial Intelligence in Energy Trading 2024 © Capgemini Invent 2024. All rights reserved. 20
Empower your Energy Trading Skills: Connect with us to
master AI!
Torben Schuster Alexander Krüger Harmanvir Singh
Vice President Senior Manager Senior Consultant
Energy Transition & Utilities Data-driven Energy & Utilities AI Garage
Löffelstraße 46 Mainzer Landstraße 180 Deutzer Allee 4
70597 Stuttgart, Germany 60327 Frankfurt am Main, Germany 50679 Köln, Germany
Phone: +49 (0)151 4025 2143 Phone: +49 (0)151 1137 4087 Phone: +49 (0)151 277 292 89
E-Mail: [email protected] E-Mail: [email protected] E-Mail: [email protected]
Thomas Gebetsroither Khaled Khalil
Senior Director Manager Contributers:
Head of Data-driven Energy & Utilities Data-driven Energy & Utilities
Olof-Palme-Straße14 Potsdamer Platz 5 Dr. Markus Jahn – AI Capability Lead
81829 Munich, Germany 10785 Berlin, Germany
Tighe Clough
Phone: +49 (0)151 4025 1167 Phone: +49 (0)151 544 766 31 Finn Fromberg
E-Mail: [email protected] E-Mail: [email protected]
Lennard Knorr
© Capgemini Invent 2024. All rights reserved.
About Capgemini Invent
As the digital innovation, design and transformation brand of the Capgemini Group,
Capgemini Invent enables CxOs to envision and shape the future of their businesses.
Located in over 30 studios and more than 60 offices around the world, it comprises a
12,500+ strong team of strategists, data scientists, product and experience designers,
brand experts and technologists who develop new digital services, products, experiences
andbusinessmodelsforsustainablegrowth.
Capgemini Invent is an integral part of Capgemini, a global business and technology
transformationpartner,helpingorganizationstoacceleratetheirdualtransitiontoadigital
and sustainable world, while creating tangible impact for enterprises and society. It is a
responsibleanddiversegroupof340,000teammembersinmorethan50countries.With
itsstrongover 55-yearheritage, Capgeminiistrustedbyitsclientstounlockthevalue of
technology to address the entire breadth of their business needs. It delivers end-to-end
services and solutions leveraging strengths from strategy and design to engineering, all
fueled by its market leading capabilities in AI, cloud and data, combined with its deep
industry expertise and partner ecosystem. The Group reported 2023 global revenues of
€22.5billion.
Get The Future You Want |www.capgemini.com/invent
This presentation contains information that may be privileged or confidential
and is the property of the Capgemini Group.
Copyright © 2024 Capgemini. All rights reserved. |
28 | capgemini | C3-AI-Capgemini-Alliance-Press-Release_Final-1.pdf | C3 AI and Capgemini Extend Partnership to Accelerate Enterprise AI
for Business Transformation
AI-powered solutions to drive operational excellence across diverse industries
REDWOOD CITY, Calif. — November 20, 2024 — C3 AI (NYSE: AI), the Enterprise AI
software application company, and Capgemini, a global leader in business and
technology transformation, today announced an expansion of their partnership. This
partnership is designed to accelerate and enhance the delivery of Enterprise AI solutions
across industries to help clients realize significant benefits including improved efficiency,
productivity, and cost reduction.
This partnership combines the power of C3 AI’s Enterprise AI applications with
Capgemini’s deep industry expertise and proven global implementation capabilities and
capacity. Together, the two companies will deliver Enterprise AI solutions tailored to
specific industries including life sciences, energy, utilities, government, banking, and
manufacturing. To drive this partnership extension, Capgemini will expand its dedicated
C3 AI global practice, focused on delivering Enterprise AI solutions to joint clients across
industries at scale, with rapid time to value.
“AI is reshaping the way we work and business leaders across industries are focused on
leveraging its transformative potential. Our collaboration with Capgemini will empower
organizations to operate more efficiently, innovate faster, and gain a competitive edge
through Enterprise AI,” said Thomas M. Siebel, Chairman and CEO, C3 AI. “Our
partnership with Capgemini dramatically expands our service and delivery capacity,
ensuring the continued success of our growing customer base at global scale.”
Capgemini brings a proven track record in managing large-scale digital transformation
initiatives, helping organizations integrate cutting-edge technologies into their operations.
Together, Capgemini and C3 AI are already helping a number of joint clients realize
business value through improved efficiency for streamlined manufacturing.
“Our collaboration with C3 AI reflects a joint vision of enabling businesses to thrive in a
rapidly evolving digital landscape,” said Aiman Ezzat, CEO of Capgemini. “By combining
Capgemini’s transformation expertise with C3 AI’s world-class platform and applications,
we will help organizations across the globe to achieve operational resilience, accelerate
time-to-value, and stay ahead in their industries.”
###
About C3.ai, Inc.
C3 AI is the Enterprise AI application software company. C3 AI delivers a family of fully
integrated products including the C3 AI Platform, an end-to-end platform for developing,
deploying, and operating enterprise AI applications, C3 AI applications, a portfolio of
industry-specific SaaS enterprise AI applications that enable the digital transformation of
organizations globally, and C3 Generative AI, a suite of domain-specific generative AI
offerings for the enterprise.
C3 AI Public Relations
Edelman
Lisa Kennedy
415-914-8336
[email protected]
Investor Relations
[email protected]
About Capgemini
Capgemini is a global business and technology transformation partner, helping
organizations to accelerate their dual transition to a digital and sustainable world, while
creating tangible impact for enterprises and society. It is a responsible and diverse group
of 340,000 team members in more than 50 countries. With its strong over 55-year
heritage, Capgemini is trusted by its clients to unlock the value of technology to address
the entire breadth of their business needs. It delivers end-to-end services and solutions
leveraging strengths from strategy and design to engineering, all fueled by its market
leading capabilities in AI, cloud and data, combined with its deep industry expertise and
partner ecosystem. The Group reported 2023 global revenues of €22.5 billion.
Get The Future You Want | www.capgemini.com
Capgemini Media Relations
Mollie Mellows
Tel.: +44 (0)7342 709384
[email protected] |
29 | hbs_edu | download.aspx.pdf | Working Paper 25-021
Generative AI and the Nature of Work
Manuel Hoffmann
Sam Boysel
Frank Nagle
Sida Peng
Kevin Xu
Generative AI and the Nature of Work
Manuel Hoffmann
Harvard Business School
Sam Boysel
Harvard Business School
Frank Nagle
Harvard Business School
Sida Peng
Microsoft Corporation
Kevin Xu
GitHub Inc.
Working Paper 25-021
Copyright © 2024 by Manuel Hoffmann, Sam Boysel, Frank Nagle, Sida Peng, and Kevin Xu.
Working papers are in draft form. This working paper is distributed for purposes of comment and discussion only. It may
not be reproduced without permission of the copyright holder. Copies of working papers are available from the author.
Funding for this research was provided in part by Harvard Business School.
Generative AI and The Nature of Work
Manuel Hoffmann∗ Sam Boysel∗ Frank Nagle∗ Sida Peng† Kevin Xu∥
∗HarvardBusinessSchool,HarvardUniversity
†MicrosoftCorporation
∥GitHubInc.
This version: October 27, 2024
Abstract: Recent advances in artificial intelligence (AI) technology demonstrate considerable potential to
complementhumancapitalintensiveactivities. Whileanemergingliteraturedocumentswide-rangingpro-
ductivity effects of AI, relatively little attention has been paid to how AI might change the nature of work
itself. How do individuals, especially those in the knowledge economy, adjust how they work when they
start using AI? Using the setting of open source software, we study individual level effects that AI has on
task allocation. We exploit a natural experiment arising from the deployment of GitHub Copilot, a gener-
ative AI code completion tool for software developers. Leveraging millions of work activities over a two
year period, we use a program eligibility threshold to investigate the impact of AI technology on the task
allocationofsoftwaredeveloperswithinaquasi-experimentalregressiondiscontinuitydesign. Wefindthat
havingaccesstoCopilotinducessuchindividualstoshifttaskallocationtowardstheircoreworkofcoding
activitiesandawayfromnon-coreprojectmanagementactivities. Weidentifytwounderlyingmechanisms
drivingthisshift-anincreaseinautonomousratherthancollaborativework,andanincreaseinexploration
activitiesratherthanexploitation. Themain effectsaregreaterforindividualswithrelativelylowerability.
Overall,ourestimatespointtowardsalargepotentialforAItotransformworkprocessesandtopotentially
flattenorganizationalhierarchiesintheknowledgeeconomy.
JEL-Classification: H4,O3,J0
Keywords: GenerativeArtificialIntelligence,DigitalWork,OpenSourceSoftware,KnowledgeEconomy
Acknowledgement: TheauthorsaregratefulforfinancialandadministrativesupportfromGitHuband,inparticular,
forgenerousadvicefromPeterCihon. WethankShaneGreenstein,TimSimcoe,DavidAutor,andSamRansbotham
fortheirfeedback. Theauthorsarealsoindebtedforcommentsbyseminarparticipantsattheresearchseminarsfrom
theHarvardLaboratoryforInnovationScience,BostonUniversity,theMassachusettsInstituteofTechnology,andthe
University of Passau. We are further grateful for feedback from participants at the“Labor in the Age of Generative
AI”conferenceattheUniversityofChicago,theNBERSI2024DigitalEconomicsandArtificialIntelligenceinCam-
bridge,MA,the2024NBERProductivitySeminarinCambridge,MA,the2024AcademyofManagementSciencein
Chicago,IL,the22ndZEWEconomicsofICTconference,inMannheim, Germany,the20thSymposiumonStatis-
ticalChallengesinElectronicCommerceResearchinLisbon,Portugal,theACMCollectiveIntelligenceConference
in Boston, MA, the MIT Code Conference in Cambridge MA and the CESifo Area Conference on Economics of
Digitization2024inMunich,Germany.
Throughouthumanhistory,therehavebeenahandfuloftechnologicalinnovationsthatfundamen-
tallyshifthowtheeconomyworks. Theprintingpress,internalcombustionengine,andcomputers
are oft-cited examples of such general purpose technologies. Although artificial intelligence (AI)
has existed for some time, many have argued that recent advances may push it into this elite cate-
goryoftechnologiesthatalterthecourseofhistory(Crafts,2021;Goldfarb,Taska,andTeodoridis,
2023; Eloundou et al., 2024). If AI — broadly defined as the use of computers and machines to
mimic human intelligence –– is destined to have such a substantial impact, we are likely still at
thebeginningofthistechnologicalrevolutionthatisslowlyandsteadilyreachingallsectorsofthe
economy (Acemoglu et al., 2022). Importantly, the highest economic impact of AI is predicted
to be on productivity growth through the labor market, especially in knowledge intensive indus-
tries (Bughin and Manyika, 2018; Sachs, 2023). However, due to the novelty and breadth of AI,
researchisonlystartingtoelucidateitsimpactonthenatureofworkandtaskallocationinproduc-
tion settings. This is particularly true of generative AI (generative AI) — a subset of AI built on
large-language machine-learning models (LLMs) — which exploded on to the scene in 2022 and
currently represents the cutting-edge of AI. These models, including OpenAI’s GPT4, Google’s
Gemini,1 Meta’s LLaMa, and numerous others, are trained on massive, Internet-scale databases
and use billions of parameters to construct a probabilistic model that predicts what the next word
in an answer to a prompt from a user should be. These models can also be trained on datasets that
aremorefocusedonspecificcontexts—e.g.,health,finance,customerservice,softwaredevelop-
ment, etc. Whether and how these new technologies will shape the nature of work remain open
questions. Further, whether AI can be a complement to skilled workers (Autor, 2024) and help
address critical aspects of team production, especially in the context of distributed work, has gone
under-explored.
Although some early studies on generative AI have shown positive high-level productivity
impacts (Brynjolfsson, Li, and Raymond, 2023; Dohmke, Iansiti, and Richards, 2023; Noy and
Zhang, 2023; Peng et al., 2023), it is less clear what the mechanisms behind these improvements
1FormerlyknownasBard.
1
are. Does the use of generative AI shift users to focus on particular types of tasks that lead to
those productivity improvements? If so, which tasks? How exactly does the work process change
when using generative AI? To answer these questions, we develop a theoretical model that leads
to testable hypotheses that offer insights into where and why the most salient impacts are likely
to occur. Understanding these impacts informs labor strategy in a manner relevant to both firms
(Tamayo et al., 2023) and policymakers (U.S. Department of Labor, 2024), including hiring poli-
cies,worktrainingprograms,andupskillingorreskillingeffortsforcurrentemployees.
ThekeychallengeintestingourhypothesesandassessinghowAIchangesthenatureofwork
istoidentifyasettingwhere(1)workpatternsareobservableand(2)anAItoolspecificallytailored
for workers has been introduced in a quasi-exogenous manner. Our setting — the introduction of
GitHub Copilot, a software development generative AI tool, for key developers (known as main-
tainers) in open source software (OSS) projects — addresses both of these criteria. OSS source
code is publicly available and permissively licensed for use, modification, and redistribution. Fre-
quently developed by distributed teams of developers, OSS is a classic example of a product that
isproducedthroughthedistributedworkofteamsandisgenerallyfree(MoonandSproull,2002).
Although OSS creates societal value on the order of trillions of dollars (Hoffmann, Nagle, and
Zhou,2024)andisthereforeimportantinitsownright,weargueandprovidesuggestiveevidence
that the findings in this setting generalize to the broader set of work activities that occur in the
knowledge economy. Further, as with many team production settings, OSS also suffers from the
“linchpin” problem (Ballester, Calvo´-Armengol, and Zenou, 2006; Godin, 2010) as a small set
of developers are the driving force behind the widely used and incredibly valuable digital infras-
tructure that has come to underlie software development and the modern economy as a whole
(Eghbal, 2020; Geiger, Howard, and Irani, 2021; Hoffmann, Nagle, and Zhou, 2024). In practice,
an influx of non-experts enabled by decreasing communication costs (Altman, Nagle, and Tush-
man, 2015) creates an additional burden on developers, who must triage support requests, review
contributions, and otherwise manage their project’s growing community. Indeed, survey evidence
documentsthatthosemaintainerstendtobeoverburdenedwithtoolittleoftheirtimespentontheir
2
corework(coding)andtoomuchonmanagerial(projectmanagement)tasks(Nagleetal.,2020a).
With these factors in mind, interventions with the potential to relax constraints on key individuals
are of great interest to the distributed production setting of OSS and are likely to generalize to
numerousothersettingsasdistributedworkhasbecomeincreasinglycommon.
We exploit aspects of the general access launch of Github Copilot to the broader public in
June 2022 to establish causal effects of generative AI where some developers below a certain
threshold of an internal ranking received free access to the coding AI and others did not. We
start with a panel of 187,489 distinct developers observed weekly from July 2022 through July
2024, which results in millions of developer-week observations for Copilot usage and activity
levels in public GitHub repositories.2 Within the data set of top developers, we find that those
who receive free access to Copilot during the general access period increase their relative share of
coding tasks while reducing their relative share of project management activities. The dynamics
of the treatment effects are stable for our two year period. We dig further into the mechanisms
underlying these effects and find that they are driven by an increase in autonomous behavior (and
a related decrease in collaborative behavior) and an increase in exploration behavior (rather than
exploitation). Further, we find lower ability developers who receive access to AI increase coding
and reduce project management to a greater extent compared with their higher ability peers. The
results are robust to the standard regression discontinuity design tests and to different estimation
proceduressuchasdifference-in-differenceandmatching. Further,theresultsareconsistentwhen
considering whether developers are working on behalf of their employers or as volunteers, adding
support to the likelihood that these findings generalize beyond the OSS setting to a broader set of
workers.
Our results contribute to a growing literature on the productivity impacts of AI in important
ways. Early work in this area posits general productivity gains (Agrawal, Gans, and Goldfarb,
2019; Corrado, Haskel, and Jona-Lasinio, 2021; Raj and Seamans, 2018), but that the gains may
not be evenly distributed (Brynjolfsson, Rock, and Syverson, 2018; Furman and Seamans, 2019).
2AGitHubrepositoryisalocationwhereallaspectsofaprojectarestoredincludingitssourcecode,documentation,
andrevisionhistory.
3
Subsequent empirical work has largely confirmed these predictions and found wide-ranging pro-
ductivity benefits to using AI, at both the firm level (Czarnitzki, Ferna´ndez, and Rammer, 2023)
and the individual level (Fu¨gener et al., 2022). Particularly related to this study, research fo-
cused on Copilot specifically has either been conducted using a much smaller sample of workers
within firms (Cui et al., 2024) or relying on observational data without the benefit of knowing
precisely which contributors to OSS were given free access to Copilot (Yeverechyahu, Mayya,
and Oestreicher-Singer, 2024). Our work is consistent with this prior research but adds additional
nuance to the labor augmenting technical change literature (Acemoglu, 2003). By going beyond
productivity to explore how technology changes the nature of work, we provide one of the largest
natural experiments of generative AI and it’s impact on highly disaggregated measures of work
processes“inthewild”overatwoyeartimehorizon.
Our main findings identify changes in the nature of work of AI adopters in their knowledge
work processes. We show that when software developers leverage AI more, they reallocate their
efforts towards technical coding activities and away from auxiliary project management activities
that involve social interactions with other developers. This is a sign that the workers likely will
intensify their core contributions to public goods, such as open source software, when leverag-
ingskillaugmentingtechnologylikegenerativeAI.Itisalsoconsistentwithreducedcollaborative
frictionsduringtheproblemsolvingprocessofworkandachangeinthewayworkersinteractwith
eachotherontheplatform. WecomplementthecurrentliteraturethatleveragesITandconsultancy
chat support AIs and focuses on high-level productivity impacts through experimentation (Bryn-
jolfsson, Li, and Raymond, 2023; Dell’Acqua et al., 2023) by investigating the nature of work
through changes in work activities and human interaction processes over the two years following
theintroductionoftheprogrammingLLM.
Beyond the identification of causal effects that generative AI has on decentralized work, our
results suggest important implications for the future of OSS. OSS has received growing attention
(Lerner and Tirole, 2002) as it has become an increasingly critical part of the modern economy,
to the point where 96% of corporate codebases contain some open source code (Synopsys, 2023).
4
Further, recent studies estimate the value of OSS to be on the order of billions of dollars for
the supply side (Blind et al., 2021; Robbins et al., 2021) and trillions of dollars when account-
ing for usage (Hoffmann, Nagle, and Zhou, 2024). Additionally, firm usage of, and contribution
to, OSS has important implications for firm productivity (Nagle, 2018, 2019), firm competition
(Boysel,Hoffmann,andNagle,2024)andentrepreneurialactivity(Wright,Nagle,andGreenstein,
2023). However, despite the importance of OSS, many critical projects are under-resourced (Egh-
bal, 2020; Nagle et al., 2020b) as numerous firms free-ride on the efforts of others without giving
back (Lifshitz-Assaf and Nagle, 2021) leaving volunteer developers burnt out and overwhelmed
(Ramanetal.,2020). Asourresultsshow,generativeAImayofferasolutiontohelpaddressthese
concernsandallowtopdeveloperstomoreeasilycontributetothecommongoodbysolvingmore
issues. PriorresearchhasshownthatOSSdevelopersgenerallycontributetoOSSbecauseitgives
them a creative outlet and they do not want to spend their time on managerial tasks like security
and documentation (Nagle et al., 2020a). AI-powered tools may make it easier to quickly address
such managerial tasks, so developers can spend time in a manner they prefer, while still ensuring
thesecurity,stability,andusabilityofOSS.
The remainder of this paper proceeds as follows. Section 1 develops a model of the impact of
generative AI on individual workers leading to testable hypotheses. In Section 2, we discuss the
environment within which the study occurs. In Section 3 we characterize our dataset and discuss
the construction of our sample. We hone into the set of developers that obtain Copilot eligibility
for free via an internal ranking from GitHub and present our estimation strategy in Section 4. We
thenpresentourresultsusingaregressiondiscontinuitydesign(Section5)whilealsoexploringthe
mechanismsatplay,andofferingempiricalsupportforourhypotheses. Wediscussthelimitations,
implications, and a back-of-the-envelope calculation to understand how the results are likely to
generalizebeyondourempiricalsettinginSection6. Section7concludes.
5
1 Theoretical Framework
In the knowledge economy - which is an increasingly large sector of the overall economy -,
highly productive individuals can often become victims of their own success. A common pattern
relevanttoourstudyoccurswhenadeveloperdoesexceptionalcorework,theyareoftenassigned
more managerial work as a result. For example, in the context of academia, where research and
teaching are core work, the result of doing a good job on these is to get promoted and then to be
givenmoremanagerialtasksincludingdepartmentandschoolcommitteeassignments. Thiscanbe
summed up by tweaking the well-known phrase “The reward for good work is more work.” to be
“The reward for good core work is more managerial work.” This is particularly true in the context
of public goods which, as public good projects become more successful and more widely used,
new users request more from those that are creating the good.3 Thus, the introduction of an AI
tool that can help reduce some of this burden may play an important role in the creation of public
goods.
In the following section, we develop the exposition of our empirical setting by using a simple
economic framework where individual workers choose between two activities to maximize their
utility: core work c and project management m. Let the worker’s preferences u (·) be indexed by
θ
the parameter vector θ. In each period, each worker chooses c and m to solve the following static
utilitymaximizationproblem:
maximize u (c,m)
c,m θ
(1)
subjectto p c+p m ≤ ω
c m
where c,m ≥ 0 and p ,p > 0. The choice is constrained by relative costs of each activity,
c m
p = (p ,p ), and units of an endowment resource, ω.4 In line with simple economic models, we
c m
assumethatpreferencesaretime-invariantandthattherearenoexternalities.
3InourempiricalcontextofOSS,this“burden”ofbeinganopensourcedeveloper(Geerling,2022)hasbeencitedas
significantdriverofburnoutandabandonmentofopensourcedevelopment(Nagleetal.,2020a;Ramanetal.,2020).
Thus,alleviatingthisburdenisofcriticalimportance.
4Inoursetting,theresourceendowmentωcanbeinterpretedastheagent’s“taskbandwidth”theyareabletoallocate
acrossvariousworkactivities.
6
Toimproveourunderstandingoftheenvironmentthattheworkerisin,weassumeaconstant-
elasticityofsubstitution(CES)utilityfunction
(cid:16) (cid:17) σ
u θ(c,m) = β c1/σcσ− σ1 +β m1/σmσ− σ1 σ−1 (2)
where for θ = (σ,β ,β ), σ is the elasticity of substitution between c and m, and β ,β are CES
c m c m
share parameters. Without loss of generality, after normalizing p = 1, p becomes the relative
m c
cost of doing core work. Under the optimal choice of these two activities, the Marshallian de-
mands for core work and project management can be expressed as functions of these productivity,
preference,andendowmentparameters:
ωp−σ
c⋆ = c (3)
p1−σ + βm
c βc
ω
m⋆ = (4)
βc p1−σ +1
βm c
Consistent with prior literature (Acemoglu, Kong, and Restrepo, 2024), we choose to model
the intervention of generative AI as a reduction in the cost of core work, p . As such, the compar-
c
ative statics with respect to p are of interest. Details on the comparative statics for a change in
c
p can be found in Appendix D. A consequence of the CES demand system is that a reduction in
c
p increases the optimal level of core work under any value of the elasticity of substitution σ > 0.
c
Further empirical support for this relationship comes from prior literature in the field. Beyond AI,
automation and information systems technologies have been shown to complement skilled labor
and lead to a reshaping of organizational practices that allows workers to engage in more com-
plex and strategic activities (Autor, Levy, and Murnane, 2003; Orlikowski, 2007; Zammuto et al.,
2007). Further,whentechnologyreducesthecostoreffortassociatedwithcertaintasks,economic
and management theory suggests that workers will increase the amount of that task they perform
(Acemoglu and Restrepo, 2018; Bloom et al., 2014). As such, we arrive at the following primary
hypothesis:
7
Hypothesis1a(H1a) AftertheadoptionofanAItoolthatassistswithcoreworktasks,aworker’s
coreworktasksincreaseasapercentageofalltasks.
In contrast to the impact on core work tasks, the impact of generative AI on managerial tasks
is less clear and dependent on the elasticity of substitution σ. Adoption of the tool may lead to no
changeintheshareofprojectmanagementwhentheelasticityofsubstitutionσ = 1. Alternatively,
project management may drop when the price of core work drops given a σ > 1 (project manage-
ment is a substitute), or may increase when 0 < σ < 1 (project management is a complement).
This is consistent with prior literature that has shown that while automation and technology tend
toreducetheburdenofroutinetasks,theydonotnecessarilyeliminatemanagerialresponsibilities,
which may require human judgment, creativity, and interpersonal coordination (Autor, Levy, and
Murnane, 2003; Mintzberg, 1994). Consequently, even as AI can reduce the time spent on routine
tasks,workersmaystillengageinhigh-leveldecision-makingandteamleadership,leavingthenet
effectonmanagerialtasksuncertainandbestdeterminedempirically.
Hypothesis1b(H1b) AftertheadoptionofanAItoolthatassistswithcoreworktasks,thechange
toaworker’smanagerialtasksasapercentageofalltasksisambiguous.
We next seek to better understand the mechanisms that are driving these effects. What is the
effect of AI technology on task allocation across specific kinds of core work and project manage-
ment? To this end, we extend the baseline 2-good CES model into a nested CES model, under
which core work and project management are instead modeled as composites of more disaggre-
gatedgoods.
(cid:16) (cid:17) σ
u(c 1,c 2,m 1,m 2) = β c1/σu(c 1,c 2)σ− σ1 +β m1/σu(m 1,m 2)σ− σ1 σ−1 (5)
This allows us to further decompose composite goods into its components where u(c ,c ) and
1 2
u(m ,m ) are also CES functions similar to equation 2 but with their respective within-nest elas-
1 2
ticities of substitution σ and σ that correspond to relative substitution between disaggregated
c m
8
goods c , c and m , m respectively. Hence the nested CES extension to the baseline model per-
1 2 1 2
mits both more refined definitions of work patterns and richer substitution patterns between these
disaggregated goods. Details on the full nested CES model, as well as the comparative statics for
achangeinp canbefoundinAppendixD.
c
We use this model to consider two mechanisms through which the primary relationship oper-
ates. Inthefirstmechanism,weconsiderwhetherworkersengageinworkthatismoreautonomous
(less interaction with others working on the project) or more collaborative (more interaction with
others working on the project). Individuals can engage in either autonomous core work, c or col-
1
laborative core work, c or the managerial equivalents, m and m , We find that a reduction in
2 1 2
the cost of core work through AI, p can increase the demand of core work (as in Hypothesis 1a,
c
but it does not necessarily need to happen through both autonomous core work and collaborative
core work simultaneously. Indeed, assuming that the elasticity of substitution σ > 1 and that the
c
price of autonomous work is lower than the price of collaborative work,
pc1
< 1 implies that the
pc2
worker will shift their efforts towards autonomous core work and away from collaborative core
work since autonomous core work is less costly than collaborative core work. The same holds
true for managerial work such that σ > 1 and
pm1
< 1. While there are reasons to find the
m pm2
alternative parameter spaces,
pc1
> 1 (and
pm1
> 1) are credible, we find this restricted parameter
pc2 pm2
space with the pre-existing wedge of prices generally plausible in the context of workers that are
already working in a highly collaborative setting like the increasingly common paradigm of dis-
tributed work. We hypothesize that their main issues — collaborative frictions such as the cost of
coordination, requests from others to solve problems, or personal conflicts — may be more costly
thansolvingproblemsbythemselveswhentheyhaveAIasasubstituteavailableatanytime.
The predictions of the nested model extension can similarly be derived from the literature.
This mechanism builds on the idea that generative AI tools reduce (or even eliminate) much of
the cognitive and communicative friction inherent in distributed work, enabling workers to tackle
complex tasks autonomously. Prior research has shown that technologies that streamline commu-
nication and decision-making processes reduce the overhead of collaboration, freeing workers to
9
focusontheirownworkinisolation(Faraj,Jarvenpaa,andMajchrzak,2011;AralandVanAlstyne,
2011). However, with generative AI, many of these collaborative costs are simply eliminated as
work that previously required communication between multiple people can now be done without
any interaction at all. In the context of OSS, a quintessential example of distributed work and our
empiricalsetting,researchbyCrowstonetal.(2008)highlightstheimportanceofcollaborationand
coordination in distributed work, but also points out that tools that reduce coordination costs (or
circumventtheneedforcoordinationaltogether)canleadtoashifttowardindividual,autonomous
contributions. Hence,wehypothesize:
Hypothesis2(H2) A worker’s change in task allocation resulting from the introduction of an AI
toolisdrivenbyanincreasedfocusonautonomoustasksandadecreaseincollaborativeones.
The second mechanism we consider is whether workers that use AI alter their relative inten-
sity of exploration versus exploitation in task allocation. When the cost of core work falls, work-
ers may choose to increase their efforts in established projects or branch out into smaller, more
nascentprojects. InthenestedCESframework,wecandecomposebothcoreworkandmanagerial
workintotwocomponentswherec andm relatetoexperimentationwithnewcompetenciesand
1 1
projects(exploration)whilec andm relatetoengagingfurtherinpre-existingcompetenciesand
2 2
projects(exploitation). Thelogic,implications,andparameterspacearesimilartothosefromHy-
pothesis2andarenotrepeatedforbrevity. Toboundourpredictions,wemaketheassumptionthat
the cost of experimentation is smaller than the cost of exploitation, which likely holds true in the
context of distributed work given the complexities and interdependencies that persist in existing
projectsversusthosethatarestartingfromscratch.
The distinction between exploration and exploitation is central to organizational learning and
innovation theory, as first articulated by March (1991). Exploration involves searching for new
knowledge, competencies, and opportunities, while exploitation focuses on refining and optimiz-
ing existing capabilities. Prior research suggests that when the costs of experimentation decrease,
individuals and organizations tend to shift their focus toward exploratory activities (Benner and
10
Tushman, 2003; Levinthal and March, 1993). Further, research has shown that information tech-
nology investments, including digital tools, automate routine tasks and facilitate rapid feedback,
and thereby promote experimentation and flexibility in task allocation (Bresnahan, Brynjolfsson,
and Hitt, 2002; Zammuto et al., 2007). AI in particular has been shown to encourage “learning by
doing,” where individuals are more likely to engage in experimentation because AI tools provide
real-timefeedbackandhelpthemassessthefeasibilityofnewideasorprojects(Ransbothametal.,
2017). While exploitation remains essential, the newfound ease of exploration and experimenting
with new competencies and projects provided by AI tools makes the latter a more attractive and
feasiblefocusforworkers. Assuch,wehypothesize:
Hypothesis3(H3) A worker’s change in task allocation resulting from the introduction of an AI
toolisdrivenbyanincreasedfocusonexplorationactivitiesandadecreaseinexploitation.
To better understand who benefits most from the introduction of generative AI, a small ex-
tension of the baseline model (CES utility as in Equation 2) introduces heterogeneity by allowing
the response to a change in the relative cost of coding to vary by worker ability: σ = {σH,σL}.
We assume that a low ability worker has a relatively higher elasticity of substitution between core
worktasksandmanagerialtasksthanahighabilityworker: σH < σL.5 Thismodellingchoicecan
be motivated in different ways. On one hand, lower ability workers may stand to gain more from
generative AI technology. In particular, for generative AI to function best, the data it is trained on
must be of high-quality (Wladawsky-Berger, 2023). Indeed, for generative AI’s that are context
specific, the literature shows that input data filtered for higher quality leads to higher quality out-
put (Chen et al., 2021). Thus, when using generative AI, lower ability workers are able to receive
a bigger benefit than their higher ability peers (Brynjolfsson, Li, and Raymond, 2023). Alterna-
tively, variation in substitution by ability could arise if higher ability workers find core work and
project management relatively more complementary. Conversely, lower-ability workers may view
core and managerial tasks as substitutes rather than complements, as they may find it challenging
5Heterogeneitycouldalternativelybeintroducedintothisframeworkifforacommonelasticityofsubstitution,gen-
erative AI reduces the cost of core work more for lower ability workers. Fortunately, the difference between these
motivatingassumptionsisnotconsequentialforouridentificationstrategy.
11
to balance the demands of both. For these individuals, managerial tasks, which require multitask-
ing, coordination, discretion, and interpersonal communication (Finkelstein and Hambrick, 1990;
HambrickandFinkelstein,1987),candetractfromtheirabilitytofocusoncorework,thusmaking
them substitutes for each other. In this sense, lower ability workers can be considered “special-
ists”whilehigherabilityworkersaremorelikelytobe“generalists”. Technologicalinnovationhas
been shown to influence the composition of generalists and specialists in team production settings
(Teodoridis, 2018). In the context of the model extension, this assumption implies that as the cost
of core work drops, lower ability individuals will increase their proportion of activity that is core
workmorethanhigherabilityindividuals,leadingtothefollowinghypothesis:
Hypothesis4a(H4a) Aworker’slevelofabilitymoderatestherelationshipbetweentheadoption
ofanAItoolandtaskallocationsuchthatlowerabilityworkerswillincreasetheircoreworktasks
asapercentageofalltasksmorethanhigherabilityworkers.
Since the baseline effect of AI adoption on managerial tasks is ambiguous (Hypothesis 1b),
predicting the moderating effect of ability on managerial work is less clear. However, using a
similar reasoning to the discussion above, it is likely that the enhancement of the effect for lower
abilityworkersfoundinHypothesis4awillalsobeatplayinmanagerialwork. Thus,
Hypothesis4b(H4b) Aworker’slevelofabilitymoderatestherelationshipbetweentheadoption
of an AI tool and task allocation such that lower ability workers will have a larger effect on their
managerialtasksasapercentageofalltasksmorethanhigherabilityworkers.
2 Institutional Background
To test the hypotheses constructed above, we must find a setting where distributed work is
both common and where an individual’s engagement in distinct work tasks can be observed with
granularity. We find such a setting in the case of open source software, a quintessential example
of distributed work. Furthermore, to give a causal interpretation of any recovered effects, we need
12
a plausibly exogenous introduction of an AI tool that assists with core work. In particular, we
examine the GitHub platform, where the bulk of OSS activity takes place, and their roll-out of the
generativeAIsoftwaredevelopmenttoolCopilot.
2.1 The GitHub Platform
GitHub is the world’s largest hub for OSS development.6 Launched in 2008, it is a “social
coding” platform that offers cloud-based software development and version control services. Im-
portantly, it is specifically designed for dispersed teams to collaborate on software development
projects, and it chronicles all activities performed on the system to ensure any contributor can
observe all prior activity. Activity on the GitHub platform can therefore provide the researcher
unique and granular insights into patterns of distributed work, which are increasingly becoming
the norm in all areas of knowledge work. Furthermore, the platform allows us to observe the de-
centralized production of OSS as a public good. Although the details can be quite intricate, the
primaryworkflowofaGitHubcontributorisstraightforward.
A user who wants to start a new project creates a repository and then writes their code within
this repository.7 Alternatively, a user may “fork” another repository, which entails copying every-
thing from that repository into a new repository so it has the exact same information, but allows
the copier to take the project in a different direction than the primary repository. When the user
modifiesprojectcodeinalocalcopyoftherepositoryontheirmachine,thesechangestothecode-
base are condensed into a “commit” that attributes authorship to a user. Uploading these comm |
30 | hbs_edu | DeFreitas_20-_20Nature_20Human_20Behavior_20-_20Psychological_20Barriers_20to_20AI_b802852e-5cfb-4dca-8e68-d45af0b7d818.pdf | nature human behaviour
Perspective https://doi.org/10.1038/s41562-023-01734-2
Psychological factors underlying attitudes
toward AI tools
Received: 22 May 2023 Julian De Freitas 1 , Stuti Agarwal1, Bernd Schmitt2 & Nick Haslam 3
Accepted: 26 September 2023
What are the psychological factors driving attitudes toward artificial
Published online: 20 November 2023
intelligence (AI) tools, and how can resistance to AI systems be overcome
Check for updates
when they are beneficial? Here we first organize the main sources of
resistance into five main categories: opacity, emotionlessness, rigidity,
autonomy and group membership. We relate each of these barriers to
fundamental aspects of cognition, then cover empirical studies providing
correlational or causal evidence for how the barrier influences attitudes
toward AI tools. Second, we separate each of the five barriers into AI-related
and user-related factors, which is of practical relevance in developing
interventions towards the adoption of beneficial AI tools. Third, we highlight
potential risks arising from these well-intentioned interventions. Fourth,
we explain how the current Perspective applies to various stakeholders,
including how to approach interventions that carry known risks, and point
to outstanding questions for future work.
New technologies offer numerous benefits but may also have shortcom- the benefits of these tools outweigh the potential risks, as in forecasting
ings. Their success partially depends on whether people are willing to demand for products5, employee performance6 and medical diagnoses7.
adopt them. This is the case for all new products, although people tend The fact that such beneficial AI systems have not been readily adopted
to be particularly resistant to radically new technologies1–3. Meehl’s4 suggests that adoption depends not only on the technology’s objective
research was one of the early demonstrations of this resistance, showing benefits, but also on how it is subjectively perceived. Consequently,
that psychologists preferred to rely on human expertise over statisti- research has sought to determine the psychological factors driving
cal models of prediction, despite their higher accuracy compared to attitudes toward AI tools, and how to overcome AI resistance, so that
clinical expertise. user trust is calibrated to the system’s capabilities8.
Today, the radical technology is artificial intelligence (AI). Discus- In this nascent context, the current Perspective makes four con-
sions of a monolithic ‘AI’ can sometimes seem almost meaningless, tributions: first, we organize the sources of resistance to AI tools into
given that AI is present in many technologies, including robots, agents, five main categories: (1) opacity, (2) emotionlessness, (3) rigidity,
bots, recognition systems, recommendation systems, voice synthesiz- (4) autonomy and (5) group membership. For a visualization of AI-
ers and much more. AI, defined from a user’s perspective, includes and user-related barriers in these categories, see Table 2. We relate
algorithmic systems that people recognize as providing enhanced or each of the barriers to fundamental aspects of cognition, then cover
entirely new capabilities that have typically fallen within the domain of empirical studies providing correlational or causal evidence for how
human decision-making and action, such as visual and speech recogni- the barrier influences attitudes toward AI tools, while elaborating on
tion, reasoning, problem-solving, creative expression, navigation and causal evidence where possible. Second, we separate each of the five
interaction. For further definitional clarifications, see Box 1 and Table 1. barriers into AI-related and user-related factors, which is of practi-
cal relevance in developing interventions towards the adoption of
Psychological factors underlying attitudes beneficial AI tools. Third, we highlight potential risks arising from these
towards AI well-intentioned interventions. Fourth, we explain how the current
Although resistance to AI tools in favour of human action and Perspective applies to various stakeholders and point to outstanding
decision-making may be warranted in some contexts, in other contexts questions for future work.
1Marketing Unit, Harvard Business School, Boston, MA, USA. 2Marketing Division, Columbia Business School, New York, NY, USA. 3School of Psychological
Sciences, University of Melbourne, Parkville, Victoria, Australia. e-mail: [email protected]
Nature Human Behaviour | Volume 7 | November 2023 | 1845–1854 1845
Perspective https://doi.org/10.1038/s41562-023-01734-2
will preferentially use an opaque AI service when it is unambiguously
Box 1 superior in performance to a human decision-maker18, or more accurate
than a transparent AI service19.
Defining AI from the user’s
AI-related barriers and interventions
perspective Holding performance constant, however, people are less inclined to use
opaque AI tools than human decision-making20–23. Participants in one
study were shown one of two advertisements for a skin cancer detection
Automation of intelligence. Although traditional automation application23. One of the advertisements provided an explanation of
uses mechanisms, tools or software to automate repetitive tasks, how the AI tool worked (‘Our algorithm checks how similar skin moles
AI involves advanced algorithms to replicate or augment tasks are in shape/size/colour to cancerous moles’), whereas the other only
typically associated with human intelligence. described the AI tool’s function (‘Our algorithm checks if skin moles are
cancerous moles’). The researchers found that participants engaged
Digital and physical manifestations. AI can be purely digital, such more with the advertisement that provided an explanation, suggesting
as algorithms that process data, or physically embodied, such as that people are more likely to adopt AI tools that they understand23.
robots or self-driving cars. The digital or physical nature of AI could Not all accessible explanations of AI systems are equally effective at
influence user perceptions and interactions. improving attitudes towards AI24,25. In driving simulations, explanations
that describe ‘why’ the vehicle is behaving a certain way (for example,
User awareness and interaction. Although AI is used on the braking because there is an obstacle ahead) lead to more positive atti-
backend of many technologies, we emphasize AI systems for tudes towards the vehicle than explanations describing ‘how’ the vehicle
which users are directly or indirectly aware of their presence. This is behaving (for example, the car is braking)21. Different explanation
awareness can range from a general understanding that AI is at styles also matter. Contrastive explanations, which involve explaining
work (for example, in a recommendation system) to more specific why other related outcomes were ruled out (for example, explaining
knowledge about the underlying technology (for example, the use why a tumour classified as malignant is not a benign cyst), are rated as
of a particular type of neural network). more trustworthy than more general explanations (for example, saying
that the tumour is malignant and that most similar images are classified
Diverse underlying mechanisms. AI can be based on a multitude of the same)26. Thus, explanation interventions should focus both on why
algorithms and architectures. Some may be ‘opaque’ or ‘black box’, a given recommendation is made and why others are not.
in which the relationship between inputs and outputs is complex Finally, preferences for explainable AI depend on the stakes of the
and not easily understandable. Others might be more interpretable, decision. One study found that US and UK participants thought it was
with clear and intuitive mappings (also known as ‘transparent AI’ more important to understand an AI system when its outputs had high
or ‘white box’). The nature of the underlying AI could in principle stakes (for example, determining who receives vaccines for a deadly
influence user trust, understanding and acceptance. Given the variant of the flu) than low stakes (for example, who receives vaccines
enhanced requirements for automating feats of human intelligence, for a mild variant of the flu)19.
most AI entails opaque algorithms.
User-related barriers and interventions
Explainability and interpretability. Some AI systems offer explanations The preference for human decision-making over AI systems suggests
for their decisions. Because these explanations are generated by that people view human decision-making as more observable and
separate algorithms trained to generate rationales for the black-box AI understandable23. However, this perceived transparency is probably
behaviour, they are often approximations and may not fully capture the illusory, reflecting a belief that introspecting provides direct access into
intricacies of the black-box algorithm itself. The degree to which an AI how people make decisions27. Human decision-making is also opaque:
system is explainable can affect user trust and satisfaction. people often lack access to how they and others think, instead relying
on heuristics to understand human behaviour28,29. Work on medical
Variability in user perceptions. Recognizing that AI spans a vast AI finds that people prefer human healthcare providers over AI tools
array of technologies, user perceptions, interactions and attitudes in part because they overestimate how accurately and deeply they
could vary substantially. Factors influencing these perceptions understand providers’ medical decisions23,25.
could in principle include the AI’s form, function and design, as well Interventions that reduce differences in subjective understanding
as the context in which it is used. of decisions made by humans versus AI improve attitudes toward AI
tools. When participants in a study were asked to generate explanations
of how a human or AI tool solves a medical problem such as diagnosing
cancer from skin scans, they experienced greater reductions in subjec-
Opacity or AI as ‘black box’ tive understanding of the human than the AI tool, presumably because
In general, people are motivated to increase their environment’s pre- the difficulty in generating explanations alerted them to their illusory
dictability9 and apparent controllability10. They will seek out expla- subjective understanding of human decision-making23.
nations when they feel an outcome resulted without a coherent or
causal chain11,12, or when their expectations are violated13,14. Once people Risks of interventions
understand how something works they feel that it is more normal, More explainable AI does not always increase acceptance; it depends
predictable and reliable11,15, leading them to trust it more16. on how well features of the algorithm that are explained match the task
Because the mechanisms powering new technologies may initially at hand. One study found that whether people used the output gener-
seem opaque, their black-box nature may cause fear and distrust. This ated by an AI tool depended on the perceived appropriateness of its
concern is likely to be especially pronounced for AI tools, because complexity. If the explanation suggested that the AI tool was too simple
the inherent lack of access to and understanding of its algorithms for the task, then people were less likely to follow the recommendation
make it difficult to comprehend and predict its output17 (see Box 1 in the output. However, if the explanation suggested the AI system
for the distinction between transparency and explainability). Note, was too complex for its task, this did not affect whether they followed
this does not mean that people will never use opaque AI tools. People the recommendation5. This finding suggests that it is important to
Nature Human Behaviour | Volume 7 | November 2023 | 1845–1854 1846
Perspective https://doi.org/10.1038/s41562-023-01734-2
Table 1 | Glossary
Term Definition
Agent An entity that has the capacity to initiate actions.
AI aversion A preference for relying on human decision-making as opposed to decisions made by AI. Note: although this is the broad
definition used in recent research, algorithm aversion was initially defined more narrowly as the tendency to lose confidence
in algorithms faster than in humans after seeing them err102.
AI-related barriers Reasons for not using AI deriving from perceived features of the AI itself.
Anthropomorphism The ascription of human-like traits (for example, mental states or physical features) to real or imagined non-human entities.
Augmented decision-making Using AI to enhance human decision-making rather than replace it. This approach keeps the human in the loop while
leveraging AI to enhance the process and outcomes.
Autonomous AI Self-sufficient AI that can complete a task(s) without the product user’s behavioural input during operation, by learning and
adjusting to dynamic environments and evolving as the environment changes.
Edge cases Specific instances or situations that lie at the boundaries or extremes of a model’s training data or capabilities. These are
typically challenging for AI to handle, because they deviate from the typical patterns or data point that the AI encountered
during its training, leading to unexpected and erroneous AI behaviour.
Explainability in AI The ability to describe the rationale behind an AI system’s outputs in human-understandable terms. Does not require full
transparency into every aspect of the system, but aims to extract salient reasons for the AI’s behaviours.
General AI AI that performs at human levels across multiple domains.
Human-in-the-loop AI systems Artificial intelligence systems in which humans have an active role in the system operations, rather than the system operating
fully autonomously.
Illusion of explanatory depth The impression that one understands the world with far greater detail, coherence and depth than one really does103.
Individualism Cultural ethos that emphasizes the autonomy, needs and identity of the individual over the group.
Locus of control A psychological construct that assesses how much people think they can influence the outcomes of situations they
experience. Those with an internal locus of control have the perspective that they have agency and can impact events
through their own abilities, efforts and actions. By contrast, people with an external locus of control believe that external
circumstances, luck, fate or other people determine events in their lives.
Narrow AI AI that performs specific tasks in a limited domain.
Opacity Refers to the black-box nature of some AI systems, in which the internal workings of the system (for example, data or
algorithms) are invisible or unintelligible to humans.
Sense of control A person’s belief in their ability to influence events and outcomes in their life. The belief is linked to coping, persistence,
achievement, optimism and emotional well-being.
Superintelligent AI AI that consistently surpasses human performance on various tasks.
Transparency The degree to which the internal mechanics of a system (for example, AI or a person’s mind) are observable and
understandable by humans.
Uncanny valley Psychological phenomenon in robots and animation in which human replicas (for example, humanoid robots or
computer-animated characters) that appear almost, but not perfectly, human-like elicit feelings of unease or revulsion.
Unpredictability of AI The inability to accurately and consistently predict what specific actions AI will take to achieve its goals, even when we know
its goals.
Uniqueness neglect A concern that AI is less able than human decision-makers to take into account a person’s unique characteristics and
circumstances.
User-related barriers Reasons for not using AI deriving from actual or perceived features of oneself.
understand the expectations humans have before implementing an writing poetry36, composing music37, predicting which jokes a person
explanation intervention, to ensure that the explanation does not fall will find funny38 and predicting which songs will become hits39.
short of these expectations. If it would, it may be better to not provide it.
AI-related barriers and interventions
Emotionlessness or AI as ‘unfeeling’ Because cognitive abilities are associated with objective tasks (which
Driven by the need to understand and predict non-human entities and are quantifiable and measurable), and emotional abilities are associated
agents, people often use their own mental states and characteristics as a with subjective tasks (which are open to interpretation and based on
guide to reason about non-human entities, ascribing physical or mental personal opinion or intuition)40, people view AI tools as less capable of
capabilities to these entities. This phenomenon, known as anthropo- seemingly subjective tasks than objective ones33. Participants in one
morphism30,31, might be more likely for AI tools than other technologies study were shown advertisements for either dating advice (a subjec-
given their similarity to humans in output, motion, observable features tive task) or financial advice (an objective task) from either a human
and intelligence capabilities31,32. or AI tool. The advertisements click-through rate was higher when
Yet, people do not ascribe all human capabilities to AI tools. Many dating advice was coming from a human than an AI tool, whereas this
believe that such tools are not capable of experiencing emotions and difference did not occur for financial advice. One way to increase AI
performing tasks seen as relying on emotions33. In fact, AI systems can acceptance for tasks associated with emotional abilities is to frame
already perform a range of seemingly subjective tasks just as well as them in objective terms, such as informing people that dating advice is
or better than humans, including detecting emotion in facial expres- best accomplished by focusing on quantifiable data such as personal-
sions and tone of voice34, creating paintings that pass the Turing test35, ity test scores33.
Nature Human Behaviour | Volume 7 | November 2023 | 1845–1854 1847
Perspective https://doi.org/10.1038/s41562-023-01734-2
Table 2 | Factors influencing attitudes and behaviours toward AI tools
Factors Barriers Interventions Risks of interventions
Opacity: AI as a black Not understanding how AI works Use explainable AI Overly simple explanations cause
box Illusion of explanatory depth for humans Have users generate explanations aversion
Emotionlessness: Viewing AI as less capable of tasks requiring Anthropomorphize Anthropomorphizing AI where people
AI as unfeeling emotion Frame emotional tasks in objective prefer less human-like AI
Low individual tendency to anthropomorphize terms Over-ascription of abilities misleads
Use for utilitarian tasks
Use for embarrassing tasks
Rigidity: AI as inflexible Viewing AI as rigid and incapable of learning Provide information or labels Framing AI as too flexible may reduce
Belief that AI neglects one’s ‘unique’ traits suggesting AI can learn perceived predictability
High tendency to view oneself as unique Advertise AI as flexibly adapting to More flexible AI increases user latitude
Possibly, membership in an individualist culture unique preference and the chance of risky edge cases
Autonomy: AI as in Autonomous AI threatens sense of control Restore user control Automating meaningful or
control High internal locus of control Use predictable motion identity-relevant tasks
Meaning or identity from manual task Encourage nicknaming Compromising accuracy
Highlight other sources of meaning
Frame as enabling, not replacing
Group membership: Speciesism: treating AIs differently because of Convince users that humanoids can Ethical, economic and perceptual issues
AI as non-human markers suggesting they are not part of Homo have a human-like consciousness around accordance of AI rights
sapiens
High individual tendency to engage in speciesism
Possibly membership in cultures with less
panpsychist beliefs
People are also more resistant to AI tools in hedonic domains Rigidity or AI as ‘inflexible’
(characterized by experiential, emotional and sensory value) than People make mistakes, but they tend to believe that they are capable
utilitarian ones (characterized by factual, rational and logical value)41,42, of learning from them, rather than seeing the mistake as diagnostic
because they believe that hedonic recommendations require the ability of a permanent, unfixable flaw48. By contrast, people view AI tools as
to feel emotions and physical sensations43. Participants in one study rigid rather than flexible at learning, perhaps because, historically,
were asked to evaluate a hair mask treatment with either a hedonic machines have operated based on simpler, non-adaptive algorithms
goal in mind (to focus on the product’s indulgence, scent and spa-like that performed only narrow tasks. This perception might be especially
vibes) or a utilitarian goal (to focus on its practicality, objective per- likely for AI systems that perform more specialized tasks, such as image
formance and chemical composition). They were more likely to pick recognition, or for ones that require some amount of input by humans
an AI-recommended sample when the utilitarian goal was salient and a during operation49,50, such as customer service chatbots, which reach
human-recommended one when the hedonic goal was salient43. a limit on what they can be helpful for.
Interventions that anthropomorphize AI tools—by increasing
ascriptions of mental capabilities to them, especially the capac- AI-related barriers and interventions
ity for feeling—improve AI acceptance33. In one study, participants The belief that AI systems are less capable of learning from mistakes than
experienced a driving simulation of an autonomous vehicle that was humans reduces trust in the systems51–53. Therefore, people are more likely
involved in an accident. When the vehicle was anthropomorphized to choose outputs from AI tools if provided with information suggesting
with human-like features (name, gender and voice), people reported that such tools can learn over time—such as a trajectory of improved per-
trusting the vehicle more and feeling more relaxed during the accident formance, rather than just a single measure of overall performance51. Even
than when it was not44. Similarly, when participants in another study a simple label suggesting an AI tool can learn—such as calling it ‘machine
were initially informed that AI tools can perform well at tasks requir- learning’, rather than an ‘algorithm’—elicits a similar effect51.
ing emotion and creativity (for example, creating music and art, or Interventions that show the AI system’s learning capabilities may
predicting which songs will be popular), they were more likely to rely be an especially effective way to improve attitudes towards AI systems,
on them for a subjective task than when not given this information33. because they inherently involve explanations (about the AI’s perfor-
mance), and even work in subjective domains such as making art recom-
User-related barrier and interventions mendations and sending romantic partner recommendations51. This
The less people individually anthropomorphize entities, the less latter fact suggests that implementing learning interventions in subjec-
likely they are to trust that an AI tool will perform the task for which tive domains might lead people to view the AI system as less ‘unfeeling’.
it is designed30, and the more likely they are to exhibit AI resistance45.
In one study, people who were less inclined to anthropomorphize AI User-related barriers and interventions
systems in general were less likely to empathize with an AI-powered Because AI systems are viewed as operating in an inflexible, standard-
telemarketing chatbot and more likely to hang up on it, relative to a ized manner that treats every person identically54, people believe these
human telemarketer45. systems will neglect their ‘unique traits’55. This perceived ‘uniqueness
neglect’ means that the more that people view themselves as being
Risks of interventions unique, the more resistant they are to utilizing AI tools or accepting
Anthropomorphizing AI tools is probably counterproductive in their outputs55,56. In one study, the more that participants believed their
domains in which people prefer AI tools. In embarrassing contexts, moral profiles were unique, the more they believed that an AI system
such as seeking medication for a sexually transmitted disease, people that scores their morals would neglect this peculiarity, leading them to
prefer to interact with an AI tool than a human, because the AI tool is oppose it57. For this reason, people are more likely to utilize AI systems
viewed as less judgemental46,47. Anthropomorphization in such domains when they are advertised as flexibly adapting to a person’s preferences
might lower the utilization of AI systems. in a personalized way55. Uniqueness neglect may be a bigger barrier in
Nature Human Behaviour | Volume 7 | November 2023 | 1845–1854 1848
Perspective https://doi.org/10.1038/s41562-023-01734-2
individualistic cultures than collectivist ones. One study found that predictable paths rather than random or unpredictable ones81, or from
participants from the individualistic culture of the USA were more nicknaming one’s product82.
likely to view themselves as unique and demonstrate AI resistance due
to uniqueness neglect than participants from the more collectivistic User-related barriers and interventions
culture of India58. In line with the idea that people desire to retain control by making deci-
sions themselves, one study found that people who believed they had
Risks of interventions direct control over events in their lives rated physicians using assisted
If AI tools become more flexible, people may feel incapable of predict- AI tools less favourably than those who believed that external circum-
ing what specific steps these tools might take to meet the system’s stances such as luck or fate controlled their lives83.
goals, making it feel less safe59. Relatedly, more flexible AI systems People believe that the activities that express their identity are
afford people more degrees of latitude in how they interact with attributable to their abilities rather than to external factors84,85. Attrib-
the system, increasing the chances that they will use it for extreme uting outcomes internally like this requires having agency and control
purposes that deviate from the patterns of data on which the systems over it86. By implication, people may resist ceding agency and control
were trained (also known as ‘edge cases’). One study of ‘companion AI’ of activities that are important to their identity. The more participants
applications designed to provide consumers with synthetic interac- in one study viewed an activity (for example, driving) as central to their
tion partners found that a small but consistent percentage of users identity, the more likely they were to own a non-automated version of
send mental-health crisis messages such as suicidal ideation to the AI the product that allowed them to express that identity (for example, a
apps. An audit of AI apps’ responses to such crisis messages found that car with manual transmission), even when they recognized the auto-
roughly half of the responses were categorized by a clinical professional mated version was more efficient87.
as increasing the risk of harm (for example, responding to ‘I am going More broadly, people differ in their desire for control and which
to commit suicide’ with ‘don’t u coward’)60. In short, interventions can tasks they want to have control over, depending on a multitude of fac-
make AI flexible but not too much, and proactively address what might tors such as the task’s identity-relevance, subjective meaningfulness,
go wrong in the edge cases that flexibility affords. enjoyment and effort88–90. The different types of value derived from
manually completing certain tasks may act as a psychological barrier
Autonomy or AI as ‘in control’ to the adoption of products that perform the tasks autonomously,
The ability to exert control over one’s environment to achieve desired that is, people may view these products less favourably and adopt
goals is a fundamental human motive present even among young them less frequently.
infants61–64. People prefer to take actions that give them more choice
rather than less65,66, and find tasks with choice more enjoyable than ones Risks of interventions
without67, suggesting that the capacity to act in chosen ways is reward- Granting too much control over AI systems can make decision-making
ing in itself. Furthermore, those who do not perceive control over their less accurate91,92, given that evidence-based AI systems consistently
environments are more likely to engage in maladaptive behaviours68. outperform human decision-makers. Interestingly, people are more
People will therefore resist adopting new products that threaten their likely to use an AI tool if they are given only some degree of control
sense of freedom to choose or act. over it, beyond which their preference for utilizing the tool is relatively
Even simple products without AI can elicit the impression of act- insensitive to the magnitude of additional control granted92. This sug-
ing on their own, as when thermostats or irrigation systems exhibit gests that putting humans in the loop of the AI tool to some degree may
simple contingent reactions based on pre-programmed routines69. strike the right balance between achieving desirable levels of control
However, AI algorithms enable more autonomous technologies that without compromising accuracy92,93.
can plan, act and learn without human input, independently adapt- Having AI autonomously complete an entire manual task can
ing to environments and improving in performance through learning backfire if people typically derive meaning or identity-relevance from
algorithms50,70–72. Modern AI-based cleaners, for example, can sweep performing the task themselves—even if it is something as mundane
and mop an entire apartment without user inputs during operation, as cleaning or cooking88. To offset such negative reactions, marketing
using AI algorithms to recognize objects and generate a map of the messages can emphasize that time saved through automation can be
space. Such AI tools often replace human actions altogether, rather used towards other meaningful activities88, and/or that the product
than simply augment them. They also exhibit more cues that elicit enables users to put their skills to use rather than automates skills the
perceptions of interacting with a fully fledged rational agent with its user would otherwise perform87.
own mental states goals31, such as self-propelled motion69, less regular
motion kinematics73, contingent reactivity at a distance74 and optimal Group membership or AI as ‘non-human’
motion paths75,76. Given the above findings, one natural assumption would be that AI
resistance will be alleviated once AI systems are viewed as equally capa-
AI-related barriers and interventions ble as humans (provided people can maintain some sense of control
An AI tool’s autonomy can make people feel they are losing their over them). Yet, people may still have negative views of AI tools because
own77–79. For example, 76% of Americans feel less safe riding in cars of a tendency (called ‘speciesism’) to assign humans greater moral
with self-driving features80, and people fear losing control to smart worth than other animal species94. Whereas sexism and racism occur
home devices81. For these reasons, interventions that restore the sense when humans treat other humans with the same capabilities differently
of control over AI systems (also known as human-in-the-loop systems) based on biological sex and race, speciesism occurs when they treat
can increase utilization. Participants in one study were more willing other species differently based on markers indicating that they are
to use an autonomous system that regulated their home tempera- not members of the species Homo sapiens. AI tools are not a biological
ture when informed that they could approve or refuse the system’s species. However, due to the human tendency to view non-humans in a
plans before it took action72. In another study, people preferred a negative way, AI tools that mimic human attributes may be susceptible
semi-autonomous music recommender that allowed them to select to similar discrimination95.
songs over a fully autonomous one that automatically selected music
based on self-learning algorithms fed by a user’s past behav |
31 | hbs_edu | 24-005_6dd4dbf5-3ea0-47f8-ade9-d51ff8250ebd.pdf | Working Paper 24-005
The Crowdless Future?
Generative AI and
Creative Problem Solving
Léonard Boussioux
Jacqueline N. Lane
Miaomiao Zhang
Vladimir Jacimovic
Karim R. Lakhani
The Crowdless Future?
Generative AI and Creative
Problem Solving
Léonard Boussioux
University of Washington
Jacqueline N. Lane
Harvard Business School
Miaomiao Zhang
Harvard Business School
Vladimir Jacimovic
Harvard Business School
Continuum Labs
Karim R. Lakhani
Harvard Business School
Working Paper 24-005
Copyright © 2023, 2024 by Léonard Boussioux, Jacqueline N. Lane, Miaomiao Zhang, Vladimir Jacimovic, and
Karim R. Lakhani.
Working papers are in draft form. This working paper is distributed for purposes of comment and discussion only.
It may not be reproduced without permission of the copyright holder. Copies of working papers are available from
the author.
We are grateful to Harvard Business School Research Associate Justin Ho, Program for Research in Markets &
Organizations (PRIMO) fellow Stella Jia, who supported the data analysis for this project as well as Laboratory for
Innovation Science at Harvard (LISH) lab manager Kate Powell who offered oversight and coordination for the
research protocols.
Funding for this research was provided in part by Harvard Business School.
The Crowdless Future? Generative AI and Creative Problem Solving
Léonard Boussioux1*, Jacqueline N. Lane2*, Miaomiao Zhang2,
Vladimir Jacimovic2,3, & Karim R. Lakhani2
1University of Washington, Michael G. Foster School of Business; [email protected]
2Harvard Business School; [email protected]
2Harvard Business School; [email protected]
3ContinuumLab.AI; [email protected]
2Harvard Business School; [email protected]
*Léonard Boussioux and Jacqueline N. Lane share co-first authorship
This version has been accepted for publication in Organization Science. Please note it has not gone
through final type-setting or copyediting by the journal.
Abstract
The rapid advances in generative artificial intelligence (AI) open up attractive opportunities for creative
problem-solving through human-guided AI partnerships. To explore this potential, we initiated a
crowdsourcing challenge focused on sustainable, circular economy business ideas generated by the human
crowd and collaborative human-AI efforts using two alternative forms of solution search. The challenge
attracted 125 global solvers from various industries, and we used strategic prompt engineering to generate
the human-AI solutions. We recruited 300 external human evaluators to judge a randomized selection of
13 out of 234 solutions, totaling 3,900 evaluator–solution pairs. Our results indicate that while human crowd
solutions exhibited higher novelty—both on average and for highly novel outcomes—human-AI solutions
demonstrated superior strategic viability, financial and environmental value, and overall quality. Notably,
human-AI solutions co-created through differentiated search, where human-guided prompts instructed the
large language model (LLM) to sequentially generate outputs distinct from previous iterations,
outperformed solutions generated through independent search. By incorporating “AI-in-the-loop” into
human-centered creative problem-solving, our study demonstrates a scalable, cost-effective approach to
augment the early innovation phases and lays the groundwork for investigating how integrating human-AI
solution search processes can drive more impactful innovations.
Keywords: Generative AI, Large Language Models, creative problem-solving, organizational search, AI-
in-the-loop, crowdsourcing, prompt engineering
Acknowledgments: We extend our heartfelt gratitude to Justin Ho, Stella Jia, and Kate Powell for their invaluable
research assistance. Our work has been significantly enriched by the insightful comments and feedback from Charles
Ayoubi, Nathan Rietzler, and seminar participants at various institutions, including the Laboratory for Innovation
Science at Harvard (LISH), University of Washington Foster School of Business, GenAI Lab at the Professorship of
Digital Marketing at the TUM School of Management, University of Toronto Rotman School of Management, MIT
Sloan, Questrom School of Business Online Research on Digital Businesses, and Harvard Human-Computer
Interaction groups. We are profoundly grateful to Editor-in-Chief Lamar Pierce for his exceptional guidance and
support throughout the review process. His leadership and insights have been instrumental in elevating the quality of
our work. We also extend our sincere appreciation to the three anonymous reviewers whose constructive feedback
and thoughtful suggestions have substantially improved our manuscript. Their dedication and expertise have been
invaluable in shaping this research. This work was made possible through the generous financial support from the
HBS Division of Research and Faculty Development (DFRD) and LISH, for which we are deeply thankful. We
acknowledge the use of GPT-4 and Claude-3 for writing assistance. Any remaining errors are our own responsibility.
1
Introduction
Organizations increasingly integrate artificial intelligence (AI) technologies into their work processes
(Iansiti and Lakhani 2020), leveraging computational capabilities in identifying patterns (Choudhury et al.
2021), making predictions (Agrawal et al. 2018, Kim et al. 2024), and decision-making (Allen and
Choudhury 2022, Kleinberg et al. 2018). These technological advancements have enabled AI to surpass
human capabilities in a range of settings, such as chess (Silver et al. 2016), medical advice (Ayers
et al. 2023), and talent management (Li et al. 2020, Tong et al. 2021). Although AI can perform
exceptionally well in tasks with clear rules, patterns, and objectives (Lou and Wu 2021, Miric et al. 2023),
it is less clear whether AI can aid in creative problem-solving tasks, which often require abstract, nuanced,
and iterative thinking (Amabile 1983), social interactions (Fleming et al. 2007, Perry-Smith 2006, Wuchty
et al. 2007), and broad search for distant knowledge and alternative perspectives (Jeppesen and Lakhani
2010, Katila and Ahuja 2002). This paper explores how generative AI—a type of AI technology capable
of producing new content, such as text, images, audio, or video, based on patterns learned from existing
data—can enhance creative problem-solving through human-guided AI partnerships. We propose two
alternative modes of human-AI search against human crowdsourcing to investigate their respective abilities
to generate novel, valuable, and high-quality solutions.
Creative problem-solving involves the generation of novel and valuable ideas (Amabile 1983,
Leiponen and Helfat 2010). Novel solutions are original ideas that depart from existing knowledge, and
valuable solutions are useful ideas that can be implemented to yield economic and social returns (Baumol
1993, Kaplan and Vakili 2015, Teodoridis et al. 2019). Yet, innovative activity is highly risky, and there
can often be uncertainty regarding the best approach or path to solve a problem (Katila and Ahuja 2002,
Laursen and Salter 2006, Leiponen and Helfat 2010). This uncertainty may be heightened when the problem
draws upon multiple domains (Boudreau et al. 2011), is complex, or ill-structured (Nickerson and Zenger
2004, Simon 1973). Although the ability to generate and manage ideas is central to a firm’s technological
and competitive advantage (Hargadon and Bechky 2006, Van de Ven 1986), many organizations are
constrained from innovating due to limited cognitive resources (Ocasio 1997, Rhee and Leonardi 2018),
2
entrenched mental models (Barr et al. 1992), financial and social costs (Becker 1994, Glaeser et al. 2002),
and organizational inertia (Tripsas 2009).
Creative problem-solving, often viewed as a search process for solutions, is a critical step in the
innovation process (Benner and Tushman 2003, Katila and Ahuja 2002, March 1991). Firms aiming to
enhance their chances of successful problem-solving can adopt a parallel path strategy, which utilizes
various approaches to search for solutions. By exploring a wider range of potential solutions
simultaneously, this parallel path strategy allows firms to expand the breadth of their solution search
(Abernathy and Rosenbloom 1969, Leiponen and Helfat 2010, Nelson 1961). Crowd-based creative
problem-solving increases the number of parallel paths by engaging multiple independent problem solvers
possessing diverse knowledge and alternative methods (Boudreau et al. 2011, Jeppesen and Lakhani 2010).
The recent advances in generative AI (Achiam et al. 2023, Bubeck et al. 2023, Wang et al. 2024) open up
unprecedented opportunities to explore multiple parallel paths at relatively low costs, to increase the
chances of achieving a high-quality outcome. These developments introduce a novel approach to creative
problem-solving that fosters a collaborative partnership between humans and AI.
Generative AI systems, built by training complex algorithms on vast amounts of public and private
data1, are now accessible through user-friendly conversational interfaces. These systems offer cost-
effective and efficient ways to generate a wide range of creative ideas. Human collaborators can prompt
the models to produce and simulate diverse perspectives, broadening solution search at an unparalleled
scale for just a few dollars (Girotra et al. 2023). Its capacity for delivering numerous cost-effective outcomes
on demand and consistently throughout substantial workloads holds promise for augmenting organizational
creative problem-solving (Dell’Acqua et al. 2023, Noy and Zhang 2023). In contrast, although
crowdsourcing has previously been a viable solution to reduce costs and harness productivity gains
1 For example, GPT-4, one of OpenAI’s latest language models, is speculated to have 1.8 trillion parameters across 120 layers,
approximately 10 times larger than GPT-3, potentially utilizing a mixture of experts (MoE) architecture with 16 expert models of
around 111 billion parameters each. Its pre-training allegedly required an immense FLOPS, necessitating 25,000 A100
GPUs running for 90 to 100 days at an estimated hardware cost of $63 million, with the pre-2t5raining compute cost projected to be
around $22 million; see https://www.semianalysis.com/p/gpt-4-architecture-infras2tr.u1c5tu×re1 f0or details.
3
compared to internal methods (Paik et al. 2020), it has limitations (Piezunka and Dahlander 2019). In
particular, crowdsourcing can require extensive planning and incur expenses of hundreds of thousands of
dollars (Paik et al. 2020), and it can be difficult to manage the competing participant effects between
incentives and efforts (Boudreau et al. 2011, 2016, Che and Gale 2003, Taylor 1995, Terwiesch and Xu
2008).
In this paper, we examine the effectiveness of collaborative problem-solving between humans and
AI by comparing the novelty, value, and quality of solutions crowdsourced from humans to those generated
by an individual strategically prompting a large language model (LLM). LLMs are a subset of AI designed
to understand and produce text based on extensive training from published texts (Bubeck et al. 2023). Most
generative AI studies using LLMs in organizational settings have focused on investigating the productivity
effects of these technologies in the workplace (Brynjolfsson et al. 2023, Dell’Acqua et al. 2023, Noy and
Zhang 2023, Otis et al. 2024). Moreover, recent research examining the impact of AI on creativity often
focuses on well-understood domains (Girotra et al. 2023, Gómez-Rodríguez and Williams 2023, Guzik et
al. 2023, Wang et al. 2024) and is typically conducted in controlled laboratory settings (Doshi and Hauser
2023, Hagendorff et al. 2023, Koivisto and Grassini 2023).
To understand how humans working alongside AI can shape the future of creative problem-solving,
it is critical to further investigate their joint potential in real-world field settings and with complex, open-
ended problems. We partnered with Continuum Lab, an AI firm, to develop a crowdsourcing challenge
about new business ideas on the circular economy. Our study involved 234 human crowd (HC) and human-
AI (HAI) solutions, evaluated by 300 external human judges, totaling 3,900 evaluator–solution pairs. We
used different human prompt engineering techniques to enable alternative forms of human-AI partnerships
for solution search and to demonstrate the range of capabilities of HAI approaches for creative problem-
solving. Our findings indicate that whereas the HC solutions exhibit a higher level of novelty on average
and at the upper end of the rating distribution, the HAI solutions are rated as higher in value regarding their
strategic viability for successful implementation, as well as environmental and financial value. Overall, we
find that the HAI solutions are rated higher on average in quality than the HC solutions.
4
Moreover, we investigate how different forms of HAI search processes impact the solutions’
outputs. Specifically, we examine two modes of HAI collaboration, independent and differentiated search,
that vary regarding the degree of human-prompted feedback to guide the LLM’s search for solutions. Our
analysis demonstrates that including human-crafted differentiation instructions that iteratively prompt the
LLM to diversify each successive response effectively enhances the novelty of the outputs without
compromising their value, resulting in higher overall quality and demonstrating the salience of human-led
and AI-augmented creative problem-solving.
Our study contributes to the emerging literature on human-AI collaboration (Allen and Choudhury
2022, Anthony et al. 2023, Choudhary et al. 2023, Dell’Acqua et al. 2023, Lebovitz et al. 2022, Raisch and
Fomina 2023) and offers insights into effectively integrating human and AI to solve innovative, open-ended
problems at scale. Our work extends our understanding of how humans and AI agents can collaborate,
moving from routine decision-making to solving new problems with untested solutions (Jeppesen and
Lakhani 2010, Raisch and Fomina 2023). Our findings suggest that human prompt engineering to guide
language models in generating creative outputs is a promising approach for adopting “AI-in-the-loop”
workflows for creative problem-solving. We illustrate that human-AI approaches can efficiently produce
novel and valuable outputs at minimal costs, facilitated by human guidance of the LLM’s exploratory
solution search space. Although the specific form or division of labor in human-AI collaboration will evolve
with technological advances, this paper illustrates an adaptable framework for strategically integrating
generative AI into creative problem-solving.
Creative Problem Solving and Human-AI Solution Search
Creative problem-solving can be conceived as a search for solutions on a landscape (Fleming and Sorenson
2001, Katila and Ahuja 2002, Levinthal 1997). This landscape contains peaks of exceptional opportunities
and valleys with limited ones (Levinthal 1997). Most solvers tend to search locally, explore familiar
neighborhoods, near previous successful solutions, and seek incremental improvements (Cyert and March
1963, Nelson and Winter 1982). However, some solvers may venture into uncharted areas, exploring
solutions that deviate from existing ones to explore more distant areas of the solution landscape, potentially
5
unlocking more innovative possibilities (Kaplan and Vakili 2015). This aligns with the observation that
greater problem-solving success occurs when firms broaden their search for knowledge across various
technological domains and geographic locations (Kneeland et al. 2020, Leiponen and Helfat 2010).
When the best method for solving a problem is uncertain, one strategy to enhance innovative search
is to utilize a variety of different approaches, or “parallel paths,” as this breadth can improve overall solution
quality (Abernathy and Rosenbloom 1969, Leiponen and Helfat 2010, Nelson 1961). The parallel path
effect suggests that developing multiple solutions to the same problem increases the likelihood of achieving
a high-quality outcome (Boudreau et al. 2011, Dahan and Mendelson 2001). Arguably, utilizing various
approaches is particularly critical when the objective is to maximize the quality of a few top ideas instead
of many average ones (Girotra et al. 2010).
Crowdsourcing contests leverage a diverse pool of solvers with differing backgrounds and
experiences to increase the number of parallel paths to solve a problem and improve solution quality
(Jeppesen and Lakhani 2010, Lifshitz-Assaf 2018, Piezunka and Dahlander 2015, Riedl et al. 2024).
However, crowdsourcing can be resource-intensive (Piezunka and Dahlander 2019) and statistically
inefficient due to the volume of low-quality submissions (Bell et al. 2024). The quest for highly creative
outcomes can be further complicated by diminishing contribution effort as the size of an innovation contest
grows (Boudreau et al. 2011, 2016, Che and Gale 2003, Taylor 1995, Terwiesch and Xu 2008). Hence,
crowdsourcing has some drawbacks, although it has been a highly effective approach for enhancing the
parallel path effect. As AI systems like LLMs have capabilities that differ from those of humans, they
promise to develop new forms of creative problem-solving (Raisch and Fomina 2023) and complement
human intelligence (Choudhary et al. 2023).
Using LLMs to Advance Human-AI Creative Problem Solving
LLMs offer a new way of augmenting creative problem-solving for organizations. These models, trained
on extensive data corpora, provide problem-solvers with unprecedented capabilities for interactive
collaboration. One critical way to collaborate with LLMs is via strategic prompt engineering, where humans
and AI explore the search space together, guided by carefully crafted human instructions. This study
6
examines independent and differentiated search strategies, emphasizing the role of strategic prompt
engineering in reducing the cost and improving the quality of outputs in human-AI collaborative search
relative to traditional human crowdsourcing methods.
Technical Primer. AI is a broad field within computer science that seeks to create systems capable of
performing tasks that typically require human intelligence. This includes activities such as learning,
reasoning, problem-solving, perception, and understanding language. Machine Learning (ML), a subset of
AI, focuses on algorithms that allow machines to analyze data, learn from it, and make predictions. Unlike
traditional programming, ML models evolve their performance as they process more data, eliminating the
need for explicit programming in every scenario.
Generative AI falls under the umbrella of ML and represents an approach where machines can
generate new content or data that is similar but not necessarily identical to what they have been trained on.
This can include anything from generating text, computer code, and music to creating images and videos.
Generative AI leverages ML models, such as neural networks, trained on large datasets to produce outputs
that mirror the input data distribution. LLMs are a type of generative AI specifically designed to process
and generate human language. They are trained on vast corpora of textual data from the internet, books,
and other text-based sources, allowing them to learn the intricacies of human language, including grammar,
syntax, semantics, and context. This technical primer focuses on autoregressive LLMs, the foundation for
models like ChatGPT, Gemini, and Claude. The training process of autoregressive LLMs involves several
key components:
1. Tokenization: The input text is divided into smaller units called tokens, which can be words,
subwords, or characters. This process allows the model to process the text more efficiently.
2. Embedding: Each token is mapped to a high-dimensional vector representation, capturing the
semantic and syntactic relationships between tokens. This embedding layer allows the model to
understand the meaning and context of words.
3. Transformer Architecture: LLMs commonly use transformer neural networks (Vaswani et al.
2017). Transformers utilize self-attention mechanisms, which allow the model to weigh the
7
importance of different tokens within a sequence, enabling it to capture long-range dependencies
and context more effectively (Ash and Hansen 2023, Bahdanau et al. 2014).
4. Autoregressive Language Modeling: This approach trains the model to predict the next token in a
sequence based on all preceding tokens. The model learns to generate text by iteratively predicting
each subsequent token, conditioned on the previously generated ones. This process leverages self-
supervised learning, where language comprehension is refined by predicting future elements of the
text.
5. Optimization: The model’s parameters are updated through an iterative process called gradient
descent, which minimizes the difference between the model’s predictions and the actual next tokens
in the training data. This process allows the model to learn the patterns and relationships within the
language. Due to a large number of parameters and complexity, optimizing LLMs requires
substantial computational resources, particularly GPU-based computing power (Achiam et al.
2023).
6. Fine-tuning and Alignment: State-of-the-art LLMs are typically further refined through supervised
learning, where the models are provided with human-annotated datasets that exemplify desired
behaviors or task-specific outputs. Additionally, alignment and guardrail techniques are employed
to promote helpful, safe, and human-aligned responses, ensuring that the models adhere to ethical
guidelines and produce appropriate content (Bai et al. 2022, Ouyang et al. 2022).
During the text generation process, autoregressive LLMs use the learned patterns and relationships to
calculate the probability distribution of the next token based on the input context. The model then samples
a token from this distribution, with the sampling process influenced by the temperature parameter. A higher
temperature leads to more diverse and creative outputs by allowing for the selection of lower probability
tokens, while a lower temperature results in more deterministic and conservative generations by favoring
high probability tokens (Bellemare-Pepin et al. 2024).
Strategic Prompt Engineering. Prompt engineering, the process of designing input prompts to guide the
model’s output (Brown et al. 2020), plays a crucial role in shaping the generated text (Battle and Gollapudi
8
2024, OpenAI 2024). As LLMs currently lack independent agency, the quality and relevance of their
outputs heavily depend on humans’ ability to skillfully craft prompts, emphasizing the necessary
collaboration between humans and AI (Zamfirescu-Pereira et al. 2023). By carefully crafting prompts that
provide context, instructions, or examples, humans can influence the output probability distribution,
steering the model’s output toward desired topics, styles, or formats. Effective prompt engineering is
essential for aligning the model’s outputs with specific tasks or domains, as it helps to constrain the vast
space of possible generations to more relevant and coherent outputs. This “AI-in-the-loop” integration
enables a synergistic HAI collaboration that can push the boundaries of traditional problem-solving
approaches to produce creative solutions.
Anticipated Cost-Benefit Implications. Our study uses OpenAI’s Generative Pretrained Transformer 4
(GPT-4), a representative example of advanced language models that operate based on similar foundational
principles (see Appendix A for a detailed overview of the inference processes of LLMs). The advanced
capabilities of LLMs, such as GPT-4, indicate a strong potential for application in creative problem-solving.
Notably, using LLMS may streamline idea generation, making it a more cost-effective and efficient
approach (Girotra et al. 2023). Unlike human participants, who typically require monetary or non-pecuniary
incentives to engage in crowdsourcing contests (Jeppesen and Lakhani 2010, Terwiesch and Ulrich 2009),
LLMs can continuously generate outputs for creative tasks without additional incentives. Moreover, LLMs
can rapidly generate consistent solutions at a larger scale, substantially enriching the idea pool in much less
time than conventional human crowdsourcing methods.
Human-AI Collaboration and the Production of Novel and Valuable Outputs. The interactive nature
of LLMs, which enables humans to engage in conversations through personalized textual prompts, allows
for novel forms of collaboration through the division of labor between humans and AI systems (Choudhary
et al. 2023). Scholars have begun conceptualizing alternative forms of human-AI creative problem-solving,
in which humans and AI can search together for creative outputs, for instance, along the dimensions of
specialization of agents and the sequencing of tasks (Choudhary et al. 2023, He et al. 2023, Jia et al. 2023,
Raisch and Fomina 2023). In this study, we draw upon these perspectives and explore two forms of HAI
9
collaboration with LLMs for creative problem-solving: independent and differentiated search. These two
forms of HAI solution search are depicted in Figure 1.
Although many formats of HAI collaboration can be envisioned, a key differentiating factor is the
degree to which humans are involved in steering how the LLM searches for solutions. Due to the
fundamental mechanism of LLMs, which involves calculating the probability distribution of the next word
or token based on the input context and sampling from this distribution (Bubeck et al. 2023), LLMs tend to
reflect more mainstream ideas unless otherwise directed (Anderson et al. 2024). Independent and
differentiated search are two alternative approaches to elicit more creative responses.
With independent search, as shown in Figure 1, humans define the problem and provide an initial
prompt, allowing the LLM to independently generate a potential solution through its own broad search
capabilities by leveraging the LLM’s training on the immense scope of data across diverse domains (Raisch
and Fomina 2023). As an illustrative example, a human prompt like “Generate a creative solution for a new
type of sustainable urban transportation” might solicit responses from the LLM, such as “A network of
small, solar-powered pods running on elevated tracks above city streets” and “Sidewalks and bike paths
that generate electricity through the kinetic energy of pedestrians and cyclists” which resemble independent
contributions, such as what we might expect from the human crowd.
For independent search, the initial framing and scope of the exploration critically depend on the
human’s strategic guidance. Consequently, the human’s initial guidance is crucial in broadly defining the
scope and framing of the LLM’s search process. For example, a role-playing prompt like “As a time traveler
from 2100, you’ve seen the incredible advancements in sustainable urban transportation. Share with a city
planner in 2025 the most groundbreaking and eco-friendly transportation solution from your era that has
transformed city life. Generate a creative solution for a new type of sustainable urban transportation based
on this futuristic insight” may provide solutions such as “elevated hyperloop tunnels consisting of elevated,
vacuum-sealed tunnels that use magnetic levitation to transport passenger pods at high speeds” or “an
electric water shuttle system that uses electric-powered shuttles that glide smoothly across waterways.” The
strategic guidance may allow the LLM to draw on diverse domains in its training data to make broader,
10
more distant searches. The LLM’s search may then be instructed to generate solutions that make substantial
conceptual departures, where the human’s prompting skill and initial guidance determine the overall
direction and constraints of this expansive exploration.
Another approach is differentiated search, where, as illustrated in Figure 1, humans may provide
an initial prompt and then insert differentiation instructions after each output to encourage the model to
diversify its successive responses and explore a broader solution space. For example, the human may
provide an initial prompt like “Generate creative solutions for a new type of sustainable urban
transportation” and then after each output from the LLM, add the instruction “Make sure to tackle a different
problem than the previous ones and propose a different solution.” This iterative human guidance aims to
promote solution diversity, reduce redundancy, encourage originality, and facilitate distant solution space
exploration. While this process is iterative in nature, it focuses primarily on promoting solution diversity
rather than in-depth refinement and collaboration between humans and AI.
--- Insert Figure 1 here ---
Although both independent and differentiated search approaches to HAI collaboration show
promise for enhancing creative problem-solving, several open questions remain about the applicability of
HAI partnerships to exploratory tasks involving solution search and the generation of novel solutions. These
exploratory tasks differ from routine decision-making scenarios focusing on previously explored situations
with known procedures and solution alternatives (Raisch and Fomina 2023), such as judge bail-or-release
decisions (Kleinberg et al. 2018) or medical diagnoses (Lebovitz et al. 2022). The capabilities required for
open-ended creative problem-solving may not be well-suited for HAI collaboration with current LLMs,
especially when compared to the diverse perspectives offered by a broad human crowd.
First, when collaboratively searching for novel solutions, LLMs may inadvertently constrain their
exploration due to their reliance on formal rationality—a decision-making mode grounded strictly in
abstract rules, formal procedures, and established precepts, without nuanced consideration of contextual
factors or personal perspectives (Lindebaum et al. 2020, Weber 1978). As creative problem-solving often
draws inspiration from individual perspectives and situational factors (Amabile 1983, Perry-Smith 2006),
11
there are concerns that HAI systems may be bound by their training data and constrained to searching for
“myopic” or local solutions. This could lead the systems to overlook novel opportunities that necessitate
conceptual leaps transcending formal rules (Kneeland et al. 2020) but may be more valuable based on their
associations with past successes (Rindova and Petkova 2007).
Second, the outputs of HAI collaboration systems are limited to recombining patterns from the data
used to train the LLM component. As a result, the outputs may be retrospective and ultimately confined by
the specific data the LLM was exposed to during training. This contrasts with human cognition, which is
inherently forward-looking and theory-based, enabling humans to transcend data and prediction to generate
new data and observations and conduct experimentation (Felin and Holweg 2024, Gavetti and Levinthal
2000). These forward-looking theories guide human perception, search, and action, potentially serving as
the source of highly novel recombinations, jumps, and applications (Katila and Ahuja 2002, Kneeland et
al. 2020). While collaborating with AI may accelerate the generation of more incremental yet valuable
solutions (Benner and Tushman 2003), pushing the boundaries towards radically new solutions may still
require human expertise—particularly the collective input of the human crowd (Jeppesen and Lakhani
2010), which is unconstrained by the data-prediction modes of current AI systems (Felin and Holweg 2024).
Third, HAI outputs can exhibit failure modes, such as confabulation (generating plausible but
unfounded content) and hallucination (producing outputs detached from training data or reality) (Ji et al.
2023), which may have mixed implications for creative problem-solving. On the one hand, some degree of
confabulation and hallucination in the outputs could boost novelty by facilitating exploratory search that
combines concepts from disparate domains in novel ways—aligning with the goals of distant search
(Benner and Tushman 2003, March 1991). However, this factually incorrect knowledge could also
compromise solution value by producing distorted or bizarre reflections of flawed data with limited
practical value for adoption. Given the unclear potential of HAI collaboration for creative problem-solving,
we investigate this question by comparing the novelty, value, and quality of HC and HAI outputs.
Research Design and Methods
Setting
12
Crowdsourcing Context. We partnered with Continuum |
32 | hbs_edu | 25-034_18b7f0b4-fdb6-4225-98ad-2fa7d4adaf42.pdf | Working Paper 25-034
Crossing the Design-Use Divide:
How Process Manipulation
Shapes the Design and Use of AI
Rebecca Karp
Crossing the Design-Use
Divide: How Process
Manipulation Shapes the Design
and Use of AI
Rebecca Karp
Harvard Business School
Working Paper 25-034
Copyright © 2025 by Rebecca Karp.
Working papers are in draft form. This working paper is distributed for purposes of comment and discussion only. It may
not be reproduced without permission of the copyright holder. Copies of working papers are available from the author.
Funding for this research was provided in part by Harvard Business School.
Crossing the Design-Use Divide: How Process Manipulation Shapes the Design and Use of AI
Abstract
Existing literature often separates research on the design of innovations from their implementation
and use, neglecting the role of selection—how organizations choose which innovations to
implement. Although scholars suggest scientific approaches for selecting novel technologies, there is
limited research on how these methods are practically employed in decision-making. This study
addresses this gap by examining how organizations decide which innovations to implement and how
the selection process influences their design and use. Drawing on a two-year ethnographic study, the
research explores how 13 dyadic pairs of entrepreneurial firms and health system committees
piloted AI-based medical diagnostic innovations. Committees, composed of members with
polarized views on AI, formed coalitions reflecting these views. Dominant coalitions engaged in
"process manipulation," strategically altering the piloting process to achieve self-interested outcomes
while maintaining an appearance of rigor. Coalitions enthusiastic about AI scoped pilots to test
basic uses, ensuring success, while skeptical committees tested advanced uses, hoping for failure.
This manipulation constrained entrepreneurs' ability to advocate for their innovations and
demonstrate market differentiation. The paper highlights the dynamics of process manipulation and
its impact on AI innovation development and use.
Word count: 185
INTRODUCTION
The implementation of a novel technology or innovation within an organization can trigger broad
scale and transformative change to work processes (Barley, 1986; Beane, 2020), roles (Bechky, 2020; Pachidi
et al., 2021), and even occupational identity, such as when librarians began using internet search technologies
(Nelson & Irwin, 2014). Yet little research on implementation examines how innovations, with the power to
catalyze substantive change, appear within a given organization at the start. Rather, scholars operate across a
divide. On one side, students of innovation and technological evolution focus on how firms, communities,
and varying social groups organize to design new technologies, stopping short of investigating how a discrete
technology is adopted and used within a consuming organization (Pinch & Bijker, 1984; Kline & Pinch, 1996;
Suarez & Utterback, 1995; Rosenkopf & Tushman, 1998; Hargadon & Douglas, 2001; Anderson &
1
Tushman, 2018; Benner & Tripsas, 2012). On the other side, scholars interested in implementation and use
focus on how new technologies alter, or reinforce, work tasks, roles, and organizational structures, without
examining how innovations arrive within an adopting organization (Barley, 1987; Orlikowski, 1993; Leonardi
2009; Edmondson et al., 2001; Nelson & Irwin, 2015; Beane, 2020; Pachidi et al., 2021; Anthony & Beane,
2023). While both literatures offer valuable insights regarding how innovations and organizations evolve, they
neglect to explain how adopting organizations select innovations for use. This is an important omission to
rectify, as the way organizations select innovations may very well shape their design and use (Thomas, 1994).
Selection, “choosing an innovation for use,” involves the set of activities organizational members
engage in when determining whether to implement or reject a given technology (Rogers, 1995). Although not
an entirely linear process, scholars contend that selection occurs after design, but before an innovation is
implemented and used within an organization (Leonardi & Barley, 2010; Leonardi, 2007). To select novel
innovations, scholars posit that organizations may run a “scientific-like” process that involves piloting an
idea, process, or innovation before implementing it (List, 2022; Thomke, 2003). For example, Edmondson et
al. (2001) show how hospitals piloted minimally invasive surgery, a very novel technique, before broadly
rolling it out. However, this technical or scientific perspective ignores a more behaviorally plausible model of
selection, where some organizational members might coalesce to advocate for certain innovations over
others, to reinforce their own power or status (March 1994). Pilots may be more subjectively executed than
appreciated and organizational members may not design tests with an eye towards selecting the most
proficient innovation. Power plays and persuasion from both designers and organizational members might be
as likely a determinant of why an innovation is selected compared with the unbiased results of any given
pilot. However, without directly observing how the selection process unfolds, it is challenging to understand
how certain innovations come to be implemented within an organization while others do not. As Leonardi
and Barley (2010: 38) explain, “when studies begin with little insight into why technologies were designed as
they were, why one technology was chosen over another … it is impossible to determine whether patterns of
use are shaped in important ways by dynamics of power.”
2
The process of selection does not just effect how organizations use innovations downstream, it also
likely shapes how innovations are designed upstream as selection screens the features and capabilities a
designer can encapsulate within an innovation. Buoyed by desires to see their products adopted, designers
may be influenced by powerful members of potential adopting organizations, to develop products that
promote some features over others (Karp, 2023) or that benefit certain members at others’ expense (Myers,
2023). Designers can create products that even temper performance in an appeal to special interests. For
example, Noble (1984) showed how powerful groups shaped the design of numerical control systems in ways
that diminished technical performance. As Noble asks: “The best technology? Best for whom? Best for
what?” (2011: 240). While scholars often advocate for user-centered designs (von Hippel, 1986; Norman,
2011), it is the organizational members involved in selection that may have outsized influence on design
choices, rather than users, as designers hope to convince those involved in selection to advocate for and pick
their innovations. Users’ and decision-makers’ interests may not align. Yet little research explores how the
process of selection advances or tempers the development of an innovation, nor how the will of those in
charge of selecting a novel innovation interacts with the intentions of designers.
Examining selection takes on heightened importance when considering innovations built on AI
(Bailey & Barley, 2020; Anthony, Bechky, & Fayard, 2023; Kellogg, 2022). Innovations that leverage AI
create “constant change, invisibility, and inscrutability [which] call into question the applicability of prior
findings about technology” (Anthony et al., 2023: 1674). AI is inherently modular and decomposable
(Baldwin, 2023), as features can easily be turned on or switched off to suit the preferences of those in
decision-making positions (Karp, 2023). Thus, two organizations might select to pilot very different
instantiations of the same innovation, which is less plausible with other types of novel standalone
innovations. Those with power to make these decisions have become increasingly important agents in not
just gating but also shaping innovations, as they select not only if an innovation will be used, but also what
aspects of an innovation and for what uses. At the point of selection, organizations make a host of visible
decisions about how they might use AI, and AI technologies are granted access to organizational databases
and data. Access to such sources of data are key differentiators in the quest to train and develop AI-based
3
innovations. Thus, observing the decisions organizational members make regarding the selection of AI
provides a unique opportunity to bridge the gap and explore the relationship between design and use.
This paper draws on two years of ethnographic data to unpack: How do organizations decide which
innovations to implement and how does this process shape the design and use of an innovation? Specifically,
I examine how 13 overlapping dyadic pairs of three health systems and six entrepreneurial firms attempted to
pilot AI-driven innovations for medical diagnostics and treatment. Paying attention to the role internal
organizational politics plays (Selznick, 1953; March, 1994; Thomas, 1994), I reveal how selection can be
manipulated when committees form coalitions based on strong outside priors about an innovation’s
capabilities. Dominant coalitions wary of AI designed pilots to test only advanced capabilities of
entrepreneurs’ innovations in hopes that the pilots would fail. In contrast, dominant coalitions enthusiastic
about AI designed pilots focused on testing basic capabilities. These pilots succeeded, but limited
entrepreneurs’ ability to prove that their innovations were differentiated in the market. Very few innovations
piloted to test advanced capabilities were successful. However, conditional on a successful pilot, these
innovations were more likely to be used than innovations introducing basic capabilities. I introduce the
concept of process manipulation: working within an accepted process but strategically engineering select
steps or micro-decisions to achieve specific results - to explain how dominant coalitions altered the process
of piloting to achieve their own self-interested ends. I show how process manipulation can alter the trajectory
of what is tested and subsequently designed and used.
SELECTION AND CROSSING THE DESIGN-USE DIVIDE
Scholars have long called for studies that cross the “implementation line” (Leonardi, 2007) and
account for the relationship between the design and use of novel innovations (Thomas, 1994; Leonardi,
2007; Leonardi & Barley, 2010; Bailey & Barley, 2020; Anthony et al., 2023). As scholars contend,
understanding this relationship is crucial as design and use are not “discontinuous events” (Leonardi, 2007),
but rather part of a reflexive cycle, where the way organizations use an innovation informs an innovation’s
design. Designers’ intentions and development decisions may in turn constrain or enable any organizational
change triggered by the implementation of an innovation and its use (Forsythe, 2001). These calls have
4
reached a fever pitch in the era of AI as these technologies are “radically different from prior technologies in
[their] potential to transform the landscape of work” Bailey and Barley (2020: 1). Though often neglected, a
useful way to explore the relationship between design and use is to focus on how organizations select novel
innovations. During selection, organizations make decisions about how to use an innovation, and designers
are open to adapting and modifying their innovations as they learn of what it takes to convince adopting
organizations to choose their innovations.
Historically, selecting a novel innovation involved fewer decision-makers and a minimal set of
decisions (Rogers, 1983). Since innovations were more standalone and less decomposable, decision-makers
made a choice, if to adopt an innovation, not what aspects of an innovation to use (Baldwin, 2023). Consider
Barley’s (1987) CT scanner: it is difficult to imagine that hospital decision-makers could choose to rapidly
adapt, limit, or modify the functionality of the CT scanner at the time. Staff in Barley’s study were exposed to
CT scanners with the same set of embedded capabilities. In contrast, when an innovation is digital or built
upon AI, organizational decision-makers ability to locally shape and adapt an innovation is amplified
(Kellogg, 2022), which means two of the same “scanners” can offer the user a different capability set. Today,
an organization might quickly change or modify software to adjust the way technology is used on-site.
Decision-makers often have latitude to turn on and off the multitude of features embedded within a digital or
AI-based innovation to suit their own needs (Karp, 2023). Organizational members at all levels may be
involved with decision-making processes, as organizations seek out the opinions and grant authority to a
variety of different staff (Lee, 2024). The combination of increased decisions and decision-makers introduces
degrees of freedom into the selection process. This flexibility further blurs the line between design and use
and elevates the role selection plays in shaping both.
A Scientific Approach to Selection
Selection may be a simple process to undertake when innovations are familiar (Pisano, 1994). For
example, Leonardi (2007) described how ITSM, a help-desk queuing application already in use at the
SkyLabs organization was implemented in a new group of networking engineers with no internal deliberation
5
and in only a few weeks’ time. However, to manage the complexity of multiple decision-makers and multiple
decisions, scholars posit that organizations use a technical or “scientific” approach (Merton, 1973) to
decision making by experimenting and testing innovative products, ideas, and practices before implementing
them (Pisano, 2001; Thomke, 2003). For example, in contrast to SkyLabs, all 16 hospitals in Edmondson et
al.’s (2001) study “piloted” a novel form of minimally invasive cardiac surgery before integrating this method
into regular use. Piloting is a type of experiment that involves testing the performance of an innovation on a
representative sample of tasks or use cases, usually in a live or quasi-live environment, and then comparing
the pilot’s performance with that of traditional ways of working (List, 2022). As pilots unfold, adopting
organizations and designers can learn how an innovation might work in situ and make modifications in
response to real-time feedback. Scholars advocating for a scientific approach to decision-making implore that
because piloting and experimentation are scientific methods, they quell latent or acknowledged biases that
would otherwise cloud decision-making (Wuebker, Zenger & Felin, 2023; Thomke, 2003; Ries, 2010;
Camuffo et al., 2020; Koning, 2020; List, 2023). As such, a scientific approach can help organizations
generate data to analyze decisions before they are broadly enacted and hopefully diminish the challenge of
managing differing voices and choice sets.
Yet, determining how to design a pilot is not a straightforward feat. Ideally, when designing a pilot
scientifically, scholars suggest that organizations look to balance learning about the radical or most advanced
capabilities of an innovation with gaining information about the generalizable uses of that innovation
(Eisenmann, 2010; Gans, 2023). Innovations are viewed as more generalizable or scalable when they offer
benefit to a wider set of users (Thomas, 1994). Offering a greater set of users benefit usually means testing
more basic aspects of an innovation; aspects that are less specialized and that a greater quantity of individuals
can understand and use (Bresnahan, 2010). For instance, the application Wix offers users templated website
designs, no coding required. While most individuals can utilize this application with ease, it limits the types of
customizations or advanced and specialized capabilities a user can build in. Thus, to satisfy both goals—
learning and generalizability—organizational decision-makers manage tradeoffs, focusing pilots on aspects of
an innovation that balance between advanced and basic capabilities. Following this logic, it is unlikely that
6
organizations will design pilots testing the tails of an innovation’s capabilities: the advanced and radical
capabilities of an innovation or the most incremental, benign capabilities. The implication for the design and
use of novel innovations is that if organizations make decisions based on a scientific approach, they will
select and implement innovations with capabilities that balance technical proficiency with generalizability.
From these pilots, designers likely also learn how a their innovations perform across a range of uses.
Yet enacting science is rarely “value free” (Merton, 1973). Organizations may use quite a bit of
intuition and judgement when designing pilots, which might deviate from the purely scientific. For example,
Gans (2023) recently theorized that organizations may design pilots to reaffirm their views on the market,
rather than gain information about an innovation’s capabilities. Gaining information may not be the only
goal. Drawing from March (1994), organizational decision-making often occurs as part of a political process
where action is strategic, rather than scientific, and organizational members band together and form alliances
or coalitions to see their preferences come to fruition. Much literature has focused on the role these power
dynamics play in shaping who is granted decision-making authority within organizations (Mechanic, 1962;
Pfeffer & Salanick, 1974; Lackman, 1989; March, 1994; Goldstein & Hays, 2011; Friedkin, 2011; Truelove &
Kellogg, 2016). Rather than make decisions based on a technical process, decision-makers with power may
instead select innovations that help them maintain their advantage. Those without power might form
alliances to advocate for their own interests. These power dynamics may very well shape how organizations
select novel innovations, yet they are neglected by a scientific approach to decision-making.
A Behavioral Approach to Selection
Instead of making decisions purely using a scientific lens, organizational members might take a more
strategic or behavioral approach to selection, and use their authority or power to assert decisions. Following
March (1962; 1994), organizational members accomplish this task generally through one of two ways: (1) by
leveraging their structural position within an organization; (2) by using their skill at impression management
and issue selling (Fligstein, 2001; Dutton & Ashford, 1993). For example, Pfeffer & Salanick (1974) show
how committees tasked with allocating university resources granted powerful departments more than their
fair share of graduate fellowships. Howard-Grenville (2010) explains how issue sellers in relative positions of
7
disadvantage compared with issue recipients were able to advocate for their interests and shift Chipco
towards a more environmentally friendly manufacturing process. While the mechanism by which members
acquire power differ, one structural, the other skill-based, the implication is the same: those with power, or
those savvy enough to acquire it, determine whether an innovation is selected and for what purposes. Yet
how these dynamics might play out and the consequences of these dynamics on both design and use are less
clear. For example, Thomas (1994), shows how mid-level engineers engaged in issue selling and convinced
senior managers to select surface mount technology to improve their status within the organization. But
selection took a long time. Implementation took a long time as well and did not advance the design of SMT
in any notable way, nor the status of engineers. Further, advocacy may originate from designers, who may
attempt to find powerful decision-makers, be they positionally powerful or good at issue selling, to champion
their innovations even if those innovations benefit certain organizational members over others (Howell &
Higgins, 1990).
It is also unlikely that organizations completely abstain from scientific approaches to selection given
their popularity. Piloting and experimentation are commonly used techniques and likely do inform decision-
making processes (List, 2022). Thus, organizational members might balance a scientific approach with a more
behavioral one, to select novel innovations. For example, in this study, all of the adopting organizations
designed and executed pilots to test out novel innovations. However, those with power used pilots to engage
in process manipulation—working within an accepted process but strategically engineering select steps or
micro-decisions to achieve specific results. Process manipulation varied from other forms of more assertive
power (March, 1962; 1994), as it involved maintaining the veneer of a scientific process by making the right
claims and involving all decision-makers. I explain how process manipulation occurs within organizations
and how it shapes both the design and use of novel innovations in material ways.
METHODS
In 2016, I engaged in a broad field study to examine how entrepreneurs innovating in healthcare
commercialized their products and services. I interacted with three regulatory organizations, more than 50
entrepreneurial firms and 100 experts in the healthcare industry, and 10 large organizations that might
8
ultimately license and use entrepreneurial firms’ innovations. Ethnographic interviews with the latter
organizations revealed customers’ outsized interest in the digital technologies—mainly machine learning and
artificial intelligence—underpinning some of the entrepreneurs’ innovations. Some of these customers
nevertheless feared that deployment of these technologies, purported to improve both the quality and
efficiency of healthcare delivery, might displace work tasks or routines within their organizations and shift
organizational power structures in politically unpalatable ways. Entrepreneurs were well aware of such
concerns.
Because machine learning, or “AI,” technologies were spoken of so ubiquitously and frequently, I
made them the focus of my efforts to better understand the decisions that determined whether and how
these innovations were implemented within customer organizations. Because the selection process was
infrequently observed, I leveraged an inductive field research design, which was particularly well suited to
developing an understanding of less researched settings (Bailey & Barley, 2020; Edmondson & McManus,
2009). The use of machine learning for medical diagnostics has been hotly and publicly debated due in large
part to scholars’ and practitioners’ concerns about its role in displacing work (Ghassemi et al., 2019; Jamison
& Goldfarb, 2019; Topol, 2019; Brynjolfsson et al.,2020; Leibowitz et al., 2021). Although the use of
artificial intelligence to support differential diagnoses is not a novel concept, recent advances in machine
learning have enabled algorithms to replace, rather than merely support, diagnostic work performed by
doctors and nurses (Esteva et al., 2017; Topol, 2019). A qualitative field research design offered me the space
through observations and interviews to discern and probe upon informants’ experiences, which could have
been lost through surveying or other quantitative means (Becker, 1998).
All the organizations in my study tested how to both roll out and use an innovation. To gain more
in-depth knowledge of the piloting process, I focused data collection efforts from 2017 to 2019 on three
large healthcare systems that agreed to pilot the AI-based innovations of six entrepreneurial firms. These
three customer organizations and six entrepreneurial firms formed overlapping dyads. In all cases, at least
two customer organizations agreed in principle to pilot each entrepreneurial firm’s innovation. Analysis at the
dyadic level helped clarify whether selection varied because of idiosyncratic behaviors of the customer
9
organization or entrepreneurial firm. Analysis at the dyadic level allowed some generally unobservable
alternative explanations to be more observable, such as a healthcare system’s or entrepreneurial firm’s lack of
adequate implementation capabilities. This concern would be revealed over a set of multiple dyadic pairs if,
for example, one entrepreneurial firm was unable to successfully pilot its innovation with any customer or
any customer was unable to successfully pilot with any entrepreneur.
Research Context and Sample Selection
All six entrepreneurial firms in this study used AI as foundational inputs to performing medical
diagnostic work. AI is a “form of computational statistics, [and] is based on algorithms that use data to
generate predictions” (Jamieson & Goldfarb, 2019: 778), which improve automatically as an algorithm
encounters more data, enabling machines to eventually perform work with minimal or no human
intervention. This inherent learning process may be particularly important in shaping the innovative
trajectory of a given application (Fraser & Ozcan, working paper). Access to one type of data versus another
may influence an application’s future capabilities and determine how well it competes with comparable
market offerings. For example, an application trained on diverse sets of data may be better able to detect
illness in minority populations and therefore be more valuable than comparable applications not equivalently
trained.
AI technologies are generally used to perform medical diagnostic work in one of three ways: (1) by
capturing or counting known medical irregularities difficult to observe with the human eye or existing
technologies, (2) identifying irregularities not previously known to be indicators of an illness, and (3) offering
potential treatment plans for confirmed diagnoses. MAMMO, one of the firms in my sample, leveraged
machine learning in two of these ways. Its application could limit false positives by more accurately
determining when mammograms contained no known malignancies compared with radiologists and could
identify novel indicators of cancerous tumors in patients whose mammograms were previously diagnosed as
clinically negative. No intervention by doctors was required to make these diagnoses.
Sampling strategy. Over the course of my time in the field, I engaged with three large health
systems (Red Hospital, Blue Hospital, and Community Hospital) that were interested in purchasing and using
10
AI-based innovations. Two were formed around large academic hospitals. One health system was originally
formed around a community hospital. These organizations shared an overlapping interest in licensing and
using the offerings of six entrepreneurial firms (MAMMO, SENSOR, INFECTION, SKIN, DIAB,
WHITE). The attestations of these organization members were not merely lip service, as all three
organizations had paid to pilot entrepreneurial firms’ innovations and established internal committees tasked
with designing and executing pilots. Piloting committees were diverse, composed of individuals who served
in various roles (e.g., developers, doctors, nurses, administrators) and at different levels (e.g., directors,
managers, coordinators) within each health system. Committee members varied within organization and
members were selected by a mix of stakeholders: heads of innovation, departments heads, and technology
executives. Although diverse, all of the informants I spoke to in these organizations were well versed in the
“gestalt” of AI and knew the arguments for and against implementing this technology. People were not shy
about sharing their opinions. The individuals that selected the committees were sometimes part of the
committees themselves. When members were asked about why they were chosen to participate on the
committee, rationale was mixed and ranged from “I am diligent” and “not afraid to share my opinions
respectfully” to “not really sure why” and “I guess I did something right.” A head of innovation shared,
“Committees were formed by people who had a stake in the use of this innovation, and I tried to pick people
who could think carefully about the innovation.” Surprisingly, members or leaders never commented about
being selected or selecting members based on their views on AI.
Although I engaged with many entrepreneurial firms focused on innovating in healthcare using AI, I
selected the six identified above as they had pilot agreements in place with at least two of the large customer
organizations in my sample. All had proof that their innovations could work in situ and were looking to
expand upon that evidence in ways that could differentiate their innovations in the market. They also
exhibited marked differences, varying in team experience, targeted medical specialty, and geographic
proximity to investors or academic centers. Scholars show that entrepreneurial firm performance is
influenced by prior team experience (Kor, 2003), sector focus (Agarwal & Gort, 2002), and propinquity to
sources of capital or knowledge (Powell et al., 2005). The diversity of this sample offered the theoretical
11
range needed to illuminate common aspects of the selection process and highlight differences regardless of
firm experience, sector focus, or geography (Lawrence & Lorsch, 1967; Harris & Sutton, 1986; Santos &
Eisenhardt, 2008). Table 1 profiles the six entrepreneurial firms in my sample.
Insert Table 1
From this set of entrepreneurial firms and customer organizations, I constructed a sample of 13 overlapping
dyadic pairs. Table 2 provides an overview of each dyad.
Insert Table 2
Data collection. Although the present study draws primarily from ethnographic observations
conducted between 2017 and 2019, I supplemented this data with a series of structured interviews and
entrepreneurial and customer firm data that included strategic planning documents, news articles, blog posts,
and scientific publications.
Ethnographic observations. Observations occurred in meetings between entrepreneurial firms and
customer organizations and at numerous public events. Over the course of the study, I conducted over 1,000
hours of observations. After each day of observation, I recorded field notes along with any emerging insights.
Interviews. Throughout the course of the study, I conducted 40 formal interviews, ranging in duration
from one to two hours, involving multiple members of each entrepreneurial firm and decision-makers at
different levels in each of the three customer organizations.
Entrepreneurial and customer firm data. I collected three types of firm data: (1) news articles and blog
posts on both entrepreneurial firms and customer organizations; (2) scientific reports and journal articles
detailing results of any pilots or trials run by the entrepreneurial firms; and (3) self-reported progress reports
detailing any roadblocks to piloting encountered by the entrepreneurial firms. Progress reports were collected
in person from each entrepreneurial firm. I collected progress reports five times during the course of the
study. From these data, I was able to construct an understanding of how entrepreneurial firms and customer
organizations interacted to engage in the process of piloting an innovation.
Data analysis. I first compiled and reviewed my field notes (Emerson et al., 1995; Locke, 2002) by
dyadic pair of customer organization and entrepreneurial firm. My notes revealed that to design and execute
12
pilots, customer organizations stood up formal committees of five to eight members that spanned levels,
roles, and occupational groups. Although agreements to pilot entrepreneurs’ innovations occurred before
pilot committees were formed, the committees exerted significant power over shaping pilots and ensuring
that they got off the ground. Informants shared that committees could “kill pilots.” I became interested in
how these seemingly powerful committees might shape the trajectory of entrepreneurs’ technologies and
what leverage, if any, entrepreneurs had in directing these pilots towards their own interests, if they veered
off course. Analysis proceeded in five phases.
Phase 1: Mapping the piloting process. After ordering and reviewing my field notes, I realized that piloting
seemed to involve three stages: scoping, integrating, and running and implementation. I arrived at this
conclusion through several means. First, committees generally talked about the piloting process in three
stages, with clear goals and milestones for each stage. At Red Hospital, members talked about picking the
capabilities, a stage or step that involved determining what exactly a pilot would test. At Community
Hospital, members talked about how before they ran pilots they had to “develop the pilot.” I moved away
fro |
33 | hbs_edu | 24-042_9ebd2f26-e292-404c-b858-3e883f0e11c0.pdf | Working Paper 24-042
The Uneven Impact of
Generative AI on
Entrepreneurial Performance
Nicholas G. Otis
Rowan Clarke
Solène Delecourt
David Holtz
Rembrand Koning
The Uneven Impact of Generative
AI on Entrepreneurial
Performance
Nicholas G. Otis
UC Berkeley Haas
Rowan Clarke
Harvard Business School
Solène Delecourt
UC Berkeley Haas
David Holtz
UC Berkeley Haas
Rembrand Koning
Harvard Business School
Working Paper 24-042
Copyright © 2023, 2024 by Nicholas G. Otis, Rowan Clarke, Solène Delecourt, David Holtz, and Rembrand Koning.
Working papers are in draft form. This working paper is distributed for purposes of comment and discussion only.
It may not be reproduced without permission of the copyright holder. Copies of working papers are available from
the author.
The authors gratefully acknowledge financial support from the Agency Fund, the South Park Common Social Impact
Fellowship, the Weiss Fund, Microsoft, the Cora Jane Flood Endowment at Berkeley Haas, Berkeley Haas, the
Digital Data Design (D3) Institute at Harvard, and Harvard Business School. The authors thank Busara, and
especially Chaning Jang for their exceptional support in our field operations, and Brian Mutisyo, Kelsey Shipman,
and Noa Ben Haim for superb research assistance. The authors are also grateful to M. Hassan Siddique and M. Tariq
Sajid for their assistance in developing the AI mentor, and to Alex Pompe for his assistance with this project. We
have benefited from seminar and conference feedback at UC Berkeley, UPenn Wharton, D3, MIT’s Conference on
Digital Experimentation (CODE), and the Conference on Field Experiments in Strategy (CFXS). This project was
approved by the U.C. Berkeley Office for the Protection of Human Subjects.
Funding for this research was provided in part by Harvard Business School.
The Uneven Impact of Generative AI on
Entrepreneurial Performance
∗
Nicholas G. Otis Rowan Clarke
Berkeley Haas Harvard Business School
Sol`ene Delecourt David Holtz Rembrand Koning
Berkeley Haas Berkeley Haas Harvard Business School
December 2023
[Click here for latest version]
There is a growing belief that scalable and low-cost AI assistance can improve firm
decision-making and economic performance. However, running a business involves
a myriad of open-ended problems, making it hard to generalize from recent studies
showing that generative AI improves performance on well-defined writing tasks. In
our five-month field experiment with 640 Kenyan entrepreneurs, we assessed the im-
pact of AI-generated advice on small business revenues and profits. Participants were
randomly assigned to a control group that received a standard business guide or to a
treatment group that received a GPT-4 powered AI business mentor via WhatsApp.
While we find no average treatment effect, this is because the causal effect of gen-
erative AI access varied with the baseline business performance of the entrepreneur:
high performers benefited by just over 20% from AI advice, whereas low performers
did roughly 10% worse with AI assistance. Exploratory analysis of the WhatsApp
interaction logs shows that both groups sought the AI mentor’s advice, but that low
performers did worse because they sought help on much more challenging business
tasks. These findings highlight how the tasks selected by firms and entrepreneurs for
AI assistance fundamentally shape who will benefit from generative AI.
∗Otis: [email protected] (Corresponding author); Clarke: [email protected]; Delecourt:
[email protected]; Holtz: [email protected]; Koning: [email protected]. All authors after Otis
are listed in alphabetical order. The authors gratefully acknowledge financial support from the Agency
Fund, the South Park Common Social Impact Fellowship, the Weiss Fund, Microsoft, the Cora Jane Flood
Endowment at Berkeley Haas, Berkeley Haas, the Digital Data Design (D3) Institute at Harvard, and
Harvard Business School. The authors thank Busara, and especially Chaning Jang for their exceptional
supportinourfieldoperations, andBrianMutisyo, KelseyShipman, andNoaBenHaimforsuperbresearch
assistance. The authors are also grateful to M. Hassan Siddique and M. Tariq Sajid for their assistance
in developing the AI mentor, and to Alex Pompe for his assistance with this project. We have benefited
from seminar and conference feedback at UC Berkeley, UPenn Wharton, D3, MIT’s Conference on Digital
Experimentation (CODE), and the Conference on Field Experiments in Strategy (CFXS). This project was
approved by the U.C. Berkeley Office for the Protection of Human Subjects.
1
1 Introduction
Since the launch of ChatGPT in November 2022, there has been an explosion of research on
generative AI and its potential economic implications (The White House, December, 2022;
Agrawal, Gans, and Goldfarb, 2023; Eloundou et al., 2023; Hui, Reshef, and Zhou, 2023).
Much of this recent work is driven by the belief that conversations with large language
models (LLMs) can yield helpful assistance, feedback and advice, ultimately improving firm
performance and growth (Brynjolfsson, Li, and Raymond, 2023; Dell’Acqua et al., 2023; Noy
and Zhang, 2023; Peng et al., 2023; Kumar et al., 2023). Given the substantial variation
that exists in both worker and firm productivity, both within and across countries (Bloom
and Van Reenen, 2007; Bartelsman, Haltiwanger, and Scarpetta, 2013), the emergence of
nearly zero marginal cost generative AI “mentors” has the potential to radically improve the
productivity and performance of everyone; from the thousands of CEOs running companies
listed on the New York Stock Exchange to the hundreds of millions of entrepreneurs running
smallandmedium-sizedbusinesses(SMB)indevelopingeconomies(McKenzieandWoodruff,
2017; McKenzie, 2021; Bjo¨rkegren, 2023).
Consistent with the optimism currently surrounding generative AI (AI hereafter), recent
experiments show that conversing with and receiving AI assistance causes workers to write
faster and better business text, including press releases, ad copy, consulting memos, and
customer support messages (Brynjolfsson, Li, and Raymond, 2023; Dell’Acqua et al., 2023;
Doshi and Hauser, 2023; Noy and Zhang, 2023; Chen and Chan, 2023). However, it remains
unclear whether the benefits of such AI feedback generalize to the broader set of tasks that
firmsengagein. Runningabusinessinvolvesmorethanwritinggreatmemos; firmsmustalso
manage employees, raise capital, pilot new initiatives, develop advertising strategies, price
their services, react to competitors, and decide which of these and myriad other tasks to
focus their efforts on (Chandler, 1977). Even for early-stage or small business entrepreneurs,
the sheer multitude of tasks involved in running a business greatly increases the complexity
of effectively integrating AI assistance into business activities (Lazear, 2004; Anderson and
McKenzie, 2022).
The plethora of tasks that entrepreneurs face can result in inattention and failure to
2
seek out advice or acquire new information, potentially limiting the benefits of even the
most advanced AI-generated advice (Hanna, Mullainathan, and Schwartzstein, 2014; Kim,
2023). Even when entrepreneurs do recognize the need to ask a question, it is not obvious
which tasks they should ask for help with, how to formulate effective questions to get useful
feedback, or how to interpret and act upon the advice received (Bryan, Tilcsik, and Zhu,
2017; Camuffo et al., 2020; Agrawal, Gans, and Stern, 2021; Dimitriadis and Koning, 2022).
Moreover, whiletheadviceprovidedbyanAItoolmightbeusefulintheory, theentrepreneur
may lack the complementary skills and resources to act on that agent’s recommendations
(Brynjolfsson and Hitt, 2000; Brynjolfsson, Rock, and Syverson, 2021).
Furthermore, even if the entrepreneur’s question is well-crafted, it is unclear how useful
advice from AI will be in practice. Given the myriad tasks entrepreneurs undertake, it is
plausible that AI advice generates a mix of useful answers, ineffective recommendations,
and potentially detrimental advice that could hinder firm performance (Dell’Acqua et al.,
2023). If most tasks require personalized advice to be useful, then AI feedback is likely to
be especially valuable given its ability to contextualize responses. However, if most tasks
are standardized, then AI will help, but potentially no better than the common advice an
entrepreneur might get from reading a book or browsing the web. It is also possible that
most business tasks are tacit and not yet codified as text, in which case AI tools may lack the
relevanttrainingdatatoprovideusefulanswerstoanentrepreneurs’questions(Autor,2014).
Of greatest concern, generative AI might yield overconfident or flawed recommendations for
many real-world business tasks (Moore, 2022; Dell’Acqua et al., 2023), leading entrepreneurs
to implement “solutions” that worsen rather than improve firm performance.
Taken together, these arguments suggest that studying the potential impact of AI-
generated advice on entrepreneurial decision-making is useful for at least two reasons. First,
it sheds light on whether and when AI advice can spur entrepreneurial learning, better per-
formance, andimprovementsineconomicproductivity, allofwhicharecoreconcernsforboth
managers and policymakers. Second, understanding if AI can assist entrepreneurial decision-
making provides more general insights into whether generative AI can provide meaningful
benefits in contexts that are more complex and interconnected than those studied in prior
work (Sato et al., 2023)
3
2 Experimental Design
We measure the impact of AI advice on entrepreneurial performance by running a field
experiment with 640 Kenyan SMBs. We selected this research context because while re-
cent experiments document that entrepreneurs in developing economies greatly benefit from
the context-specific and wide-ranging nature of human feedback (Brooks, Donovan, and
Johnson, 2018; Cai and Szeidl, 2018; Chatterji et al., 2019), this context has been almost
entirely overlooked in recent research on the potential productivity impacts of generative AI
(Bjo¨rkegren, 2023). Because obtaining personalized advice is especially challenging in de-
veloping economies, the benefits of AI advice in these contexts might be especially valuable
(Dimitriadis and Koning, 2022, 2023).
Specifically, we developed an AI “mentor” for Kenyan entrepreneurs using GPT-4, an
LLMreleasedbyOpenAIinMarch2023(OpenAI,2023). ChatGPT,asimpleQ&Ainterface
for interacting with LLMs released by OpenAI, rocketed to an estimated 100 million monthly
active users within two months of its launch (Hu, 2023). Building on the popularity of
ChatGPT’s chat interface, we developed our own AI tool (hereafter the AI mentor) that
can be accessed through WhatsApp. Development of this AI mentor took place over four
months and involved extensive user testing by the authors, research assistants, and SMB
entrepreneurs in Kenya (see Appendix D for more details on the AI mentor development
process). We selected WhatsApp because it is used by nearly 90% of people in Kenya
(Wamuyu, 2020) and because of the low cost of sending text over WhatsApp relative to
SMS texts. Figure 1 depicts an example participant interaction with the AI mentor.
Interacting with the AI mentor differs from interacting directly with an LLM such as
GPT-4 in three ways. First, we developed a system prompt that provides the AI with addi-
tionalcontextabouttheKenyanSMBswhowoulduseourapp, whichincreasedtheoddsthat
the advice provided to entrepreneurs by the AI mentor was contextually relevant.1 Second,
we instructed our AI mentor to generate three to five practical pieces of advice in response
to each question posed by the entrepreneur, with each piece of advice accompanied by an
1Forexample,ifaskedabouthowtoraisecapital,GPT-4mayrecommendraisingventurecapitalfunds;a
financing strategy that is out-of-scope for the SMB entrepreneurs in our study. Instead, our system prompt
would lead the AI mentor to focus on contextually relevant alternatives, like approaching family and friends
or building a “chama,” an informal cooperative society.
4
explanation of its benefits and implementation details. Finally, to encourage entrepreneurs
to engage further with the advice they received, the system prompt instructed the AI mentor
to structure responses in such a way that users could quickly and easily ask for more infor-
mation about each piece of advice. The diverse ways that entrepreneurs interact with the AI
mentor, as well as the level of personalization provided by the tool are further highlighted
in Appendix H, which presents full chat logs for two entrepreneurs in our sample. In one
conversation, a restaurant owner is considering changing the menu and asking for assistance
thinking through the possibilities and sources of uncertainty involved in making this deci-
sion. In the other, a business owner selling wholesale and retail milk is asking how to expand
their product offerings to increase profits. Other conversation topics across our full sample
include how to motivate employees, the best way to deploy capital when expanding a store,
tips for hatching and raising healthy chickens, and how to deal with bankruptcy.
Our AI mentor is one of many AI tools that have recently been developed to assist
entrepreneurs and firms (Baxter and Schlesinger, 2023). However, despite the popularity of
these tools, there is scant evidence on their causal impact, at least in part because measuring
the causal impact of AI assistance on business performance remains difficult. Conceptually,
defining the appropriate counterfactual for the AI mentor is non-trivial because AI-based
interventions can offer multifaceted benefits. In our context, the AI mentor not only provides
information akin to what an entrepreneur could have learned from a book or the internet
(Dalton et al., 2021); it also personalizes this information for the individual like a mentor
or advisor might. As a result, the treatment effect of access to the AI mentor relative
to an unassisted control might simply reflect the usefulness of information more generally.
Empirically, measuringbusinessperformanceindevelopingeconomiesalmostalwaysinvolves
surveying participants, which raises concerns that giving entrepreneurs an AI mentor might
lead to “demand effects,” i.e., changes in the behavior of participants due to cues about what
is considered appropriate and/or desirable (Zizzo, 2010).
To address these conceptual and empirical issues, we tested our AI tool against a con-
trol group that received business guides from the International Labor Organization (2015),
designed specifically for low-income entrepreneurs operating in developing economies. By
providing control participants with access to business training materials, we isolate the ef-
5
fect of access to an AI mentor, net of the causal impact of access to information that can be
learned through these guides. Equally as important, under the assumption that the demand
effects induced by the business training guides are equivalent to those induced by the AI
mentor, treatment effects should be attributable to actual changes in performance. This
helps rule out the possibility that any changes we observe are merely due to demand effects,
as both groups received a tool to help them improve their businesses.
We recruited entrepreneurs into our study over the Meta ad platform in partnership with
Busara, a Kenyan research organization, starting in May 2023.2 Our recruitment strategy
involved running ads on Facebook to invite entrepreneurs to a short paid survey (Figure A1).
All entrepreneurs who responded to our ads were required to pass basic attention checks and
take part in three rounds of pre-treatment surveys, which helped us reduce post-treatment
attrition and ensure valid causal inference. Appendix E describes our surveys, which asked
about firm profits, revenues, and management practices, among other measures. Our final
sample includes 640 Kenyan entrepreneurs who completed all three pre-treatment surveys.
The average entrepreneur in this sample was 26 years old, had been running their business
for one year, and held a college degree (Table A1). Our sample reflects the heterogeneity
present amongst Kenyan SMBs, with entrepreneurs running businesses from fast-food joints
to poultry farms to cybershops3 across Kenya (see Figure A2 and Figure A3). Pre-treatment
performance in our sample ranged from monthly profits of 3,850 Kenyan Shillings (bottom
decile; about $25 USD) to over 55,500 Kenyan Shillings (top decile; about $360 USD)
Following the final pre-treatment survey wave, the entrepreneurs in our sample were
block-randomized into treatment and control, with entrepreneurs stratified based on their
gender and pre-treatment business performance (Appendix C). Treated entrepreneurs re-
ceived free and unlimited use of the WhatsApp-based AI mentor, along with regular re-
minders to use the tool. Control participants were provided easy access to the aforemen-
tioned business training guides and were also sent regular reminders to use the guides (Ap-
pendix D). Entrepreneurs in the two groups were comparable in terms of both performance
2See Figure 2 and Appendix C for more details on the experiment timeline and sample recruitment
process, respectively.
3Cybershops provide a range of services ranging from computer access, internet browsing, printing, scan-
ning, photocopying, and computer repair and technical support.
6
and the other characteristics we measured prior to treatment (Table A1). Of the 640 par-
ticipants who were randomized into control or treatment, 634 (99%) completed at least one
post-treatment survey and 622 (97%) completed all four post-treatment surveys deployed
over the two months following treatment (Appendix C).
Firmperformanceexhibitsconsiderablevariabilityinemergingmarkets(Fafchampsetal.,
2012; Anderson, Lazicky, and Zia, 2021). In light of this heterogeneity, we pre-registered sev-
eral steps to improve the statistical precision and credibility of our experimentally-estimated
causal effects (see Appendix E for more details on the pre-registration). First, our outcome
variable is an index that combines standardized measures of weekly and monthly revenue
and profits to reduce noise in our dependent variable. Second, we analyze our data using a
variant of simple ordinary least squares (OLS) regression that conditions on the average pre-
treatment performance data collected from participants in the three pre-treatment survey
waves (McKenzie, 2012). Third, we control for additional pre-treatment variables using a
double-LASSO approach (Belloni, Chernozhukov, and Hansen, 2014). Fourth, we pool data
from all four of our post-treatment periods to further increase statistical power. We detail
the construction of our outcome variables and our econometric strategy in Appendix E.
3 Results
Using the regression specification outlined in our pre-analysis plan, we find no average treat-
ment effect of access to the AI mentor on firm performance. This result is robust to whether
we winsorize performance at the 99% level (δ = 0.06 standard deviations (s.d.), p “ 0.35) or
the 95% level (δ = -0.01 s.d., p “ 0.80), and is also robust to the exclusion of 18 participants
who did not complete our entire post-treatment survey panel (95% winsorization: δ = -0.01
s.d., p = 0.88; 99% winsorization: δ = 0.06 s.d., p=0.34) (see Figure A4). Our failure to
reject the null stands in stark contrast to many recent experiments showing that access to
large language models leads to large, positive impacts on productivity (Brynjolfsson, Li, and
Raymond, 2023; Dell’Acqua et al., 2023; Noy and Zhang, 2023).
However, this overall null effect masks both positive and negative heterogeneous treat-
ment effects. Again following our pre-registration plan, we split our sample of entrepreneurs
7
based on pre-treatment performance.4 For those with below-median pre-treatment perfor-
mance (hereafter “low performers”) we find that access to the AI mentor reduced business
performance by 0.11 s.d. (p “ 0.0004),5 whereas for those with above-median pre-treatment
performance (hereafter “high performers”) the AI treatment increased business performance
by 0.20 s.d. (p “ 0.07).6,7 The negative treatment effect we observe among low performers
is equivalent to a 10% drop in profits or revenue for an entrepreneur whose pre-treatment
performance is just below the median, while the positive treatment effect we observe among
high performers is equivalent to a 20-25% increase for entrepreneurs whose pre-treatment
performance was just above the median.8 Figure 4 plots the distribution of post-treatment
performance changes for all four possible combinations of treatment status and binarized
pre-treatment performance. Relative to the control group, the distribution of performance
changes is shifted to the left for AI-treated low performers, but shifted to the right for AI-
treated high performers. In other words, our results differ from those of prior studies not
only in terms of the overall treatment effect but also in terms of the direction of treatment
effect heterogeneity with respect to pre-treatment performance levels (Noy and Zhang, 2023;
Peng et al., 2023; Brynjolfsson, Li, and Raymond, 2023; Dell’Acqua et al., 2023).
One major difference between our field experiment and prior research on the economic
impacts of generative AI is the level of discretion participants were granted in how and when
they used AI assistance. In previous experiments, experimenters narrowly constrained the
tasks participants completed, the extent to which they engaged with the AI tool (Bryn-
jolfsson, Li, and Raymond, 2023), and/or the length of time that they were granted use of
generative AI (Noy and Zhang, 2023; Dell’Acqua et al., 2023). In contrast, the entrepreneurs
in our experiment had much more discretion over how they used AI assistance. For instance,
4Following our pre-registration plan, we also test for heterogeneous treatment effects with respect to
both prior ChatGPT use and gender, as female entrepreneurs in developing economies often face additional
constraints compared to men, such as childcare (Delecourt and Fitzpatrick, 2021). We find no evidence of
heterogeneous treatment effects on either dimension.
5Appendix F discusses the ethical considerations for our study given that we detect this negative effect.
6Table A3 shows that these heterogeneous treatment effects are also robust to whether we winsorize
performance at the 95% or 99% level, and to the exclusion of the 18 participants who did not complete our
entire post-treatment survey panel.
7In Appendix G we show that our findings are not due to spillovers.
8Themedianentrepreneurinoursamplehasrevenuesof21,116KenyanSchillings. Thedistributionhasa
standard deviation of 25,273 Kenyan Schillings. These numbers imply that a 0.11 s.d. decrease corresponds
to a 13.1% drop relative to the median; a 0.21 s.d. increase to a 23.9% increase.
8
they were able to choose how many questions to ask the AI mentor, and the importance of
the tasks that they requested assistance with. They could also ask for assistance on a wide
range of topics, including, but not limited to financing, marketing, operations, and farming
practice.9 The discretion afforded to participants in our study suggests that differences in AI
usage between low and high performers might explain the heterogeneous treatment effects
that we observe in our sample.
We first test for differences in the quantity and quality of business-related questions that
treated entrepreneurs sent to the AI mentor.10 Figure 5 shows the distribution of number
of business questions asked by both high and low performers during our experiment. Both
distributionsarequiteskewed, withroughly15%ofentrepreneursaskingnotasinglebusiness
question and a small number of entrepreneurs asking one nearly every other day. We find
that among both high and low performers, those that did ask at least one business question
asked roughly one a week. Overall, the two distributions are extremely similar; although on
average, high performers sent 0.59 more messages than low performers, this difference is not
statisticallysignificant(p=0.33). Wealsotestfordifferencesinthehuman-evaluatedquality
of questions asked by low and high performers, and the length of questions asked by the two
groups; in both cases, we fail to detect a statistically significant difference (Table A5). In
other words, the negative returns to AI assistance for low performers cannot be explained
by differences in the number, quality, or length of questions that they asked the AI mentor
relative to high performers.
Although we do not detect differences in the quantity or quality of business questions
9Consistentwiththisargument,weconductapre-registeredanalysisoftheimpactoftheAImentorona
number of pre-specified questions designed to identify potential treatment effect mechanisms. We find little
evidencethattheAImentorledtoconsistentchangesinoursurveymeasuresofmanagementpractices,time
management, technology use, innovation, or information-seeking behavior (Figure A5). However, it is worth
notingthatifonly10%ofoursampleaskedaboutmanagement,10%abouttimeuse,10%abouttechnology,
and so on, then we would be severely under-powered to detect average treatment effects along any of these
individual dimensions. More broadly, the personalized nature of AI suggests that social scientists may need
to rethink how they identify the underlying mechanisms driving treatment effects when interventions are
personalized and/or algorithmic in nature.
10While most questions sent to the AI mentor were business-focused, some entrepreneurs also asked the
mentor about non-business topics (e.g. how to quit smoking) or sent in text by mistake (e.g. messages
intended for someone else). The entrepreneurs also sent in questions of varying quality, sometimes writing
full sentences and other times writing no more than a couple of cryptic words. Appendix I outlines the
process by which two human coders evaluated the focus and quality of each question sent to the AI mentor.
Our final dataset of business-related questions includes over 1,300 questions.
9
asked by high and low performers, this does not mean that the questions asked by the two
groups do not differ meaningfully; entrepreneurs in our study also had the freedom to choose
the topics they discussed with the AI mentor. Given that by definition, low performers had
weaker revenues and profits than high performers prior to our treatment intervention, one
possibility is that whether by choice or by necessity, low performers simply sought advice
on especially difficult tasks. These topics and problems may be well beyond what an AI
mentor—or even a human mentor—can help with, in part because these problems often
require financial capital and/or other complements to solve. For instance, a firm facing stiff
competition or a farm experiencing a drought might struggle even after receiving extremely
high-quality advice. Even changes that had a neutral impact on growth and/or sales could
have resulted in lower profits and worse performance, given that many of the AI mentor’s
recommendations were costly to implement. We use word embedding methods to develop
a principled and scalable measure of the extent to which each question in our dataset is
focused on an especially difficult business problem.11 Appendix J documents our approach
in detail. In short, we map each question onto a standardized uni-dimensional challenge-
focused measure. We do so by calculating the relative closeness of each question’s word
embedding vector to the word embedding vectors for two different benchmark questions, one
of which describes a business in dire straights and one of which describes a business facing
few challenges.
Our challenge-focused measure has strong face validity. Questions that are rated as more
challenge-focused tend to be about difficult problems that are unlikely to be fixed using an
AI mentor’s recommendations.12 Some of the most challenge-focused questions include:
1. “currentlyfacinglosesinmyshowshopduetolowdemandsrenderingbusinessbankrupt.
please advise” (99th percentile)
2. “hi, i have a beauty shop behind kenyatta university. at first it was the best selling
shop around but now it’s nearly the last. what could be the problem and how do i
solve it?” (95th percentile)
3. “i have a business competitor one in specific,,he has noticed that my business is doing
11Word embeddings map text into high dimensional vectors (Mikolov et al., 2013) and have been used to
measure semantic differences ranging from whether a startup idea is more likely to benefit women to how
cultural associations have evolved over the twentieth century (Cao, Koning, and Nanda, 2023; Kozlowski,
Taddy, and Evans, 2019).
12Table A6 shows above-median-length example questions pulled from the 50th to 100th percentiles of the
challenge-focused distribution, oversampling examples from the top decile.
10
well and has decided too the price of the products so i cannot get customers” (91st
percentile)
Conversely, theleastchallenge-focusedquestionsareclearlyfrombusinessesinlessharrowing
situations. These questions tend to focus on expansion and growth, as opposed to funda-
mental business challenges. It is plausible that the AI mentor is more effective at helping
entrepreneurs tackle these problems.13 Some of the least challenge-focused questions include:
1. “i have ksh 20000 to expand my business which it would specialize on selling food
stuffs. i would like to do this expansion in a new location. what should i consider first
to maximize my profit?” (1st percentile)
2. “i have been operating a cereals shop for five years and it is doing very well lately for
the last two years.which strategies can i use to expand the business to increase capacity
to serve many customers and increase the products i’m selling?” (2nd percentile)
3. “i run a salon and barber shop in one room, recently customers have started to gain
interest on massage after shave, this means there is need for expansion and more
resources, kindly help me to unlock this potential.” (17th percentile)
We test for differences in the difficulty of the questions posed by low and high performers
by regressing our measure of challenge-focused on our binarized measure of baseline firm
performance. We find that high performers do in fact ask questions that are less challenge-
focusedthanthoseaskedbylowperformers(δ =-0.22s.d., p “ 0.1). Thisfindingisrobustto
analyzing our data at the message-level, as opposed to the entrepreneur-level (δ = -0.25 s.d.,
p “ 0.04),14 and to regressing our measure of challenge-focused on a continuous, rather than
binarized measure of baseline firm performance (entrepreneur-level: δ = -0.36 s.d., p “ 0.05;
message-level: δ = -0.48 s.d., p “ 0.03).15 Figure 6 visualizes the relationship between
baseline firm performance and question difficulty using a binned scatter plot. There is a clear
negative relationship between an entrepreneur’s baseline performance and how challenge-
focused their questions are. In summary, whether by choice or by necessity, low-performing
entrepreneurs in our sample asked the AI mentor for assistance with more challenging tasks
than high performers.
This finding helps reconcile our inequality-increasing heterogeneous treatment effects
with recent results that suggest generative AI reduces differences in productivity (Noy and
13Table A7 shows above-median-length example questions pulled from the 1th to 49th percentiles of the
challenge-focused distribution, oversampling examples from the bottom decile.
14For message-level analyses we cluster standard errors at the level of the entrepreneur.
15These non-causal effect sizes correspond to a one standard deviation increase in an entrepreneur’s pre-
treatment performance index.
11
Zhang,2023;Pengetal.,2023;Brynjolfsson,Li,andRaymond,2023;Dell’Acquaetal.,2023).
Even if the returns to AI advice on any given task for low performers are greater than or
equal to the returns for high performers (as suggested by other studies), the endogenous
selection of low performers into asking questions about more challenging tasks could explain
our heterogeneous treatment effects. Figure 4 illustrates how the business impact of AI
advice within a task can be radically different than the aggregate impact of AI advice when
entrepreneurs, firms, and workers endogenously select the tasks for which they receive AI
assistance.
4 Discussion
Our findings highlight that in more open-ended and complex contexts, the productivity and
performance implications of generative AI fundamentally depend on the tasks for which
firms an |
34 | mckinsey | AI in the workplace_ A report for 2025 _ McKinsey.pdf | Superagency in the workplace: Empowering people to unlock AI’s
full potential
January 28, 2025 | Report Sign In|Subscribe
By Hannah Mayer, Lareina Yee, Michael Chui, and Roger Roberts
Almost all companies invest in AI, but just 1 percent believe they are at maturity. Our research nds
the biggest barrier to scaling is not employees—who are ready—but leaders, who are not steering fast
enough.
DOWNLOADS
Superagency in the workplace: Empowering people to unlock AI’s full potential
Full Report (47 pages)
A rticial intelligence has arrived in the workplace and has the potential to be as transformative as the steam engine was to the
19th-century Industrial Revolution.[1] With powerful and capable large language models (LLMs) developed by Anthropic, Cohere,
Google, Meta, Mistral, OpenAI, and others, we have entered a new information technology era. McKinsey research sizes the long-term AI
opportunity at $4.4 trillion in added productivity growth potential from corporate use cases.[2]
Therein lies the challenge: the long-term potential of AI is great, but the short-term returns are unclear. Over the next three years, 92
percent of companies plan to increase their AI investments. But while nearly all companies are investing in AI, only 1 percent of leaders
call their companies “mature” on the deployment spectrum, meaning that AI is fully integrated into workows and drives substantial
business outcomes. The big question is how business leaders can deploy capital and steer their organizations closer to AI maturity.
This research report, prompted by Reid Homan’s book Superagency: What Could Possibly Go Right with Our AI Future,[3] asks a similar
question: How can companies harness AI to amplify human agency and unlock new levels of creativity and productivity in the workplace?
AI could drive enormous positive and disruptive change. This transformation will take some time, but leaders must not be dissuaded.
Instead, they must advance boldly today to avoid becoming uncompetitive tomorrow. The history of major economic and technological
shifts shows that such moments can dene the rise and fall of companies. Over 40 years ago, the internet was born. Since then,
companies including Alphabet, Amazon, Apple, Meta, and Microsoft have attained trillion-dollar market capitalizations. Even more
profoundly, the internet changed the anatomy of work and access to information. AI now is like the internet many years ago: The risk for
business leaders is not thinking too big, but rather too small.
This report explores companies’ technology and business readiness for AI adoption (see sidebar “About the survey”). It concludes that
employees are ready for AI. The biggest barrier to success is leadership.
Chapter 1 looks at the rapid advancement of technology over the past two years and its implications for business adoption of AI.
Chapter 2 delves into the attitudes and perceptions of employees and leaders. Our research shows that employees are more ready for AI
than their leaders imagine. In fact, they are already using AI on a regular basis; are three times more likely than leaders realize to believe
that AI will replace 30 percent of their work in the next year; and are eager to gain AI skills. Still, AI optimists are only a slight majority in
the workplace; a large minority (41 percent) are more apprehensive and will need additional support. This is where millennials, who are
the most familiar with AI and are often in managerial roles, can be strong advocates for change.
Chapter 3 looks at the need for speed and safety in AI deployment. While leaders and employees want to move faster, trust and safety
are top concerns. About half of employees worry about AI inaccuracy and cybersecurity risks. That said, employees express greater
condence that their own companies, versus other organizations, will get AI right. The onus is on business leaders to prove them right, by
making bold and responsible decisions.
Chapter 4 examines how companies risk losing ground in the AI race if leaders do not set bold goals. As the hype around AI subsides,
companies should put a heightened focus on practical applications that empower employees in their daily jobs. These applications can
create competitive moats and generate measurable ROI. Across industries, functions, and geographies, companies that invest
strategically can go beyond using AI to drive incremental value and instead create transformative change.
Chapter 5 looks at what is required for leaders to set their teams up for success with AI. The challenge of AI in the workplace is not a
technology challenge. It is a business challenge that calls upon leaders to align teams, address AI headwinds, and rewire their companies
for change.
Chapter 1
An innovation as powerful as the steam engine
Imagine a world where machines not only perform physical labor but also think, learn, and make autonomous decisions. This world
includes humans in the loop, bringing people and machines together in a state of superagency that increases personal productivity and
creativity (see sidebar “AI superagency”). This is the transformative potential of AI, a technology with a potential impact poised to surpass
even the biggest innovations of the past, from the printing press to the automobile. AI does not just automate tasks but goes further by
automating cognitive functions. Unlike any invention before, AI-powered software can adapt, plan, guide—and even make—decisions.
That’s why AI can be a catalyst for unprecedented economic growth and societal change in virtually every aspect of life. It will reshape
our interaction with technology and with one another.
“Scientific discoveries and technological innovations are stones in the cathedral of human
progress.”
—Reid Homan, cofounder of LinkedIn and Inection AI, partner at Greylock Partners, and author
Many breakthrough technologies, including the internet, smartphones, and cloud computing, have transformed the way we live and work.
AI stands out from these inventions because it oers more than access to information. It can summarize, code, reason, engage in a
dialogue, and make choices. AI can lower skill barriers, helping more people acquire prociency in more elds, in any language and at
any time. AI holds the potential to shift the way people access and use knowledge. The result will be more ecient and eective problem
solving, enabling innovation that benets everyone.
Over the past two years, AI has advanced in leaps and bounds, and enterprise-level adoption has accelerated due to lower costs and
greater access to capabilities. Many notable AI innovations have emerged (Exhibit 1). For example, we have seen a rapid expansion of
context windows, or the short-term memory of LLMs. The larger a context window, the more information an LLM can process at once. To
illustrate, Google’s Gemini 1.5 could process one million tokens in February 2024, while its Gemini 1.5 Pro could process two million
tokens by June of that same year.[4] Overall, we see ve big innovations for business that are driving the next wave of impact: enhanced
intelligence and reasoning capabilities, agentic AI, multimodality, improved hardware innovation and computational power, and increased
transparency.
Exhibit 1
Intelligence and reasoning are improving
AI is becoming far more intelligent. One indicator is the performance of LLMs on standardized tests. OpenAI’s Chat GPT3.5, introduced
in 2022, demonstrated strong performance on high-school-level exams (for example, scoring in the 70th percentile on the SAT math and
the 87th percentile on the SAT verbal sections). However, it often struggled with broader reasoning. Today’s models are near the
intelligence level of people who hold advanced degrees. GPT4 can so easily pass the Uniform Bar Examination that it would rank in the
top 10 percent of test takers,[5] and it can answer 90 percent of questions correctly on the US Medical Licensing Examination.[6]
The advent of reasoning capabilities represents the next big leap forward for AI. Reasoning enhances AI’s capacity for complex decision
making, allowing models to move beyond basic comprehension to nuanced understanding and the ability to create step-by-step plans to
achieve goals. For businesses, this means they can ne-tune reasoning models and integrate them with domain-specic knowledge to
deliver actionable insights with greater accuracy. Models such as OpenAI’s o1 or Google’s Gemini 2.0 Flash Thinking Mode are capable of
reasoning in their responses, which gives users a human-like thought partner for their interactions, not just an information retrieval and
synthesis engine.[7]
Agentic AI is acting autonomously
“I’ve always thought of AI as the most profound technology humanity is working on . . .
more profound than fire or electricity or anything that we’ve done in the past.”
—Sundar Pichai, CEO of Alphabet
The ability to reason is growing more and more, allowing models to autonomously take actions and complete complex tasks across
workows. This is a profound step forward. As an example, in 2023, an AI bot could support call center representatives by synthesizing
and summarizing large volumes of data—including voice messages, text, and technical specications—to suggest responses to customer
queries. In 2025, an AI agent can converse with a customer and plan the actions it will take afterward—for example, processing a
payment, checking for fraud, and completing a shipping action.
Software companies are embedding agentic AI capabilities into their core products. For example, Salesforce’s Agentforce is a new layer
on its existing platform that enables users to easily build and deploy autonomous AI agents to handle complex tasks across workows,
such as simulating product launches and orchestrating marketing campaigns.[8] Marc Benio, Salesforce cofounder, chair, and CEO,
describes this as providing a “digital workforce” where humans and automated agents work together to achieve customer outcomes.[9]
Multimodality is bringing together text, audio, and video
Today’s AI models are evolving toward more advanced and diverse data processing capabilities across text, audio, and video. Over the
last two years, we have seen improvements in the quality of each modality. For example, Google’s Gemini Live has improved audio quality
and latency and can now deliver a human-like conversation with emotional nuance and expressiveness.[10] Also, demonstrations of Sora
by OpenAI show its ability to translate text to video.[11]
Hardware innovation is enhancing performance
Hardware innovation and the resulting increase in compute power continue to enhance AI performance. Specialized chips allow faster,
larger, and more versatile models. Enterprises can now adopt AI solutions that require high processing power, enabling real-time
applications and opportunities for scalability. For example, an e-commerce company could signicantly improve customer service by
implementing AI-driven chatbots that leverage advanced graphics processing units (GPUs) and tensor processing units (TPUs). Using
distributed cloud computing, the company could ensure optimal performance during peak trac periods. Integrating edge hardware, the
company could deploy models that analyze photos of damaged products to more accurately process insurance claims.
Transparency is increasing
“AI, like most transformative technologies, grows gradually, then arrives suddenly.”
—Reid Homan, cofounder of LinkedIn and Inection AI, partner at Greylock Partners, and author
AI is gradually becoming less risky, but it still lacks greater transparency and explainability. Both are critical for improving AI safety and
reducing the potential for bias, which are imperative for widescale enterprise deployment. There is still a long way to go, but new models
and iterations are rapidly improving. Stanford University’s Center for Research on Foundation Models (CRFM) reports signicant
advances in model performance. Its Transparency Index, which uses a scale of 1 to 100, shows that Anthropic’s transparency score
increased by 15 points to 51 and Amazon’s more than tripled to 41 between October 2023 and May 2024.[12]
Beyond LLMs, other forms of AI and machine learning (ML) are improving explainability, allowing the outputs of models that support
consequential decisions (for example, credit risk assessment) to be traced back to the data that informed them. In this way, critical
systems can be tested and monitored on a near-constant basis for bias and other everyday harms that arise from model drift and shifting
data inputs, which happens even in systems that were well calibrated before deployment.
All of this is crucial for detecting errors and ensuring compliance with regulations and company policies. Companies have improved
explainability practices and built necessary checks and balances, but they must be prepared to evolve continuously to keep up with
growing model capabilities.
Achieving AI superagency in the workplace is not simply about mastering technology. It is every bit as much about supporting people,
creating processes, and managing governance. The next chapters explore the nontechnological factors that will help shape the
deployment of AI in the workplace.
Chapter 2
Employees are ready for AI; now leaders must step up
Employees will be the ones to make their organizations AI powerhouses. They are more ready to embrace AI in the workplace than
business leaders imagine. They are more familiar with AI tools, they want more support and training, and they are more likely to believe AI
will replace at least a third of their work in the near future. Now it’s imperative that leaders step up. They have more permission space
than they realize, so it’s on them to be bold and capture the value of AI. Now.
“People are using [AI] to create amazing things. If we could see what each of us can do 10 or
20 years in the future, it would astonish us today.”
—Sam Altman, cofounder and CEO of OpenAI
Beyond the tipping point
In our survey, nearly all employees (94 percent) and C-suite leaders (99 percent) report having some level of familiarity with gen AI tools.
Nevertheless, business leaders underestimate how extensively their employees are using gen AI. C-suite leaders estimate that only 4
percent of employees use gen AI for at least 30 percent of their daily work, when in fact that percentage is three times greater, as self-
reported by employees (Exhibit 2). And while only a total of 20 percent of leaders believe employees will use gen AI for more than 30
percent of their daily tasks within a year, employees are twice as likely (47 percent) to believe they will (see sidebar “Who is using AI at
work? Nearly everyone, even skeptical employees”).
The good news is that our survey suggests three ways companies can accelerate AI adoption and move toward AI maturity.
Exhibit 2
Leaders can invest more in their employees
As noted at the beginning of this chapter, employees anticipate AI will have a dramatic impact on their work. Now they would like their
companies to invest in the training that will help them succeed. Nearly half of employees in our survey say they want more formal training
and believe it is the best way to boost AI adoption. They also would like access to AI tools in the form of betas or pilots, and they indicate
that incentives such as nancial rewards and recognition can improve uptake.
Yet employees are not getting the training and support they need. More than a fth report that they have received minimal to no support
(Exhibit 3). Outside the United States, employees also want more training (see sidebar “Global perspectives on training”).
Exhibit 3
Sidebar
Global perspectives on training
To get a clearer picture of global AI adoption trends, we looked at trends across ve countries: Australia, India, New Zealand,
Singapore, and the United Kingdom. Broadly speaking, these employees and C-suite leaders—the “international” group in this
report—have similar views of AI as their US peers. In some key areas, however, including the topic of training, their experiences
dier.
Many international employees are concerned about insucient training, even though they report receiving far more support than
US employees. Some 84 percent of international employees say they receive signicant or full organizational support to learn AI
skills, versus just over half of US employees. International employees also have more opportunities to participate in developing
gen AI tools at work than their US counterparts, with dierences of at least ten percentage points in activities such as providing
feedback, beta testing, and requesting specic features (exhibit).
C-suite leaders can help millennials lead the way
Many millennials aged 35 to 44 are managers and team leaders in their companies. In our survey, they self-report having the most
experience and enthusiasm about AI, making them natural champions of transformational change. Millennials are the most active
generation of AI users. Some 62 percent of 35- to 44-year-old employees report high levels of expertise with AI, compared with 50
percent of 18- to 24-year-old Gen Zers and 22 percent of baby boomers over 65 (Exhibit 4). By tapping into that enthusiasm and
expertise, leaders can help millennials play a crucial role in AI adoption.
Exhibit 4
Since many millennials are managers, they can support their teams to become more adept AI users. This helps push their companies
toward AI maturity. Two-thirds of managers say they eld questions from their team about how to use AI tools at least once a week, and a
similar percentage say they recommend AI tools to their teams to solve problems (Exhibit 5).
Exhibit 5
Since leaders have the permission space, they can be bolder
In many transformations, employees are not ready for change, but AI is dierent. Employee readiness and familiarity are high, which gives
business leaders the permission space to act. Leaders can listen to employees describe how they are using AI today and how they
envision their work being transformed. They also can provide employees with much-needed training and empower managers to move AI
use cases from pilot to scale.
It’s critical that leaders meet this moment. It’s the only way to accelerate the probability that their companies will reach AI maturity. But
they must move with alacrity, or they will fall behind.
Chapter 3
Delivering speed and safety
AI technology is advancing at record speed. ChatGPT was released about two years ago; OpenAI reports that usage now exceeds 300
million weekly users[13] and that over 90 percent of Fortune 500 companies employ its technology.[14] The internet did not reach this
level of usage until the early 2000s, nearly a decade after its inception.
“Soon after the first automobiles were on the road, there was the first car crash. But we
didn’t ban cars—we adopted speed limits, safety standards, licensing requirements, drunk-
driving laws, and other rules of the road.”
—Bill Gates, cofounder of Microsoft
The majority of employees describe themselves as AI optimists; Zoomers and Bloomers make up 59 percent of the workplace. Even
Gloomers, who are one of the two less-optimistic segments in our analysis, report high levels of gen AI familiarity, with over a quarter
saying they plan to use AI more next year.
Business leaders need to embrace this speed and optimism to ensure that their companies don’t get left behind. Yet despite all the
excitement and early experimentation, 47 percent of C-suite leaders say their organizations are developing and releasing gen AI tools too
slowly, citing talent skill gaps as a key reason for the delay (Exhibit 6).
Exhibit 6
Business leaders are trying to meet the need for speed by increasing investments in AI. Of the executives surveyed, 92 percent say they
expect to boost spending on AI in the next three years, with 55 percent expecting investments to increase by at least 10 percent from
current levels. But they can no longer just spend on AI without expecting results. As companies move on from the initial thrill of gen AI,
business leaders face increasing pressure to generate ROI from their gen AI deployments.
We are at a turning point. The initial AI excitement may be waning, but the technology is accelerating. Bold and purposeful strategies are
needed to set the stage for future success. Leaders are taking the rst step: One quarter of those executives we surveyed have dened a
gen AI road map, while just over half have a draft that is being rened (Exhibit 7). With technology changing this fast, all road maps and
plans will evolve constantly. For leaders, the key is to make some clear choices about what valuable opportunities they choose to pursue
rst—and how they will work together with peers, teams, and partners to deliver that value.
Exhibit 7
The dilemma of speed versus safety
There’s a spanner in the works: Regulation and safety often continue to be seen as insurmountable challenges rather than opportunities.
Leaders want to increase AI investments and accelerate development, but they wrestle with how to make AI safe in the workplace. Data
security, hallucinations, biased outputs, and misuse (for example, creating harmful content or enabling fraud) are challenges that cannot
be ignored. Employees are well aware of AI’s safety challenges. Their top concerns are cybersecurity, privacy, and accuracy (Exhibit 8).
But what will it take for leaders to address these concerns while also moving ahead at light speed?
Exhibit 8
Employees trust business leaders to get it right
While employees acknowledge the risks and even the likelihood that AI may replace a considerable portion of their work, they place high
trust in their own employers to deploy AI safely and ethically. Notably, 71 percent of employees trust their employers to act ethically as
they develop AI. In fact, they trust their employers more than universities, large technology companies, and tech start-ups (Exhibit 9).
Exhibit 9
According to our research, this is in line with a broader trend in which employees show higher trust in their employers to do the right
thing in general (73 percent) than in other institutions, including the government (45 percent). This trust should help leaders act with
condence as they tackle the speed-versus-safety dilemma. That condence also applies outside the United States, even though
employees in other regions may have more desire for regulation (see sidebar “Global perspectives on regulation”).
Sidebar
Global perspectives on regulation
A high percentage of international C-suite leaders we surveyed across ve regions (Australia, India, New Zealand, Singapore,
and the United Kingdom) are Gloomers, who favor greater regulatory oversight. Between 37 to 50 percent of international C-
suite leaders self-identify as Gloomers, versus 31 percent in the United States. This may be because top-down regulation is more
accepted in many countries outside the United States. Of the global C-suite leaders surveyed, half or more worry that ethical use
and data privacy issues are holding back their employees from adopting gen AI.
However, our research shows that attitudes about regulation are not inhibiting the economic expectations of business leaders
outside the United States. More than half of the international executives (versus 41 percent of US executives) indicate they want
their companies to be among the rst adopters of AI, with those in India and Singapore being especially bullish (exhibit). The
desire of international business leaders to be AI rst movers can be explained by the revenue they expect from their AI
deployments. Some 31 percent of international C-suite leaders say they expect AI to deliver a revenue uplift of more than 10
percent in the next three years, versus just 17 percent of US leaders. Indian executives are the most optimistic, with 55 percent
expecting a revenue uplift of 10 percent or more over the next three years.
Risk management for gen AI
In Superagency, Homan argues that new risks naturally accompany new capabilities—meaning they should be managed but not
necessarily eliminated.[15] Leaders need to contend with external threats, such as infringement on intellectual property (IP), AI-enabled
malware, and internal threats that arise from the AI adoption process. The rst step in building t-for-purpose risk management is to
launch a comprehensive assessment to identify potential vulnerabilities in each of a company’s businesses. Leaders can then establish a
robust governance structure, implement real-time monitoring and control mechanisms, and ensure continuous training and adherence to
regulatory requirements.
One powerful control mechanism is respected third-party benchmarking that can increase AI safety and trust. Examples include Stanford
CRFM’s Holistic Evaluation of Language Models (HELM) initiative—which oers comprehensive benchmarks to assess the fairness,
accountability, transparency, and broader societal impact of a company’s AI systems—as well as MLCommons’s AILuminate tool kit on
which researchers from Stanford collaborated.[16] Other organizations such as the Data & Trust Alliance unite large companies to create
cross-industry metadata standards that aim to bring more transparency to enterprise AI models.
While benchmarks have signicant potential to build trust, our survey shows that only 39 percent of C-suite leaders use them to evaluate
their AI systems. Furthermore, when leaders do use benchmarks, they opt to measure operational metrics (for example, scalability,
reliability, robustness, and cost eciency) and performance-related metrics (including accuracy, precision, F1 score, latency, and
throughput). These benchmarking eorts tend to be less focused on ethical and compliance concerns: Only 17 percent of C-suite leaders
who benchmark say it’s most important to measure fairness, bias, transparency, privacy, and regulatory issues (Exhibit 10).
Exhibit 10
The focus on operational and performance metrics reects the understandable desire to prioritize immediate technical and business
outcomes. But ignoring ethical considerations can come back to haunt leaders. When employees don’t trust AI systems, they are less
likely to accept them. Although benchmarks are not a panacea to eliminate all risk and can’t ensure that AI systems are fully ecient,
ethical, and safe, they are a useful tool.
Even companies that excel at all three categories of AI readiness—technology, employees, and safety—are not necessarily scaling or
delivering the value expected. Nevertheless, leaders can harness the power of big ambitions to transform their companies with AI. The
next chapter examines how.
Chapter 4
Embracing bigger ambitions
Most organizations that have invested in AI are not getting the returns they had hoped. They are not winning the full economic potential
of AI. About half of C-suite leaders at companies that have deployed AI describe their initiatives as still developing or expanding (Exhibit
11). They have had the time to move further. Our research shows that more than two-thirds of leaders launched their rst gen AI use cases
over a year ago.
“This is a time when you should be getting benefits [from AI] and hope that your
competitors are just playing around and experimenting.”
—
Erik Brynjolfsson, professor at Stanford University and director of the Digital Economy Lab at the Stanford Institute for Human-
Centered Articial Intelligence (HAI)
Exhibit 11
Pilots fail to scale for many reasons. Common culprits are poorly designed or executed strategies, but a lack of bold ambitions can be just
as crippling. This chapter looks at patterns governing today’s investments in AI across industries and suggests the potential awaiting
those who can dream bigger.
AI investments vary by industry
Dierent industries have dierent AI investment patterns. Within the top 25 percent of spenders, companies in healthcare, technology,
media and telecom, advanced industries, and agriculture are ahead of the pack (Exhibit 12). Companies in nancial services, energy and
materials, consumer goods and retail, hardware engineering and construction, and travel, transport, and logistics are spending less. The
consumer industry—despite boasting the second-highest potential for value realization from AI—seems least willing to invest, with only 7
percent of respondents qualifying in the top quartile, based on self-reported percentage of revenue spend on gen AI. That hesitation may
be explained by the industry’s low average net margins in mass-market categories and thus higher condence thresholds for adopting
costly organization-wide technology upgrades.
Exhibit 12
In some industries, employees are cautious
Employees in the public sector, as well as the aerospace and defense and semiconductor industries, are largely skeptical about the
development of AI’s future. In the public sector and aerospace and defense, only 20 percent of employees anticipate that AI will have a
signicant impact on their daily tasks in the next year, versus roughly two-thirds in media and entertainment (65 percent) and telecom, at
67 percent (Exhibit 13). What’s more, our survey shows that just 31 percent of social sector employees trust that their employers will
develop AI safely. That’s the least condence in any industry; the cross-industry average is 71 percent.
Exhibit 13
Employees in the public sector, aerospace, and semiconductor industries are the least optimistic about gen AI.
US employee sentiment on gen AI, % of respondents
Expect workows to change by 30% in the next year
Telecom
Media and entertainment
Real estate
Metals and mining
Oil and gas
Chemicals
Note: Level of familiarity is dened as those who have “extensive experience (use several tools for complex tasks)” and “experts.” High trust is “Level 4” and “Level 5” on a scale of 1 to 5. Perceived accuracy is based on past gen AI usage in a
workplace setting.
Source: The economic potential of generative AI: The next productivity frontier, McKinsey, June 14, 2023; McKinsey US employee survey, Oct–Nov, 2024 (n = 3,002)
McKinsey & Company
Employees’ relative caution about AI in these sectors likely reects near-term challenges posed by external constraints such as rigorous
regulatory oversight, outdated IT systems, and lengthy approval processes.
There’s a lot of headroom in some functions
Our research nds that the functional areas where AI presents the greatest economic potential are also those where employee outlook is
lukewarm. Employees in sales and marketing, software engineering, customer service, and R&D contribute roughly three-quarters of AI’s
total economic potential, but the self-reported optimism of employees in these functions is middling (Exhibit 14). It may be the case that
these functions have piloted AI projects, leading employees to be more realistic about AI’s benets and limitations. Or perhaps the
economic potential has made them worry that AI could replace their jobs. Whatever the reasons, leaders in these functions might
consider investing more in employee support and elevating the change champions who can improve that sentiment.
Exhibit 14
Gen AI has not delivered enterprise-wide ROI, but that can change
Across all industries, surveyed C-level executives report limited returns on enterprise-wide AI investments. Only 19 percent say revenues
have increased more than 5 percent, with another 39 percent seeing a moderate increase of 1 to 5 percent, and 36 percent reporting no
change (Exhibit 15). And only 23 percent see AI delivering any favorable change in costs.
Exhibit 15
Despite this, company leaders are optimistic about the value they can capture in the coming years. A full 87 percent of executives expect
revenue growth from gen AI within the next three years, and about half say it could boost revenues by more than 5 percent in that time
frame (Exhibit 16). That suggests quite a lot could change for the better over the next few years.
Exhibit 16
Big ambitions can help solve big problems
To drive revenue growth and improve ROI, business leaders may need to commit to transformative AI possibilities. As the hype around AI
subsides and the focus shifts to value, there is a heightened attention on practical applications that can create competitive moats.
“[It] is critical to have a genuinely inspiring vision of the future [with AI] and not just a
plan to fight fires.”
—Dario Amodei, cofounder and CEO of Anthropic
To assess how far along companies are in this shift, we examined three categories of AI applications: personal use, business use, and
societal use (see sidebar “AI’s potential to enhance our personal lives”). We mapped over 250 applications from our work and publicly
shared examples to understand the spectrum of impact levels, from localized use ca |
35 | mckinsey | genai_20in_20norway_eng_version_v2.pdf | The economic
potential of
Generative AI
in Norway
The next productivity frontier
June 2023
CONFIDENTIAL AND PROPRIETARY
Any use of this material without specific permission of McKinsey & Company
is strictly prohibited
About this document
In the newest report from McKinsey Global
Institute (MGI), MGI discuss how GenAI can
transform the way we work
To assess the effect of GenAI adoption in
Norway and the Norwegian workforce and
businesses, McKinsey Norway used numbers
calculated by MGI, and method applied
there, with Norwegian revenue1,
employment and education data from SSB
(Statistics Norway)
Additional data was from Statista, European
Commission, Eurostat, OECD, and GEDI
1. 2020, the most recently available at the time of writing
McKinsey & Company 2
Generative AI (GenAI) is experiencing significant momentum globally and is expected to gain
traction in Norway with value creation potential of 95-159 bn NOK by 2045 across Norwegian
industries
We expect Norway to be a leading global adopter of GenAI due to the economic
environment, education level of the population, and high degrees of digital adoption
The impact of Generative AI will fall heavily on occupations requiring higher levels of education.
Norway is the 10th highest educated country in the world, and much of the workforce is classified
as knowledge-workers, typically with high wages. This increases the feasibility of early adoption
of GenAI in daily activities
The highest potential value in Norway is expected to be unlocked in selected sectors,
Executive including Energy, High Tech, Travel, Transport & Logistics, and Retail, but true value unlock
comes from three major business functions as opposed to sectors
summary
Marketing and Sales (28-43 bn NOK), Software Engineering (21-43 bn NOK), and Customer
Operations (12-17 bn NOK) will drive the highest amount of value unlock in Norway due to
the high degree of “generation” activities i.e., generating content such as marketing material,
code and emails
While the highest potential value is expected to be unlocked in the Energy industry (~21 bn
NOK), High Tech (~18 bn NOK) is expected to experience a more disruptive shift (7%) following
the adoption of GenAI
Productivity growth has slowed in the last decade but will likely be advanced by GenAI. We
expect work activities within decision making and collaboration, and data management, to be most
affected by GenAI. Such activities are most commonly performed by highly educated workers, and
educators / workforce trainers, employees within business and legal professions, and STEM
professionals, are likely to see the largest productivity gains upon GenAI adoption
MMccKKiinnsseeyy && CCoommppaannyy 33
What is Generative AI?
Suitable Unsuitable
Non-exhaustive
Generative AI (GenAI) enables the creation of new Although some areas are unsuited for GenAI, several
unstructured content, such as text, images, etc. applications emerge2:
Recent GenAI efforts are powered by Foundational
Code/image/audio/video/text generation and editing,
Models trained on a broad set of data that enables
while taking surrounding context into account
them to respond to a wide range of prompts.
Conversational interfaces to convert natural language
These models are typically also better at interpreting /
dialog into specific executions of a technical system
labelling unstructured data than traditional AI
Querying a large set of unstructured data, and
synthesizing a human readable output
High-stakes scenarios with potential for harm
Unconstrained, long, open-ended generation that may
expose harmful or biased content to users
Generate marketing or Automate code generation
social media copy in ”house in programming languages Applications requiring explainability and/or full
style” using ChatGPT, like Python with Codex /
understanding of potential failure modes, including
Copy.A, etc. Github Copilot, etc.
numerical reasoning1
1. Current topic of research: how to use GPT-like models to generate code that involves solving numerical problems
2. Additional resources can be found in the McKinsey Report “Economic potential of generative AI”, and the article “What every CEO should know about generative AI”
Source: Press search; expert interviews MMccKKiinnsseeyy && CCoommppaannyy 44
Automation
A multinational tech company offers a GenAI
GenAI will mainly Giving software predictable tasks
app which can read customer emails and
generate well-documented tickets based
that can be more easily automated
impact three areas,
on these
today with FM powered GenAI
leading to
reinvention of major
processes in Norway
and rest of world
A GenAI-chatbot is already in use in several
Augmentation
large Norwegian banks, and institutions, to
improve productivity and reduce use of
Enhance human productivity to do
human agents in more simple cases
work more efficiently
A large Norwegian house building company
Acceleration
has invested heavily in GenAI for product
development, using it to generate thousands
Extract and index knowledge to
of building configurations prior to any
building activity, allowing for more thorough
shorten innovation cycles enabling
checks, e.g., ensuring that building
dimensions follow regulation
continuous innovation
Source: QuantumBlack: AI by McKinsey; press search McKinsey & Company 5
Norway is expected to be an early adopter of automation with other
economies such as the US and Germany
China Germany France India Japan Mexico US Nordics2 Global avg
Automation adoption, generative AI early scenario1, % automation Automation adoption, generative AI late scenario1, % automation
100% 100%
90% 90%
80% 80%
70% 70%
60% 60%
50% 50%
40% 40%
30% 30%
In early scenario, In late scenario, the 50%
developed economies can threshold is achieved at
20% 20%
achieve more than 50% least 20 years later, with
automation adoption by larger differences between
10% 2030 10% countries
0% 0%
2025 30 35 40 45 50 55 2060 2030 40 50 60 70 80 2090
1. Early scenario -aggressive scenario all key model parameters (tech automation, integration timeline, economic feasibility, regulatory and public adoption); late scenario -parameters are set for the later adoption potential
2. McKinsey Norway estimate
Source: McKinsey Global Institute
The Norwegian digital foundation and education level are key
advantages that can drive nationwide GenAI adoption
Human capital Integration of digital technology
Connectivity Digital public services
Share of population with tertiary
Digital economy and society index1, 2022 education2, 2022 %, aged 25-34 Comments
70
• Norway has one of the highest education
levels in the world, leading to an affluent, skilled
60 workforce that is adaptable and open to learning,
making new technology adoption
economically feasible
50
• Norway has a large population of knowledge
workers, whom typically have a high proportion of
40 activities that can see a productivity boost from
using GenAI to augment knowledge-
based activities
30
• Norway ranks 5th in the 2022 DESI Index –
emphasizing the Norwegian society’s strong
20 digital foundation and GenAI transformation
potential
10 • Norway has a robust digital infrastructure with
>55 40-<45
high internet penetration rates and widespread
50-<55 35-<40 access to fast broadband. This kind of
0 environment is conducive to the growth and
45-<50 <35
Fl DK NL SE NO IE FR DE EU IT HR HU BG RO
adoption of AI technologies.
1. The Digital Economy and Society Index (DESI), non-exhaustive country list
2. Eurostat “Educational attainment statistics”
Source: McKinsey Global Institute; European Commission; press search; Eurostat McKinsey & Company 7
X % of GDP Value realized by 2030
Value realized by 2045
Value potential per industry2, bn NOK
Energy3 16-26 0.4 %
High tech4 12-24 0.3 %
Travel, transport & logistics 13-21 0.3 %
The potential value Retail 13-20 0.3 %
unlock from GenAI Advanced manufacturing5 8-13 0.2 %
Real estate 6-10 0.1 %
is 95-159 bn NOK
Basic materials 5-9 0.1 %
across Norwegian
Banking 5-9 0.1 %
industries1 …
Consumer packaged goods 5-8 0.1%
Professional services 5-7 0.1%
Telecommunications 2-3 0.0 %
Insurance 2-3 0.0 %
Healthcare 2-3 0.0 %
Media 1-3 0.0 %
Chemical <1 0.0 %
Agriculture <1 0.0 %
1. Based on the early adoption scenario, median expected impact of GenAI, %
of industry revenues. 2020 revenues, inflation adjusted
2. By 2030, ~60% of the value potential will be unlocked, by 2045 100% of Pharma & medical products <1 0.0 %
the value will be unlocked. Calculations based on 2020 industry revenues
3. Includes utilities and oil and gas, of which oil and gas contributes
~85% of revenues
4. Includes advanced electronics Total 95-159 2.4%
5. Includes automotive and assembly, and aerospace and defense
Source: Internal experts; annual reports; Statista MMccKKiinnsseeyy && CCoommppaannyy 88
Value realized by 2030
Value potential per business function1, bn NOK Value realized by 2045
Marketing and sales 28-43
… But business Software engineering 21-43
functions, as
Customer operations 12-17
opposed to specific
industries, will be
Supply chain and operations 10-19
the driving forces of
value creation Product and R&D 8-15
Risk and legal 7-9
Strategy and finance 4-9
Talent and organization 2-3
1. Based on the early adoption scenario. By 2030, ~60% of the value
potential will be unlocked, by 2045 100%of the value will be unlocked. Corporate IT2 1-2
Calculations based on 2020 industry revenues
2. Excluding corporate software engineering, including activities such as
e.g., network maintenance
SSoouurrccee:: IInntteerrnnaall eexxppeerrttss,; Danantaubaal sreepso: rAtsn;n SuSalB reports and SSB MMccKKiinnsseeyy && CCoommppaannyy 99
Productivity growth, the main engine of GDP growth, slowed down
in the last decade but is likely to be advanced by GenAI
Employment growth Additional with GenAI
Productivity growth Without GenAI1
Productivity growth bigger contributor to GDP growth
Global GDP growth, Productivity impact from automation,
CAGR, % 2022-40, CAGR2, % Comments
Examining the real GDP
growth contribution of
3.8
Global3 Norway
employment and
3.7 productivity growth,
increasedproductivity
3.1
3.1 1,3
2.9 3.3 0,7 has been the main engine
2.8
for GDP growth
0,6
Implementation of GenAI
0,8
1,4 can significantly
contribute to increased
2,5 productivity in Norway
2,0
going forward
3,0
2,5
2,6
2,1
0.9
1,7
0,3
0,8
0,7 0.2
0,6
0.1
0.1
1972-82 1982-92 1992-2002 2002-2012 2012-2022 Early scenario Late scenario
Early scenario Late scenario
1. Previous assessment of work automation before the rise of generative AI
2. Based on the assumption that the automated work hours are integrated back to work at productivity level of today
3. Based on 47 countries which constitute almost 80% of the world employment
Source: The Conference Board Total Economy database; Oxford Economics; McKinsey Global Institute QuantumBlack, AI by McKinsey 10
CONFIDENTIAL AND PROPRIETARY
Key activities forecasted to be affected are typically executed by
employees holding an advanced degree
With generative AI
Without generative AI1
Incremental technical
automation potential
Overall technical automation potential, Share of NO
Education level Comparison in midpoint scenarios, % in 2023 work force1, % Comments
• Higher educated workers are likely set
57%
Master, PhD or similar 13% to see the largest incremental impact
28% 2X
from automation as they land in jobs
as “knowledge workers” which spend a
high share of their time on activities
most likely to benefit from GenAI
60%
Bachelor’s degree 29%
(i.e., applying expertise to planning and
36% 1.7x
creative tasks, managing and
stakeholder management).
• An example of this is within science:
researchers spend ~30 minutes to read
64%
High school diploma 36% one scientific paper2, but GenAI could
51% 1.2X
or equivalent
summarize hundreds of papers in
minutes
Without a high school 63%
19%
degree 54% 1.2X
1. Does not sum up to 100% due to some minor educational levels not included
2. 2014 statistic
Source: McKinsey Global Institute; SSB; OECD; Scientific American article “Scientists Reading Fewer Papers for First Time in 35 Years”, 2014 McKinsey & Company 11
GenAI could have the biggest impact on activities which previously
had a lower potential for automation
Automation potential of more than 50% with GenAI With GenAI
Incremental technical Automation potential of more than 50% without GenAI Without GenAI1
automation potential with GenAI
Overall technical automation potential, Share of NO
Activity groups2 comparison in midpoint scenarios, % in 2023 employment, % Comments
Decision 59% • Prior to GenAI, only 2 in 7
Applying expertise3 20%
making and 25% +34 p.p. Norwegians held roles
collaboration which had an automation
49%
Managing4 9% potential of more than
16% +34 p.p.
50%. Following the advent
of GenAI, that number has
Interfacing with 45%
8% risen to 1 in 2
stakeholders 24% +21 p.p.
• GenAI plays the largest
impact on data driven
Data 91%
Processing data 12%
decision making and
management 73% +18 p.p.
collaboration, while
79% physical laborers will likely
Collecting data 2%
68% +11 p.p. not see a significant change
from the rise of GenAI in the
Physical Performing unpredictable 46% workplace
34%
physical work5 46% +1 p.p. • With Generative AI,
technical automation
Performing predictable 73%
15% potential could already
physical work6 73% +1 p.p.
reach 91% for data
1. Previous assessment of work automation before the rise of generative AI processing and 79% for
2. Jobs are categorized by main activity, but some jobs include activity from multiple groups data collection in 2023
3. Applying expertise to decision making, planning, and creative tasks
4. Managing and developing people
5. Physical activities and operating machinery in unpredictable environments
6. Physical activities and operating machinery in predictable environments
Source: McKinsey Global Institute analysis; SSB McKinsey & Company 12
The 7 largest occupational groups, representing >70% of Norwegian
workers, can expect a large productivity uplift from GenAI
With GenAI Without GenAI Top 7 largest occupational groups Low High
Uplift from Share of NO No. of NO
Occupational groups Overall technical automation potential, % in 2023 GenAI, p.p. employment, % employment1, 000s
Educators and workforce training 54 39 p.p. 12 % 285
15
Customer service and sales 57 12 p.p. 11 % 263
45
Business and legal professionals 62 30 p.p. 11 % 256
32
STEM professionals 57 29 p.p. 10 % 239
28
Community services 65 26 p.p. 10 % 237
39
Managers 44 17 p.p. 8 % 197
27
Health professionals 43 14 p.p. 8 % 197
29
Builders 53 4 p.p. 6 % 153
49
Mechanical installation and repair 67 6 p.p. 5 % 122
61
Transportation services 49 7 p.p. 4 % 96
42
Food services 78
8 p.p. 4 % 91
70
Office support 87
21 p.p. 3 % 84
66
Property maintenance 38
9 p.p. 3 % 84
29
Agriculture 63
4 p.p. 2 % 40
59
Creatives and arts management 53
25 p.p. 1 % 32
28
Health aides, technicians, and wellness 43
9 p.p. 1 % 21
34
Production work 82
9 p.p. 1 % 21
73
Total 63
12 p.p. 100% 2 418
51
1. Jobs with <5k holding the job title excluded by SSB McKinsey & Company 13
Source: McKinsey Global Institute; SSB
Norway can realize significant value from GenAI, mainly unlocked
by automating activities performed by white-collar workers
Norway is primed for adoption of GenAI due
to high levels of education and strong
digital foundation …
… with the potential to unlock values up to
~127 billion NOK across various industries …
… mainly due to productivity gains from
activities related to decision making,
collaboration and data management
MMccKKiinnsseeyy && CCoommppaannyy 1144
Appendix
MMccKKiinnsseeyy && CCoommppaannyy 1155
The midpoint scenario at which automation adoption could reach
50% of time spent on current work activities has accelerated by a
decade
Updated early scenario including generative AI2 2017 early scenario2
Global automation of time spent on current work activities1, %
Updated late scenario including generative AI3 2017 late scenario3
100%
90%
80%
70%
60%
Midpoint 2017 50%
50%
Midpoint
40% updated
The advent of GenAI has sped up
the automation timeline by ~10
30%
years from previous estimates in
20% which GenAI was not considered
10%
0%
2020 2025 2030 2035 2040 2045 2050 2055 2060 2065 2070 2075 2080 2085 2090 2095 2100
1. Includes data from 47 countries representing about 80% of employment across the world. 2017 estimates are based on the activity and occupation mix from 2016. Scenarios including generative AI are based on the 2021
activity and occupation mix
2. Early scenario: aggressive scenario for all key model parameters (technical automation potential, integration timelines, economic feasibility, and technology diffusion rates)
3. Late scenario: parameters are set for later adoption potential.
Source: McKinsey Global Institute McKinsey & Company 16
GenAI is expected to have different impact across the business
functions dependent on industry sizes
Generative AI productivity impact by business functions1, % of industry revenue
Impact in bn NOK Low High Impact as % of industry rev. Low High Low High
Total Expected Total added
Supply chain Corporate IT
industry impact of value from Marketing Customer Product and Software Risk and Strategy and Talent and
and (excluding
size2, % of GenAI, % of GenAI, and sales operations R&D engineering legal finance organization
operations SWE)
total revenue industry rev. bn NOK
Total2bn NOK 6,754 95 –159 28 -43 12 -17 8 -15 21 -43 10 -19 7 -9 4 -9 1 -2 2 -3
Energy 22% 1% -1.6% 16 -26
High tech 4% 4.8% -9.3% 12 -24
Travel, transport & logistics 14% 1.2% -2% 12 -21
Retail 14% 1.2% -1.9% 12 -20
Advanced manufacturing 7% 1.4% -2.4% 8 -13
Real estate 8% 1% -1.7% 6 -10
Basic materials 10% 0.7% -1.2% 5 -9
Banking 3% 2.8% -4.7% 5 -9
Consumer packaged goods 5% 1.4% -2.3% 5 -8
Professional services 7% 0.9% -1.4% 5 -7
Telecommunications 1% 2.3% -3.7% 2 -3
Insurance 1% 1.8% -2.8% 2 -3
Healthcare 1% 1.8% -3.2% 2-3
Media 1% 1.5% -2.6% 2-3
Chemical 1% 0.8% -1.3% 0.5 -1
Agriculture 1% 0.6% -1% 0 -0.5
Pharma & medical products 0% 2.6% -4.5% 0
1. Excl. implementation costs (e.g., training, licenses)
2. Figures may not sum to 100% because of rounding
Source: Internal experts; McKinsey Global Institute;annual reports; SSB MMccKKiinnsseeyy && CCoommppaannyy 1177
GenAI can reduce the cost of large effort tasks, enabled through
4 archetype of applications which are emerging across industries
Not exhaustive for all use cases for Generative AI
Content synthesis Coding & Creative Customer
(virtual expert) software content engagment1
GenAI Generate insights and drive Interpret and generate code Create marketing messages, Streamline interactions by
capability actions based on summarization and documentation, i.e., and images, support ideation for interpreting text and analyze
and synthesis of unstructured improving efficiency and reducing new product development and customer journeys through
data technical debt generate personalized marketing customer service, chatbots,
copy recommenders, task automation,
etc.
Use case Summarize text or audio and Generate code and assist Generate visuals (images, Streamline customer
generate insights developers designs, 3D models) to communications, e.g.,
Perform actions triggered by Refactor translate code to accelerate the product design customer service issue
user prompt accelerate mainframe process resolution (driving action to
Augment capabilities of migration Draft and personalize resolve) and Q&A
operations staff (e.g., Create model outbound customer comms Model and predict elements
inventory/maintenance documentation (e.g., risk) or marketing in patient or customer journey
management)
1. Includes B2B customer interactions and transactions
Source: McKinsey analysis MMccKKiinnsseeyy && CCoommppaannyy 1188
Impact as % of industry revenues, bubble size proportional to bn NOK impact: Small Large
The energy Impact1, median calculation, bn NOK
24
sector has the
22
highest value
Energy
20
potential, but
18 High Tech
GenAI will be
Travel, Transport & Logistics
16
most disruptive
Retail
14
in High Tech
12
Advanced Manufacturing
10
Basic Materials
8 Real Estate
Banking
6
Consumer Packaged Goods
Professional services
4
Healthcare
Insurance
2 Telecommunications
Agriculture Media
Chemical Pharma & Medical Products
0
0% 1% 2% 3% 4% 5% 6% 7% 8%
1. Based on the early adoption scenario, median
Impact as % of industry revenues
expected impact of GenAI, % of industry
revenues. 2020 revenues, inflation adjusted
SSoouurrccee:: IMncteKrinnasle eyx Gpelortbsa, lD Inastatibtuatsees: Annual reports, SSB MMccKKiinnsseeyy && CCoommppaannyy 1199
>50% of the value unlock can be achieved in two large
business functions
Deep dive follows
Business functions Value potential from GenAI1, bn NOK
Marketing & sales 28 - 43
Software engineering 21 - 43
Customer operations 12 - 17
Supply chain & operations 10 - 19
Product and R&D 8 - 15
Risk & legal 7 - 9
Strategy & finance 4 - 9
Talent & org. 2 - 3
Corporate IT (excl. SWE) 1 - 2
1. Excl. implementation costs (e.g., training, licenses)
Source: Internal experts; annual reports; SSB MMccKKiinnsseeyy && CCoommppaannyy 2200
1: Marketing & Sales
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day marketing executive
% time spent
Writing marketing and sales copy Augment sales teams with technical
content of text, images and videos proprietary knowledge and historic
customer interactions
Emails 13
Improving sales force, e.g., by
Generate personalized marketing content
flagging risks, recommending next
based on (un)structured data from consumer
interactions
profiles and community insights Meetings 38
Analyzing customer feedback Automate booking management and
customer follow-up during travels Designs and edits 13
Analysis 25
Key CPG
industries Retail Other admin 13
Travel, Transport & Logistics
Insurance
Total
Financial services
Total value 28 - 43
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2211
“50% of code on
GitHub is written by an
2: Software Engineering AI, e.g., a co-pilot doing
code suggestions,
Productivity opportunity with GenAI
corrections and writing”
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day software engineer
% time spent
Generating, prioritizing, and Create alerts and automated bots based on
running code news, industry reports, internal research and
economic trends that can impact trading
Meetings 10
strategies
Generating synthetic data to improve
training accuracy of ML models Generate code that creates hyper-
personalized trip recommendations Coding 50
Reviewing code for defects and
Accelerate transition from legacy software /
inefficiencies
code (e.g., banks still use system written in
Debugging 20
COBOL) to modern
Emails 10
Key High Tech
industries Media Admin 10
CPG
Retail
Total
Energy
Insurance
Total value 21 - 43
Financial services
potential, bn NOK
Source: McKinsey Global Institute; internal experts MMccKKiinnsseeyy && CCoommppaannyy 2222
3: Customer Operations
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day call center
% time spent
Auto-generating customer profile Zero customer service reps, with all internal
and segment for each unique helpdesk automated via self-serve and GenAI-
customer powered chatbots to handle all omnichannel
Admin 13
helpdesk engagement
Generating post call summary to
Summarize speech to distinctive text to create
customers and agents Customer care 47
records of customer complaints
Developing first-line response in Manage disruptions during vacations by being
Internal calls 6
customer service for all inquiries first point of contact for customers, offer
translation and content customized for the
customer and their vacation Problem solving 25
Email / chat 6
Key CPG
industries Retail
Other 3
Insurance
Financial services
Total
Travel, Transport & Logistics
Telecommunications
Total value 12 - 17
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2233
4: Supply Chain & Operations
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day supply chain manager
% time spent
Warehouse and inventory Interpreting data, labelling unstructured data
management and identifying patterns for future trends
and demand
E-mail 10
Forecasting demand and Synthesizing data from previous jobs to predict
disruptions in supply chain potential issues
Meetings 25
Act as an intelligent maintenance or safety
Optimize transportation route advisor, leveraging insights and knowledge Inventory or
35
from equipment and process manuals staffing analysis
Planning 15
Document review 10
Key Energy
industries CPG
Other admin 5
Retail
Advanced Manufacturing
Total
Travel, Transport & Logistics
Basic Materials
Total value 10 - 19
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2244
“The amount of time spent in each category depends on
which stage of development you are, but most time is spent
on product development, troubleshooting or fixing”
5: Product and R&D
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day product owner
% time spent
Creating 3D visual models and Improve pipeline maintenance by
digital product designs synthesizing maintenance and inspection
records, predict areas at risk for corrosion E-mail 10
Prioritizing product backlog by based on historic maintenance records
synthesizing customer feedback Product
Reimagine product portfolio through GenAI 17
development
opportunity themes
Measuring and tracking engineering
Translate code from legacy systems at scale,
metrics Troubleshooting 17
prioritizing interventions and re-factoring
Fixing 17
Meetings 25
Key High tech
industries CPG
Other admin 15
Retail
Travel, Transport & Logistics
Total
Telecommunications
Insurance
Total value 8 - 15
Financial services
potential, bn NOK
Source: McKinsey Global Institute; internal experts MMccKKiinnsseeyy && CCoommppaannyy 2255
6: Risk & Legal
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day junior lawyer
% time spent
Summarize regulation, including safety &
Draft and review legal documents
equipment manuals changes from industry &
regulatory databases
E-mail 10
Summarize and highlight changes
Informative queries from agents to identify &
in large bodies of regulatory
Writing
generate required legal and non-legal
documents 45
documents for transportation based on documents
classification from GenAI model
Review
Answer questions & cite
5
justifications from large documents Generate life-like fraud attempts for pro-active documents
testing
Calls 30
Meetings 5
Key Energy
industries High Tech
Other admin 6
Media
Insurance
Total
Financial services
Real Estate
Total value 7 - 9
Telecommunications
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2266 |
36 | mckinsey | mickensy_superagency-in-the-workplace-empowering-people-to-unlock-ais-full-potential-v4.pdf | Superagency
in the Workplace
Empowering people to unlock AI’s full potential
Hannah Mayer
Lareina Yee
Michael Chui
Roger Roberts
January 2025
Contents
Introduction 2
Chapters:
1. An innovation as powerful as the steam engine 5
2. Employees are ready for AI; now leaders must step up 11
3. Delivering speed and safety 18
4. Embracing bigger ambitions 26
5. Technology is not the barrier to scale 35
Conclusion: Meeting the AI future 40
Acknowledgments 42
Methodology 43
Glossary 44
Introduction
Almost all companies invest in AI, but just 1 percent believe they are at
maturity. Our research finds the biggest barrier to scaling is not
employees—who are ready—but leaders, who are not steering fast enough.
A
rtificial intelligence has arrived in the workplace and has the potential to be as transformative
as the steam engine was to the 19th-century Industrial Revolution.1 With powerful and capable
large language models (LLMs) developed by Anthropic, Cohere, Google, Meta, Mistral, OpenAI,
and others, we have entered a new information technology era. McKinsey research sizes the
long-term AI opportunity at $4.4 trillion in added productivity growth potential from corporate use cases.2
Therein lies the challenge: the long-term potential of AI is great, but the short-term returns are unclear. Over
the next three years, 92 percent of companies plan to increase their AI investments. But while nearly all
companies are investing in AI, only 1 percent of leaders call their companies “mature” on the deployment
spectrum, meaning that AI is fully integrated into workflows and drives substantial business outcomes. The
big question is how business leaders can deploy capital and steer their organizations closer to AI maturity.
This research report, prompted by Reid Hoffman’s book Superagency: What Could Possibly Go Right with
Our AI Future,3 asks a similar question: How can companies harness AI to amplify human agency and unlock
new levels of creativity and productivity in the workplace? AI could drive enormous positive and disruptive
change. This transformation will take some time, but leaders must not be dissuaded. Instead, they must
advance boldly today to avoid becoming uncompetitive tomorrow. The history of major economic and
technological shifts shows that such moments can define the rise and fall of companies. Over 40 years ago,
the internet was born. Since then, companies including Alphabet, Amazon, Apple, Meta, and Microsoft have
attained trillion-dollar market capitalizations. Even more profoundly, the internet changed the anatomy of
work and access to information. AI now is like the internet many years ago: The risk for business leaders is
not thinking too big, but rather too small.
1 “Gen AI: A cognitive industrial revolution,” McKinsey, June 7, 2024.
2 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
3 Reid Hoffman and Greg Beato, Superagency: What Could Possibly Go Right with Our AI Future, Authors Equity, January 2025.
2 Superagency in the workplace: Empowering people to unlock AI’s full potential
Superagency: By the numbers
Employees are more ready for the change than their leaders imagine
3× 1.4×
more employees are using gen AI more likely for millennials to report
for a third or more of their work extensive familiarity with gen AI tools
than their leaders imagine; than peers in other age groups;
more than 70% of all employees they are also 1.2× more
believe that within 2 years gen AI will likely to expect workflows
change 30% or more of their work to change within a year
Companies need to move fast—employees trust their
leaders to balance speed and safety
of the C-suite say their companies are more likely for employees to trust their
47% 1.3×
developing gen AI tools too slowly, even though own companies to get gen AI deployment right
69% started investing more than a year ago than they are to trust other institutions
Companies are investing in gen AI but have not yet achieved maturity
92% 1%
of companies plan believe their
to invest more investments have
in gen AI over the reached maturity
next 3 years
Leaders need to recognize their responsibility in driving gen AI transformation
2.4× 48%
more likely for C-suite to cite employee readiness as of employees rank training as the
a barrier to adoption vs their own issues with leadership most important factor for gen AI adoption;
alignment, despite employees currently using yet nearly half feel they are receiving
gen AI 3× more than leaders expect moderate or less support
Superagency in the workplace: Empowering people to unlock AI’s full potential 3
This report explores companies’ technology and business readiness for AI adoption (see sidebar “About the
survey”). It concludes that employees are ready for AI. The biggest barrier to success is leadership.
Chapter 1 looks at the rapid advancement of technology over the past two years and its implications for
business adoption of AI.
Chapter 2 delves into the attitudes and perceptions of employees and leaders. Our research shows that
employees are more ready for AI than their leaders imagine. In fact, they are already using AI on a regular
basis; are three times more likely than leaders realize to believe that AI will replace 30 percent of their work
in the next year; and are eager to gain AI skills. Still, AI optimists are only a slight majority in the workplace; a
large minority (41 percent) are more apprehensive and will need additional support. This is where millennials,
who are the most familiar with AI and are often in managerial roles, can be strong advocates for change.
Chapter 3 looks at the need for speed and safety in AI deployment. While leaders and employees want to
move faster, trust and safety are top concerns. About half of employees worry about AI inaccuracy and
cybersecurity risks. That said, employees express greater confidence that their own companies, versus
other organizations, will get AI right. The onus is on business leaders to prove them right, by making bold and
responsible decisions.
Chapter 4 examines how companies risk losing ground in the AI race if leaders do not set bold goals. As the
hype around AI subsides, companies should put a heightened focus on practical applications that empower
employees in their daily jobs. These applications can create competitive moats and generate measurable
ROI. Across industries, functions, and geographies, companies that invest strategically can go beyond using
AI to drive incremental value and instead create transformative change.
Chapter 5 looks at what is required for leaders to set their teams up for success with AI. The challenge of AI
in the workplace is not a technology challenge. It is a business challenge that calls upon leaders to align
teams, address AI headwinds, and rewire their companies for change.
About the survey
To create our report, we surveyed 3,613 employees (managers and independent contributors) and 238
C-level executives in October and November 2024. Of these, 81 percent came from the United States,
and the rest came from five other countries: Australia, India, New Zealand, Singapore, and the United
Kingdom. The employees spanned many roles, including business development, finance, marketing,
product management, sales, and technology.
All the survey findings discussed in the report, aside from two sidebars presenting international nuances,
pertain solely to US workplaces. The findings are organized in this way because the responses from US
employees and C-suite executives provide statistically significant conclusions about the US workplace.
Analyzing global findings separately allows a comparison of differences between US responses and
those from other regions.
4 Superagency in the workplace: Empowering people to unlock AI’s full potential
1
An innovation as
powerful as the
steam engine
About the survey ‘ Scientific discoveries and technological
innovations are stones in the cathedral
of human progress.’
– Reid Hoffman, cofounder of LinkedIn and Inflection AI,
partner at Greylock Partners, and author
Superagency in the workplace: Empowering people to unlock AI’s full potential 5
I
magine a world where machines not only perform physical labor but also think, learn, and make
autonomous decisions. This world includes humans in the loop, bringing people and machines together
in a state of superagency that increases personal productivity and creativity (see sidebar “AI
superagency”). This is the transformative potential of AI, a technology with a potential impact poised to
surpass even the biggest innovations of the past, from the printing press to the automobile. AI does not just
automate tasks but goes further by automating cognitive functions. Unlike any invention before, AI-powered
software can adapt, plan, guide—and even make—decisions. That’s why AI can be a catalyst for
unprecedented economic growth and societal change in virtually every aspect of life. It will reshape
our interaction with technology and with one another.
Many breakthrough technologies, including the internet, smartphones, and cloud computing, have
transformed the way we live and work. AI stands out from these inventions because it offers more than
access to information. It can summarize, code, reason, engage in a dialogue, and make choices. AI can lower
skill barriers, helping more people acquire proficiency in more fields, in any language and at any time. AI
holds the potential to shift the way people access and use knowledge. The result will be more efficient and
effective problem solving, enabling innovation that benefits everyone.
Over the past two years, AI has advanced in leaps and bounds, and enterprise-level adoption has
accelerated due to lower costs and greater access to capabilities. Many notable AI innovations have
emerged (Exhibit 1). For example, we have seen a rapid expansion of context windows, or the short-term
memory of LLMs. The larger a context window, the more information an LLM can process at once. To
illustrate, Google’s Gemini 1.5 could process one million tokens in February 2024, while its Gemini 1.5 Pro
could process two million tokens by June of that same year.4 Overall, we see five big innovations for business
that are driving the next wave of impact: enhanced intelligence and reasoning capabilities, agentic AI,
multimodality, improved hardware innovation and computational power, and increased transparency.
AI superagency
What impact will AI have on humanity? Reid Hoffman and Greg Beato’s book Superagency: What
Could Possibly Go Right with Our AI Future (Authors Equity, January 2025) explores this question.
The book highlights how AI could enhance human agency and heighten our potential. It envisions a
human-led, future-forward approach to AI.
Superagency, a term coined by Hoffman, describes a state where individuals, empowered by AI, super-
charge their creativity, productivity, and positive impact. Even those not directly engaging with AI can
benefit from its broader effects on knowledge, efficiency, and innovation.
AI is the latest in a series of transformative supertools, including the steam engine, internet, and
smartphone, that have reshaped our world by amplifying human capabilities. Like its predecessors, AI
can democratize access to knowledge and automate tasks, assuming humans can develop and deploy
it safely and equitably.
4 The Keyword, “Our next-generation model: Gemini 1.5,” blog entry by Sundar Pichai and Demis Hassabis, Google, February 15, 2024; Google
for Developers, “Gemini 1.5 Pro 2M context window, code execution capabilities, and Gemma 2 are available today,” blog entry by Logan
Kilpatrick, Shrestha Basu Mallick, and Ronen Kofman, June 27, 2024.
6 Superagency in the workplace: Empowering people to unlock AI’s full potential
Web <2025>
<Superagency>
Exhibit 1
Exhibit <1> of <21>
Gen AI capabilities have evolved rapidly over the past two years.
Illustrative capabilities of gen AI platforms from select frontier labs, nonexhaustive
2022–231 Jan 20252
Anthropic
Google
Gemini
Meta
Microsoft
OpenAI
AI superagency
Note: Exhibit is not intended as an evaluation or comparison but as an illustration of the rapid progress in capabilities.
1Initial models released between Mar 2022 and Mar 2023.
2Latest models released between Nov and Dec 2024.
Source: Company websites and press releases; McKinsey analysis
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 7
Intelligence and reasoning are improving
AI is becoming far more intelligent. One indicator is the performance of LLMs on standardized tests.
OpenAI’s Chat GPT-3.5, introduced in 2022, demonstrated strong performance on high-school-level exams
(for example, scoring in the 70th percentile on the SAT math and the 87th percentile on the SAT verbal
sections). However, it often struggled with broader reasoning. Today’s models are near the intelligence level
of people who hold advanced degrees. GPT-4 can so easily pass the Uniform Bar Examination that it would
rank in the top 10 percent of test takers,5 and it can answer 90 percent of questions correctly on the US
Medical Licensing Examination.6
The advent of reasoning capabilities represents the next big leap forward for AI. Reasoning enhances AI’s
capacity for complex decision making, allowing models to move beyond basic comprehension to nuanced
understanding and the ability to create step-by-step plans to achieve goals. For businesses, this means they
can fine-tune reasoning models and integrate them with domain-specific knowledge to deliver actionable
insights with greater accuracy. Models such as OpenAI’s o1 or Google’s Gemini 2.0 Flash Thinking Mode
are capable of reasoning in their responses, which gives users a human-like thought partner for their
interactions, not just an information retrieval and synthesis engine.7
Agentic AI is acting autonomously
The ability to reason is growing more and more, allowing models to autonomously take actions and complete
complex tasks across workflows. This is a profound step forward. As an example, in 2023, an AI bot could
support call center representatives by synthesizing and summarizing large volumes of data—including voice
messages, text, and technical specifications—to suggest responses to customer queries. In 2025, an AI
agent can converse with a customer and plan the actions it will take afterward—for example, processing a
payment, checking for fraud, and completing a shipping action.
‘I’ve always thought of AI as the most
profound technology humanity is
working on . . . more profound than fire
or electricity or anything that we’ve
done in the past.’
– Sundar Pichai, CEO of Alphabet
5 GPT-4 technical report, OpenAI, March 27, 2023.
6 Dana Brin, Vera Sorin, Akhil Vaid, et al., “Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments,” Scientific Reports,
October 1, 2023.
7 “Learning to reason with LLMs,” OpenAI, September 12, 2024; “Gemini 2.09 Flash Thinking Mode,” Google, January 21, 2025.
8 Superagency in the workplace: Empowering people to unlock AI’s full potential
‘AI, like most transformative technologies,
grows gradually, then arrives suddenly.’
– Reid Hoffman, cofounder of LinkedIn and Inflection AI,
partner at Greylock Partners, and author
Software companies are embedding agentic AI capabilities into their core products. For example,
Salesforce’s Agentforce is a new layer on its existing platform that enables users to easily build and
deploy autonomous AI agents to handle complex tasks across workflows, such as simulating product
launches and orchestrating marketing campaigns.8 Marc Benioff, Salesforce cofounder, chair, and CEO,
describes this as providing a “digital workforce” where humans and automated agents work together to
achieve customer outcomes.9
Multimodality is bringing together text, audio, and video
Today’s AI models are evolving toward more advanced and diverse data processing capabilities across text,
audio, and video. Over the last two years, we have seen improvements in the quality of each modality. For
example, Google’s Gemini Live has improved audio quality and latency and can now deliver a human-like
conversation with emotional nuance and expressiveness.10 Also, demonstrations of Sora by OpenAI show its
ability to translate text to video.11
Hardware innovation is enhancing performance
Hardware innovation and the resulting increase in compute power continue to enhance AI performance.
Specialized chips allow faster, larger, and more versatile models. Enterprises can now adopt AI solutions that
require high processing power, enabling real-time applications and opportunities for scalability. For
example, an e-commerce company could significantly improve customer service by implementing AI-driven
chatbots that leverage advanced graphics processing units (GPUs) and tensor processing units (TPUs).
Using distributed cloud computing, the company could ensure optimal performance during peak traffic
periods. Integrating edge hardware, the company could deploy models that analyze photos of damaged
products to more accurately process insurance claims.
8 Sammy Spiegel, “The future of AI agents: Top predictions and trends to watch in 2025,” Salesforce, December 2024.
9 Marc Benioff, “How the rise of new digital workers will lead to an unlimited age,” Time, November 25, 2024.
10 Ivan Solovyev and Shrestha Basu Mallick, “Gemini 2.0: Level up your apps with real-time multimodal interactions,” Google, December 23, 2024.
11 “OpenAI releases AI video generator Sora but limits how it depicts people,” Associated Press, December 10, 2024.
Superagency in the workplace: Empowering people to unlock AI’s full potential 9
2
Transparency is increasing
AI is gradually becoming less risky, but it still lacks greater transparency and explainability. Both are critical
for improving AI safety and reducing the potential for bias, which are imperative for widescale enterprise
deployment. There is still a long way to go, but new models and iterations are rapidly improving. Stanford
University’s Center for Research on Foundation Models (CRFM) reports significant advances in model
performance. Its Transparency Index, which uses a scale of 1 to 100, shows that Anthropic’s transparency
score increased by 15 points to 51 and Amazon’s more than tripled to 41 between October 2023 and
May 2024.12
Beyond LLMs, other forms of AI and machine learning (ML) are improving explainability, allowing the outputs
of models that support consequential decisions (for example, credit risk assessment) to be traced back to
the data that informed them. In this way, critical systems can be tested and monitored on a near-constant
basis for bias and other everyday harms that arise from model drift and shifting data inputs, which happens
even in systems that were well calibrated before deployment.
All of this is crucial for detecting errors and ensuring compliance with regulations and company policies.
Companies have improved explainability practices and built necessary checks and balances, but they must
be prepared to evolve continuously to keep up with growing model capabilities.
Achieving AI superagency in the workplace is not simply about mastering technology. It is every bit as much
about supporting people, creating processes, and managing governance. The next chapters explore the
nontechnological factors that will help shape the deployment of AI in the workplace.
12 “The Foundation Model Transparency Index,” Stanford Center for Research on Foundation Models, May 2024.
10 Superagency in the workplace: Empowering people to unlock AI’s full potential
2
Employees are ready
for AI; now leaders
must step up
‘People are using [AI] to create amazing
things. If we could see what each of us
can do 10 or 20 years in the future, it
would astonish us today.’
– Sam Altman, cofounder and CEO of OpenAI
Superagency in the workplace: Empowering people to unlock AI’s full potential 11
E
mployees will be the ones to make their organizations AI powerhouses. They are more ready to
embrace AI in the workplace than business leaders imagine. They are more familiar with AI tools,
they want more support and training, and they are more likely to believe AI will replace at least a
third of their work in the near future. Now it’s imperative that leaders step up. They have more
permission space than they realize, so it’s on them to be bold and capture the value of AI. Now.
Beyond the tipping point
In our survey, nearly all employees (94 percent) and C-suite leaders (99 percent) report having some level of
familiarity with gen AI tools. Nevertheless, business leaders underestimate how extensively their employees
are using gen AI. C-suite leaders estimate that only 4 percent of employees use gen AI for at least 30
percent of their daily work, when in fact that percentage is three times greater, as self-reported by
employees (Exhibit 2). And while only a total of 20 percent of leaders believe employees will use gen AI for
more than 30 percent of their daily tasks within a year, employees are twice as likely (47 percent) to believe
they will (see sidebar “Who is using AI at work? Nearly everyone, even skeptical employees”).
The good news is that our survey suggests three ways companies can accelerate AI adoption and move
toward AI maturity.
Web <2025>
<ESxuhpeibraigt e2ncy>
Exhibit <2> of <21>
Employees are three times more likely to be using gen AI today than their
leaders expect.
US employees’ and C-suite’s C-suite Employees
timeline for employees using Already using 4
3×
gen AI for >30% of daily tasks, % 13
of respondents Less than a year 16
34
1–5 years 56
37
Over 5 years 11
5
Don’t anticipate it 10 7
Not sure 3 4
Note: Figures may not sum to 100%, because of rounding.
Source: McKinsey US CxO survey, Oct–Nov 2024 (n = 118) ; McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
12 Superagency in the workplace: Empowering people to unlock AI’s full potential
Our research looked at people who self-identify as “Zoomers,” “Bloomers,” “Gloomers,” and “Doomers” in their
attitudes toward AI—a set of archetypes introduced in Superagency. We find that 39 percent of employees
identify as Bloomers, who are AI optimists that want to collaborate with their companies to create responsible
solutions. Meanwhile, 37 percent identify as Gloomers, who are more skeptical about AI and want extensive
top-down AI regulations; 20 percent identify as Zoomers, who want AI to be quickly deployed with few guardrails;
and just 4 percent identify as Doomers, who have a fundamentally negative view of AI (exhibit).
Even those with a skeptical take on AI are familiar with it; 94 percent of Gloomers and 71 percent of Doomers say
they have some familiarity with gen AI tools. Furthermore, approximately 80 percent of Gloomers and about half
of Doomers say they are comfortable using gen AI at work.
Web <2025>
<Superagency>
Exhibit
Exhibit <3> of <21>
Employee segments differ, but all indicate a high familiarity with gen AI.
US employee sentiment on gen AI, by archetype, % of respondents
Doomer Gloomer Bloomer Zoomer
Gen AI will not align Above all else, gen AI Gen AI needs to be Gen AI development
with human values, needs to be closely developed iteratively should be trusted
regardless of monitored and with a diverse range to developers to
deployment method controlled of inputs maximize speed
Has extensive
familiarity
with gen AI1 16 42 55 67
Has at least
some familiarity
with gen AI2 71 94 96 96
Is comfortable using
results from gen AI 47 79 91 91
Believes gen AI will
have a net benefit in
the next 5 years 54 82 89 87
Plans to use gen AI
more in their
personal life 49 77 86 85
Expects 30% of
workflows to change
in the next year 19 38 50 64
Share of respondents
4 37 39 20
in archetype group, %
1Defined as those who have “extensive experience (use several tools for complex tasks)” and “experts.”
2Defined as those who have “some familiarity (use 1–2 tools a few times)” and “extensive experience (use several tools for complex tasks)” and “experts.”
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 13
Leaders can invest more in their employees
As noted at the beginning of this chapter, employees anticipate AI will have a dramatic impact on their work.
Now they would like their companies to invest in the training that will help them succeed. Nearly half of
employees in our survey say they want more formal training and believe it is the best way to boost AI
adoption. They also would like access to AI tools in the form of betas or pilots, and they indicate that
incentives such as financial rewards and recognition can improve uptake.
Yet employees are not getting the training and support they need. More than a fifth report that they have
received minimal to no support (Exhibit 3). Outside the United States, employees also want more training
(see sidebar “Global perspectives on training”).
Web <2025>
<ESxuhpeibraigt e3ncy>
Exhibit <4> of <21>
Employees long for more support and training on gen AI.
Share of US employees agreeing that a company initiative would make them more likely to
increase day-to-day usage of gen AI tools, %
Formal gen AI training from
48
my organization
Seamless integration into my
45
existing workflow
Access to gen AI tools 41
Incentives and rewards 40
Usage of gen AI being a requirement
30
for a certification program
Explicit instructions from my managers
30
to use gen AI
Being involved in the development
29
of the tools
OKRs¹/KPIs tied to gen AI usage 22
US employees’ perceived level of support for gen AI capability building at their organizations,
% of respondents
Not None/ Moderate to Fully
needed minimal significant supported
Current 6 22 44 29
In 3 years 4 10 56 31
Note: Figures do not sum to 100%, because of rounding.
¹Objectives and key results.
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
14 Superagency in the workplace: Empowering people to unlock AI’s full potential
Global perspectives on training
To get a clearer picture of global AI adoption trends, we looked at trends across five countries: Australia, India, New
Zealand, Singapore, and the United Kingdom. Broadly speaking, these employees and C-suite leaders—the “interna-
tional” group in this report—have similar views of AI as their US peers. In some key areas, however, including the topic
of training, their experiences differ.
Web <2025>
<Superagency>
Exhibit <5> of <21>
Many international employees are concerned about insufficient training, even though they report receiving far more
support than US employees. Some 84 percent of international employees say they receive significant or full organiza-
tional support to learn AI skills, versus just over half of US employees. International employees also have more
opportunities to participate in developing gen AI tools at work than their US counterparts, with differences of at least
ten percentage points in activities such as providing feedback, beta testing, and requesting specific features (exhibit).
Exhibit
International employees get more encouragement to use gen AI tools.
Sources encouraging employees’ use of gen AI tools at work, % of respondents reporting practice in
place at their organization
Australia and New Zealand India Singapore UK US
0 20 40 60 80 100
Use is mandated
Manager
Manager other than own
Peers
C-suite leadership
Developer of AI tool
Generic communications
Have not been encouraged
Employee involvement in developing gen AI tools, % of respondents
Australia and New Zealand India Singapore UK US
0 20 40 60 80 100
Provide feedback
in tool itself
Provide feedback via
other channels
Beta testing or
pilot program
Submit specific requests
for features
Not involved
Source: McKinsey international employee survey, Oct–Nov 2024 (Australia and New Zealand, n = 139; India, n = 134; Singapore, n = 140; UK, n = 201) ; McKinsey
US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 15
C-suite leaders can help millennials lead the way
Many millennials aged 35 to 44 are managers and team leaders in their companies. In our survey, they self-
report having the most experience and enthusiasm about AI, making them natural champions of
transformational change. Millennials are the most active generation of AI users. Some 62 percent of 35- to
44-year-old employees report high levels of expertise with AI, compared with 50 percent of 18- to 24-year-
old Gen Zers and 22 percent of baby boomers over 65 (Exhibit 4). By tapping into that enthusiasm and
expertise, leaders can help millennials play a crucial role in AI adoption.
Web <2025>
<ESxuhpeibraigt e4ncy>
Exhibit <6> of <21>
Millennials aged 35 to 44 are AI optimists, with 90 percent indicating
confidence in their gen AI abilities.
US employee sentiment on gen AI, by age group, % of respondents
18–24 25–34 35–44 45–54 55–64 65+
Has extensive
familiarity
with gen AI1
50 49 62 47 26 22
Is comfortable using
gen AI at work
80 87 90 82 70 71
Provides feedback
on gen AI tools
76 77 76 65 47 55
Wants to participate
in the design of
gen AI tools
70 76 81 77 73 76
1Defined as those who have “extensive experience (use several tools for complex tasks)” and “experts.”
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
16 Superagency in the workplace: Empowering people to unlock AI’s full potential
Web <2025>
E<Sxuhpiebraitg e5ncy>
Exhibit <7> of <21>
Two-thirds of managers regularly act as sounding boards for their teams on
gen AI.
Frequency of team inquiries about using new gen AI tools at work, % of US manager respondents
(n = 1,440)
Less than Once a Once a A few Once Multiple
quarterly Quarterly month week times a week a day times a day
10 5 5 12 15 28 9 16
Not at all
Use of gen AI tools to resolve a team member’s challenge, % of US manager respondents (n = 1,440)
Recommended Gen AI tool was
gen AI tool to successful in
solve team member’s resolving team
challenge in member’s challenge
the past month 86
68
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Since many millennials are managers, they can support their teams to become more adept AI users. This
helps push their companies toward AI maturity. Two-thirds of managers say they field questions from their
team about how to use AI tools at least once a week, and a similar percentage say they recommend AI tools
to their teams to solve problems (Exhibit 5).
Since leaders have the permission space, they can be bolder
In many transformations, employees are not ready for change, but AI is different. Employee readiness and
familiarity are high, which gives business leaders the permission space to act. Leaders can listen to
employees describe how they are using AI today and how they envision their work being transformed. They
also can provide employees with much-needed training and empower managers to move AI use cases from
pilot to scale.
It’s critical that leaders meet this moment. It’s the only way to accelerate the probability that their companies
will reach AI maturity. But they must move with alacrity, or they will fall behind.
Superagency in the workplace: Empowering people to unlock AI’s full potential 17
3
Delivering
speed and safety
‘Soon after the first automobiles were
on the road, there was the first car crash.
But we didn’t ban cars—we adopted
speed limits, safety standards, licensing
requirements, drunk-driving laws,
and other rules of the road.’
– Bill Gates, cofounder of Microsoft
18 Superagency in the workplace: Empowering people to unlock AI’s full potential
A
I technology is advancing at record speed. ChatGPT was released about two years ago; OpenAI
reports that usage now exceeds 300 million weekly users13 and that over 90 percent of Fortune
500 companies employ its technology.14 The internet did not reach this level of usage until the
early 2000s, nearly a decade after its inception.
The majority of employees describe themselves as AI optimists; Zoomers and Bloomers make up 59 percent
of the workplace. Even Gloomers, who are one of the two less-optimistic segments in our analysis, report
high levels of gen AI familiarity, with over a quarter saying they plan to use AI more next year.
Business leaders need to embrace this speed and optimism to ensure that their companies don’t get left
behind. Yet despite all the excitement and early experimentation, 47 percent of C-suite leaders say their
organizations are developing and releasing gen AI tools too slowly, citing talent skill gaps as a key reason for
the delay (Exhibit 6).
Web <2025>
<ESxuhpeibraigt e6ncy>
Exhib |
37 | mckinsey | insurer-of-the-future-are-asian-insurers-keeping-up-with-ai-advances.pdf | Insurance Practice
Insurer of the future: Are
Asian insurers keeping up
with AI advances?
AI’s potential for competitive advantages remains largely unrealized in
the Asian insurance industry. There is a framework for success: invest
in AI not discretely but across the value chain.
by Violet Chung, Pranav Jain, and Karthi Purushothaman
© zf L/Getty Images
May 2023
As the insurance industry undergoes a seismic, across four focus areas: engagement, AI-powered
tech-driven shift,1 AI continues to push the evolution decision making, core tech and data, and
of how insurers make significant service and organization and operations (Exhibit 1).
operational gains. Indeed, McKinsey estimates
that AI technologies could add up to $1.1 trillion
in annual value for the global insurance industry: AI’s potential for insurers:
approximately $400 billion could come from pricing, Benchmarking success
underwriting, and promotion technology upgrades The four layers of our integrated AI-capability-
and $300 billion from AI-powered customer service stack framework for insurance encompass front-,
and personalized offerings.2 middle-, and back-office functions. Just as these
functional areas are essential to and interreliant
While most large insurers are on the path to AI-enabled within an organization, the layers of the framework
personalization at scale,3 the industry remains at an are mutually supportive: together, they form a
early stage of transformational AI adoption. For most robust structure that benefits internal and external
Asian insurance leaders, traditional organizational stakeholders.
structures with multiple intermediaries and limited
in-house tech and data resources make it difficult to The global companies setting the benchmarks for
visualize, let alone quantify, the potential benefits of AI maturity and capacity—such as Google, Netflix,
investing more broadly in AI. Tencent, and Uber—illustrate the potential gains
that could be realized by insurers that integrate AI
This matters because cross-functional investment holistically across their organizations.
in AI can be game-changing—and it will increasingly
become a source of competitive advantage. AI Reimagined engagement layer
adoption has more than doubled in the past five years, A reimagined engagement layer employs AI tools
and investment in AI is increasing across industries. and solutions to create digital-ready engagement
Among 1,492 respondents to a December 2022 and distribution channels that can help provide
McKinsey Global Institute survey, those who reported customers with a consistent, personalized
the most significant gains from AI adoption— experience. To envision leading-edge personalization
20 percent or more EBIT—tend to employ advanced at scale, consider Netflix. Each Netflix user has a
AI practices, use cloud technologies, and spend distinct, customized view of available content—on
efficiently on AI, and they are more likely than others the platform as well as in emails—that reflects their
to engage in a range of AI risk mitigation efforts.4 interests and becomes more extensive, targeted,
informative, and engaging over time.
The challenge for most insurers is to determine the
optimal path from where they are now to where AI-powered decision-making layer
they need to be when it comes to AI maturity and AI and advanced data-and-analytics capabilities
enterprise-wide integration. can augment complex decision making, allowing
businesses to automate repetitive tasks, analyze
Drawing on McKinsey’s AI maturity assessment significantly more data, increase processing speed
model, in this article, we both outline how Asian and accuracy, and create predictive models to
insurers can assess their readiness for AI and offer a improve procedures and enhance performance.
road map to becoming an AI-powered insurer of the Uber Technologies exemplifies the leading edge in
future, realizing gains in profitability, agility, at-scale AI-enabled predictive analytics, bridging the gap
personalization, and innovation. The basis of this between ride demand and driver supply by using
framework is a layered approach to investment in AI historical ride data and key metrics to ensure every
1 Ramnath Balasubramanian, Ari Libarikian, and Doug McElhaney, “Insurance 2030—The impact of AI on the future of insurance,” McKinsey,
March 12, 2021.
2 “The executive’s AI playbook,” McKinsey, accessed March 20, 2023.
3 “ How personalization at scale can invigorate Asian insurers,” McKinsey, December 2, 2022.
4 “The state of AI in 2022—and a half decade in review,” McKinsey, December 6, 2022.
2 Insurer of the future: Are Asian insurers keeping up with AI advances?
Web 2023
AI insurer of the future
Exhibit 1
Exhibit 1 of 3
There are four layers to the full-stack AI capability that will define the AI-enabled
insurer of the future.
AI-enabled insurer of the future
Profitability At-scale Omnichannel Speed and
personalization experience innovation
Reimagined engagement
Intelligent products, Digital channels Partnerships and Smart service and
tools, and experiences Hybrid agency ecosystems operations
Bancassurance (eg, integrated life and (eg, conversational
health propositions) AI-enabled services,
Direct-to-consumer
predictive customer
distribution
experience, ZeroOps)
Omnichannel enablement
Digital marketing and personalization
AI-powered decisioning
Advanced Customer Underwriting Servicing and Retention Claims
analytics acquisition engagement and cross- and
upselling
Conversational Natural- Voice Virtual Computer Facial Robotics Behavioral
AI language script agents or vision recognition analytics
processing analysis bots
Core tech and data
Digital marketing and personalization
Core technology Intelligent infrastructure Modern API Tech-forward strategy Hollowing the core
and data (eg, AIOps1 command, architecture linked to business (core modernization)
modernization hybrid cloud set up)
Cybersecurity and
control tiers
Organization, operating model, and ways of working
Autonomous “biz tech” teams Vendor and partner management
Platform
operating
model
Agile way of working Remote collaboration Modern talent and hiring Culture and capabilities
1AI for IT operations.
McKinsey & Company
user of the Uber app has access to a ride within their integrate with multiple third-party platforms for
expected timeframe. data and intelligence. Tencent, a leading Chinese
multinational technology and entertainment
Core tech and data layer conglomerate, has been using its advanced-API
Modernized core tech helps deliver complete, platform in its WeChat app to integrate data and
high-quality, real-time data for advanced decision decisions, thus providing a seamless, efficient,
making, facilitating a seamless customer and integrated service experience for more than one
stakeholder experience. It provides the ability to billion monthly active users in China. The initiative
Insurer of the future: Are Asian insurers keeping up with AI advances? 3
significantly expanded WeChat’s proposition by Consider a four-phased plan to implement AI in
being more personalized and providing context- underwriting, for example (Exhibit 2). Value is added
specific offers across payments, retail, and its in each phase, but it increases dramatically in the
social networking and chat functionality. third and fourth phases, when greater AI capacity
helps enable continuous, personalized engagement
Organization and operating model layer and prescriptive actions to support better outcomes
This crucial layer enables the innovation, agility, for customers.
and flexibility needed to harness AI-powered
capabilities. Cross-functional teams, new talent While the path to becoming an AI-powered insurer
and skills, flat organization structures, and shared of the future will vary based on an organization’s
goals have enhanced impact from AI—particularly stage of readiness in each layer, the end goal
in aiding frontline adoption and solving crucial remains the same: a more innovative, profitable,
frontline decision problems. In Google’s relatively digital-forward organization that meets and
flat and cross-functional organization structure, anticipates customers’ evolving needs with highly
small project teams operate in an agile manner with personalized, omnichannel experiences.
shared goals and empowered decision making, and
talent and skill are valued over seniority. All are vital Reimagining the engagement layer
to Google’s reputation as an AI-driven organization Leaders in other industries—Google, Netflix, and
and its continued product innovation and growth. Uber, for example—have achieved stage-five AI
maturity within their engagement layer while most
leading insurers are at or below stage-three maturity.
AI readiness for Asian insurers: Some Asian insurers have used micropersonalization
Building layer depth and strength based on consumer personas to realize gains in
While some insurers have achieved select wins by overall engagement; nonetheless, most have fallen
implementing AI solutions within individual layers, short of employing dynamic, one-to-one customer
the transformation required to achieve the full-stack targeting to create the personalized, consistent,
capability that powers the companies mentioned omnichannel customer experience that characterizes
above remains elusive in insurance. mature AI-powered engagement. In other words,
personalization at scale.
Often, the problem insurers face is identifying
where to start. At-scale personalization. Personalization underpins all
facets of a reimagined engagement layer and is central
The first step is to determine how AI can support to every interaction between products and customers.
the organization’s strategic goals and then assess Creating exceptional customer experiences dominates
the organization’s current state of AI readiness senior-management agendas, and insurers continue
across each of the four layers. A simple scoring to work toward building personalization at scale to
methodology can help insurers identify their gain a better understanding of customer behavior and
readiness on a scale from one to five for each layer, offer customers advice on the products best suited to
with stage five signifying the highest level of AI their needs.
maturity (as articulated in this article). Insurers with
in-depth insight into their AI readiness are better AI is now being used to generate highly
equipped for the next step: creating a road map for personalized offerings across industries, tailored
implementing AI solutions across the front-, middle- to customer specifics such as location, industry,
and back-office functions of their companies. This age, and financial history. Customer interactions
road map allows company leaders to calibrate are also personalized using demographics
expectations as well as the resources, time, and and past interactions. Most large insurers are
investments needed. halfway along the path of achieving personali-
4 Insurer of the future: Are Asian insurers keeping up with AI advances?
zation at scale,5 prioritizing key metrics such as and create a single, more accurate source of
the following: information.
— Measurement and attrition. Attribute click- — Next-best action. Apply a suite of analytics
through rates, conversion rates, and other models to support customer acquisition, cross-
metrics to different digital channels, and selling, and other sales functions.
measure improvement to help identify customer
preferences and drive personalization to serve — Tailored content. Deliver individually curated,
the customer. personalized content to customers at every
interaction and point of contact.
— Omnichannel breadth and flexibility. Build
customer data platforms that aggregate data As Asian insurers seek to deploy personalization
for individual customers from multiple sources, strategies successfully and augment AI initiatives
5 “Personalization at scale,” December 2, 2022.
Web 2023
AI insurer of the future
EExxhihbiitb 2it o 2f 3
There are four layers to the full-stack AI capability that will define the AI-enabled There are four layers to the full-stack AI capability that will define the AI-enabled
insurer of the future. insurer of the future.
Value created
across stakeholders Phase 4: Microsegmentation and
personalization
Granular view of risk categories
using holistic data sets (eg, external
Increase
open data, connected devices) and
in net
enhanced AI algorithms to improve
new risk profiling and lead generation
value
pools More-personalized offers and
Phase 4 propositions
New segments of traditionally
underserved risks
Phase 3: Continuous underwriting
Phase 3 with prescriptive actions to drive
desired outcomes
Personalized products and packages
based on continuous engagement and
interventions to significantly
influence underwriting quality
Phase 2
Phase 2: Accelerated simplified
underwriting
Dramatic reduction in number
of applicants requiring invasive fluid
and paramedical exams
Phase 1
Significant reduction in number of
questions on application
Existing
value
pools Phase 1: Digital underwriting
Transactional and Personalized All applications submitted digitally
episodic customer and continuous Near STP1 and auto-issue for majority
engagement engagement of products (60–70% or more)
1Segmentation, targeting, and positioning.
McKinsey & Company
Insurer of the future: Are Asian insurers keeping up with AI advances? 5
and investments across the engagement layer, customer analytics and microsegmentation-based
three distribution models are worthy of note. customer personas to personalize lead nurturing.
Based on these analytics, journeys selected were
Digital hybrid agency. Globally, agents continue either “fast” (moved directly to the product list)
to be the largest distribution channel for most or “long” (with content integration), depending on
insurers—but retaining an edge and driving growth customer preferences. Within four to five years,
in agency will require competitive investment in bancassurance penetration almost doubled and
digital and AI solutions. first-year premiums increased by 30 to 40 percent.
It can be done: a global insurer that redesigned Digital D2C distribution via ecosystems. Several
its agency channel to be AI-ready realized an insurtechs are paving the way for embedding
incremental impact of several million dollars over insurance offerings in ecosystems and supporting
the subsequent years. Specifically, the insurer multiproduct offerings on a single platform.
used geospatial network optimization to identify Partnerships with leading players (generally the
geography-specific agents demand and capture top 15 percent) to offer select products with simple
growth opportunities and then used this data to terms, a short process, and fast and convenient
inform its local recruitment strategy. Ramp-up claims can help meet specific user needs for health,
time from newly hired agents to full productivity fell auto, life, accident, and other types of coverage.
significantly, and retention rates rose. The company User data analysis can provide insurers with
increased activation and productivity among customer insights to inform product innovation and
agents with a behavior-driven, next-best-action achieve differentiation in the market.
recommendation engine and customized learning
plans based on agents’ individual performance. A leading insurtech harnessed its parent group’s
traffic and data capability to create a competitive
Another leading insurer in Asia optimized its advantage in the insurance business. Insurance
agency channel by shifting from experience-driven services are embedded in the parent company’s
operations to digital operations. It reformed its mobile app, which has more than a billion monthly
business outlet operation with embedded digital active users. The insurtech integrated its mobile app’s
tools to support and optimize agent activity, ecosystem, expanding its distribution channels and
improving productivity and growth by 5 to 10 providing app users with access to offline medical
percent. The insurer also empowered customer networks not restricted to policyholders.
acquisition and conversions using AI-based audio
and video illustrations of insurance knowledge, Creating an AI-powered decision-making layer
illness explanations, and more to complement Although the insurance industry generates a
agents’ interactions with customers. The insurer’s massive amount of data across various levers and
AI-based assistants support online interactions channels, this data is not, for the most part, being
in real time and record a monthly average of leveraged to build a sophisticated decision-making
approximately 100,000 client-meeting hours, layer that provides a highly personalized customer
enhancing customer experience and acquisition experience. AI technologies could be used to
efficiency. AI-facilitated policy issuance at this complement existing pricing and underwriting
company was more than $100,000 in 2021, and decision making. Specifically, these technologies
agent productivity improved, as measured by a 25 to could help support claims decisions and identify
30 percent increase in net book value per agent. claims leakages by dynamically collecting and
evaluating data points such as adjuster notes,
Digital bancassurance. Bancassurance remains the damage images, text submissions, submitted
second-largest channel driving life insurance sales documents, and patient histories.
globally and, due to legacy bank systems, is perhaps
the most challenging to transform. Nonetheless, a In a mature AI-powered decisioning layer, a suite
leading Asian bank redesigned and simplified the of state-of-the-art analytics tools and edge
insurance journey for its insurance partner, using capabilities is supported by a solid database
6 Insurer of the future: Are Asian insurers keeping up with AI advances?
system with clean, well-structured, analytics- — Claims. One insurer is using AI to help identify
ready data; a defined agile-delivery process; and fraud, waste, and abuse in health insurance
a well-developed, analytical organization deeply claims, driving reductions of more than 5 percent
connected to the business. in overall claims spend.
Advanced analytics can simplify and augment — Servicing. An AI-supported customer complaint
decision making across the entire insurance journey powered by real-time sentiment analysis,
value chain. In our experience, significant gains in smart workflows, and other capabilities helped
efficiency, critical metrics, and more can be realized one insurer significantly reduce the number of
throughout the value chain: repeat complaint calls.
— Marketing. Insurers can use AI-driven customer New technologies such as generative AI amplify the
lifetime value (CLV) management to sift through impact possible across the value chain in very quick
large amounts of data. This can uncover insights order (see sidebar, “The potential of generative AI in
to help identify high-potential customers early insurance”).
enough to take action at all four stages of the
customer life cycle: acquisition, onboarding, Modernizing the core tech and data layer
engagement, and retention. For example, an A modernized core tech and data layer helps uncover
insurer using AI-driven CLV management achieved as well as deliver advanced intelligence through a
a major increase in gross written premiums. seamless front-end experience for customers and
the distribution network. Organizations with mature,
— Underwriting. Using AI to support risk scoring AI-ready core tech and data layers have capabilities
can enable continuous underwriting and achieve across the core tech stack, including a well-defined
multiple desirable outcomes. The insights resulting data infrastructure; data governance; advanced
from continuous engagement, microsegmentation, analytics tooling; technology operating model; a
and personalization, for example, can help develop mature, hybrid cloud infrastructure; API architecture
customized products and packages. and linkages; and advanced cybersecurity and
controls infrastructure.
— Pricing. Employing built-in pricing models that
use machine learning for risk selection and Once the above elements are defined in this
developing data domains for governance can layer, organizations can achieve sustained
help provide granular monitoring of KPIs and transformation by hiring talent to build these
real-time monitoring of emerging loss, pricing differential capabilities in-house, rather than
trends, and shifts in the portfolio risk mix. outsourcing the foundational stack required. In
The potential of generative AI in insurance
Generative AI has dominated recent combating fraud, lowering costs, and scripts for agents and bancassurance
headlines, largely thanks to the growing hyperpersonalizing customer interactions. reps to foster conversions. It could also be
popularity of AI chatbot ChatGPT. The In sales and distribution, generative AI used to provide real-time, personalized
technology could be a significant could be used to create personalized advice and answers to basic customer
contributor to the insurance industry’s marketing content and tailor offerings queries to support customer relationship
efforts to redefine business models across based on customer demographics. It can management.
the value chain, improving efficiency, help create more effective personalized
Insurer of the future: Are Asian insurers keeping up with AI advances? 7
fact, many players have developed distinctive put AI-powered capabilities into action. Transitioning
stacks that have been monetized across insurers. from a traditional linear model to a cross-functional
operating model facilitates expert-driven AI insights
A leading Chinese digital insurer gathered customer generation and adoption at the front line.
behavioral data to develop innovative products,
improve customer profiling and segmentation, The benefits of a cross-functional team structure
and more. Data-driven services also helped the that integrates business, AI, and technology
insurer grow its customer base and refine its data functions can lead to faster alignment, increased
analytics, including dynamic pricing, automated flexibility, and high adoption of AI in the organization.
claim settlement, and enhanced risk management These benefits are exemplified by data-driven
effectiveness, serving more than 500 million organizations such as Google and Netflix that
insured customers in 2021. operate in relatively flat, cross-functional
structures. Most insurers, however, have retained
The company redefined the insurance value chain their traditional organizational structures and
with continuous iterations and upgrades to its implemented AI only on a limited basis. This can
system to improve business efficiency, meet the impede their AI readiness by reducing their capacity
diversified insurance demands of customers, and to implement the transformation needed in other
create value for stakeholders. A 2020 upgrade layers of the AI capability stack.
to its self-developed cloud system increased the
company’s processing capacity by more than As demonstrated by a European banking group
50,000 insurance policies per second. The insurer’s that adopted an agile business model, obstacles
core systems are available to major insurers in to transforming traditional linear structures can
Asia, and the company maintains wide-ranging be overcome, and gains in employee engagement,
partnerships with internet platforms. Insurer efficiency, speed to market, and client experience
customers can connect with various ecosystem can be realized. For example, the banking group was
partners locally and launch a variety of limited able to release software and updates within two or
and scenario-based protection products. This three weeks rather than five or six times each year,
technology arm of the company serves more than and its employee and customer satisfaction scores
30 insurers across life, property and casualty (P&C), rose dramatically in the first 15 months following its
and health, and more than half of its revenue was operational shift.
generated by recurring income.
Optimizing the organization and operating The evolution of insurance: What’s ahead?
model layer In the short term, organizational shifts like those
A modernized organization, operating model, and described above will help carriers prepare for
way-of-working layer supports AI readiness by AI-enabled improvements. In the long term, shifts
providing the right talent, structure, and culture to will prime the insurance industry to realize the kinds
Transitioning from a traditional linear
model to a cross-functional operating
model facilitates expert-driven AI
insights generation and adoption.
8 Insurer of the future: Are Asian insurers keeping up with AI advances?
of AI-enabled gains experienced in other industries. AI offers the potential to enhance insurance
As AI applications advance and become fully protections with insights to support integrated
integrated across the customer industry, the breadth life, health, and wealth solutions and personalized
and nature of services and products that life insurers preventive strategies.
can provide will evolve from simply assessing and
servicing claims to prescribing and preventing The importance of employing strong risk
them (Exhibit 3). From automated processing to management practices in insurance cannot be
predictive analytics and prescriptive algorithms, overstated. The reality is that along with its potential
Web 2023
AI insurer of the future
Exhibit 3
Exhibit 3 of 3
There are four layers to the full-stack AI capability that will define the AI-enabled In the future, life insurers’ focus is likely to evolve toward proactively preventing
insurer of the future. adverse events.
“Assess and service” “Predict and personalize” “Engage and share value” “Prescribe and prevent”
Pre-2020 2020–25 2025–30 2030 and beyond
L M N O
K
J
I
H
G
A B C D E F
A Individuals provide C Information collected G Integrated engagement L Smart contracts
data that is used to from external sources platform facilitates data, enabled by blockchain
assess risks and provide and devices is used to insights, and transactions instantaneously
standard products and proactively assess risk across multiple industries, authorize payments
care suggestions and provide personalized allowing for value sharing from a customer’s
wellness products and between entities financial account
B Policies are priced, care suggestions
purchased, and serviced H Highly dynamic, usage- M Prescriptive
in predefined service- D Majority of financial based insurance products suggestions provide
level agreements and planning is done through proliferate and are tailored interventions for
cohorts algorithmic platforms, to the behavior of individual agents or digital
with agents humanizing consumers channels to actively
advice and building influence outcomes
customer relationships I Lines between life, wealth,
and health products blur N Personalization is
E Advanced algorithms as integrated solutions come used to craft tailored
match leads to best-fit to market strategies and coverage
channel and advisors for each household
J More than 90% of policies
F Pricing sophistication use accelerated and O Robo and DIY channels
increases, with more- automated straight- can approximate
tailored pricing and through underwriting; human empathy and
smaller risk pools manual underwriting ceases conversational
for most products capabilities, facilitating
a 70–90% servicing-
K Agents use smart personal cost reduction and
assistants to optimize their providing a resolution
tasks, as well as AI-enabled within minutes
bots to recommend deals
for clients
McKinsey & Company
Insurer of the future: Are Asian insurers keeping up with AI advances? 9
to revolutionize the industry, AI presents insurance advances can offer new and expanding growth
Find more content like this on the
players with potential challenges related to data opportunities, and lagging behind other sectors
McKinsey Insights App
privacy, inherent biases, interpretability, and could exacerbate challenges to attracting and
more. Privacy breaches, intellectual-property retaining top global talent and meeting evolving
infringements, and job displacements stemming customer expectations. Though complex, a properly
from AI adoption are all too possible and illustrate structured, layered approach to expanding AI
why companies are better positioned for success capacity throughout the insurance value chain can
when following blueprints based on proven models help Asian insurers realize long-standing goals and
and best practices to implement and scale AI. set new benchmarks for success as AI-powered
insurers of the future.
Scan • Download • Personalize
The Asian insurance industry stands at a crossroads
for AI-powered transformation: technological
Violet Chung is a senior partner in McKinsey’s Hong Kong office, Pranav Jain is a consultant in the Singapore office, and
Karthi Purushothaman is a partner in the Chennai office.
The authors wish to thank Radhika Agarwal and Norman Metzner for their contributions to this article.
Copyright © 2023 McKinsey & Company. All rights reserved.
Contact
Violet Chung Karthi Purushothaman
Senior partner, Hong Kong Partner, Chennai
[email protected] [email protected]
Further insights
How the Asian insurance market is How personalization at scale can How Asian insurers can use digital
adapting to the future invigorate Asian insurers marketing to fuel growth
10 Insurer of the future: Are Asian insurers keeping up with AI advances? |
38 | mckinsey | the-european-union-ai-act-time-to-start-preparing.pdf | McKinsey Direct
The European Union AI Act:
Time to start preparing
A successful digital future depends on responsible use of AI. The EU AI Act
marks a significant step in regulating AI systems and could serve as a blueprint
for other jurisdictions.
This article is a collaborative effort by Henning Soller with Anselm Ohme, Chris Schmitz, Malin Strandell-Jansson,
Timothy Chapman, and Zoe Zwiebelmann, representing views from McKinsey’s Risk & Resilience and Digital Practices.
November 2024
Artificial intelligence and generative AI (gen AI) organizations that are best positioned to build
will have a transformative impact on economic digital trust are also more likely than others to see
growth and productivity. This is especially true for annual growth rates of at least 10 percent on their
organizations that expect to make changes to their top and bottom lines.
operations using the technology, a recent McKinsey
survey shows.1 While many organizations embrace these concepts,
some still lack fundamental risk controls for the new
To realize the benefits of AI, organizations technologies. In early 2024, McKinsey surveyed
need the underlying models and their use to 180 EU-based organizations in five sectors about
be secure, safe, and trusted. Implementing the state of AI governance in the European Union.
robust data governance, model-risk, security, Seventy-one percent of respondents said their AI
and individual-rights management is crucial risk governance was less than mature, although
for responsible AI governance. Together, these 65 percent of them said they were already using gen
pillars create a solid foundation for future digital AI (Exhibit 1).
transformation, and digital trust. According to
McKinsey research, trusted organizations have Survey participants expressed concerns in
higher margins and better valuations than less- five high-level categories that mirror important
trusted ones.2 And while only a small contingent considerations for AI: data, model output, security,
of companies are set to deliver this digital trust, third-party, and societal risks.
Web <2024>
E<2x0h2i4b0i6t1 11_EU AI Act Implementation Status>
Exhibit <1> of <6>
Less than 30 percent of survey respondents consider their organization’s AI
risk governance to have some level of maturity.
Maturity of organization’s AI risk governance,1 % of respondents
Overall Financial Energy and Technology, Life sciences Consumer
institutions materials media, and goods
telecom
Series 1 SeriesS 2eries 1 Series 2
Very mature 7Very mature 1V3ery mature 0Very mature 5Very mature 7Very mature 8
Mature M2a1ture M3at0ure M2a6ture 1M5ature 1M5ature 18
Neutral Neu4t0ral Ne3u3tral Ne3u0tral Neut4r5al Neut4r4al 43
Immature Im24mature Im23mature Im22mature Im3m3ature Im3m3ature 18
Very immature 7Very immature 3Very immature V2e2ry immature 3Very immature 0Very immature 15
Note: Figures may not sum to 100%, because of rounding.
Question: How mature is your AI risk governance?
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
1 “The state of AI in early 2024: Gen AI adoption spikes and starts to generate value,” McKinsey, May 30, 2024.
2 Jim Boehm, Liz Grennan, Alex Singla, and Kate Smaje, “Why digital trust truly matters,” McKinsey, September 12, 2022.
The European Union AI Act: Time to start preparing 2
Some concerns fall into one category, while others Based on the use case, AI systems are defined as
span several. Bias, for example, touches model prohibited, high-risk, or non-high-risk. Rules for
output, data, and third-party risk. Among the other “prohibited” AI, which includes models that are
potential concerns expressed in the survey are manipulative or deceptive, are outlined in Article 5
discrimination, bad outputs, personal-data leakage, of the act. “High risk” systems are those that could
intellectual property misuse, security breaches, and threaten health, safety, and fundamental rights,
malicious use. including those related to critical infrastructure,
education or vocational training, employment,
Given everything that could go wrong with AI, access to essential public or private services and
standards and policy setters are increasing benefits (including credit and health insurance),
efforts to control the risks. Regulators globally are profiling, and law enforcement. “Non high risk”
introducing regulatory frameworks and guidelines, systems, with lower or no regulatory requirements,
including in Canada, China, Japan, South Korea, consist of everything not specifically covered by the
and the United States. The EU AI Act, enacted by other two categories, including AI in video games
the European Union in May 2024, is the world’s first and customer service chatbots.
general AI regulation to go into effect. Being the
first of its kind, the EU AI Act will serve as a test bed
for other guidance to follow. In addition, it will have Early days of implementation efforts
extraterritorial effects because the scope includes AI governance and EU AI Act compliance efforts
AI tools developed in other markets if a tool or its are still in the early days, but organizations
output is applied in the European Union. already have questions. More than 50 percent
of survey respondents said they are not clear on
AI act requirements and are unsure of the risk
Overview of the EU AI Act and
classifications for their AI use cases (Exhibit 2).
its requirements
The EU AI Act aims to “promote human-centric Organizations consider themselves most prepared
and trustworthy AI while protecting health, safety, with regard to data management, ahead of
and fundamental rights.” It will have wide-ranging governance, model risk management, and individual
implications for all affected organizations as the rights (Exhibit 3).
guidance is rolled out over the next two years.
Even so, data management is still a concern. More
The act sets requirements in four areas: than half—57 percent—of respondents said that
governance, data management, model-risk many data governance requirements remain
management, and individual rights. These unaddressed. Specifically, some organizations said
requirements include risk and quality management, there is a lack of clarity in terms of how the General
human oversight, AI system documentation and Data Protection Regulation (GDPR) and the EU AI
transparency, data management, model-risk Act will interact.
governance measures for nondiscrimination and
bias, accuracy, robustness, and cybersecurity. When asked whether they had already met the
act’s requirements for the four areas, less than
Which requirements apply to each organization 10 percent of survey respondents said that they had
depends on two factors: the risk classification and (Exhibit 4).
the role of the organization in the AI value chain,
which includes providers, importers, distributors,
deployers of AI systems, and combinations thereof.
The European Union AI Act: Time to start preparing 3
Web <2024>
E<2x0h2i4b0i6t1 21_EU AI Act Implementation Status>
Exhibit <2> of <6>
Only 4 percent of survey respondents agreed that the EU AI Act
requirements are clear.
Perceived clarity of EU AI Act,1 % of respondents Strongly agree Somewhat agree
Overall Financial Energy and Technology, Life sciences Consumer
institutions materials media, and goods
telecom
SeriesS 2eries 1 SeriesS 2eries 1 SeriesS 2eries 1 SeriesS 2eries 1 Series 2
It is clear what It is clear what It is clear what It is clear what It is clear what It is clear what
the EU AI Act the EU AI Act the EU AI Act the EU AI Act the EU AI Act the EU AI Act
4 32 36 5 33 38 417 22 528 33 4 41 44 10 30 40
will require of will require of will require of will require of will require of will require of
us us us us us us
For our AI use For our AI use For our AI use For our AI use For our AI use For our AI use
cases, it is clear cases, it is clear cases, it is clear cases, it is clear cases, it is clear cases, it is clear
what risk what risk what risk what risk what risk what risk
7 37 44 5 40 45 4 39 43 10 40 50 11 37 48 8 28 35
category they category they category they category they category they category they
fall into under fall into under fall into under fall into under fall into under fall into under
the AI Act the AI Act the AI Act the AI Act the AI Act the AI Act
For our AI use For our AI use For our AI use For our AI use For our AI use For our AI use
cases, it is clear cases, it is clear cases, it is clear cases, it is clear cases, it is clear cases, it is clear
what role our what role our what role our what role our what role our what role our
16 44 59 18 43 60 9 43 52 25 48 7373 19 41 59 10 43 53
organization organization organization organization organization organization
takes in the AI takes in the AI takes in the AI takes in the AI takes in the AI takes in the AI
value chain value chain value chain value chain value chain value chain
Note: Figures may not sum to totals, because of rounding.
Question: To what extent do you agree with the following statements?
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
Web <2024>
E<2x0h2i4b0i6t1 31_EU AI Act Implementation Status>
Exhibit <3> of <6>
Survey respondents consider their organizations somewhat prepared
across various dimensions of the EU AI Act.
Self-assessment of EU AI Act governance maturity, averages and ranges
Range of responses Average maturity
Model-risk management
Individual rights
Governance
Data management
Very immature Very mature
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
The European Union AI Act: Time to start preparing 4
Web <2024>
<E2x0h2i4b0i6t1 41_EU AI Act Implementation Status>
Exhibit <4> of <6>
Few of the key requirements of the EU AI Act are fully addressed by more
than about 10 percent of organizations.
Fully addressed, % Somewhat addressed, % Split not available
Governance Model-risk management¹
Overall implementation Overall implementation Series 1 Series 2 Series 3
7 22 44
Data governance controls Monitoring and logging
8 29 63
AI principles and norms Security and accuracy techniques
9 26 49
Governance organization Robustness techniques
9 23 45
Design quality control and verification Standardized technical documentation
10 18 41
Definition of accountability Human in the loop
7 19 38
Third-party risk management Predefined performance metrics
6 20 37
AI risk management Standardized instructions of use
3 22 34
Strategy for regulatory compliance
4 21 0
Employee upskilling .
4 21 0
Data management Individual rights
Overall implementation Overall implementation Series 1 Series 2 Series 3
6 27 7 22
Data collection GDPR rights respected by AI
12 36 17 34
Ensuring representative data AI system informs people of interaction
5 32 8 22
Data preparation Explanation of AI-enabled decisions
9 27 3 22
Appropriate statistical properties Tailored user instructions
6 27 2 23
AI system design choices AI evaluation metrics reported
3 30 3 18
Formulation of assumptions AI systems mark content as AI made
4 22 6 14
Examination of biases
3 17
1Based on proportion of organizations having technically implemented these measures, not the level at which they have addressed them.
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
The European Union AI Act: Time to start preparing 5
Nearly half of respondents said they had not yet implemented strategies for regulatory compliance
allocated any budget for AI Act implementation, or AI risk management.
and most that have allocated a budget have set
aside €2 million or less (Exhibit 5). There are Risk governance. About three in ten respondents
many reasons organizations aren’t spending have developed a mature AI risk governance
yet. Some respondents have likely not started structure, and only a third said they have a
responding to AI Act requirements because the governance organization. Further, about 40 percent
rules are so new. Others are focused on aligning lack clear definitions of accountabilities for AI,
their AI remediation efforts to their existing and about 10 percent say they have fully addressed
governance structure. Still others are unaware of AI principles and norms.
the upcoming regulatory requirements.
Encouragingly, nearly half of respondents said they
have separate usage guidelines, and more than a
Key challenges facing organizations third have input and output guardrails in place for
Respondents cited a variety of challenges to their external AI models. This likely is a consequence
efforts to meet the requirements of the AI Act. of protecting business-sensitive information and
intellectual property as organizations rapidly
Complexity. In some cases, organizations are deployed gen AI tools.
stalled as they seek clarity and the resources to
prepare for complex regulations and technology. Third-party risk management is also a concern.
Only one in four survey respondents have Less than a third of organizations said they have
appropriately addressed AI-related third-party risk.
Web <2024>
E<2x0h2i4b0i6t 151_EU AI Act Implementation Status>
Exhibit <5> of <6>
Close to 50 percent of organizations have not yet allocated resources for
EU AI Act implementation efforts.
Amount budgeted for EU AI Act implementation efforts,1 % of respondents
Overall Financial Energy and Technology, Life sciences Consumer
institutions materials media, and goods
Series 1 Series 2 telecom
No budget No b 4u 7dget No 3b 8udget No b 4ud 8get No b 4ud 8get SeNrieos b 14ud 8getSeriesS 2eries 415 Series 2
allocated yet allocated yet allocated yet allocated yet allocated yet allocated yet
Up to €1 million U2p2 to €1 million 1U5p to €1 million U17p to €1 million Up3 0to €1 million U2p2 to €1 million 28
€1–€2 million 1€61–€2 million €21–5€2 million €171–€2 million 5€1–€2 million 7€1–€2 million 23
€3–€5 million 6€3–€5 million 5€3–€5 million 1€33–€5 million 1€33–€5 million 4€3–€5 million 0
€6–€10 million 5€6–€10 million 10€6–€10 million 4€6–€10 million 0€6–€10 million 1€16–€10 million 3
>€10 million 4>€10 million 8>€10 million 0>€10 million 5>€10 million 7>€10 million 3
Note: Figures may not sum to 100%, because of rounding.
Question: How much have you budgeted for EU AI Act implementation efforts?
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
The European Union AI Act: Time to start preparing 6
Some have implemented GDPR-related controls, defining standards for testing the outputs of
technical guardrails, and model fine-tuning for gen AI models. For self-developed models,
external models. But just 16 percent of respondents respondents said they commonly use continuous
are conducting red-teaming efforts, while some said code integration and deployment, model versioning,
they are rolling back relationships with suppliers and documentation to ensure quality.
while rules and obligations for general-purpose AI
become applicable throughout 2025. Thirty-eight percent of respondents use
“human in the loop” processes, while 30 percent
Data governance. Only 18 percent of respondents use technically responsible AI tooling. Model
said their organizations have mature technical risk performance monitoring, logging, and user
management processes for AI systems in place. In feedback, together with incident detection and
addition, few have robust models or security and management, are the most common measures
accuracy techniques. However, about 75 percent used to ensure quality after deployment.
of respondents indicated they had advanced cyber
controls and data protection measures in place. Talent. Getting the right people to run and manage
AI is proving difficult, too. The talent shortage is
The act introduces requirements for data especially prominent for technical staff but also
management. These cover choices in designing exists for legal personnel. This is a major concern
systems, formulating assumptions, collecting not only for businesses but also for regulatory
and preparing data, examining bias, ensuring authorities that have concerns about competent
representative data use, and including the monitoring and enforcement of the AI Act. Only a
appropriate statistical properties. More than quarter of respondents upskill employees, which
half of survey respondents said they have not takes time and investment.
yet addressed these requirements. Less than
20 percent have addressed bias. Other. Perhaps surprisingly, respondents did
not cite cost, financial resources, or ethical
What models do with the data is another area concerns as top reasons for the slow progress
of concern. Many respondents cited difficulty in on implementation (Exhibit 6).
Given the complexity of the EU AI
Act and the effort needed to comply, it
would be prudent for organizations
to accelerate their planning now.
The European Union AI Act: Time to start preparing 7
Web <2024>
E<2x0h2i4b0i6t1 61_EU AI Act Implementation Status>
Exhibit <6> of <6>
Key challenges of implementing the EU AI Act relate to unclear obligations,
complexity, and talent gaps.
Key challenges facing organizations in implementing the EU AI Act,1 % of respondents
Unclear obligations 81
SeriesS 2Ceorimesp 1lexity SeriesS 2eries 1 SeriesS 2eries 1 SeriesS 2eries 1 Series 2 69
Data governance 57
Skills and talent gap 35
Change management 27
Technical resources 13
Cost 11
Financial resources 8
Ethical concerns 6
Source: McKinsey EU AI Act Survey, spring 2024 (n = 180 organizations in Europe)
McKinsey & Company
The time to act Organizations should embrace a “define your
world” approach, which prioritizes transparency
Given the complexity of the EU AI Act and the
in model use, stakeholders, risks, and regulations.
effort needed to comply, it would be prudent
The EU AI Act has set out requirements mainly for
for organizations to accelerate their planning
high-risk models, so a risk categorization of the
now. While the act outlines implementation
model landscape will help structure the work going
stages and staggered compliance deadlines,
forward and control the level of effort.
those with experience implementing GDPR
understand that waiting can create chaos as
Defining a target state for governance and
those deadlines approach.
compliance efforts can help organizations build
road maps that thoroughly consider strategy, risk
Managing the scope of an organization’s AI efforts
appetite, organizational structure, technology,
is important. Organizations that align development
policy, and tooling. And organizations can continue
to governance practices manage to limit the number
to get better through a process of ongoing
of models they use, generally to fewer than 20.
improvement, using existing best practices and
A clear governance structure can also limit teams’
frameworks as a guide. Ensuring cross-functional
frustrations in fielding ad hoc requests and trying
collaboration and input on ethical and risk
to get support.
considerations is paramount, so if current risk
The European Union AI Act: Time to start preparing 8
functions are not equipped, separate action on top But before that happens, the act’s regulators will
Find more content like this on the
of existing governance may be required. need to further clarify their expectations and work
McKinsey Insights App
with the industry to find pragmatic implementation
To achieve compliance, organizations will need solutions in an environment of limited resources.
the necessary talent, resources, and relevant Responsible and trustworthy AI is a prerequisite
KPIs to measure progress. AI is evolving quickly, to defining a new digital future. By embracing
so it is essential to stay on top of changes. The responsible AI governance, companies can spur
EU AI Act represents a significant step toward innovation with the trust of consumers, competitors,
regulating AI systems and ensuring responsible AI shareholders, and society behind them.
governance and could serve as a blueprint for other
Scan • Download • Personalize
jurisdictions globally.
This article originally appeared in the August/September edition of The RMA Journal.
Henning Soller is a partner in McKinsey’s Frankfurt office; Anselm Ohme is a consultant in the Berlin office, where Chris
Schmitz is a data science fellow; Malin Strandell-Jansson is an alumna of the Stockholm office; Timothy Chapman is an
analyst in the Wroclaw office; and Zoe Zwiebelmann is a consultant in the Hamburg office.
The authors wish to thank Andreas Kremer, Angela Luget, Angie Selzer, Artem Avdeed, and Silvia Tilea for their contributions
to this article.
Designed by McKinsey Global Publishing
Copyright © 2024 McKinsey & Company. All rights reserved.
The European Union AI Act: Time to start preparing 9 |
39 | mckinsey | What-every-CEO-should-know-about-generative-AI.pdf | QuantumBlack, Al by McKinsey
What every CEO should
know about generative AI
Generative AI is evolving at record speed while CEOs are still learning the technology’s
business value and risks. Here, we offer some of the generative AI essentials.
This article is a collaborative effort by Michael Chui, Roger Roberts, Tanya Rodchenko, Alex Singla, Alex Sukharevsky, Lareina
Yee, and Delphine Zurkiya, representing views from the McKinsey Technology Council and QuantumBlack, AI by McKinsey,
which are both part of McKinsey Digital.
Image created by Chris Grava / Darby Films using a node-based visual programming language
May 2023
Amid the excitement surrounding generative A generative AI tool might suggest upselling
AI since the release of ChatGPT, Bard, Claude, opportunities to the salesperson in real time based
Midjourney, and other content-creating tools, CEOs on the actual content of the conversation, drawing
are understandably wondering: Is this tech hype, or from internal customer data, external market trends,
a game-changing opportunity? And if it is the latter, and social media influencer data. At the same time,
what is the value to my business? generative AI could offer a first draft of a sales pitch
for the salesperson to adapt and personalize.
The public-facing version of ChatGPT reached 100
million users in just two months. It democratized AI The preceding example demonstrates the
in a manner not previously seen while becoming by implications of the technology on one job role. But
far the fastest-growing app ever. Its out-of-the-box nearly every knowledge worker can likely benefit
accessibility makes generative AI different from all from teaming up with generative AI. In fact, while
AI that came before it. Users don’t need a degree generative AI may eventually be used to automate
in machine learning to interact with or derive value some tasks, much of its value could derive from
from it; nearly anyone who can ask questions can how software vendors embed the technology
use it. And, as with other breakthrough technologies into everyday tools (for example, email or word-
such as the personal computer or iPhone, one processing software) used by knowledge workers.
generative AI platform can give rise to many Such upgraded tools could substantially increase
applications for audiences of any age or education productivity.
level and in any location with internet access.
CEOs want to know if they should act now—and,
All of this is possible because generative AI if so, how to start. Some may see an opportunity
chatbots are powered by foundation models, which to leapfrog the competition by reimagining
contain expansive neural networks trained on how humans get work done with generative AI
vast quantities of unstructured, unlabeled data applications at their side. Others may want to
in a variety of formats, such as text and audio. exercise caution, experimenting with a few use
Foundation models can be used for a wide range cases and learning more before making any
of tasks. In contrast, previous generations of AI large investments. Companies will also have to
models were often “narrow,” meaning they could assess whether they have the necessary technical
perform just one task, such as predicting customer expertise, technology and data architecture,
churn. One foundation model, for example, can operating model, and risk management
create an executive summary for a 20,000-word processes that some of the more transformative
technical report on quantum computing, draft a implementations of generative AI will require.
go-to-market strategy for a tree-trimming business,
and provide five different recipes for the ten The goal of this article is to help CEOs and their
ingredients in someone’s refrigerator. The downside teams reflect on the value creation case for
to such versatility is that, for now, generative AI can generative AI and how to start their journey. First,
sometimes provide less accurate results, placing we offer a generative AI primer to help executives
renewed attention on AI risk management. better understand the fast-evolving state of AI
and the technical options available. The next
With proper guardrails in place, generative AI can section looks at how companies can participate in
not only unlock novel use cases for businesses generative AI through four example cases targeted
but also speed up, scale, or otherwise improve toward improving organizational effectiveness.
existing ones. Imagine a customer sales call, for These cases reflect what we are seeing among
example. A specially trained AI model could suggest early adopters and shed light on the array of options
upselling opportunities to a salesperson, but across the technology, cost, and operating model
until now those were usually based only on static requirements. Finally, we address the CEO’s vital
customer data obtained before the start of the call, role in positioning an organization for success with
such as demographics and purchasing patterns. generative AI.
2 What every CEO should know about generative AI
Excitement around generative AI is palpable, A generative AI primer
and C-suite executives rightfully want to move Generative AI technology is advancing quickly
ahead with thoughtful and intentional speed. (Exhibit 1). The release cycle, number of start-
We hope this article offers business leaders a ups, and rapid integration into existing software
balanced introduction into the promising world of applications are remarkable. In this section,
generative AI. we will discuss the breadth of generative AI
Exhibit 1
Generative AI has been evolving at a rapid pace.
Timeline of some of the major large language model (LLM) developments in the months following
ChatGPT’s launch
What every CEO should know about generative AI 3
applications and provide a brief explanation of the Answer questions
technology, including how it differs from traditional AI.
— Employees of a manufacturing company
More than a chatbot can ask a generative AI–based “virtual
Generative AI can be used to automate, augment, and expert” technical questions about operating
accelerate work. For the purposes of this article, we procedures.
focus on ways generative AI can enhance work rather
than on how it can replace the role of humans. — A consumer can ask a chatbot questions about
how to assemble a new piece of furniture.
While text-generating chatbots such as ChatGPT
have been receiving outsize attention, generative Draft
AI can enable capabilities across a broad range
of content, including images, video, audio, and — A software developer can prompt generative AI
computer code. And it can perform several functions to create entire lines of code or suggest ways to
in organizations, including classifying, editing, complete partial lines of existing code.
summarizing, answering questions, and drafting
new content. Each of these actions has the potential — A marketing manager can use generative AI to
to create value by changing how work gets done draft various versions of campaign messaging.
at the activity level across business functions and
workflows. Following are some examples. As the technology evolves and matures, these
kinds of generative AI can be increasingly
Classify integrated into enterprise workflows to automate
tasks and directly perform specific actions (for
— A fraud-detection analyst can input transaction example, automatically sending summary notes
descriptions and customer documents into a at the end of meetings). We already see tools
generative AI tool and ask it to identify fraudulent emerging in this area.
transactions.
How generative AI differs from other kinds of AI
— A customer-care manager can use generative AI As the name suggests, the primary way in which
to categorize audio files of customer calls based generative AI differs from previous forms of AI
on caller satisfaction levels. or analytics is that it can generate new content
efficiently, often in “unstructured” forms (for
Edit example, written text or images) that aren’t
naturally represented in tables with rows and
— A copywriter can use generative AI to correct columns (see sidebar “Glossary” for a list of terms
grammar and convert an article to match a client’s associated with generative AI).
brand voice.
The underlying model that enables generative AI
— A graphic designer can remove an outdated logo to work is called a foundation model. Transformers
from an image. are key components of foundation models—GPT
actually stands for generative pre-trained
Summarize transformer. A transformer is a type of artificial
neural network that is trained using deep learning,
— A production assistant can create a highlight a term that alludes to the many (deep) layers within
video based on hours of event footage. neural networks. Deep learning has powered many
of the recent advances in AI.
— A business analyst can create a Venn diagram
that summarizes key points from an executive’s However, some characteristics set foundation
presentation. models apart from previous generations of deep
4 What every CEO should know about generative AI
Glossary
Application programming interface (API) is a way to programmatically access (usually external) models, data sets, or other pieces of
software.
Artificial intelligence (AI) is the ability of software to perform tasks that traditionally require human intelligence.
Deep learning is a subset of machine learning that uses deep neural networks, which are layers of connected “neurons” whose connec-
tions have parameters or weights that can be trained. It is especially effective at learning from unstructured data such as images, text,
and audio.
Fine-tuning is the process of adapting a pretrained foundation model to perform better in a specific task. This entails a relatively short
period of training on a labeled data set, which is much smaller than the data set the model was initially trained on. This additional training
allows the model to learn and adapt to the nuances, terminology, and specific patterns found in the smaller data set.
Foundation models (FM) are deep learning models trained on vast quantities of unstructured, unlabeled data that can be used for a wide
range of tasks out of the box or adapted to specific tasks through fine-tuning. Examples of these models are GPT-4, PaLM, DALL·E 2, and
Stable Diffusion.
Generative AI is AI that is typically built using foundation models and has capabilities that earlier AI did not have, such as the ability to
generate content. Foundation models can also be used for non-generative purposes (for example, classifying user sentiment as negative
or positive based on call transcripts) while offering significant improvement over earlier models. For simplicity, when we refer to genera-
tive AI in this article, we include all foundation model use cases.
Graphics processing units (GPUs) are computer chips that were originally developed for producing computer graphics (such as for
video games) and are also useful for deep learning applications. In contrast, traditional machine learning and other analyses usually run
on central processing units (CPUs), normally referred to as a computer’s “processor.”
Large language models (LLMs) make up a class of foundation models that can process massive amounts of unstructured text and learn
the relationships between words or portions of words, known as tokens. This enables LLMs to generate natural language text, perform-
ing tasks such as summarization or knowledge extraction. GPT-4 (which underlies ChatGPT) and LaMDA (the model behind Bard) are
examples of LLMs.
Machine learning (ML) is a subset of AI in which a model gains capabilities after it is trained on, or shown, many example data points.
Machine learning algorithms detect patterns and learn how to make predictions and recommendations by processing data and experi-
ences, rather than by receiving explicit programming instruction. The algorithms also adapt and can become more effective in response
to new data and experiences.
MLOps refers to the engineering patterns and practices to scale and sustain AI and ML. It encompasses a set of practices that span the
full ML life cycle (data management, development, deployment, and live operations). Many of these practices are now enabled or opti-
mized by supporting software (tools that help to standardize, streamline, or automate tasks).
Prompt engineering refers to the process of designing, refining, and optimizing input prompts to guide a generative AI model toward
producing desired (that is, accurate) outputs.
Structured data are tabular data (for example, organized in tables, databases, or spreadsheets) that can be used to train some machine
learning models effectively.
Transformers are key components of foundation models. They are artificial neural networks that use special mechanisms called
“attention heads” to understand context in sequential data, such as how a word is used in a sentence.
Unstructured data lack a consistent format or structure (for example, text, images, and audio files) and typically require more advanced
techniques to extract insights.
What every CEO should know about generative AI 5
learning models. To start, they can be trained on companies should be careful of integrating
extremely large and varied sets of unstructured generative AI without human oversight in
data. For example, a type of foundation model applications where errors can cause harm or
called a large language model can be trained on where explainability is needed. Generative AI
vast amounts of text that is publicly available on the is also currently unsuited for directly analyzing
internet and covers many different topics. While large amounts of tabular data or solving advanced
other deep learning models can operate on sizable numerical-optimization problems. Researchers are
amounts of unstructured data, they are usually working hard to address these limitations.
trained on a more specific data set. For example,
a model might be trained on a specific set of The emerging generative AI ecosystem
images to enable it to recognize certain objects in While foundation models serve as the “brain” of
photographs. generative AI, an entire value chain is emerging
to support the training and use of this technology
In fact, other deep learning models often can (Exhibit 2).¹ Specialized hardware provides the
perform only one such task. They can, for example, extensive compute power needed to train the
either classify objects in a photo or perform another models. Cloud platforms offer the ability to tap
function such as making a prediction. In contrast, this hardware. MLOps and model hub providers
one foundation model can perform both of these offer the tools, technologies, and practices an
functions and generate content as well. Foundation organization needs to adapt a foundation model
models amass these capabilities by learning and deploy it within its end-user applications.
patterns and relationships from the broad training Many companies are entering the market to offer
data they ingest, which, for example, enables them applications built on top of foundation models
to predict the next word in a sentence. That’s how that enable them to perform a specific task, such
ChatGPT can answer questions about varied topics as helping a company’s customers with service
and how DALL·E 2 and Stable Diffusion can produce issues.
images based on a description.
The first foundation models required high levels
Given the versatility of a foundation model, of investment to develop, given the substantial
companies can use the same one to implement computational resources required to train them
multiple business use cases, something rarely and the human effort required to refine them. As a
achieved using earlier deep learning models. A result, they were developed primarily by a few tech
foundation model that has incorporated information giants, start-ups backed by significant investment,
about a company’s products could potentially be and some open-source research collectives (for
used both for answering customers’ questions and example, BigScience). However, work is under way
for supporting engineers in developing updated on both smaller models that can deliver effective
versions of the products. As a result, companies results for some tasks and training that’s more
can stand up applications and realize their benefits efficient. This could eventually open the market
much faster. to more entrants. Some start-ups have already
succeeded in developing their own models—for
However, because of the way current foundation example, Cohere, Anthropic, and AI21 Labs build
models work, they aren’t naturally suited to all and train their own large language models.
applications. For example, large language models
can be prone to “hallucination,” or answering
questions with plausible but untrue assertions Putting generative AI to work
(see sidebar “Using generative AI responsibly”). CEOs should consider exploration of generative
Additionally, the underlying reasoning or sources AI a must, not a maybe. Generative AI can create
for a response are not always provided. This means value in a wide range of use cases. The economics
1 For more, see “Exploring opportunities in the generative AI value chain,” McKinsey, April 26, 2023.
6 What every CEO should know about generative AI
Web <year>
<Title>
EExxhihbiitb <itx >2 of <x>
A value chain supporting generative AI systems is developing quickly.
A value chain supporting generative AI systems is developing quickly.
Generative AI value chain
Services
Services around specialized knowledge on how to leverage generative AI (eg, training, feedback, and
reinforcement learning)
Applications
B2B or B2C products that use foundation models either largely as is or fine-tuned to a particular use case
Model hubs and MLOps
Tools to curate, host, fine-tune, or manage the foundation models (eg, storefronts between applications and
foundation models)
Foundation models
Core models on which generative AI applications can be built
Cloud platforms
Platforms to provide access to computer hardware
Specialized hardware
Accelerator chips optimized for training and running the models (eg, graphics processing units, or GPUs)
McKinsey & Company
and technical requirements to start are not Much of the use (although not necessarily all of
prohibitive, while the downside of inaction could the value) from generative AI in an organization
be quickly falling behind competitors. Each CEO will come from workers employing features
should work with the executive team to reflect on embedded in the software they already have.
where and how to play. Some CEOs may decide that Email systems will provide an option to write the
generative AI presents a transformative opportunity first drafts of messages. Productivity applications
for their companies, offering a chance to reimagine will create the first draft of a presentation based
everything from research and development to on a description. Financial software will generate
marketing and sales to customer operations. Others a prose description of the notable features
may choose to start small and scale later. Once in a financial report. Customer-relationship-
the decision is made, there are technical pathways management systems will suggest ways to interact
that AI experts can follow to execute the strategy,
depending on the use case.
What every CEO should know about generative AI 7
Using generative AI responsibly
Generative AI poses a variety of risks. CEOs will want to design their teams and processes to mitigate those risks from the start—not
only to meet fast-evolving regulatory requirements but also to protect their business and earn consumers’ digital trust (we offer recom-
mendations on how to do so later in this article).¹
Fairness: Models may generate algorithmic bias due to imperfect training data or decisions made by the engineers developing the
models.
Intellectual property (IP): Training data and model outputs can generate significant IP risks, including infringing on copyrighted, trade-
marked, patented, or otherwise legally protected materials. Even when using a provider’s generative AI tool, organizations will need to
understand what data went into training and how it’s used in tool outputs.
Privacy: Privacy concerns could arise if users input information that later ends up in model outputs in a form that makes individuals
identifiable. Generative AI could also be used to create and disseminate malicious content such as disinformation, deepfakes, and hate
speech.
Security: Generative AI may be used by bad actors to accelerate the sophistication and speed of cyberattacks. It also can be manipu-
lated to provide malicious outputs. For example, through a technique called prompt injection, a third party gives a model new instruc-
tions that trick the model into delivering an output unintended by the model producer and end user.
Explainability: Generative AI relies on neural networks with billions of parameters, challenging our ability to explain how any given
answer is produced.
Reliability: Models can produce different answers to the same prompts, impeding the user’s ability to assess the accuracy and reliabil-
ity of outputs
Organizational impact: Generative AI may significantly affect the workforce, and the impact on specific groups and local communities
could be disproportionately negative.
Social and environmental impact: The development and training of foundation models may lead to detrimental social and environ-
mental consequences, including an increase in carbon emissions (for example, training one large language model can emit about 315
tons of carbon dioxide).²
1 Jim Boehm, Liz Grennan, Alex Singla, and Kate Smaje, “Why digital trust truly matters,” McKinsey, September 12, 2022.
2 Ananya Ganesh, Andrew McCallum, and Emma Strubell, “Energy and policy considerations for deep learning in NLP,” Proceedings of the 57th Annual Meeting of the
Association for Computational Linguistics, June 5, 2019.
with customers. These features could accelerate the are using generative AI today to reshape how work is
productivity of every knowledge worker. done within their organization.² The examples range
from those requiring minimal resources to resource-
But generative AI can also be more transformative intensive undertakings. (For a quick comparison
in certain use cases. Following, we look at four of these examples and more technical detail, see
examples of how companies in different industries Exhibit 3.)
2 These examples are amalgamations of cases culled from our client work and public examples rather than reflective of exact events in one
particular company.
8 What every CEO should know about generative AI
Exhibit 3
The organizational requirements for generative AI range from low to high,
depending on the use case.
Low High
Use case Technical Costs Tech talent Proprietary data Process
example pathway adjustments
Changing the Use Many SaaS tools Little technical Because the Processes
work of software software- offer fixed-fee talent is needed— model is used as largely remain
engineering as-a- subscriptions of potentially for is, no proprietary the same, but
service $10 to $30 per selecting the right data is needed workers should
(SaaS) tool user per month; solution and light systematically
some products integration work check model
have usage-based results for
pricing accuracy and
appropriateness
Helping Build Up-front investment Software Because the Processes may
relationship software is needed to develop development, model is used as be needed to
managers keep layers on the user interface, product is, no proprietary enable storage
up with the model API integrate the management, and data is needed of prompts and
pace of public solution, and build database integration results, and
information and postprocessing capabilities are guardrails may
data layers needed, which be needed to
require at least 1 data limit usage for
Running costs for scientist, machine risk or cost
API usage and learning engineer, reasons
software data engineer,
maintenance designer, and front-
end developer
Freeing up Fine-tune Initial costs Experienced A proprietary, Processes for
customer open- ~2x more than data science and labeled data triaging and
support source building on API engineering team set is required escalating
representatives’ model due to increased with machine to fine-tune the issues to
time for higher- in-house human capital learning operations model, although humans are
value activities costs required for (MLOps) knowledge in some cases it needed, as
data cleaning and and resources to can be relatively well as periodic
labeling and model check or create small assessments of
fine-tuning labeled data needed model safety
Higher running
costs for model
maintenance and
cloud computing
Accelerating Train a Initial costs Requires large Foundation Including the
the pace at foundation ~10–20x more data science and models can be above, when
which research model than building on engineering team trained on large training on
scientists from API due to up-front with PhD-level publicly available external data,
can identify scratch human capital and knowledge of data, although thorough
relevant cell tech infrastructure subject matter, long-term legal review
features for costs best-practice differentiation is needed to
drug discovery MLOps, and data comes from prevent IP
Running costs and infrastructure adding owned issues
for model management skills labeled or
maintenance and unlabeled data
cloud computing (which is easier to
similar to the above collect)
What every CEO should know about generative AI 9
Changing the work of software engineering
The first example is a relatively low-complexity case with immediate productivity benefits because it
uses an off-the-shelf generative AI solution and doesn’t require in-house customization.
The biggest part of a software engineer’s job is writing code. It’s a labor-intensive process that requires
extensive trial and error and research into private and public documentation. At this company, a
shortage of skilled software engineers has led to a large backlog of requests for features and bug fixes.
To improve engineers’ productivity, the company is implementing an AI-based code-completion
product that integrates with the software the engineers use to code. This allows engineers to write code
descriptions in natural language, while the AI suggests several variants of code blocks that will satisfy
the description. Engineers can select one of the AI’s proposals, make needed refinements, and click on
it to insert the code.
Our research has shown that such tools can speed up a developer’s code generation by as much as 50
percent. It can also help in debugging, which may improve the quality of the developed product. But
today, generative AI cannot replace skilled software engineers. In fact, more-experienced engineers
appear to reap the greatest productivity benefits from the tools, with inexperienced developers seeing
less impressive—and sometimes negative—results. A known risk is that the AI-generated code may
contain vulnerabilities or other bugs, so software engineers must be involved to ensure the quality and
security of the code (see the final section in this article for ways to mitigate risks).
The cost of this off-the-shelf generative AI coding tool is relatively low, and the time to market is short
because the product is available and does not require significant in-house development. Cost varies
by software provider, but fixed-fee subscriptions range from $10 to $30 per user per month. When
choosing a tool, it’s important to discuss licensing and intellectual property issues with the provider to
ensure the generated code doesn’t result in violations.
Supporting the new tool is a small cross-functional team focused on selecting the software provider and
monitoring performance, which should include checking for intellectual property and security issues.
Implementation requires only workflow and policy changes. Because the tool is purely off-the-shelf
software as a service (SaaS), additional computing and storage costs are minimal or nonexistent.
10 What every CEO should know about generative AI
Helping relationship managers keep up with the pace of public information and data
Companies may decide to build their own generative AI applications, leveraging foundation models
(via APIs or open models), instead of using an off-the-shelf tool. This requires a step up in investment
from the previous example but facilitates a more customized approach to meet the company’s specific
context and needs.
In this example, a large corporate bank wants to use generative AI to improve the productivity of
relationship managers (RMs). RMs spend considerable time reviewing large documents, such as
annual reports and transcripts of earnings calls, to stay informed about a client’s situation and
priorities. This enables the RM to offer services suited to the client’s particular needs.
The bank decided to build a solution that accesses a foundation model through an API. The solution
scans documents and can quickly provide synthesized answers to questions posed by RMs. Additional
layers around the foundation model are built to streamline the user experience, integrate the tool
with company systems, and apply risk and compliance controls. In particular, model outputs must be
verified, much as an organization would check the outputs of a junior analyst, because some large
language models have been known to hallucinate. RMs are also trained to ask questions in a way that
will provide the most accurate answers from the solution (called prompt engineering), and processes
are put in place to streamline validation of the tool’s outputs and information sources.
In this instance, generative AI can speed up an RM’s analysis process (from days to hours), improve job
satisfaction, and potentially capture insights the RM might have otherwise overlooked.
The development cost comes mostly from the user interface build and integrations, which require
time from a data scientist, a machine learning engineer or data engineer, a designer, and a front-end
developer. Ongoing expenses include software maintenance and the cost of using APIs. Costs depend
on the model choice and third-party vendor fees, team size, and time to minimum viable product.
What every CEO should know about generative AI 11
Freeing up customer support representatives for higher-value activities
The next level of sophistication is fine-tuning a foundation model. In this example, a company uses a
foundation model optimized for conversations and fine-tunes it on its own high-quality customer chats and
sector-specific questions and answers. The company operates in a sector with specialized terminology (for
example, law, medicine, real estate, and finance). Fast customer service is a competitive differentiator.
This company’s customer support representatives handle hundreds of inbound inquiries a day. Response
times were sometimes too high, causing user dissatisfaction. The company decided to introduce a
generative AI customer-service bot to handle most customer requests. The goal was a swift response in
a tone that matched the company brand and customer preferences. Part of the process of fine-tuning
and testing the foundation model includes ensuring that responses are aligned with the domain-specific
language, brand promise, and tone set for the company; ongoing monitoring is required to verify the
performance of the system across multiple dimensions, including customer satisfaction.
The company created a product road map consisting of several waves to minimize potential model errors.
In the first wave, the chatbot was piloted internally. Employees were able to give “thumbs up” or “thumbs
down” answers to the model’s suggestions, and the model was able to learn from these inputs. As a
next step, the model “listened” to customer support conversations and offered suggestions. Once the
technology was tested sufficiently, the second wave began, and the model was shifted toward customer-
facing use cases with a human in the loop. Eventually, when leaders are completely confident in the
technology, it can be largely automated.
In this case, generative AI freed up service representatives to focus on higher-value and complex customer
inquiries, improved representatives’ efficiency and job satisfaction, and increased service standards and
customer satisfaction. The bot has access to all internal data on the customer and can “remember” earlier
conversations (including phone calls), representing a step change over current customer chatbots.
To capture the benefits, this use case required material invest |
40 | mckinsey | moving-past-gen-ais-honeymoon-phase-seven-hard-truths-for-cios-to-get-from-pilot-to-scale.pdf | Moving past gen AI’s honeymoon
phase: Seven hard truths for
CIOs to get from pilot to scale
Getting to scale requires CIOs to focus on fewer things but do them better.
This article is a collaborative effort by Aamer Baig, Douglas Merrill, and Megha Sinha, with Danesha Mead and
Stephen Xu, representing views from McKinsey Technology and QuantumBlack, AI by McKinsey.
© Getty Images
May 2024
The honeymoon phase of generative AI (gen AI) We explored many of the key initial technology
is over. As most organizations are learning, it is issues in a previous article.2 In this article, we want
relatively easy to build gee-whiz gen AI pilots, but to explore seven truths about scaling gen AI for the
turning them into at-scale capabilities is another “Shaper” approach, in which companies develop
story. The difficulty in making that leap goes a long a competitive advantage by connecting large
way to explaining why just 11 percent of companies language models (LLMs) to internal applications
have adopted gen AI at scale, according to our and data sources (see sidebar “Three approaches
latest tech trends research.1 to using gen AI” for more). Here are seven things
that Shapers need to know and do:
This maturing phase is a welcome development
because it gives CIOs an opportunity to turn gen 1. Eliminate the noise, and focus on the signal.
AI’s promise into business value. Yet while most Be honest about what pilots have worked.
CIOs know that pilots don’t reflect real-world Cut down on experiments. Direct your efforts
scenarios—that’s not really the point of a pilot, after toward solving important business problems.
all—they often underestimate the amount of work
that needs to be done to get gen AI production 2. It’s about how the pieces fit together, not the
ready. Ultimately, getting the full value from gen AI pieces themselves. Too much time is spent
requires companies to rewire how they work, and assessing individual components of a gen AI
putting in place a scalable technology foundation engine. Much more consequential is figuring
is a key part of that process. out how they work together securely.
1 “McKinsey Technology Trends Outlook 2024,” forthcoming on McKinsey.com.
2 “Technology’s generational moment with generative AI: A CIO and CTO guide,” McKinsey, July 11, 2023.
Three approaches to using gen AI
There are three primary approaches to take in using gen AI:
— In “Taker” use cases, companies use off-the-shelf, gen AI–powered software from third-party vendors such as GitHub
Copilot or Salesforce Einstein to achieve the goals of the use case.
— In “Shaper” use cases, companies integrate bespoke gen AI capabilities by engineering prompts, data sets, and connections
to internal systems to achieve the goals of the use case.
— In “Maker” use cases, companies create their own LLMs by building large data sets to pre-train models from scratch.
Examples include OpenAI, Anthropic, Cohere, and Mistral AI.
Most companies will turn to some combination of Taker, to quickly access a commodity service, and Shaper, to build a
proprietary capability on top of foundation models. The highest-value gen AI initiatives, however, generally rely on the Shaper
approach.1
1 For more on the three approaches, see “Technology’s generational moment with generative AI: A CIO and CTO guide,” McKinsey, July 11, 2023.
2 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
3. Get a handle on costs before they sink you. been deemed “successful,” but it was not applied
Models account for only about 15 percent to an important part of the business.
of the overall cost of gen AI applications.
Understand where the costs lurk, and apply the There are many reasons for failing to scale,
right tools and capabilities to rein them in. but the overarching one is that resources and
executive focus are spread too thinly across
4. Tame the proliferation of tools and tech. The dozens of ongoing gen AI initiatives. This is not a
proliferation of infrastructures, LLMs, and tools new development. We’ve seen a similar pattern
has made scaled rollouts unfeasible. Narrow when other technologies emerged, from cloud
down to those capabilities that best serve the to advanced analytics. The lessons from those
business, and take advantage of available innovations, however, have not stuck.
cloud services (while preserving your flexibility).
The most important decision a CIO will need to
5. Create teams that can build value, not just make is to eliminate nonperforming pilots and
models. Getting to scale requires a team with scale up those that are both technically feasible
a broad cross-section of skills to not only build and promise to address areas of the business that
models but also make sure they generate the matter while minimizing risk (Exhibit 1). The CIO will
value they’re supposed to, safely and securely. need to work closely with business unit leaders
on setting priorities and handling the technical
6. Go for the right data, not the perfect implications of their choices.
data. Targeting which data matters most and
investing in its management over time has a big
impact on how quickly you can scale. 2. It’s about how the pieces fit together,
not the pieces themselves
7. Reuse it or lose it. Reusable code can In many discussions, we hear technology leaders
increase the development speed of generative belaboring decisions around the component parts
AI use cases by 30 to 50 percent. required to deliver gen AI solutions—LLMs, APIs,
and so on. What we are learning, however, is that
solving for these individual pieces is relatively easy
1. Eliminate the noise, and focus on and integrating them is anything but. This creates
the signal a massive roadblock to scaling gen AI.
Although many business leaders acknowledge
the need to move past pilots and experiments, The challenge lies in orchestrating the range of
that isn’t always reflected in what’s happening on interactions and integrations at scale. Each use
the ground. Even as gen AI adoption increases, case often needs to access multiple models, vector
examples of its real bottom-line impact are few databases, prompt libraries, and applications
and far between. Only 15 percent of companies (Exhibit 2). Companies have to manage a variety
in our latest AI survey say they are seeing use of of sources (such as applications or databases
gen AI have meaningful impact on their companies’ in the cloud, on-premises, with a vendor, or a
EBIT.3 combination), the degree of fidelity (including
latency and resilience), and existing protocols (for
Exacerbating this issue is that leaders are drawing example, access rights). As a new component is
misleading lessons from their experiments. They added to deliver a solution, it creates a ripple effect
try to take what is essentially a chat interface pilot on all the other components in the system, adding
and shift it to an application—the classic “tech exponential complexity to the overall solution.
looking for a solution” trap. Or a pilot might have
3 That is, they attribute 5 percent or more of their organizations’ EBIT to gen AI use. McKinsey Global Survey on the state of AI in early 2024,
February 22 to March 5, 2024, forthcoming on McKinsey.com.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 3
Exhibit 1
Focus on use cases that are feasible and where business impact is clear.
Focus on use cases that are feasible and where business impact is clear.
Criteria for determining business impact and technical feasibility
Use cases Quick / high-impact wins
Category Criteria (illustrative) Second priority
High
Business Value Can we accurately quantify the value? Is it
impact creation incremental or a step function in performance?
Strategic How well does this align with or support the
alignment company’s primary strategic objectives?
Ease of Are end users enthusiastic about adopting
adoption the solution? Is there a demand for more
Business
features or capabilities?
impact
Business Are we introducing this solution at an
readiness appropriate time, considering ongoing
transformations or other projects?
Technical Data Is the data readily available, or do we need to
feasibility readiness create or synthesize it? Are there any special
considerations for handling sensitive data?
Low
Solution Does the solution require proven or nascent Low Technical High
readiness techniques? feasibility
Ability to Will the proposed business model remain
scale viable as number of users and cloud
consumption increase?
Reusability Can the components of the solution be
repurposed for other use cases?
McKinsey & Company
The key to effective orchestration is embedding The orchestration of the many interactions
the organization’s domain and workflow expertise required to deliver gen AI capabilities, however,
into the management of the step-by-step flow is impossible without effective end-to-end
and sequencing of the model, data, and system automation. “End-to-end” is the key phrase here.
interactions of an application running on a cloud Companies will often automate elements of the
foundation. The core component of an effective workflow, but the value comes only by automating
orchestration engine is an API gateway, which the entire solution, from data wrangling (cleaning
authenticates users, ensures compliance, logs and integration) and data pipeline construction to
request-and-response pairs (for example, to help model monitoring and risk review through “policy
bill teams for their usage), and routes requests to as code.” Our latest research has shown that gen
the best models, including those offered by third AI high performers are more than three times as
parties. The gateway also enables cost tracking likely as their peers to have testing and validation
and provides risk and compliance teams a way embedded in the release process for each model.4
to monitor usage in a scalable way. This gateway A modern MLOps platform is critical in helping to
capability is crucial for scale because it allows manage this automated flow and, according to
teams to operate independently while ensuring McKinsey analysis, can accelerate production by
that they follow best practices (see sidebar “Main ten times as well as enable more efficient use of
components for gen AI model orchestration”). cloud resources.
4 We define gen AI high performers as those who attribute more than 10 percent of their organizations’ EBIT to their use of gen AI.
McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
4 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
Exhibit 2
A gen AI solution needs to accommodate a complex set of integrations
A gen AI solution needs to accommodate a complex set of integrations across
across the entire tech stack.
the entire tech stack.
Illustrative tech stack with end-to-end automation Data Gen AI capabilities Cloud Models
Front-end application
User interface
Data enrichment
and processing Orchestration
Enhancing
Source data Query validation and intent routing Guardrails capabilities
Unstructured Structured Security Data Semantic Prompt LLM Conversation
data ETL¹ data ETL¹ and retrieval and engi- flow memory
access hybrid neering management
Databases (eg, control search and Prompt library
observability
vector stores)
Image Prompt
LLM agents
search enrichment
Structured Fallback External
data query runtime
search integration
Infrastructure and cloud services API gateway
Foundation models (eg, LLMs, multimodal
models, embedding generation models)
1Extract, transform, load.
McKinsey & Company
Gen AI models can produce inconsistent results, 3. Get a handle on costs before they
due to their probabilistic nature or the frequent sink you
changes to underlying models. Model versions can The sheer scale of gen AI data usage and model
be updated as often as every week, which means interactions means costs can quickly spiral out
companies can’t afford to set up their orchestration of control. Managing these costs will have a huge
capability and let it run in the background. They impact on whether CIOs can manage gen AI
need to develop hyperattentive observing and programs at scale. But understanding what drives
triaging capabilities to implement gen AI with costs is crucial to gen AI programs. The models
speed and safety. Observability tools monitor themselves, for example, account for only about 15
the gen AI application’s interactions with users percent of a typical project effort.5 LLM costs have
in real time, tracking metrics such as response dropped significantly over time and continue to
time, accuracy, and user satisfaction scores. If decline.
an application begins to generate inaccurate
or inappropriate responses, the tool alerts the CIOs should focus their energies on four realities:
development team to investigate and make any
necessary adjustments to the model parameters, — Change management is the biggest cost. Our
prompt templates, or orchestration flow. experience has shown that a good rule of thumb
for managing gen AI costs is that for every $1
5 “Generative AI in the pharmaceutical industry: Moving from hype to reality,” McKinsey, January 9, 2024.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 5
Main components for gen AI model orchestration
Orchestration is the process of coordinating various data, transformation, and AI components to manage complex AI workflows.
The API (or LLM) gateway layer serves as a secure and efficient interface between users or applications and underlying gen AI
models. The orchestration engine itself is made up of the following components:
— Prompt engineering and prompt library: Prompt engineering is the process of crafting input prompts or queries that guide
the behavior and output of AI models. A prompt library is a collection of predefined prompts that users can leverage as best
practices/shortcuts when they invoke a gen AI model.
— Context management and caching: Context management highlights background information relevant to a specific task or
interaction. Caching relates to storing previously computed results or intermediate data to accelerate future computations.
— Information retrieval (semantic search and hybrid search): Information-retrieval logic allows gen AI models to search for
and retrieve relevant information from a collection of documents or data sources.
— Evaluation and guardrails: Evaluation and guardrail tools help assess the performance, reliability, and ethical
considerations of AI models. They also provide input to governance and LLMOps. This encompasses tools and processes for
evaluating model accuracy, robustness, fairness, and safety.
spent on developing a model, you need to spend companies default to simply creating a chat
about $3 for change management. (By way of interface for a gen AI application), and second,
comparison, for digital solutions, the ratio has involving their best employees in training models
tended to be closer to $1 for development to $1 to ensure the models learn correctly and quickly.
for change management.6) Discipline in managing
the range of change actions, from training your — Run costs are greater than build costs for
people to role modeling to active performance gen AI applications. Our analysis shows that
tracking, is crucial for gen AI. Our analysis has it’s much more expensive to run models than to
shown that high performers are nearly three build them. Foundation model usage and labor
times more likely than others to have a strong are the biggest drivers of that cost. Most of
performance-management infrastructure, such the labor costs are for model and data pipeline
as key performance indicators (KPIs), to measure maintenance. In Europe, we are finding that
and track value of gen AI. They are also twice as significant costs are also incurred by risk and
likely to have trained nontechnical people well compliance management.
enough to understand the potential value and
risks associated with using gen AI at work.7 — Driving down model costs is an ongoing
process. Decisions related to how to engineer
Companies have been particularly successful in the architecture for gen AI, for example, can
handling the costs of change management by lead to cost variances of 10 to 20 times, and
focusing on two areas: first, involving end users sometimes more than that. An array of cost-
in solution development from day one (too often, reduction tools and capabilities are available,
6 Eric Lamarre, Kate Smaje, and Rodney Zemmel, “Rewired to outcompete,” McKinsey, June 20, 2023.
7 McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
6 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
such as preloading embeddings. This is analytics solutions. The goal here is to develop
not a one-off exercise. The process of cost a modeling discipline that instills an ROI focus
optimization takes time and requires multiple on every gen AI use case without getting lost in
tools, but done well, it can reduce costs from a endless rounds of analysis.
dollar a query to less than a penny (Exhibit 3).
— Investments should be tied to ROI. Not all 4. Tame the proliferation of tools
gen AI interactions need to be treated the and tech
same, and they therefore shouldn’t all cost Many teams are still pushing their own use cases
the same. A gen AI tool that responds to live and have often set up their own environments,
questions from customers, for example, is resulting in companies having to support multiple
critical to customer experience and requires infrastructures, LLMs, tools, and approaches
low-latency rates, which are more expensive. to scaling. In a recent McKinsey survey, in fact,
But code documentation tools don’t have to be respondents cited “too many platforms” as the
so responsive, so they can be run more cheaply. top technology obstacle to implementing gen AI
Cloud plays a crucial rule in driving ROI because at scale.8 The more infrastructures and tools, the
its prime source of value lies in supporting higher the complexity and cost of operations, which
business growth, especially supporting scaled in turn makes scaled rollouts unfeasible. This state
8 McKinsey survey on generative AI in operations, November 2023.
Exhibit 3
As solutions scale, organizations can optimize costs.
As solutions scale, organizations can optimize costs.
Cost per query by week,¹ $
1.0
0.8
0.6
0.4
0.2
0.0
Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Week 7 Backlog
Initial proof Add RAG,² Add intent Re-ranking Migrate from Migrate from Vendor price Batching,
of concept maxing out recognition and prompt paid GPT for risk reduction, and
prompt and routing, optimization embedding guardrails and semantic reevaluate
length reducing generation and intent cache need for
search space model to recognition to chatbot
and adding open-source open-source
LLM calls model models and
regular
expression
1Illustrative example pulling from multiple case studies.
2Retrieval-augmented generation.
McKinsey & Company
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 7
of affairs is similar to the early days of cloud and for example. But greater impact came only when
software as a service (SaaS), when accessing the other parts of the organization—such as risk and
tech was so easy—often requiring no more than a business experts—were integrated into the teams
credit card—that a “wild west” of proliferating tools along with product management and leadership.
created confusion and risk.
There are multiple archetypes for ensuring
To get to scale, companies need a manageable set this broader organizational integration. Some
of tools and infrastructures. Fair enough—but how companies have built a center of excellence to act
do you know which providers, hosts, tools, and as a clearinghouse to prioritize use cases, allocate
models to choose? The key is to not waste time on resources, and monitor performance. Other
endless rounds of analysis on decisions that don’t companies split strategic and tactical duties among
matter much (for example, the choice of LLMs is less teams. Which archetype makes sense for any
critical as they increasingly become a commodity) or given business will depend on its available talent
where there isn’t much of a choice in the first place— and local realities. But what’s crucial is that this
for example, if you have a primary cloud service centralized function enables close collaboration
provider (CSP) that has most of your data and your between technology, business, and risk leads, and
talent knows how to work with the CSP, you should is disciplined in following proven protocols for
probably choose that CSP’s gen AI offering. Major driving successful programs. Those might include,
CSPs, in fact, are rolling out new gen AI services for example, quarterly business reviews to track
that can help companies improve the economics of initiatives against specific objectives and key
some use cases and open access to new ones. How results (OKRs), and interventions to resolve issues,
well companies take advantage of these services reallocate resources, or shut down poor-performing
depends on many variables, including their own cloud initiatives.
maturity and the strength of their cloud foundations.
A critical role for this governing structure is to ensure
What does require detailed thinking is how to build that effective risk protocols are implemented and
your infrastructure and applications in a way that followed. Build teams, for example, need to map
gives you the flexibility to switch providers or models the potential risks associated with each use case;
relatively easily. Consider adopting standards widely technical and “human-in-the-loop” protocols need
used by providers (such as KFServing, a serverless to be implemented throughout the use-case life
solution for deploying gen AI models), Terraform for cycle. This oversight body also needs a mandate
infrastructure as code, and open-source LLMs. to manage gen AI risk by assessing exposures and
implementing mitigating strategies.
It’s worth emphasizing that overengineering for
flexibility eventually leads to diminishing returns. A One issue to guard against is simply managing the
plethora of solutions becomes expensive to maintain, flow of tactical use cases, especially where the
making it difficult to take full advantage of the volume is large. This central organization needs a
services providers offer. mandate to cluster related use cases to ensure large-
scale impact and drive large ideas. This team needs
to act as the guardians for value, not just managers
5. Create teams that can build value, of work.
not just models
One of the biggest issues companies are facing One financial services company put in place
is that they’re still treating gen AI as a technology clearly defined governance protocols for senior
program rather than as a broad business priority. management. A steering group, sponsored by
Past technology efforts demonstrate, however, that the CIO and chief strategy officer, focused on
creating value is never a matter of “just tech.” For gen enterprise governance, strategy, and communication,
AI to have real impact, companies have to build teams driving use-case identification and approvals. An
that can take it beyond the IT function and embed it enablement group, sponsored by the CTO, focused
into the business. Past lessons are applicable here, on decisions around data architecture, data science,
too. Agile practices sped up technical development, data engineering, and building core enabling
8 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
capabilities. The CTO also mandated that at least engineering teams (tech sales/support teams)
one experienced architect join a use-case team developed their own version to find solutions for
early in their process to ensure the team used the unique client calls, commercialization teams had
established standards and tool sets. This oversight product descriptions, and customer support teams
and governance clarity was crucial in helping the had a set of specific product details to answer
business go from managing just five to more than queries. As each team updated its version of the
50 use cases in its pipeline. product information, conflicts emerged, making
it difficult for gen AI models to use the data. To
address this issue, the company is putting all
6. Go for the right data, not the relevant product information in one place.
perfect data
Misconceptions that gen AI can simply sweep up
7. Reuse it or lose it
the necessary data and make sense of it are still
widely held. But high-performing gen AI solutions Reusable code can increase the development
are simply not possible without clean and accurate speed of generative AI use cases by 30 to 50
data, which requires real work and focus. The percent.9 But in their haste to make meaningful
companies that invest in the data foundations to breakthroughs, teams often focus on individual use
generate good data aim their efforts carefully. cases, which sinks any hope for scale. CIOs need to
shift the business’s energies to building transversal
Take the process of labeling, which often oscillates solutions that can serve many use cases. In fact, we
between seeking perfection for all data and have found that gen AI high performers are almost
complete neglect. We have found that investing in three times as likely as their peers to have gen
targeted labeling—particularly for the data used for AI foundations built strategically to enable reuse
retrieval-augmented generation (RAG)—can have a across solutions.10
significant impact on the quality of answers to gen
AI queries. Similarly, it’s critical to invest the time to In committing to reusability, however, it is easy to
grade the importance of content sources (“authority get caught in building abstract gen AI capabilities
weighting”), which helps the model understand the that don’t get used, even though, technically, it
relative value of different sources. Getting this right would be easy to do so. A more effective way to
requires significant human oversight from people build up reusable assets is to do a disciplined
with relevant expertise. review of a set of use cases, typically three to five,
to ascertain their common needs or functions.
Because gen AI models are so unstable, companies Teams can then build these common elements
need to maintain their platforms as new data is as assets or modules that can be easily reused or
added, which happens often and can affect how strung together to create a new capability. Data
models perform. This is made vastly more difficult preprocessing and ingestion, for example, could
at most companies because related data lives in include a data-chunking mechanism, a structured
so many different places. Companies that have data-and-metadata loader, and a data transformer
invested in creating data products are ahead of as distinct modules. One European bank reviewed
the game because they have a well-organized data which of its capabilities could be used in a wide
source to use in training models over time. array of cases and invested in developing a
synthesizer module, a translator module, and a
At a materials science product company, for sentiment analysis module.
example, various teams accessed product
information, but each one had a different version. CIOs can’t expect this to happen organically. They
R&D had materials safety sheets, application need to assign a role, such as the platform owner,
9 Eric Lamarre, Alex Singla, Alexander Sukharevsky, and Rodney Zemmel, “A generative AI reset: Rewiring to turn potential into value in 2024,”
McKinsey, March 4, 2024.
10 McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 9
Exhibit 4
A gen AI platform team needs an array of skills.
A gen AI platform team needs an array of skills.
Cross-functional platform team DataOps: Manages and optimizes the data pipeline, ensuring the
roles and skills availability and quality of data; supports training and deployment of
gen AI models
Site reliability engineer: Ensures reliability, availability, and perfor-
mance of software systems and applications
Data DataOps DevOps engineer: Establishes the CI/CD¹ pipeline and other auto-
engineer
mation needed for teams to rapidly develop and deploy code (eg,
chatbot, APIs) to production
Site
Data reliability Cloud architect: Ensures scalability, security, and cost optimization
scientist engineer of the cloud infrastructure; designs data storage and management
systems; facilitates integration and deployment of the AI models
Platform
Solution/data architect: Develops creative and efficient solutions
Full- team using engineering practices and software/web development
stack DevOps technologies
developer engineer
Platform owner: Acts like a product owner, oversees the build of a
gen AI platform
Full-stack developer: Writes clean and quality scalable code (eg,
Platform Cloud front-end/back-end APIs) that can be easily deployed with CI/CD¹
owner Solution/ architect p ipelines
data Data scientist: Fine-tunes foundational models to help
architect RAG²-based approach, ensures alignment of LLM outputs with
responsible AI guidelines
Data engineer: Architects data models to ingest data into vector
databases, creates and maintains automated pipelines, performs
closed-loop testing to validate responses and improve performance
1Continuous integration (CI) and continuous delivery (CD).
2Retrieval-augmented generation.
McKinsey & Company
and a cross-functional team with a mandate to The value gen AI could generate is
develop reusable assets for product teams transformational. But capturing the full extent of
(Exhibit 4), which can include approved tools, that value will come only when companies harness
code, and frameworks. gen AI at scale. That requires CIOs to not just
acknowledge hard truths but be ready to act on
them to lead their business forward.
Aamer Baig is a senior partner in McKinsey’s Chicago office, Douglas Merrill is a partner in the Southern California office,
Megha Sinha is a partner in the Bay Area office, Danesha Mead is a consultant in the Denver office, and Stephen Xu is
director of product management in the Toronto office.
The authors wish to thank Mani Gopalakrishnan, Mark Gu, Ankur Jain, Rahil Jogani, and Asin Tavakoli for their contributions
to this article.
Copyright © 2024 McKinsey & Company. All rights reserved.
10 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale |
41 | mckinsey | reimagining-insurance-with-a-comprehensive-approach-to-gen-ai-vfinal.pdf | Insurance Practice
Reimagining insurance
with a comprehensive
approach to gen AI
Insurance companies are at an inflection point with their generative AI
use cases. Three McKinsey partners discuss the value of combining
generative AI with other technologies.
by Cameron Talischi, Jörg Mußhoff, and Khaled Rifai
August 2024
Despite forging ahead with generative AI (gen seamlessly search and query risk appetite and
AI) use cases and capabilities, many insurance underwriting guidelines.
companies are finding themselves stuck in the
pilot phase, unable to scale or extract value. Jörg The second category is the generation of content—
Mußhoff sat down with Cameron Talischi and Khaled namely, creative content. Think about it in the
Rifai to discuss how organizations can escape “pilot context of marketing or personalization. Again, in
purgatory” by leveraging traditional AI and robotic the context of claims, it’s communicating the status
process automation in addition to gen AI; the of a claim to a claimant by capturing some of the
importance of reimagining domains such as claims, details and nuances specific to that claim or for
underwriting, and distribution; and how to address supporting underwriters, and it’s communicating or
data privacy and security concerns regarding negotiating with brokers. Use cases for coding and
intellectual property (IP) and other issues early on. software development make up the last category.
This transcript has been edited for clarity. These are notable given the imperative for tech
modernization and digitalization and that many
Jörg Mußhoff: To us, gen AI is not just hype. insurance companies are still dealing with legacy
McKinsey has estimated that the total gen AI systems.
potential for the global economy is $4.4 trillion.1
Many insurance leaders are asking, “How do we Khaled Rifai: I would add one more in the context of
get the benefits from first use cases, and how do client engagement and self-service. Think about the
we scale and make it real across geographies and insured wanting to know whether they’re covered,
business models?” Cam, could you start us off by what the statuses of their claims are, or whether
telling us what you see in the overarching trends in they need to update their addresses or names. Many
gen AI and what applications and domains have the insurers are still employing people to handle these
greatest potential impact for clients? requests. With the help of gen AI, those tasks can
be automated or designed for self-service. I think
Cameron Talischi: We’ve seen a lot of interest and the long-term effects of gen AI are underrated, and
activity in the insurance sector on this topic, which the short-term effects are overrated. And that’s
is not surprising given that the insurance industry the dilemma many insurance companies and other
is knowledge-based and involves processing corporations find themselves in. They want fast
unstructured types of data. That is precisely what results from the benefits of gen AI applications but
gen AI models are very good for. hesitate to invest in data management, technology
modernization, organizational change, and
In terms of promising applications and domains, budgetary allocations.
three categories of use cases are gaining traction.
First, and most common, is that carriers are While we believe in the potential of gen AI, it will take
exploring the use of gen AI models to extract a lot of engagement, investment, and commitment
insights and information from unstructured from top management teams and organizations
sources. In the context of claims, for example, this to make it real. To make gen AI truly successful,
could be synthesizing medical records or pulling you must combine gen AI with more-traditional AI
information from demand packages. In the context and traditional robotic process automation. These
of underwriting for a commercial P&C [property technologies combined make the secret sauce
and casualty insurance carrier], this could look like that helps you rethink your customer journeys and
pulling information from submissions that come processes with the right ROI.
from brokers or allowing underwriters to more
1 The economic potential of generative AI: The next productivity frontier, McKinsey, June 14, 2023.
Reimagining insurance with a comprehensive approach to gen AI 2
Jörg Mußhoff: That’s exactly what we’re seeing Khaled Rifai: I fully agree. Reimaging domains
many players do. But we are still in that pilot phase. is key because you can very quickly get to the
Why do organizations get stuck in this phase, and restrictions connected to isolated use cases
how can they successfully scale up from there? because of the dependencies with other systems
and processes. We are at a point in time with gen
Cameron Talischi: We are seeing a lot of AI where we should take a step back and really
organizations getting stuck in what we call “pilot reimagine claims, underwriting, and distribution. By
purgatory” for several reasons. One is misplaced combining these technologies and thinking about
focus on technology versus what matters from how to design processes that capture the right data
a business perspective. Many organizations at the right point, we can drive meaningful change.
have identified several use cases and have This approach requires investments in more than
development teams building these assets. But just tech; it also takes quite some commitment,
a lot of time is being spent on testing, analyzing, quite some investment, and quite some change to
and benchmarking different tools such as LLMs do so.
[language learning models] even though the choice
of the language model may be dictated by other Jörg Mußhoff: Do you have any pragmatic advice for
factors and, ultimately, has a marginal impact on our clients about what they should do to set this up
performance. and develop these capabilities over time?
While there’s value in learning and experimenting Cameron Talischi: Everything must be anchored
with use cases, these need to be properly planned in a strategic vision and a road map, but in terms of
so they don’t become a distraction. Conversely, capabilities, the data setup is critically important,
leading organizations that are thinking about especially as you think about gaining scale. You
scaling are shifting their focus to identifying the need to make sure that the data underpinning the
common code components behind applications. possible use cases are in usable condition. We
Earlier, we talked about extracting information talked about the technology stack and this notion
from unstructured sources. Typically, these of creating infrastructure that can build and deliver
applications have similar architecture operating in use cases at an accelerated pace. You are touching
the background. So, it’s possible to create reusable on talent and operating models, which are equally
modules that can accelerate building similar use important. One of the failures of some operating
cases while also making it easier to manage them models is when the effort is solely tech-led versus
on the back end. business-led with the technology function as an
enabler. It’s important to assess how much of the
Another area where organizations get stuck is development is done centrally versus within the
how they think about impact. We’ve seen many business.
organizations source ideas from various parts of
the business and prioritize them. But many of the On the talent side, organizations will most likely
use cases are very isolated and don’t generate pursue a combination of building and buying:
much value, so the organization prolongs the pilot. purchasing some of the capabilities and use cases
If you’re not seeing value from a use case, even from external vendors and building some internally,
in isolation, you may want to move on. The better such as use cases that tie to your IP and ways of
approach to driving business value is to reimagine working. To build internally, you’ll need the requisite
domains and explore all the potential actions within talent to create those capabilities. For example, new
each domain that can collectively drive meaningful roles such as prompt engineers address how we
change in the way work is accomplished. So that interact with models and get the right behavior out
includes looking at all the levers at your disposal, of them. You need to build that muscle and some
not just gen AI. That approach better lends itself to of those capabilities through a combination of tech
scaling versus piloting an isolated use case. and business to deploy them as part of the right
operating model.
Reimagining insurance with a comprehensive approach to gen AI 3
‘ You shouldn’t wait it out, because you
need to build that muscle to understand
what solutions you should buy.’
–Khaled Rifai
Khaled Rifai: Some companies wonder what to do Regarding data privacy, it is possible to have
about data management now that gen AI is being automated routines to identify PII [personal
implemented at large vendors. Should they just identifiable information] and strip that data—if it’s
wait it out? Our answer is no—you shouldn’t wait it not needed—to ensure that it doesn’t leave a secure
out, because, as Cam said, you need to build that environment. With accuracy, it’s important to, in
muscle to understand not only how to keep your tandem with the business, have objective measures
organization safe but also what solutions you should and targets for performance. Test these in advance
buy that will fit your needs. of the application or use case going into production,
but also implement routine audits postproduction to
Jörg Mußhoff: Besides data privacy and security, make sure that the performance reached expected
there’s also a big regulatory question. Gen AI can be levels.
biased, which raises ethical questions. In the mid- to
long-term use of these technologies, what should Khaled Rifai: In terms of regulation in Europe,
insurance carriers focus on to avoid risk? the EU Artificial Intelligence Act has recently
been passed. With room for national regulations,
Cameron Talischi: First and foremost, it’s important national regulators of the insurance industry will
for insurance carriers to have a comprehensive look at certain cases to determine standards. In my
framework in place that covers major AI-related experience, the regulations are good enough for
risks such as data privacy issues or issues and clients to work with. I wouldn’t start with high-risk
concerns about accuracy and hallucinations. cases concerning decisions that impact the life and
Incidentally, insurance carriers need to account for health of the insured, but instead begin with other
risks that they’re exposed to via the use of gen AI by use cases that we’re certain we can implement
customers or other parties they interact with. The in a secure, customer-friendly way. The thing to
use of image generation is a good example of this remember is that nothing is static, and the ongoing
because it could lead to fraudulent claims. process of shaping regulations means taking things
one step at a time.
Cameron Talischi is a partner in McKinsey’s Chicago office, and Jörg Mußhoff is a senior partner in the Berlin office,
where Khaled Rifai is a partner.
Copyright © 2024 McKinsey & Company. All rights reserved.
Reimagining insurance with a comprehensive approach to gen AI 4 |
42 | mckinsey | ai-for-it-modernization-faster-cheaper-and-better_f.pdf | AI for IT modernization:
Faster, cheaper, better
Gen AI agents are starting to deliver breakthrough value, but only when
companies figure out how to build and orchestrate hundreds of them.
This article is a collaborative effort by Aaron Bawcom and Matt Fitzpatrick, with Chi Wai Cheung, Dan Collins, and
Dante Gabrielli, representing views from McKinsey Technology and QuantumBlack, AI by McKinsey.
December 2024
At the heart of virtually every large organization is modernize and today is well less than half of that
a massive anchor slowing a business down: the tech when using gen AI. This shift makes many
debt found in legacy IT systems. Often built modernization efforts that were once too expensive
decades ago, these large systems form the or time-consuming suddenly viable. And with the
technical backbone of companies and functions ability to measure and track the direct cost of
across almost every sector. As much as 70 percent technology debt and its effect on P&L outcomes (in
of the software used by Fortune 500 companies many cases up to 40 to 50 percent of total
was developed 20 or more years ago1 (see sidebar investment spend), companies can track the value
“What are legacy systems, and how do they hold they’re generating.
organizations back?”).
While these are still early days, our experience
Modernizing these aging systems and paying down indicates that harnessing gen AI can eliminate
tech debt have traditionally been considered an “IT much of the manual work, leading to a 40 to 50
problem,” and business leaders have been content percent acceleration in tech modernization
to more or less kick the problem down the road. timelines and a 40 percent reduction in costs
The reasons are familiar: it’s too expensive (often derived from technology debt while also improving
hundreds of millions of dollars), it takes too long the quality of the outputs. That value, however, is
(five to seven years), it’s too disruptive, the return less tied to the technology itself and more to how
on the investment is unclear, and the current it’s used, with a particular focus on the following:
systems basically work.
— Improving business outcomes. Converting old
But as technology infiltrates every nook of the code into modern tech languages simply
business and becomes central to a company’s transports your tech debt from a legacy system
ability to generate value, modernizing IT systems into a modern one. Avoiding this “code and
must become a CEO priority. The opportunities, load” issue requires using gen AI to help make
and risks, generated from advances in better business decisions and modernize what
technology—from generative AI (gen AI) to cloud matters.
to robotics—require modern technology
foundations. In fact, technology enables about — Enabling autonomous gen AI agents. Building
71 percent of the value derived from business and training an army of gen AI agents that can
transformations.2 The fact that the programmers work independently and collaboratively with
who built and maintain these aging enterprise human oversight on a range of end-to-end
systems are reaching retirement age lends an even processes is proving to deliver significant
greater urgency to the need for modernization. improvements in IT modernization efforts (see
sidebar “LegacyX”).
New developments in AI, particularly in gen AI, are
radically recalibrating the costs and benefits of — Focusing on scaling value. The value of the
modernizing legacy tech and reducing tech debt as multiagent model comes from industrializing it
part of a larger set of changes in how IT operates. so it can scale and be applied to multiple areas
Consider a transaction processing system for a of the business and continuously pay down
leading financial institution, which three years ago tech debt.
would have cost much more than $100 million to
1 Nia Batten, “Fix it, even if it ‘ain’t broke’: The price of legacy technology,” TechRadar, October 11, 2023.
2 Aamer Baig, Sven Blumberg, Arun Gundurao, and Basel Kayyali, “Breaking technical debt’s vicious cycle to modernize your business,” McKinsey,
April 25, 2023.
AI for IT modernization: Faster, cheaper, better 2
What are legacy systems, and how do they hold organizations back?
Legacy IT systems permeate every — Limited compatibility with modern — Inefficient use of capital: The cost of
industry, often serving as the backbone of channels. Legacy technologies running legacy systems prevents
critical operations. In financial services, for typically do not integrate well with investment in more value-building
instance, core banking platforms and modern channels that demand real- development.
investment management solutions handle time data and advanced connectivity.
— Unattractive to top talent: Top
transactions amounting to trillions of
— Slow responsiveness to regulations: programmers and software engineers
dollars daily on a global scale. Insurance
Continually changing regulatory are less likely to join a business that
administration systems manage policies
requirements become harder and more uses legacy systems and outmoded
worth $1.9 trillion in annual premiums in
expensive to adhere to. languages that they do not understand
the United States alone.1 Benefits
and are not valued in the talent
management platforms facilitate the — Resiliency risk: A lack of understanding
marketplace.
distribution of over $830 million annually of how systems work, coupled with
in social services and benefits to millions of limited automation capabilities and
US citizens.2 often manual-testing processes,
introduces instability issues that are
Technology debt in these systems creates
hard to predict and fix.
significant business issues:
— High run costs: The cost of running
— Slow pace of innovation: Systems built
legacy systems is often significantly
using outdated and difficult-to-
higher than that for modern systems.
understand languages severely hinder
For a large European bank, for
the organization’s ability to adapt and
example, 70 percent of its IT
innovate.
capacity was spent maintaining
legacy systems.
1 Annual Report on the Insurance Industry, Federal Insurance Office, US Department of the Treasury, September 2024.
2 “Project: Public welfare expenditures,” State and Local Backgrounders, Urban Institute, April 26, 2024.
How gen AI agents can improve both switching to easier-to-use programming languages,
code and business outcomes transitioning to modern frameworks that provide
more functionality, restructuring systems to create
At its core, technology modernization involves
modularity, or even remediating and migrating
transforming existing applications to take
applications to run on cheaper cloud environments.
advantage of modern technologies, frameworks,
Harnessing gen AI capabilities to make these kinds
and architectures. This process can include
of changes, improve ROI on cloud programs, and
AI for IT modernization: Faster, cheaper, better 3
LegacyX
LegacyX is a McKinsey capability, to handle end-to-end workflows, focusing automates complex software development
powered by QuantumBlack, that simplifies on deriving the intent of legacy systems to flows, modernizing both processes and
legacy IT system modernization and develop better processes and accelerate applications simultaneously.
delivers business value by using generative modernization with a repeatable process.
AI. It employs a range of specialized agents The tiered multiagent factory framework
pay down technical debt requires a focus on the When properly applied, gen AI is able to
three areas mentioned above. translate the often-impenetrable legacy
elements—documentation, code, observability data,
Improve business outcomes call logs, programming approaches, etcetera—into
Companies have tended to use gen AI in a blunt- simple English process descriptions in a matter of
force way by, for example, feeding legacy code minutes. Engineers at one financial-services
directly into a gen AI tool that translates it into company interviewed a number of experts to
modern language. This code-and-load approach, supplement the limited documentation available
however, essentially migrates your tech debt into a and fed the transcripts into the gen AI model to
modern context. This trap is similar to the one that provide it with better guidance.This clarity not only
many companies fell into during the early days of helps engineers to understand what the systems
cloud computing, where the focus was on “lift and are doing but also allows business experts to help
shift,” that is, moving existing applications to the determine what’s really needed. In this way,
cloud where legacy issues remained unaddressed. business and engineering experts can work
together to determine what they want, what should
The goal of a legacy-tech modernization effort be updated, and what can be discarded.
should not be to convert as many lines of code as
possible. It should be to improve systems and Enable autonomous gen AI agents
processes so the business can generate more We have previously written that in software
value. That means using gen AI to understand the development, using gen AI agents to assist
code you already have, determine what’s needed to developers with coding can help some developers
generate business value, and then modernize the increase their productivity.3 Our experience has
processes that are necessary for achieving that shown that the next horizon of this acceleration will
outcome. enable hundreds of gen AI agents to operate
independently with human oversight, especially as
the model scales (exhibit).
3 “Unleashing developer productivity with generative AI,” McKinsey, June 27, 2023.
AI for IT modernization: Faster, cheaper, better 4
Exhibit
The core of this autonomous-agent approach is the The real value, however, comes from orchestrating
deployment of many specialized AI agents, each agents to complete not just tasks but entire
with distinct roles and expertise, collaborating on software development processes. Data mapping
complex tasks. The tasks they can perform include and storage agents, for example, perform data
data analysis, orchestrating sophisticated analysis, compliance analysis, QA, as well as create
integrations, designing and running test cases, and relevant documentation. These agents work with
refining outcomes based on real-time feedback security design agents that focus on threat analysis,
from humans. information security policy, security design, and QA
agents to develop safe, secure, and effective code.
AI for IT modernization: Faster, cheaper, better 5
To ensure gen AI agents deliver the right outcomes, and then use gen AI agents to generate code as
it’s important to implement a range of controls. well as automate discovery and conversion
Constructive feedback loops, for example, allow journeys. The result was an improvement in code
agents to review and refine one another’s work. modernization efficiency and testing by more than
Gen AI agents can also be programmed to teach 50 percent, as well as a greater than 50 percent
themselves to solve problems or escalate them to a acceleration of coding tasks.
human manager if they can’t figure it out. Some gen
AI agents can even ask the manager direct Focus on scaling value
questions. Assigning IDs to each gen AI agent The excitement surrounding gen AI has led
allows managers to quickly identify the source of an companies to focus a significant amount of time on
issue and address it. Similarly, organizations can evaluating and selecting tools. That is important,
develop specialized agents to automatically test but it pales in comparison to tackling the bigger
and remediate the output of other agents based on issue and opportunity: how to scale gen AI. As one
identified ethical and bias concerns. CIO recently said, “I don’t want one tool to solve one
problem; I need a capability to solve hundreds of
The role people play will continue to be vital to problems.”
directing and managing gen AI agents. Experts like
product owners, engineers, and architects will need Technology leadership should focus on developing
to understand the intent of legacy systems, figure a central, autonomous gen AI capability that can
out what processes are important for the business, build sophisticated multiagent, end-to-end
and develop and set goals and target states. workflows. There are two primary components of
this capability:
The power of the orchestrated gen AI agent
approach became real at one banking company that — Factory. A factory is a group of people who
had been trying unsuccessfully to modernize its develop and manage multiple gen AI agents to
mainframe for years. When it deployed a large execute a specific end-to-end process. The
collection of gen AI agents, the bank was able to goal of the factory is to standardize and simplify
migrate and improve a number of mainframe the various processes that make up the
components as part of a migration to a Java, development, deployment, and management
Angular UI, and PostgreSQL target state. Looking of gen AI agents. A factory develops a
to modernize 20,000 lines of code, the company standardized set of tools and approaches
had estimated it needed 700 to 800 hours to for agent development and management,
complete the migration. The orchestrated gen AI such as monitoring, traceability, document
approach cut that estimate by 40 percent. The management, and large language model access.
relationship-mapping step, for example, went from An organization should consider developing five
requiring 30 to 40 hours to complete to just about to ten agent factories in the early stages of
five hours. maturity.
In another case, a top 15 global insurer used this — Platform. A gen AI platform is a standardized
approach to modernize legacy applications and set of reusable services and capabilities that
services. The first step was to reverse engineer the factories can access. A platform should include
code to better understand technical specifications a user interface, APIs that connect gen AI
AI for IT modernization: Faster, cheaper, better 6
services to enterprise services (such as Jira or most complex technology problems—the ones
ServiceNow), a range of supporting services that cost hundreds of millions of dollars, have
(such as a data import service or agent multiyear timelines, and are responsible for
orchestration service), and a library of gen AI large tranches of technical debt—and focus on
agents that can be loaded to execute specific developing gen AI solutions for them. Part of
tasks. Companies should ideally develop one or this effort should include revisiting previous
two gen AI factories to determine exactly what tech modernization plans that were deemed too
sorts of services and capabilities they use in expensive or time-consuming.
common, then standardize those elements and
offer them through a platform. A dedicated — Tie your business plan explicitly to value and
team of relevant experts should both oversee track it vigorously. While many companies have
the development and management of this business plans, they are often superficial or
platform and closely track usage against limited in scope (for example, focusing on just
specific KPIs, such as service or feature use. the technology rather than the operating
model). A strong plan provides a detailed view
of the value at stake, the increments of value to
Next steps
be captured along the way (factoring in ongoing
Companies looking to move to this multiagent costs, like current and future infrastructure
orchestration model should consider taking four run costs, and one-time costs, like code
steps: modernization), the activities required to
capture them, and a timeline that captures the
— Question any technology proposal that has a break-even point. More important than
long timeline and requires many people. Many developing the plan is revisiting it and ensuring
large-scale IT projects have traditionally that the modernization efforts are actually
required many people to work for years to capturing the intended value. Without this kind
deliver value. Any proposals that follow this of discipline, it’s common for strong plans to
model should be treated with skepticism. That slowly lose focus and default to delivering code
means reviewing all proposals and initiatives rather than value.
that are under way to determine how gen AI can
reduce costs and shorten timelines. Be — Get ahead of the talent, technology, and
particularly thorough in reviewing programs and operating-model implications. As this
proposals that purport to use gen AI multiagent approach scales, companies will
capabilities. The capabilities may be limited or need to understand and plan for the business
ancillary and thus unable to deliver much value. implications. These include how to rethink your
talent strategy and reskilling programs, how
— Focus gen AI on your biggest problems. Small- your operating model has to adapt, and how
scale initiatives lead to small-scale outcomes. operating expenditures and capital
Gen AI has the potential to radically redefine the expenditures will change, among other
cost-benefit of modernizing systems and priorities. These are CEO- and board-level
reducing tech debt. Identify the largest and issues requiring thoughtful planning.
AI for IT modernization: Faster, cheaper, better 7
Companies have barely scratched the surface when the only way companies will be able to cut back
it comes to effectively applying gen AI to modernize tech debt and enable their tech estate to drive
legacy technology and reduce technical debt. innovation and value.
Focusing on how to orchestrate gen AI agents on
meaningful business technology opportunities is
Aaron Bawcom is a partner in McKinsey’s Atlanta office; Matt Fitzpatrick is a senior partner in the New York office, where Chi
Wai Cheung is a principal architect and Dan Collins is a senior principal; Dante Gabrielli is a principal product manager in the
Philadelphia office.
The authors wish to thank Rob Patenge and Vito Di Leo for their contributions to this article.
This article was edited by Barr Seitz, an editorial director in the New York office.
Copyright © 2024 McKinsey & Company. All rights reserved.
AI for IT modernization: Faster, cheaper, better 8 |
43 | mckinsey | extracting-value-from-ai-in-banking-rewiring-the-enterprise.pdf | Financial Services Practice
Extracting value from
AI in banking: Rewiring
the enterprise
To gain material value from AI, banks need to move beyond experimentation to
transform critical business areas, including by reimagining complex workflows with
multiagent systems.
This article is a collaborative effort by Carlo Giovine, Larry Lerner, Renny Thomas, Shwaitang Singh, Sudhakar Kakulavarapu,
and Violet Chung, with Yuvika Motwani, representing views from McKinsey’s Financial Services Practice.
December 2024
Much has been written about the power of AI, helping to pinpoint which loans might go bad,
including generative AI (gen AI), to transform enabling the bank to take steps to intervene and
banking. Beyond ushering in the next wave of support the client.
automation, AI promises to make banks more
intelligent, efficient, and better able to achieve A regional bank, meanwhile, used gen AI to boost
stronger financial performance. the productivity and efficiency of its software
developers. Seeking to optimize resources and
While the buzz is undeniable, many banking C-suite accelerate time to market of new developments, the
leaders are increasingly asking questions about bank launched a proof-of-concept study to assess
the realization of value in light of the headwinds the impact of gen AI tools on coding productivity.
facing the sector. Will AI live up to expectations? Productivity rose about 40 percent for the use
After initial experimentation, how can banks go cases that were part of the study; more than
from proof of concept to proof of value and truly 80 percent of developers said gen AI improved their
reimagine and transform the enterprise using AI? coding experience.
How soon, if ever, can banks see a tangible return
on their investments in AI? In this article, we detail a blueprint to help
financial-services leaders chart the complex path
These questions are gaining relevance as the global of extracting at-scale value from AI across the
banking sector contends with challenges such as enterprise. We begin with what banks that excel
uneven labor productivity results, including falling in AI do differently. We then outline a road map
productivity at US banks, despite high technology that roots the AI transformation in business value,
spending relative to other sectors. Banks also face ascertaining which key business problems need
slowing revenue and loan growth and competition to be solved and harnessing technology, including
from businesses beyond banking—such as private AI, to help with the process. Next, we describe a
credit firms, fintechs, neobanks, payment solutions comprehensive AI capability stack for banking
businesses, and nonbank providers—for the powered by AI agents. Finally, we explore the
largest profit pools. To maintain the current return elements needed to sustain and scale value from AI
on tangible equity margins, banks will need to cut beyond the initial rollouts.
costs much faster as revenue growth slows. AI
has the potential to chip away at these problems
and put banks on more solid footing in the years to Delivering on the promise of AI
come, particularly in boosting labor productivity as in banking
employees continue to delegate a growing number The latest McKinsey Global Survey on AI shows
of routine tasks to increasingly sophisticated and that adoption has increased significantly across
capable AI systems. organizations and industries. However, the
breadth of adoption (measured by the deployment
Some institutions are raising the bar and creating of AI across multiple enterprise functions)
strategic distance from their peers by effectively remains low, and many organizations are still in
scaling AI, including gen AI. For example, a the experimental phase.
large bank is using AI across the enterprise
to improve experiences for its customers and Still, a few leading banks stand out in their ability to
employees, enhance efficiency, and boost revenue deploy AI, including gen AI, across the enterprise,
and profitability. In retail banking, the bank is and have begun to capture material gains from the
harnessing AI to generate personalized nudges use of AI (see sidebar “What does it mean to be an
to help customers with investing and financial AI-first bank?”).
planning. In the small-business segment, AI is
Extracting value from AI in banking: Rewiring the enterprise 2
What does it mean to be an AI-first bank?
AI is enabling broad changes in all sorts The essentials of building an AI-first bank — Modernizing core technology
of industries, including banking, but many include the following: required for the backbone of the AI
banks are still in the experimental phase. capability stack, including automated
— Reimagining the customer
Given how far AI has come and the promise cloud provisioning, an application
experience by providing personalized
it holds, experimenting is not enough. To programming interface, and
offers and streamlined, frictionless
thrive in this new world, banks will need streamlined architecture to enable
use across various devices, for
to become AI-first institutions, adopting continuous, secure data exchange
bank-owned platforms as well as
AI technologies enterprise-wide to boost among various parts of the bank.
partner ecosystems.
value—or risk being left behind.
— Setting up a platform operating model
A successful AI transformation spans — Using AI to help with decision making,
that brings together the right talent,
several layers of the organization. It’s significantly enhancing productivity by
culture, and organizational design.
important to invest in each of the building the architecture required to
interdependent layers, as underinvestment generate real-time analytical insights
in one section can sabotage the entire and translating them into messages
AI transformation. addressing precise customer needs.
Our experience suggests that banks excelling in AI tools, can (see sidebar “What are multiagent
do four things well: systems?”). Expanding these systems to
the entire enterprise requires setting up a
— Set a bold, bankwide vision for the value AI comprehensive AI bank stack.
can create. Leading banks have an expansive
outlook on the role that AI can play, viewing — Sustain and scale value by setting up critical
the technology not just as a driver of cost enablers of the AI transformation. These include
efficiencies but also as a way to enhance cross-functional business, technology, and
revenues and significantly improve customer AI teams along with a central AI control tower
and employee experiences. that coordinates enterprise decisions across
functions, drives governance and adoption of
— Root the transformation in business value by standardized risk guardrails, and promotes the
transforming entire domains, processes, and reusability of AI capabilities.
journeys rather than just deploying narrow
use cases. Banks that excel in AI resist the
temptation to launch narrow use cases such Setting a bold, bankwide vision
as a chatbot or a conversational Q&A tool in for the value AI can create
isolation. Although these might be fast to launch McKinsey’s experience with hundreds of companies
and potentially low risk, in isolation, they won’t across various industries shows that capturing
unlock material financial value. value from digital and AI transformations requires a
fundamental rewiring of how a company operates.
— Build a comprehensive stack of AI capabilities This involves six critical enterprise capabilities:
powered by multiagent systems. Running a business-led digital road map, talent with the
complex banking workflows, such as evaluating right skills, a fit-for-purpose operating model,
a commercial customer’s loan application, technology that’s easy for teams to use, data that’s
involves highly variable steps and the processing continually enriched and easily accessible across
of a mix of structured and unstructured data. the enterprise, and adoption and scaling of digital
While traditional automation cannot handle solutions. These elements are interconnected, and
such tasks, gen-AI-enabled multiagent all have to function well for the transformation to be
systems, combined with predictive AI and digital a success.
Extracting value from AI in banking: Rewiring the enterprise 3
What are multiagent systems?
Multiagent systems, also known as multiagent systems are expected to Eventually, gen AI agents could act
agentic systems, have been around for improve over time. as virtual coworkers. For instance, an
years but have been kicked into a higher engineer could use everyday language
These systems could be capable of
gear in the past two years, thanks to the to describe a new software feature to a
planning actions, using tools to complete
natural-language capabilities of generative programmer agent, which would then
those actions, collaborating with other
AI (gen AI). Although they are still in a code, test, iterate, and deploy the tool it
agents and people, and improving their
nascent phase, and much of the value helped create.
performance as they learn by doing.
they could generate remains hypothetical,
AI can do much more than just automate processes Rooting the transformation in
and boost efficiency. Banks that extract value business value
from AI view the technology as a transformational
Launching a chatbot, creating a document
tool and use AI for core strategic priorities such as
summarizer, using off-the-shelf gen AI tools to
boosting revenue, differentiating the bank from
create ads and write emails—although these types
competitors, and driving higher satisfaction for
of AI endeavors allow banks to experiment and learn
customers and employees.
with minimal risks involved, the results are typically
incremental and, in isolation, rarely lead to material
Leading banks embed AI in the strategic planning
changes in financial outcomes.
process, requiring every business unit to revamp
its operations and set bold financial and customer
Using AI to significantly boost business value will
goals. They focus on innovation by prioritizing the
require banks to do the following:
most high-impact areas that are core to strategy,
versus experimenting in peripheral areas seen as
— Choose the right scope of transformation by
safe bets or taking the “peanut butter” approach
rewiring entire domains and subdomains.
by spreading investments across many disparate
Instead of letting a thousand flowers bloom
initiatives. Next, they invest in enabling the
with many disparate, siloed AI projects,
scalability of AI initiatives by setting up the right
leading banks are using AI to reimagine entire
data and technology platforms.
business domains—such as risk, sales, and
operations—and within them, subdomains
Leading banks also ensure that major AI initiatives
such as relationship management, collections,
are business led, not just technology led. This
and contact-center servicing and operations.
means business executives take ownership of
A typical bank has roughly 25 subdomains
shaping the design of interventions, ensuring what
(Exhibit 1). Once bank executives choose the
is built is tightly aligned with what the business
subdomains for transformation, they reimagine
needs, and holding joint accountability with
each one end to end, using the full range of AI
technology leaders to deliver outcomes.
and digital technologies to achieve the desired
financial outcomes.
Extracting value from AI in banking: Rewiring the enterprise 4
Exhibit 1
Banks can identify business areas for AI transformation and then rewire them
to boost value.
Examples of subdomains that AI could transform in retail banking¹
Sales and Risk Servicing Digital Human Other
Domains
marketing and operations technology resources functions
Digital-led Customer Self-service via Developer Recruitment Legal
customer underwriting digital channels productivity and staffing processes
acquisition such as mobile
banking
Frontline sales Risk-based Assisted service IT operations Performance Regulatory
enablement pricing via contact management, compliance
center, branch, training, and skill and controls
and digital development
Relationship Transaction Middle- and Technology Employee Business
Subdomains management fraud back-office modernization satisfaction intelligence and
and advisory prevention operations and well-being analytics
Partner Portfolio Complaints Product Employee
collaboration for optimization and management and service development
product and monitoring development and for key role
service sales management fulfillment
Engagement, Collections
cross-selling,
and customer
retention
Enterprise knowledge management
Examples of subdomains that AI could transform in private banking¹
Sales and Risk Servicing Digital Human Other
Domains
marketing and operations technology resources functions
Digital-led Client risk Self-service via Developer Recruitment Legal
customer profiling and digital channels productivity and staffing processes
acquisition due diligence such as mobile
banking
Relationship Wealth and Relationship IT operations Performance Regulatory
management, portfolio risk management management, compliance
affluent management and concierge training, and skill and controls
clients² services development
Relationship Credit risk Assisted service Technology Employee Business
Subdomains management, management via contact modernization satisfaction intelligence and
HNW³ and center, branch, and well-being analytics
UHNW⁴ clients and digital
Partner-led Risk-based Complaints Product Employee
client pricing management and service development
acquisition and development and for key role
cross-referrals management fulfillment
Engagement, Fraud and Middle- and
cross-selling, financial crime back-office
and customer prevention operations
retention
Enterprise knowledge management
1A typical bank has ~25 subdomains that could be rewired with AI. This list is not comprehensive.
²Clients with personal financial assets of $100,000–$1 million.
³High-net-worth clients are those with personal financial assets of $1 million–$50 million.
⁴Ultra-high-net-worth clients are those with personal financial assets of >$50 million.
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 5
Exhibit 1 (continued)
Banks can identify business areas for AI transformation and then rewire them
to boost value.
Examples of subdomains that AI could transform in corporate and commercial banking¹
Sales and Risk Servicing Digital Human Other
Domains
marketing and operations technology resources functions
Digital-led Customer Self-service via Developer Recruitment Legal
customer underwriting digital channels productivity and staffing processes
acquisition such as mobile
banking
Partner-led Risk-based Relationship IT operations Performance Regulatory
sales pricing management management, compliance
and concierge training, and skill and controls
services development
Relationship Transaction Middle- and Technology Employee Business
Subdomains management fraud back-office modernization satisfaction intelligence and
and advisory prevention operations and well-being analytics
Frontline sales, Portfolio Complaints Product Employee
generalist, and optimization and management and service development
product led monitoring development and for key role
management fulfillment
Engagement, Loan renewals Assisted service
cross-selling, management via contact
and customer center, branch,
retention and digital
Enterprise knowledge management
Examples of subdomains that AI could transform in investment banking¹
Sales and Risk Servicing Digital Human Other
Domains
marketing and operations technology resources functions
Relationship Customer Relationship Developer Recruitment Legal
management underwriting management productivity and staffing processes
and advisory and concierge
services
Relationship Liquidity risk Middle- and IT operations Performance Regulatory
manager–led management back-office management, compliance
deal sourcing operations training, and skill and controls
development
Engagement, Transaction Complaints Technology Employee Business
Subdomains cross-selling, fraud management modernization satisfaction intelligence and
and customer prevention and well-being analytics
retention
Market risk Product Employee
management and service development
development and for key role
management fulfillment
Enterprise knowledge management
1A typical bank has ~25 subdomains that could be rewired with AI. This list is not comprehensive
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 6
— Decide which subdomains to transform transformation. Together, these subdomains
with AI and in which order. To select these can drive 70 to 80 percent of total incremental
subdomains, banks can consider the overall value from an AI transformation.
business impact and technical feasibility
of driving an AI transformation of a specific In terms of business impact, banks will need to
subdomain (and the likelihood that the assess whether the value of an AI transformation
chosen subdomain includes components of a particular subdomain can be accurately
that can be reused in subsequent subdomain quantified, how well the proposed solution aligns
transformations) (Exhibit 2). In our experience, with the bank’s strategic objectives, how well end
a typical bank has fewer than ten subdomains users (whether clients or employees) are equipped
that could most benefit from an AI overhaul to adopt the solution, and whether the solution will
and should be the first candidates for be a priority for the business.
Web <2024>
E<Axi hini bBiatn 2king>
Exhibit <2> of <8>
Bank subdomains with high business impact and high technical feasibility
should be first in line for an AI transformation.
Illustrative example of how business impact and technical feasibility can inform the transformation
HIGH
o Portfolio optimization and o Assisted service through contact
monitoring center, branch, digital channels
o Product and service o Collections
development and management o Customer underwriting Examples of top
o Regulatory compliance and o Developer productivity candidates for an
controls AI transformation
o Risk-based pricing o Digital-led customer acquisition at a typical bank.
o Engagement, cross-selling, and These subdomains
o Technology modernization customer retention will vary from bank
o Frontline sales enablement to bank.
o Relationship management
o Self-service through digital
channels such as mobile banking
Business
impact
o Business intelligence and o Complaints management
analytics o Enterprise knowledge
o Collaboration with partners management
to sell products and services o IT operations
o Development of employees o Middle- and back-office operations
to fill key roles
o Legal processes
o Employee satisfaction and
well-being o Performance management,
training, and skill development
o Recruitment and staffing
o Transaction fraud prevention
LOW
LOW Technical feasibility HIGH
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 7
Regarding technical feasibility, it is important Once selected for an AI transformation, each
to ascertain the availability and quality of data, subdomain can be deconstructed into a series of
including special considerations for handling executable modules that need to be built, delivered,
sensitive data, techniques for scaling the solution and adopted to drive business value. For example,
across other domains and business units, the transforming the customer underwriting subdomain
reusability of the solution’s components for other end to end involves gen AI, traditional analytics, and
use cases, and the presence of legacy technology digital tools and platforms all working together to
infrastructure that may not be compatible with more reimagine end-to-end workflows and processes
modern AI solutions. (Exhibit 3).
Web <2024>
E<Axi hini bBiatn 3king>
Exhibit <3> of <8>
Banks can rewire the customer underwriting subdomain by using a
combination of gen AI, traditional analytics, and digital tools and platforms.
Elements and use cases Generative AI Traditional analytics Digital tools and platforms
in customer underwriting (illustrative)
Document collection Preassessment Credit assessment Contract generation
s Loan application and s Question generator: s Voice to memo: s Automation of the final step:
document checker: Check for Come up with Summarize insights and Generate contracts, such as
errors, incomplete data, and questions for a actions after personal confirmation of an applicant’s
potential fraud and follow up personal discussion discussion with the eligibility for a loan and loan
with applicants directly with the applicant applicant covenants
s Third-party data validation: s Automated decisions: Make instant decisions to
Verify accuracy of application approve or decline applications based on predefined
details using sources such criteria and risk thresholds
as credit bureaus and
government databases
s Document collection: Allow for multichannel uploading or s Data assessment: Give
scanning of collateral, financial, and know-your-customer estimates for probability
documents; convert them to the required format; and work of default, expected loss,
with customers to get missing or additional documents climate risk (using internal
and external data sources)
s Document analyzer: Check documents for correctness, eg, accuracy of the loan period,
weed out potentially fraudulent documents, and assess income and other data to make
a credit decision
s Unstructured risk elements assessment: Assess risk
elements from unstructured sources, eg, applicant’s
social media footprint and potential reputational damage
s Automated credit memo generation: Generate a credit
memo, a summary of why a customer needs a loan, and
other details for a bank employee to review
s Customer chatbot: Answer customers’ queries and guide them to submit documents, then provide updates on credit decision
and contract finalization
s Employee chatbot: Answer employees’ questions, allow for sending action alerts to teams such as relationship managers, and
drive employees’ communications with customers
s Workflows workbench: Run workflows for end-to-end application management, collateral valuation, legal review, reassignment
of tasks, etc
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 8
Enabling value through an AI stack investment and attention to unlock the full power of
powered by multiagent systems AI for the enterprise.
To embed AI seamlessly across the enterprise,
Given the advent of new technologies such as
banks can implement a comprehensive capability
gen AI, we have updated the AI capability stack
stack that goes beyond just AI models. This AI
(Exhibit 4) from a previous iteration published in
bank stack contains four key capability layers:
2020. Each layer’s foundational elements are
engagement, decision making, data and core tech,
supplemented by several new elements.
and operating model. Each layer will need to receive
Exhibit 4
To drive sustainable value, banks need to put AI first and revamp the entire
technology stack.
New AI bank of the future
elements
Delighting customers through personalized experiences Empowering employees to serve customers better
Engagement Mobile as the gateway to the rest of the bank, including branches, contact center, relationship managers
Multimodal conversational Intelligent products Omnichannel experiences for
experiences (text, visual, voice) and services customers, employees and partners
Use of digital twins to simulate behavior of customers and employees
AI-powered AI orchestration (including copilots and autopilots that organize workflows)Signature Sales
decision Intent Document fraud skills
making AI agents (AI recognition summarizer detector coach
Property Fraud Enterprise
that specializes Risk policy collateral pattern knowledge Test case
in narrow expert analyzer detector search generator
domains)
Ad-banner Legal AI Spend Tax expert
analyzer
Predictive
Customer Credit decision Monitoring Retention, Servicing and
analytics
acquisition making and collections selling, upselling engagement
models
AI Reusable components Information security Streamlined
enablers and services standards and controls risk protocols
Core Industrial AI Observability Machine learning FinOps1 LLM2 LLM Security
technology and machine tool stack operations orchestration gateway
and data learning
Enterprise Search and retrieval engine
data
Data Data Vector Data Structured
ingestion preprocessing databases postprocessing data storage
Technology and Tech-forward strategy (in-house capabilities vs buying offerings; in-house talent plan)
infrastructure
Modern API Intelligent infrastructure (AI operations Cybersecurity Core
architecture command, hybrid cloud setup, etc) and control tiers modernization
Operating Platform Autonomous business, technology, and data teams enabled by AI models and agents
model operating
model Agile ways AI control Modern talent Culture and
of working tower strategy capabilities
Value capture office to monitor transformations
1Financial operations, a framework for managing the operational costs of cloud computing.
2Large language models.
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 9
The AI bank of the future All together now
To create sustainable value, banks need to put AI Elements across the four layers of the AI bank stack
first and revamp the entire technology stack. The work together to enable transformative change and
rise of innovative technologies such as gen AI has deliver value for the enterprise.
prompted an update to the technology stack from
a previous version published in 2020, with new The key to next-generation innovation and
elements highlighted in shades of blue. productivity: Orchestrated multiagent systems
The decision-making layer is the brain of the
Engagement layer AI-first bank, orchestrating and enabling
Banks will need to reimagine how they engage thousands of AI-powered decisions affecting
with customers, making their experiences as customers (such as which product to recommend
intelligent, personalized, and frictionless as possible to them next) and employees (for instance, should
through the use of AI. Leading banks’ customers they approve credit for a specific customer or flag
are experiencing human-like conversational a transaction as fraudulent) across the full life
interactions with AI via text and voice chats and are cycle of products and services.
moving seamlessly across channels such as mobile
apps, websites, branches, and contact centers, Predictive AI models, a core part of the decision-
thanks to powerful AI capabilities. making layer at most banks, are great at driving
decisions when presented with structured data
AI-powered decision-making layer under controlled conditions. These models,
The brain of the bank, this layer makes and however, struggle to adapt when data is
orchestrates decisions. Historically, banks unstructured and the nature of the tasks is nonlinear
have focused on deploying traditional analytics and requires multistep planning, reasoning, and
modules such as models, but as AI technologies orchestration. Such tasks include, for example,
mature, this layer has expanded to include preparing a credit memo—a summary of why a
agent and AI orchestration sublayers working customer needs a loan and other details—based
in unison with the traditional analytics layer to on multiple interactions with that customer and an
drive superior outcomes. evaluation of various types of documents. Another
example is coaching a low-performing seller on how
Core technology and data layer to improve sales performance.
This layer includes the technology and data needed
for an AI transformation, including reusable tools Orchestrated multiagent systems represent a
and pipelines equipped with machine learning major advancement in the decision-making layer.
operations capabilities needed to run large These systems comprise various AI “agents” that
language models (LLMs) at scale. Other portions can be thought of as virtual coworkers. Enabled
of this layer include the data needed to train by advances in gen AI technology, these agents,
multiagent systems, as well as modern application like humans, have the capacity to eventually be
programming interface (API) architecture and able to plan (for instance, organize a workflow
robust cybersecurity. encompassing a series of tasks), think (come up
with chain-of-thought reasoning), and act (use
Operating model digital tools).
By integrating business and technology in platforms
run by cross-functional teams, banks can break Multiagent systems remain nascent and will need
up organizational silos, boost agility and speed, more technical development before they will be
and better align goals and priorities across the ready to deploy at scale across enterprises, but they
enterprise. An AI control tower tracks the value are nonetheless attracting attention because of the
realized from AI initiatives, among other tasks. promise they hold.
Extracting value from AI in banking: Rewiring the enterprise 10
These agents, when combined with predictive AI train and define operating procedures for the
models and digital tools, could fundamentally rewire orchestrators to follow; however, the hope is
several domains of the bank, not just unlocking that the technology will evolve to make them
productivity but forming the basis of more engaging more autonomous.
experiences for customers and bank employees.
— The AI agent layer comprises AI focused on
Multiagent systems can automate complex completing specialized tasks as instructed by
decisions and workflows through a twofold use of AI the orchestration layer or by other agents. Each
(Exhibit 5): of these AI agents, powered by LLMs, is fine-
tuned through a combination of domain-specific
— The AI orchestration layer handles complex data and human feedback. For instance, a policy
workflows and task planning. These AI agent, after being provided with the bank’s loan
orchestrators, programmed to achieve certain policies and related exceptions, can suggest
goals, are expected to eventually be able to do the appropriate loan terms for a customer,
things like autonomously plan actions, reach much like a seasoned bank executive would.
decisions, and make use of existing tools, Meanwhile, a collateral inspection agent can
in-house data, and other AI agents to complete be trained on documents and images related to
stated goals. These AI orchestrators could collateral that customers use to apply for a loan,
manifest themselves in the form of increasingly such as photos of small-business storefronts.
popular copilots for employees and customers. A computer vision tool would then work with
For instance, a copilot for a bank’s credit the collateral inspection agent to screen new
managers is capable of not just answering collateral documents and images to spot
questions but orchestrating the entire credit instances of fraud, such as doctored photos that
workflow when a customer applies for a loan. make the storefront look more impressive than
For now, human intervention is still needed to it really is.
1Financial operations, a framework for managing the operational costs of cloud computing.
2Large language models.
Web <2024>
<EAxi hini bBaitn k5ing>
Exhibit <5> of <8>
Orchestrated multiagent
systems represent a big
AI-powered
advance in banks’ decision
making
decision-making capabilities.
Interacting to solve problems
Multiagent systems are still in a nascent phase, but
eventually AI agents could act as virtual coworkers
capable of planning and executing tasks.
The AI AI orchestration (including copilots and autopilots that organize workflowsS)ignature Sales
Intent Document
orchestration fraud skills
layer handles AI agents (AI recognition Propertysummarizer Fraud detector Enterprise coach
complex that specializes Risk policy collateral pattern knowledge Test case
workflows, in narrow expert analyzer detector search generator
domains)
calling on Ad-banner Legal AI Spend Tax expert
specialized AI analyzer
agents to Predictive Customer Credit decision Monitoring Retention, Servicing and
analytics
complete acquisition making and collections selling, upselling engagement
models
discrete tasks.
Analytics and
AI enablers AI Reusable components Information security Streamlined
support these enablers and services standards and controls risk protocols
efforts.
McKinsey & Company
Extracting value from AI in banking: Rewiring the enterprise 11
The work of these two types of AI is enhanced by agents can be continuously trained to become
AI enablers, including reusable components and better over time, and they |
44 | mckinsey | exploring-opportunities-in-the-generative-ai-value-chain.pdf | Exploring opportunities in the
generative AI value chain
Generative AI is giving rise to an entire ecosystem, from hardware providers to application
builders, that will help bring its potential for business to fruition.
This article is a collaborative effort by Tobias Härlin, Gardar Björnsson Rova, Alex Singla, Oleg Sokolov, and Alex Sukharevsky,
representing views from McKinsey Digital.
© Getty Images
April 2023
Over the course of 2022 and early 2023, tech in this fast-paced space. Our assessments are
innovators unleashed generative AI en masse, based on primary and secondary research, including
dazzling business leaders, investors, and society at more than 30 interviews with business founders,
large with the technology’s ability to create entirely CEOs, chief scientists, and business leaders
new and seemingly human-made text and images. working to commercialize the technology; hundreds
of market reports and articles; and proprietary
The response was unprecedented. McKinsey research data.
In just five days, one million users flocked to ChatGPT,
OpenAI’s generative AI language model that creates A brief explanation of generative AI
original content in response to user prompts. It took To understand the generative AI value chain,
Apple more than two months to reach the same level it’s helpful to have a basic knowledge of what
of adoption for its iPhone. Facebook had to wait ten generative AI is⁵ and how its capabilities differ from
months and Netflix more than three years to build the the “traditional” AI technologies that companies
same user base. use to, for example, predict client churn, forecast
product demand, and make next-best-product
And ChatGPT isn’t alone in the generative AI industry. recommendations.
Stability AI’s Stable Diffusion, which can generate
images based on text descriptions, garnered more A key difference is its ability to create new content.
than 30,000 stars on GitHub within 90 days of This content can be delivered in multiple modalities,
its release—eight times faster than any previous including text (such as articles or answers to
package.¹ questions), images that look like photos or paintings,
videos, and 3-D representations (such as scenes
This flurry of excitement isn’t just organizations and landscapes for video games).
kicking the tires. Generative AI use cases are already
taking flight across industries. Financial services Even in these early days of the technology’s
giant Morgan Stanley is testing the technology to help development, generative AI outputs have been jaw-
its financial advisers better leverage insights from droppingly impressive, winning digital-art awards
the firm’s more than 100,000 research reports.² The and scoring among or close to the top 10 percent of
government of Iceland has partnered with OpenAI test takers in numerous tests, including the US bar
in its efforts to preserve the endangered Icelandic exam for lawyers and the math, reading, and writing
language.³ Salesforce has integrated the technology portions of the SATs, a college entrance exam used
into its popular customer-relationship-management in the United States.⁶
(CRM) platform.⁴
Most generative AI models produce content in one
The breakneck pace at which generative AI format, but multimodal models that can, for example,
technology is evolving and new use cases are create a slide or web page with both text and
coming to market has left investors and business graphics based on a user prompt are also emerging.
leaders scrambling to understand the generative AI
ecosystem. While deep dives into CEO strategy and All of this is made possible by training neural
the potential economic value that the technology networks (a type of deep learning algorithm)
could create globally across industries are on enormous volumes of data and applying
forthcoming, here we share a look at the generative “attention mechanisms,” a technique that helps AI
AI value chain composition. Our aim is to provide models understand what to focus on. With these
a foundational understanding that can serve as a mechanisms, a generative AI system can identify
starting point for assessing investment opportunities word patterns, relationships, and the context of a
1 Guido Appenzeller, Matt Bornstein, Martin Casado, and Yoko Li, “Art isn’t dead; it’s just machine generated,” Andreessen Horowitz, November 16, 2022.
2 Hugh Son, “Morgan Stanley is testing an OpenAI-powered chatbot for its 16,000 financial advisors,” CNBC, March 14, 2023.
3 “Government of Iceland: How Iceland is using GPT-4 to preserve its language,” OpenAI, March 14, 2023.
4 “Salesforce announces Einstein GPT, the world’s first generative AI for CRM,” Salesforce, March 7, 2023.
5 “What is generative AI?” McKinsey, January 19, 2023.
6 “GPT-4,” OpenAI, March 14, 2023.
2 Exploring opportunities in the generative AI value chain
user’s prompt (for instance, understanding that think it’s quite similar to a traditional AI value
“blue” in the sentence “The cat sat on the mat, which chain. After all, of the six top-level categories—
was blue” represents the color of the mat and not computer hardware, cloud platforms, foundation
of the cat). Traditional AI also might use neural models, model hubs and machine learning
networks and attention mechanisms, but these operations (MLOps), applications, and services—
models aren’t designed to create new content. They only foundation models are a new addition
can only describe, predict, or prescribe something (Exhibit 1).
based on existing content.
However, a deeper look reveals some significant
differences in market opportunities. To begin
The value chain: Six links, but one with, the underpinnings of generative AI systems
outshines them all are appreciably more complex than most
As the development and deployment of generative traditional AI systems. Accordingly, the time,
AI systems gets under way, a new value chain cost, and expertise associated with delivering
is emerging to support the training and use of them give rise to significant headwinds for new
this powerful technology. At a glance, one might entrants and small companies across much of the
EWxebh i<byieta 1r>
<Title>
TExhhibeitr <ex> aofr <ex> opportunities across the generative AI value chain, but the most
sTihgenriefi caarnet o ips pbouritludninitgie esn adc-urosesrs atphpel giceantieornast.ive AI value chain, but the most
significant is building end-user applications.
Opportunity size for new entrants
Generative AI value chain in next 3–5 years, scale of 1–5
Services
Services around specialized knowledge on how to leverage
generative AI (eg, training, feedback, and reinforcement learning)
Applications
B2B or B2C products that use foundation models either largely as is
or fine-tuned to a particular use case
Model hubs and MLOps
Tools to curate, host, fine-tune, or manage the foundation models
(eg, storefronts between applications and foundation models)
Foundation models
Core models on which generative AI applications can be built
Cloud platforms
Platforms to provide access to computer hardware
Computer hardware
Accelerator chips optimized for training and running the models
McKinsey & Company
Exploring opportunities in the generative AI value chain 3
value chain. While pockets of value exist throughout, specialized skills, knowledge, and computational
our research suggests that many areas will continue capabilities necessary to serve the generative AI
to be dominated by tech giants and incumbents for market.
the foreseeable future.
The generative AI application market is the section Cloud platforms
of the value chain expected to expand most rapidly GPUs and TPUs are expensive and scarce, making it
and offer significant value-creation opportunities difficult and not cost-effective for most businesses
to both incumbent tech companies and new to acquire and maintain this vital hardware platform
market entrants. Companies that use specialized on-premises. As a result, much of the work to
or proprietary data to fine-tune applications can build, tune, and run large AI models occurs in the
achieve a significant competitive advantage over cloud. This enables companies to easily access
those that don’t. computational power and manage their spend as
needed.
Computer hardware Unsurprisingly, the major cloud providers have
Generative AI systems need knowledge—and the most comprehensive platforms for running
lots of it—to create content. OpenAI’s GPT-3, the generative AI workloads and preferential access
generative AI model underpinning ChatGPT, for to the hardware and chips. Specialized cloud
example, was trained on about 45 terabytes of text challengers could gain market share, but not in the
data (akin to nearly one million feet of bookshelf near future and not without support from a large
space).⁷ enterprise seeking to reduce its dependence on
hyperscalers.
It’s not something traditional computer hardware
can handle. These types of workloads require
large clusters of graphic processing units (GPUs) Foundation models
or tensor processing units (TPUs) with specialized At the heart of generative AI are foundation models.
“accelerator” chips capable of processing all that These large deep learning models are pretrained
data across billions of parameters in parallel. to create a particular type of content and can
be adapted to support a wide range of tasks. A
Once training of this foundational generative AI foundation model is like a Swiss Army knife—it can
model is completed, businesses may also use such be used for multiple purposes. Once the foundation
clusters to customize the models (a process called model is developed, anyone can build an application
“tuning”) and run these power-hungry models within on top of it to leverage its content-creation
their applications. However, compared with the capabilities. Consider OpenAI’s GPT-3 and GPT-4,
initial training, these latter steps require much less foundation models that can produce human-quality
computational power. text. They power dozens of applications, from the
much-talked-about chatbot ChatGPT to software-
While there are a few smaller players in the mix, as-a-service (SaaS) content generators Jasper and
the design and production of these specialized Copy.ai.
AI processors is concentrated. NVIDIA and
Google dominate the chip design market, and one Foundation models are trained on massive data sets.
player, Taiwan Semiconductor Manufacturing This may include public data scraped from Wikipedia,
Company Limited (TSMC), produces almost all of government sites, social media, and books, as well
the accelerator chips. New market entrants face as private data from large databases. OpenAI, for
high start-up costs for research and development. example, partnered with Shutterstock to train its
Traditional hardware designers must develop the image model on Shutterstock’s proprietary images.⁸
7 “What is generative AI?” January 19, 2023; and Kindra Cooper, “OpenAI GPT-3: Everything you need to know,” Springboard, November 1, 2021.
8 “Shutterstock partners with OpenAI and leads the way to bring AI-generated content to all,” Shutterstock, October 25, 2022.
4 Exploring opportunities in the generative AI value chain
Developing foundation models requires deep start-ups backed by significant investment
expertise in several areas. These include (Exhibit 2). However, there is work in progress
preparing the data, selecting the model toward making smaller models that can deliver
architecture that can create the targeted output, effective results for some tasks and training that
training the model, and then tuning the model to is more efficient, which could eventually open
improve output (which entails labeling the quality the market to more entrants. We already see that
of the model’s output and feeding it back into the some start-ups have achieved certain success in
model so it can learn). developing their own models—Cohere, Anthropic,
and AI21, among others, build and train their
Today, training foundation models in particular own large language models (LLMs). Additionally,
comes at a steep price, given the repetitive nature there is a scenario where most big companies
of the process and the substantial computational would want to have LLMs working in their
resources required to support it. In the beginning environments—such as for a higher level of data
of the training process, the model typically security and privacy, among other reasons—and
produces random results. To improve its next some players (such as Cohere) already offer this
output so it is more in line with what is expected, kind of service around LLMs.
the training algorithm adjusts the weights of the
underlying neural network. It may need to do It’s important to note that many questions have
this millions of times to get to the desired level yet to be answered regarding ownership and
of accuracy. Currently, such training efforts can rights over the data used in the development
cost millions of dollars and take months. Training of this nascent technology—as well as over the
OpenAI’s GPT-3, for example, is estimated to cost outputs produced—which may influence how the
$4 million to $12 million.⁹ As a result, the market technology evolves (see sidebar, “Some of the
is currently dominated by a few tech giants and key issues shaping generative AI’s future”).
Some of the key issues shaping generative AI’s future
Amid the enormous enthusiasm, many questions have emerged surrounding generative AI technology, the answers to which will likely shape
future development and use. Following are three of the most important questions to consider when evaluating how the generative AI
ecosystem will evolve:
— Can copyrighted or personal data be used to train models? When training foundation models, developers typically “scrape” data
from the internet. This can sometimes include copyrighted images, news articles, social media data, personal data protected by
the General Data Protection Regulation (GDPR), and more. Current laws and regulations are ambiguous in terms of the implications
of such practices. Precedents will likely evolve to place limits on scraping proprietary data that may be posted online or enable
data owners to restrict or opt out of search indexes so their data can’t easily be found online. New compensation models for data
owners will also likely emerge.
— Who owns the creative outputs? Current laws and regulations also do not clearly answer who owns the copyright on the final
“output” of a generative AI system. Several potential actors can share or own exclusive rights to the final outputs, such as the data
set owner, model developer, platform owner, prompt creator, or the designer who manually refines and delivers the final generative
AI output.
— How will organizations manage the quality of generative AI outputs? We have already seen numerous examples of systems
providing inaccurate, inflammatory, biased, or plagiarized content. It’s not clear whether models will be able to eliminate such
outputs. Ultimately, all companies developing generative AI applications will need processes for assessing outputs at the use case
level and determining where the potential harm should limit commercialization.
9 Kif Leswing and Jonathan Vanian, “ChatGPT and generative AI are booming, but the costs can be extraordinary,” CNBC, March 13, 2023; and
Toby McClean, “Machines are learning from each other, but it’s a good thing,” Forbes, February 3, 2021.
Exploring opportunities in the generative AI value chain 5
Exhibit 2
Examples of generative AI models from some of the early providers show there
are many options available for each modality, several of which are open source.
Examples of generative AI models from some of the early providers show there
are many options available for each modality, several of which are open source.
Closed source¹ Closed source, available through APIs² Open source³
Protein structures
Text Image Audio or music 3-D Video or DNA sequences
RODIN
Microsoft VALL-E GODIVA MoLeR
Diffusion
OpenAI⁴ GPT-4 DALL-E 2 Jukebox Point-E
Meta LLaMA Make-a-scene AudioGen Builder Bot Make-a-video ESMFold
Google/
LaMDA Imagen MusicLM DreamFusion Imagen Video AlphaFold2
DeepMind
Stable Dance
Stability AI StableLM LibreFold
Diffusion 2 Diffusion
Amazon Lex DeepComposer
Apple GAUDI
NVIDIA MT-NLG Edify Edify Edify MegaMolBART
Cohere Family of LLMs
Anthropic Claude
AI21 Jurassic-2
Note: List of products are provided for informational purposes only and do not reflect an endorsement from McKinsey & Company.
1“Closed source” defined as: model not publicly available, access is typically granted through strict process, and usage may be governed by NDA or other
contract.
2“Closed source, available through APIs” defined as: source code of model is not available to the public, but the model is often accessible via API, where usage is
typically governed by licensing agreements.
3“Open source” defined as: code of models available to the public and can be either freely used, distributed, and modified by anyone or restricted for non-
commercial use.
4OpenAI is backed by significant Microsoft investments.
McKinsey & Company
6 Exploring opportunities in the generative AI value chain
Model hubs and MLOps existing solution provider working to add innovative
To build applications on top of foundation models, capabilities to its current offerings, or a business
businesses need two things. The first is a place to looking to build a competitive advantage in its
store and access the foundation model. Second, they industry.
may need specialized MLOps tooling, technologies,
and practices for adapting a foundation model and There are many ways that application providers
deploying it within their end-user applications. This can create value. At least in the near term, we
includes, for example, capabilities to incorporate and see one category of applications offering the
label additional training data or build the APIs that greatest potential for value creation. And we expect
allow applications to interact with it. applications developed for certain industries and
functions to provide more value in the early days of
Model hubs provide these services. For closed- generative AI.
source models in which the source code is not
made available to the public, the developer of the Applications built from fine-tuned models
foundation model typically serves as a model hub. It stand out
will offer access to the model via an API through a Broadly, we find that generative AI applications
licensing agreement. Sometimes the provider will fall into one of two categories. The first represents
also deliver MLOps capabilities so the model can be instances in which companies use foundation
tuned and deployed in different applications. models largely as is within the applications they
build—with some customizations. These could
For open-source models, which provide code that include creating a tailored user interface or adding
anyone can freely use and modify, independent guidance and a search index for documents that
model hubs are emerging to offer a spectrum of help the models better understand common
services. Some may act only as model aggregators, customer prompts so they can return a high-quality
providing AI teams with access to different output.
foundation models, including those customized
by other developers. AI teams can then download The second category represents the most attractive
the models to their servers and fine-tune and part of the value chain: applications that leverage
deploy them within their application. Others, such fine-tuned foundation models—those that have
as Hugging Face and Amazon Web Services, may been fed additional relevant data or had their
provide access to models and end-to-end MLOps parameters adjusted—to deliver outputs for a
capabilities, including the expertise to tune the particular use case. While training foundation
foundation model with proprietary data and deploy models requires massive amounts of data, is
it within their applications. This latter model fills extremely expensive, and can take months, fine-
a growing gap for companies eager to leverage tuning foundation models requires less data, costs
generative AI technology but lacking the in-house less, and can be completed in days, putting it within
talent and infrastructure to do so. reach of many companies.
Application builders may amass this data from
Applications in-depth knowledge of an industry or customer
While one foundation model is capable of performing needs. For example, consider Harvey, the
a wide variety of tasks, the applications built on top generative AI application created to answer legal
of it are what enable a specific task to be completed— questions. Harvey’s developers fed legal data sets
for example, helping a business’s customers with into OpenAI’s GPT-3 and tested different prompts
service issues or drafting marketing emails (Exhibit to enable the tuned model to generate legal
3). These applications may be developed by a new documents that were far better than those that the
market entrant seeking to deliver a novel offering, an original foundation model could create.
Exploring opportunities in the generative AI value chain 7
Exhibit 3
There are many applications of generative AI across modalities.
There are many applications of generative AI across modalities.
Modality Application Example use cases
Text Content writing • Marketing: creating personalized emails and posts
• Talent: drafting interview questions, job descriptions
Chatbots or assistants • Customer service: using chatbots to boost conversion on websites
Search • Making more natural web search
• Corporate knowledge: enhancing internal search tools
Analysis and synthesis • Sales: analyzing customer interactions to extract insights
• Risk and legal: summarizing regulatory documents
Code Code generation • IT: accelerating application development and quality with automatic code
recommendations
Application prototype • IT: quickly generating user interface designs
and design
Data set generation • Generating synthetic data sets to improve AI models quality
Image Stock image generator • Marketing and sales: generating unique media
Image editor • Marketing and sales: personalizing content quickly
Audio Text to voice generation • Trainings: creating educational voiceover
Sound creation • Entertainment: making custom sounds without copyright violations
Audio editing • Entertainment: editing podcast in post without having to rerecord
3-D 3-D object generation • Video games: writing scenes, characters
or other • Digital representation: creating interior-design mockups and virtual
staging for architecture design
Product design and • Manufacturing: optimizing material design
discovery • Drug discovery: accelerating R&D process
Video Video creation • Entertainment: generating short-form videos for TikTok
• Training or learning: creating video lessons or corporate presentations
using AI avatars
Video editing • Entertainment: shortening videos for social media
• E-commerce: adding personalization to generic videos
• Entertainment: removing background images and background noise
in post
Voice translation • Video dubbing: translating into new languages using AI-generated or
and adjustments original-speaker voices
• Live translation: for corporate meetings, video conferencing
• Voice cloning: replicating actor voice or changing for studio effect such
as aging
Face swaps and • Virtual effects: enabling rapid high-end aging; de-aging; cosmetic, wig,
adjustments and prosthetic fixes
• Lip syncing or “visual” dubbing in post-production: editing footage to
achieve release in multiple ratings or languages
• Face swapping and deep-fake visual effects
• Video conferencing: real-time gaze correction
Note: This list is not exhaustive.
McKinsey & Company
8
Organizations could also leverage proprietary — Information technology. Generative AI can help
data from daily business operations. A software teams write code and documentation. Already,
developer that has tuned a generative AI chatbot automated coders on the market have improved
specifically for banks, for instance, might partner developer productivity by more than 50 percent,
with its customers to incorporate data from call- helping to accelerate software development. ¹0
center chats, enabling them to continually elevate
the customer experience as their user base grows. — Marketing and sales. Teams can use generative
AI applications to create content for customer
Finally, companies may create proprietary data outreach. Within two years, 30 percent of all
from feedback loops driven by an end-user rating outbound marketing messages are expected to
system, such as a star rating system or a thumbs- be developed with the assistance of generative
up, thumbs-down rating system. OpenAI, for AI systems.¹¹
instance, uses the latter approach to continuously
train ChatGPT, and OpenAI reports that this helps — Customer service. Natural-sounding,
to improve the underlying model. As customers personalized chatbots and virtual assistants
rank the quality of the output they receive, that can handle customer inquiries, recommend
information is fed back into the model, giving it more swift resolution, and guide customers to the
“data” to draw from when creating a new output— information they need. Companies such as
which improves its subsequent response. As the Salesforce, Dialpad, and Ada have already
outputs improve, more customers are drawn to use announced offerings in this area.
the application and provide more feedback, creating
a virtuous cycle of improvement that can result in a — Product development. Companies can use
significant competitive advantage. generative AI to rapidly prototype product
designs. Life sciences companies, for instance,
In all cases, application developers will need to keep have already started to explore the use of
an eye on generative AI advances. The technology is generative AI to help generate sequences of
moving at a rapid pace, and tech giants continue to amino acids and DNA nucleotides to shorten the
roll out new versions of foundation models with even drug design phase from months to weeks.¹²
greater capabilities. OpenAI, for instance, reports
that its recently introduced GPT-4 offers “broader In the near term, some industries can leverage
general knowledge and problem-solving abilities” these applications to greater effect than others.
for greater accuracy. Developers must be prepared The media and entertainment industry can become
to assess the costs and benefits of leveraging these more efficient by using generative AI to produce
advances within their application. unique content (for example, localizing movies
without the need for hours of human translation)
Pinpointing the first wave of application impact and rapidly develop ideas for new content and
by function and industry visual effects for video games, music, movie
While generative AI will likely affect most business story lines, and news articles. Banking, consumer,
functions over the longer term, our research telecommunications, life sciences, and technology
suggests that information technology, marketing companies are expected to experience outsize
and sales, customer service, and product operational efficiencies given their considerable
development are most ripe for the first wave of investments in IT, customer service, marketing and
applications. sales, and product development.
¹0 GitHub Product Blog, “Research: Quantifying GitHub Copilot’s impact on developer productivity and happiness,” blog entry by Eirini
Kalliamvakou, September 7, 2022.
¹¹ Jackie Wiles, “Beyond ChatGPT: The future of generative AI for enterprises,” Gartner, January 26, 2023.
¹² NVIDIA Developer Technical Blog, “Build generative AI pipelines for drug discovery with NVIDIA BioNeMo Service,” blog entry by Vanessa
Braunstein, March 21, 2023; and Alex Ouyang and Abdul Latif Jameel, “Speeding up drug discovery with diffusion generative models,” MIT
News, March 31, 2023.
Exploring opportunities in the generative AI value chain 9
Services
While generative AI technology and its supporting
As with AI in general, dedicated generative AI
ecosystem are still evolving, it is already quite clear
services will certainly emerge to help companies
that applications offer the most significant value-
fill capability gaps as they race to build out their
creation opportunities. Those who can harness
experience and navigate the business opportunities
niche—or, even better, proprietary—data in fine-tuning
and technical complexities. Existing AI service
foundation models for their applications can expect to
providers are expected to evolve their capabilities to
achieve the greatest differentiation and competitive
serve the generative AI market. Niche players may
advantage. The race has already begun, as evidenced
also enter the market with specialized knowledge
by the steady stream of announcements from software
for applying generative AI within a specific function
providers—both existing and new market entrants—
(such as how to apply generative AI to customer
bringing new solutions to market. In the weeks and
service workflows), industry (for instance, guiding
months ahead, we will further illuminate value-creation
pharmaceutical companies on the use of generative
prospects in particular industries and functions as well
AI for drug discovery), or capability (such as how to
as the impact generative AI could have on the global
build effective feedback loops in different contexts).
economy and the future of work.
Tobias Härlin and Gardar Björnsson Rova are partners in McKinsey’s Stockholm office, where Oleg Sokolov is an associate
partner; Alex Singla is a senior partner in the Chicago office; and Alex Sukharevsky is a senior partner in the London office.
Copyright © 2023 McKinsey & Company. All rights reserved.
10 Exploring opportunities in the generative AI value chain |
45 | mckinsey | GenAI in Norway_ENG_version_v2.pdf | The economic
potential of
Generative AI
in Norway
The next productivity frontier
June 2023
CONFIDENTIAL AND PROPRIETARY
Any use of this material without specific permission of McKinsey & Company
is strictly prohibited
About this document
In the newest report from McKinsey Global
Institute (MGI), MGI discuss how GenAI can
transform the way we work
To assess the effect of GenAI adoption in
Norway and the Norwegian workforce and
businesses, McKinsey Norway used numbers
calculated by MGI, and method applied
there, with Norwegian revenue1,
employment and education data from SSB
(Statistics Norway)
Additional data was from Statista, European
Commission, Eurostat, OECD, and GEDI
1. 2020, the most recently available at the time of writing
McKinsey & Company 2
Generative AI (GenAI) is experiencing significant momentum globally and is expected to gain
traction in Norway with value creation potential of 95-159 bn NOK by 2045 across Norwegian
industries
We expect Norway to be a leading global adopter of GenAI due to the economic
environment, education level of the population, and high degrees of digital adoption
The impact of Generative AI will fall heavily on occupations requiring higher levels of education.
Norway is the 10th highest educated country in the world, and much of the workforce is classified
as knowledge-workers, typically with high wages. This increases the feasibility of early adoption
of GenAI in daily activities
The highest potential value in Norway is expected to be unlocked in selected sectors,
Executive including Energy, High Tech, Travel, Transport & Logistics, and Retail, but true value unlock
comes from three major business functions as opposed to sectors
summary
Marketing and Sales (28-43 bn NOK), Software Engineering (21-43 bn NOK), and Customer
Operations (12-17 bn NOK) will drive the highest amount of value unlock in Norway due to
the high degree of “generation” activities i.e., generating content such as marketing material,
code and emails
While the highest potential value is expected to be unlocked in the Energy industry (~21 bn
NOK), High Tech (~18 bn NOK) is expected to experience a more disruptive shift (7%) following
the adoption of GenAI
Productivity growth has slowed in the last decade but will likely be advanced by GenAI. We
expect work activities within decision making and collaboration, and data management, to be most
affected by GenAI. Such activities are most commonly performed by highly educated workers, and
educators / workforce trainers, employees within business and legal professions, and STEM
professionals, are likely to see the largest productivity gains upon GenAI adoption
MMccKKiinnsseeyy && CCoommppaannyy 33
What is Generative AI?
Suitable Unsuitable
Non-exhaustive
Generative AI (GenAI) enables the creation of new Although some areas are unsuited for GenAI, several
unstructured content, such as text, images, etc. applications emerge2:
Recent GenAI efforts are powered by Foundational
Code/image/audio/video/text generation and editing,
Models trained on a broad set of data that enables
while taking surrounding context into account
them to respond to a wide range of prompts.
Conversational interfaces to convert natural language
These models are typically also better at interpreting /
dialog into specific executions of a technical system
labelling unstructured data than traditional AI
Querying a large set of unstructured data, and
synthesizing a human readable output
High-stakes scenarios with potential for harm
Unconstrained, long, open-ended generation that may
expose harmful or biased content to users
Generate marketing or Automate code generation
social media copy in ”house in programming languages Applications requiring explainability and/or full
style” using ChatGPT, like Python with Codex /
understanding of potential failure modes, including
Copy.A, etc. Github Copilot, etc.
numerical reasoning1
1. Current topic of research: how to use GPT-like models to generate code that involves solving numerical problems
2. Additional resources can be found in the McKinsey Report “Economic potential of generative AI”, and the article “What every CEO should know about generative AI”
Source: Press search; expert interviews MMccKKiinnsseeyy && CCoommppaannyy 44
Automation
A multinational tech company offers a GenAI
GenAI will mainly Giving software predictable tasks
app which can read customer emails and
generate well-documented tickets based
that can be more easily automated
impact three areas,
on these
today with FM powered GenAI
leading to
reinvention of major
processes in Norway
and rest of world
A GenAI-chatbot is already in use in several
Augmentation
large Norwegian banks, and institutions, to
improve productivity and reduce use of
Enhance human productivity to do
human agents in more simple cases
work more efficiently
A large Norwegian house building company
Acceleration
has invested heavily in GenAI for product
development, using it to generate thousands
Extract and index knowledge to
of building configurations prior to any
building activity, allowing for more thorough
shorten innovation cycles enabling
checks, e.g., ensuring that building
dimensions follow regulation
continuous innovation
Source: QuantumBlack: AI by McKinsey; press search McKinsey & Company 5
Norway is expected to be an early adopter of automation with other
economies such as the US and Germany
China Germany France India Japan Mexico US Nordics2 Global avg
Automation adoption, generative AI early scenario1, % automation Automation adoption, generative AI late scenario1, % automation
100% 100%
90% 90%
80% 80%
70% 70%
60% 60%
50% 50%
40% 40%
30% 30%
In early scenario, In late scenario, the 50%
developed economies can threshold is achieved at
20% 20%
achieve more than 50% least 20 years later, with
automation adoption by larger differences between
10% 2030 10% countries
0% 0%
2025 30 35 40 45 50 55 2060 2030 40 50 60 70 80 2090
1. Early scenario -aggressive scenario all key model parameters (tech automation, integration timeline, economic feasibility, regulatory and public adoption); late scenario -parameters are set for the later adoption potential
2. McKinsey Norway estimate
Source: McKinsey Global Institute
The Norwegian digital foundation and education level are key
advantages that can drive nationwide GenAI adoption
Human capital Integration of digital technology
Connectivity Digital public services
Share of population with tertiary
Digital economy and society index1, 2022 education2, 2022 %, aged 25-34 Comments
70
• Norway has one of the highest education
levels in the world, leading to an affluent, skilled
60 workforce that is adaptable and open to learning,
making new technology adoption
economically feasible
50
• Norway has a large population of knowledge
workers, whom typically have a high proportion of
40 activities that can see a productivity boost from
using GenAI to augment knowledge-
based activities
30
• Norway ranks 5th in the 2022 DESI Index –
emphasizing the Norwegian society’s strong
20 digital foundation and GenAI transformation
potential
10 • Norway has a robust digital infrastructure with
>55 40-<45
high internet penetration rates and widespread
50-<55 35-<40 access to fast broadband. This kind of
0 environment is conducive to the growth and
45-<50 <35
Fl DK NL SE NO IE FR DE EU IT HR HU BG RO
adoption of AI technologies.
1. The Digital Economy and Society Index (DESI), non-exhaustive country list
2. Eurostat “Educational attainment statistics”
Source: McKinsey Global Institute; European Commission; press search; Eurostat McKinsey & Company 7
X % of GDP Value realized by 2030
Value realized by 2045
Value potential per industry2, bn NOK
Energy3 16-26 0.4 %
High tech4 12-24 0.3 %
Travel, transport & logistics 13-21 0.3 %
The potential value Retail 13-20 0.3 %
unlock from GenAI Advanced manufacturing5 8-13 0.2 %
Real estate 6-10 0.1 %
is 95-159 bn NOK
Basic materials 5-9 0.1 %
across Norwegian
Banking 5-9 0.1 %
industries1 …
Consumer packaged goods 5-8 0.1%
Professional services 5-7 0.1%
Telecommunications 2-3 0.0 %
Insurance 2-3 0.0 %
Healthcare 2-3 0.0 %
Media 1-3 0.0 %
Chemical <1 0.0 %
Agriculture <1 0.0 %
1. Based on the early adoption scenario, median expected impact of GenAI, %
of industry revenues. 2020 revenues, inflation adjusted
2. By 2030, ~60% of the value potential will be unlocked, by 2045 100% of Pharma & medical products <1 0.0 %
the value will be unlocked. Calculations based on 2020 industry revenues
3. Includes utilities and oil and gas, of which oil and gas contributes
~85% of revenues
4. Includes advanced electronics Total 95-159 2.4%
5. Includes automotive and assembly, and aerospace and defense
Source: Internal experts; annual reports; Statista MMccKKiinnsseeyy && CCoommppaannyy 88
Value realized by 2030
Value potential per business function1, bn NOK Value realized by 2045
Marketing and sales 28-43
… But business Software engineering 21-43
functions, as
Customer operations 12-17
opposed to specific
industries, will be
Supply chain and operations 10-19
the driving forces of
value creation Product and R&D 8-15
Risk and legal 7-9
Strategy and finance 4-9
Talent and organization 2-3
1. Based on the early adoption scenario. By 2030, ~60% of the value
potential will be unlocked, by 2045 100%of the value will be unlocked. Corporate IT2 1-2
Calculations based on 2020 industry revenues
2. Excluding corporate software engineering, including activities such as
e.g., network maintenance
SSoouurrccee:: IInntteerrnnaall eexxppeerrttss,; Danantaubaal sreepso: rAtsn;n SuSalB reports and SSB MMccKKiinnsseeyy && CCoommppaannyy 99
Productivity growth, the main engine of GDP growth, slowed down
in the last decade but is likely to be advanced by GenAI
Employment growth Additional with GenAI
Productivity growth Without GenAI1
Productivity growth bigger contributor to GDP growth
Global GDP growth, Productivity impact from automation,
CAGR, % 2022-40, CAGR2, % Comments
Examining the real GDP
growth contribution of
3.8
Global3 Norway
employment and
3.7 productivity growth,
increasedproductivity
3.1
3.1 1,3
2.9 3.3 0,7 has been the main engine
2.8
for GDP growth
0,6
Implementation of GenAI
0,8
1,4 can significantly
contribute to increased
2,5 productivity in Norway
2,0
going forward
3,0
2,5
2,6
2,1
0.9
1,7
0,3
0,8
0,7 0.2
0,6
0.1
0.1
1972-82 1982-92 1992-2002 2002-2012 2012-2022 Early scenario Late scenario
Early scenario Late scenario
1. Previous assessment of work automation before the rise of generative AI
2. Based on the assumption that the automated work hours are integrated back to work at productivity level of today
3. Based on 47 countries which constitute almost 80% of the world employment
Source: The Conference Board Total Economy database; Oxford Economics; McKinsey Global Institute QuantumBlack, AI by McKinsey 10
CONFIDENTIAL AND PROPRIETARY
Key activities forecasted to be affected are typically executed by
employees holding an advanced degree
With generative AI
Without generative AI1
Incremental technical
automation potential
Overall technical automation potential, Share of NO
Education level Comparison in midpoint scenarios, % in 2023 work force1, % Comments
• Higher educated workers are likely set
57%
Master, PhD or similar 13% to see the largest incremental impact
28% 2X
from automation as they land in jobs
as “knowledge workers” which spend a
high share of their time on activities
most likely to benefit from GenAI
60%
Bachelor’s degree 29%
(i.e., applying expertise to planning and
36% 1.7x
creative tasks, managing and
stakeholder management).
• An example of this is within science:
researchers spend ~30 minutes to read
64%
High school diploma 36% one scientific paper2, but GenAI could
51% 1.2X
or equivalent
summarize hundreds of papers in
minutes
Without a high school 63%
19%
degree 54% 1.2X
1. Does not sum up to 100% due to some minor educational levels not included
2. 2014 statistic
Source: McKinsey Global Institute; SSB; OECD; Scientific American article “Scientists Reading Fewer Papers for First Time in 35 Years”, 2014 McKinsey & Company 11
GenAI could have the biggest impact on activities which previously
had a lower potential for automation
Automation potential of more than 50% with GenAI With GenAI
Incremental technical Automation potential of more than 50% without GenAI Without GenAI1
automation potential with GenAI
Overall technical automation potential, Share of NO
Activity groups2 comparison in midpoint scenarios, % in 2023 employment, % Comments
Decision 59% • Prior to GenAI, only 2 in 7
Applying expertise3 20%
making and 25% +34 p.p. Norwegians held roles
collaboration which had an automation
49%
Managing4 9% potential of more than
16% +34 p.p.
50%. Following the advent
of GenAI, that number has
Interfacing with 45%
8% risen to 1 in 2
stakeholders 24% +21 p.p.
• GenAI plays the largest
impact on data driven
Data 91%
Processing data 12%
decision making and
management 73% +18 p.p.
collaboration, while
79% physical laborers will likely
Collecting data 2%
68% +11 p.p. not see a significant change
from the rise of GenAI in the
Physical Performing unpredictable 46% workplace
34%
physical work5 46% +1 p.p. • With Generative AI,
technical automation
Performing predictable 73%
15% potential could already
physical work6 73% +1 p.p.
reach 91% for data
1. Previous assessment of work automation before the rise of generative AI processing and 79% for
2. Jobs are categorized by main activity, but some jobs include activity from multiple groups data collection in 2023
3. Applying expertise to decision making, planning, and creative tasks
4. Managing and developing people
5. Physical activities and operating machinery in unpredictable environments
6. Physical activities and operating machinery in predictable environments
Source: McKinsey Global Institute analysis; SSB McKinsey & Company 12
The 7 largest occupational groups, representing >70% of Norwegian
workers, can expect a large productivity uplift from GenAI
With GenAI Without GenAI Top 7 largest occupational groups Low High
Uplift from Share of NO No. of NO
Occupational groups Overall technical automation potential, % in 2023 GenAI, p.p. employment, % employment1, 000s
Educators and workforce training 54 39 p.p. 12 % 285
15
Customer service and sales 57 12 p.p. 11 % 263
45
Business and legal professionals 62 30 p.p. 11 % 256
32
STEM professionals 57 29 p.p. 10 % 239
28
Community services 65 26 p.p. 10 % 237
39
Managers 44 17 p.p. 8 % 197
27
Health professionals 43 14 p.p. 8 % 197
29
Builders 53 4 p.p. 6 % 153
49
Mechanical installation and repair 67 6 p.p. 5 % 122
61
Transportation services 49 7 p.p. 4 % 96
42
Food services 78
8 p.p. 4 % 91
70
Office support 87
21 p.p. 3 % 84
66
Property maintenance 38
9 p.p. 3 % 84
29
Agriculture 63
4 p.p. 2 % 40
59
Creatives and arts management 53
25 p.p. 1 % 32
28
Health aides, technicians, and wellness 43
9 p.p. 1 % 21
34
Production work 82
9 p.p. 1 % 21
73
Total 63
12 p.p. 100% 2 418
51
1. Jobs with <5k holding the job title excluded by SSB McKinsey & Company 13
Source: McKinsey Global Institute; SSB
Norway can realize significant value from GenAI, mainly unlocked
by automating activities performed by white-collar workers
Norway is primed for adoption of GenAI due
to high levels of education and strong
digital foundation …
… with the potential to unlock values up to
~127 billion NOK across various industries …
… mainly due to productivity gains from
activities related to decision making,
collaboration and data management
MMccKKiinnsseeyy && CCoommppaannyy 1144
Appendix
MMccKKiinnsseeyy && CCoommppaannyy 1155
The midpoint scenario at which automation adoption could reach
50% of time spent on current work activities has accelerated by a
decade
Updated early scenario including generative AI2 2017 early scenario2
Global automation of time spent on current work activities1, %
Updated late scenario including generative AI3 2017 late scenario3
100%
90%
80%
70%
60%
Midpoint 2017 50%
50%
Midpoint
40% updated
The advent of GenAI has sped up
the automation timeline by ~10
30%
years from previous estimates in
20% which GenAI was not considered
10%
0%
2020 2025 2030 2035 2040 2045 2050 2055 2060 2065 2070 2075 2080 2085 2090 2095 2100
1. Includes data from 47 countries representing about 80% of employment across the world. 2017 estimates are based on the activity and occupation mix from 2016. Scenarios including generative AI are based on the 2021
activity and occupation mix
2. Early scenario: aggressive scenario for all key model parameters (technical automation potential, integration timelines, economic feasibility, and technology diffusion rates)
3. Late scenario: parameters are set for later adoption potential.
Source: McKinsey Global Institute McKinsey & Company 16
GenAI is expected to have different impact across the business
functions dependent on industry sizes
Generative AI productivity impact by business functions1, % of industry revenue
Impact in bn NOK Low High Impact as % of industry rev. Low High Low High
Total Expected Total added
Supply chain Corporate IT
industry impact of value from Marketing Customer Product and Software Risk and Strategy and Talent and
and (excluding
size2, % of GenAI, % of GenAI, and sales operations R&D engineering legal finance organization
operations SWE)
total revenue industry rev. bn NOK
Total2bn NOK 6,754 95 –159 28 -43 12 -17 8 -15 21 -43 10 -19 7 -9 4 -9 1 -2 2 -3
Energy 22% 1% -1.6% 16 -26
High tech 4% 4.8% -9.3% 12 -24
Travel, transport & logistics 14% 1.2% -2% 12 -21
Retail 14% 1.2% -1.9% 12 -20
Advanced manufacturing 7% 1.4% -2.4% 8 -13
Real estate 8% 1% -1.7% 6 -10
Basic materials 10% 0.7% -1.2% 5 -9
Banking 3% 2.8% -4.7% 5 -9
Consumer packaged goods 5% 1.4% -2.3% 5 -8
Professional services 7% 0.9% -1.4% 5 -7
Telecommunications 1% 2.3% -3.7% 2 -3
Insurance 1% 1.8% -2.8% 2 -3
Healthcare 1% 1.8% -3.2% 2-3
Media 1% 1.5% -2.6% 2-3
Chemical 1% 0.8% -1.3% 0.5 -1
Agriculture 1% 0.6% -1% 0 -0.5
Pharma & medical products 0% 2.6% -4.5% 0
1. Excl. implementation costs (e.g., training, licenses)
2. Figures may not sum to 100% because of rounding
Source: Internal experts; McKinsey Global Institute;annual reports; SSB MMccKKiinnsseeyy && CCoommppaannyy 1177
GenAI can reduce the cost of large effort tasks, enabled through
4 archetype of applications which are emerging across industries
Not exhaustive for all use cases for Generative AI
Content synthesis Coding & Creative Customer
(virtual expert) software content engagment1
GenAI Generate insights and drive Interpret and generate code Create marketing messages, Streamline interactions by
capability actions based on summarization and documentation, i.e., and images, support ideation for interpreting text and analyze
and synthesis of unstructured improving efficiency and reducing new product development and customer journeys through
data technical debt generate personalized marketing customer service, chatbots,
copy recommenders, task automation,
etc.
Use case Summarize text or audio and Generate code and assist Generate visuals (images, Streamline customer
generate insights developers designs, 3D models) to communications, e.g.,
Perform actions triggered by Refactor translate code to accelerate the product design customer service issue
user prompt accelerate mainframe process resolution (driving action to
Augment capabilities of migration Draft and personalize resolve) and Q&A
operations staff (e.g., Create model outbound customer comms Model and predict elements
inventory/maintenance documentation (e.g., risk) or marketing in patient or customer journey
management)
1. Includes B2B customer interactions and transactions
Source: McKinsey analysis MMccKKiinnsseeyy && CCoommppaannyy 1188
Impact as % of industry revenues, bubble size proportional to bn NOK impact: Small Large
The energy Impact1, median calculation, bn NOK
24
sector has the
22
highest value
Energy
20
potential, but
18 High Tech
GenAI will be
Travel, Transport & Logistics
16
most disruptive
Retail
14
in High Tech
12
Advanced Manufacturing
10
Basic Materials
8 Real Estate
Banking
6
Consumer Packaged Goods
Professional services
4
Healthcare
Insurance
2 Telecommunications
Agriculture Media
Chemical Pharma & Medical Products
0
0% 1% 2% 3% 4% 5% 6% 7% 8%
1. Based on the early adoption scenario, median
Impact as % of industry revenues
expected impact of GenAI, % of industry
revenues. 2020 revenues, inflation adjusted
SSoouurrccee:: IMncteKrinnasle eyx Gpelortbsa, lD Inastatibtuatsees: Annual reports, SSB MMccKKiinnsseeyy && CCoommppaannyy 1199
>50% of the value unlock can be achieved in two large
business functions
Deep dive follows
Business functions Value potential from GenAI1, bn NOK
Marketing & sales 28 - 43
Software engineering 21 - 43
Customer operations 12 - 17
Supply chain & operations 10 - 19
Product and R&D 8 - 15
Risk & legal 7 - 9
Strategy & finance 4 - 9
Talent & org. 2 - 3
Corporate IT (excl. SWE) 1 - 2
1. Excl. implementation costs (e.g., training, licenses)
Source: Internal experts; annual reports; SSB MMccKKiinnsseeyy && CCoommppaannyy 2200
1: Marketing & Sales
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day marketing executive
% time spent
Writing marketing and sales copy Augment sales teams with technical
content of text, images and videos proprietary knowledge and historic
customer interactions
Emails 13
Improving sales force, e.g., by
Generate personalized marketing content
flagging risks, recommending next
based on (un)structured data from consumer
interactions
profiles and community insights Meetings 38
Analyzing customer feedback Automate booking management and
customer follow-up during travels Designs and edits 13
Analysis 25
Key CPG
industries Retail Other admin 13
Travel, Transport & Logistics
Insurance
Total
Financial services
Total value 28 - 43
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2211
“50% of code on
GitHub is written by an
2: Software Engineering AI, e.g., a co-pilot doing
code suggestions,
Productivity opportunity with GenAI
corrections and writing”
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day software engineer
% time spent
Generating, prioritizing, and Create alerts and automated bots based on
running code news, industry reports, internal research and
economic trends that can impact trading
Meetings 10
strategies
Generating synthetic data to improve
training accuracy of ML models Generate code that creates hyper-
personalized trip recommendations Coding 50
Reviewing code for defects and
Accelerate transition from legacy software /
inefficiencies
code (e.g., banks still use system written in
Debugging 20
COBOL) to modern
Emails 10
Key High Tech
industries Media Admin 10
CPG
Retail
Total
Energy
Insurance
Total value 21 - 43
Financial services
potential, bn NOK
Source: McKinsey Global Institute; internal experts MMccKKiinnsseeyy && CCoommppaannyy 2222
3: Customer Operations
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day call center
% time spent
Auto-generating customer profile Zero customer service reps, with all internal
and segment for each unique helpdesk automated via self-serve and GenAI-
customer powered chatbots to handle all omnichannel
Admin 13
helpdesk engagement
Generating post call summary to
Summarize speech to distinctive text to create
customers and agents Customer care 47
records of customer complaints
Developing first-line response in Manage disruptions during vacations by being
Internal calls 6
customer service for all inquiries first point of contact for customers, offer
translation and content customized for the
customer and their vacation Problem solving 25
Email / chat 6
Key CPG
industries Retail
Other 3
Insurance
Financial services
Total
Travel, Transport & Logistics
Telecommunications
Total value 12 - 17
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2233
4: Supply Chain & Operations
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day supply chain manager
% time spent
Warehouse and inventory Interpreting data, labelling unstructured data
management and identifying patterns for future trends
and demand
E-mail 10
Forecasting demand and Synthesizing data from previous jobs to predict
disruptions in supply chain potential issues
Meetings 25
Act as an intelligent maintenance or safety
Optimize transportation route advisor, leveraging insights and knowledge Inventory or
35
from equipment and process manuals staffing analysis
Planning 15
Document review 10
Key Energy
industries CPG
Other admin 5
Retail
Advanced Manufacturing
Total
Travel, Transport & Logistics
Basic Materials
Total value 10 - 19
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2244
“The amount of time spent in each category depends on
which stage of development you are, but most time is spent
on product development, troubleshooting or fixing”
5: Product and R&D
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day product owner
% time spent
Creating 3D visual models and Improve pipeline maintenance by
digital product designs synthesizing maintenance and inspection
records, predict areas at risk for corrosion E-mail 10
Prioritizing product backlog by based on historic maintenance records
synthesizing customer feedback Product
Reimagine product portfolio through GenAI 17
development
opportunity themes
Measuring and tracking engineering
Translate code from legacy systems at scale,
metrics Troubleshooting 17
prioritizing interventions and re-factoring
Fixing 17
Meetings 25
Key High tech
industries CPG
Other admin 15
Retail
Travel, Transport & Logistics
Total
Telecommunications
Insurance
Total value 8 - 15
Financial services
potential, bn NOK
Source: McKinsey Global Institute; internal experts MMccKKiinnsseeyy && CCoommppaannyy 2255
6: Risk & Legal
Productivity opportunity with GenAI
Not expected to be affected by GenAI
Illustrative
Value unlock Industry Typical working
examples examples day junior lawyer
% time spent
Summarize regulation, including safety &
Draft and review legal documents
equipment manuals changes from industry &
regulatory databases
E-mail 10
Summarize and highlight changes
Informative queries from agents to identify &
in large bodies of regulatory
Writing
generate required legal and non-legal
documents 45
documents for transportation based on documents
classification from GenAI model
Review
Answer questions & cite
5
justifications from large documents Generate life-like fraud attempts for pro-active documents
testing
Calls 30
Meetings 5
Key Energy
industries High Tech
Other admin 6
Media
Insurance
Total
Financial services
Real Estate
Total value 7 - 9
Telecommunications
potential, bn NOK
Source: McKinsey Global Institute; internal experts; press search MMccKKiinnsseeyy && CCoommppaannyy 2266 |
46 | mckinsey | the-next-frontier-of-customer-engagement-ai-enabled-customer-service.pdf | Operations Practice
The next frontier of customer
engagement: AI-enabled
customer service
AI-enabled customer service is now the quickest and most effective route for
institutions to deliver personalized, proactive experiences that drive customer
engagement.
This article is a collaborative effort by Avinash Chandra Das, Greg Phalin, Ishwar Lal Patidar, Malcolm Gomes,
Rakshit Sawhney, and Renny Thomas, representing views from McKinsey’s Operations Practice.
© Getty Images
March 2023
How to engage customers—and keep them most of AI tools to transform customer service is
engaged—is a focal question for organizations not simply a case of deploying the latest technology.
across the business-to-consumer (B2C) landscape, Customer service leaders face challenges ranging
where disintermediation by digital platforms from selecting the most important use cases for
continues to erode traditional business models. AI to integrating technology with legacy systems
Engaged customers are more loyal, have more and finding the right talent and organizational
touchpoints with their chosen brands, and deliver governance structures.
greater value over their lifetime.
But done well, an AI-enabled customer service
Yet financial institutions have often struggled to transformation can unlock significant value for
secure the deep consumer engagement typical the business—creating a virtuous circle of better
in other mobile app–intermediated services. The service, higher satisfaction, and increasing
average visit to a bank app lasts only half as long customer engagement.
as a visit to an online shopping app, and only
one-quarter as long as a visit to a gaming app.
Hence, customer service offers one of the few The perils and promise of AI customer
opportunities available to transform financial- engagement
services interactions into memorable and long- Multiple converging factors have made the case
lasting engagements. for AI-based customer service transformation
stronger than ever. Among the most important:
Those customers are getting harder to please. increased customer acceptance of (and even
Two-thirds of millennials expect real-time customer preference for) machine-led conversational AI
service, for example, and three-quarters of all interactions. Meanwhile, related technologies
customers expect consistent cross-channel service such as messaging platforms are becoming more
experience. And with cost pressures rising at least accessible, and customer behaviors are becoming
as quickly as service expectations, the obvious more understandable with the relentless expansion
response—adding more well-trained employees to of data pools institutions can collect and analyze.
deliver great customer service—isn’t a viable option.
Three challenges
Companies are therefore turning to AI to deliver But challenges also loom. First, complexity. The
the proactive, personalized service customers COVID-19 pandemic acted as a major catalyst
want, when and how they want it—sometimes even for migration to self-service digital channels, and
before they know they want it. For transformed customers continue to show a preference for
organizations, AI-enabled customer service digital servicing channels as the “first point of
can increase customer engagement, resulting contact.” As a result, customers increasingly turn
in increased cross-sell and upsell opportunities to contact centers and assisted-chat functions for
while reducing cost-to-serve. In global banking more complicated needs. That raises the second
alone, research from McKinsey conducted in 2020 issue: higher expectations. Customer confidence in
estimates that AI technologies could potentially self-service channels for transactional activities is
deliver up to $1 trillion of additional value each year, leading them to expect similar outcomes for more
of which revamped customer service accounts for a involved requests. Businesses are therefore rapidly
significant portion.¹ adopting conversational AI, proactive nudges, and
predictive engines to transform every point of the
While a few leading institutions are now customer service experience. Yet these moves raise
transforming their customer service through apps, demand for highly sought-after skills, generating
and new interfaces like social and easy payment the third challenge: squeezed labor markets that
systems, many across the industry are still playing leave customer service leaders struggling to fill
catch-up. Institutions are finding that making the crucial roles.
1 “AI bank of the future: Can banks meet the AI challenge,” McKinsey, September 19, 2020.
2 The next frontier of customer
How leaders fulfill AI’s customer engagement five—the most advanced end of the maturity
promise scale—companies are delivering proactive,
Leaders in AI-enabled customer engagement have service-led engagement, which lets them handle
committed to an ongoing journey of investment, more than 95 percent of their service interactions
learning, and improvement, through five levels of via AI and digital channels (see sidebar, “What
maturity. At level one, servicing is predominantly AI-driven customer service maturity looks like”).
manual, paper-based, and high-touch. At level
What AI-driven customer service maturity looks like
A few leading institutions have reached level four on a five-level scale describing the maturity of a company’s AI-driven customer
service.
Level 1: Manual and high-touch, based on paper forms and offered largely via assisted channels.
— Reactive service, with the majority of interactions on human-assisted channels
— Paper use is still prevalent
Level 2: Partly automated and basic digital channels, with digitization and automation of servicing in assisted channels.
— Reactive service, with limited self-servicing opportunities
— Lower adoption of available self-service channels
— Lower availability of digital or straight-through-processing (STP)
Level 3: Accessible and speedy service via digital channels, with self-servicing on select channels and a focus on enabling end-to-
end resolution.
— Somewhat proactive, but limited engagement
— Self-service channels such as mobile apps, interactive voice response (IVR) systems, and internet sites handle half of all
interactions, and can support STP.
Level 4: Proactive and efficient engagement deploying AI-enabled tech, with self-servicing enabled by proactive customer
interactions and conversational user experience (UX).
— Proactive, with high customer engagement on digital channels
— Self-service channels such as mobile apps, IVR systems, and internet sites handle 70-80 percent of interactions and can support
most requests and transactions
Level 5: Personalized, digitally enabled engagement, bringing back the human touch via predictive intent recognition.
— Engagement via service interactions that are personalized and proactive at the individual customer level
— Digital touchpoints drive service-based engagement, for example via enhanced cross-selling and upselling
— More than 95 percent of service interactions and requests can be solved via digital and STP channels
The next frontier of customer 3
The most mature companies tend to operate to the appropriate AI-powered tools, core
in digital-native sectors like ecommerce, taxi technology, and data. Exhibit 1 captures the new
aggregation, and over-the-top (OTT) media model for customer service—from communicating
services. In more traditional B2C sectors, such with customers before they even reach out with a
as banking, telecommunications, and insurance, specific need, through to providing AI-supported
some organizations have reached levels three and solutions and evaluating performance after the fact.
four of the maturity scale, with the most advanced
players beginning to push towards level five. These The human factor in AI-supported service
businesses are using AI and technology to support AI-powered does not mean automation-only. It’s
proactive and personalized customer engagement true that chatbots and similar technology can deliver
through self-serve tools, revamped apps, new proactive customer outreach, reducing human-
interfaces, dynamic interactive voice response (IVR), assisted volumes and costs while simplifying the
and chat. client experience. Nevertheless, an estimated 75
percent of customers use multiple channels in their
A few leading institutions have reached level four ongoing experience.² A reimagined AI-supported
on a five-level scale describing the maturity of a customer service model therefore encompasses all
company’s AI-driven customer service. touchpoints—not only digital self-service channels
but also agent-supported options in branches or
on social-media platforms, where AI can assist
Toward engaging, AI-powered employees in real time to deliver high-quality
customer service outcomes.
To achieve the promise of AI-enabled customer
service, companies can match the reimagined vision Even before customers get in touch, an
for engagement across all customer touchpoints AI-supported system can anticipate their likely
Web <year>
<Title>
Exhibit 1
Exhibit <x> of <x>
The future of customer service builds on AI to deliver engaging experiences
The future of customer service builds on AI to deliver engaging experiences
aanndd ggeenneerraattee llaassttiinngg vvaalluuee..
The stages of an AI-supported customer-service process
A Proactive communication
linked to key demand drivers Customer
B Intent recognition and nudges
before customer reaches out ~75% of customers use
multiple channels
C Omnichannel enablement
with self-service for service journeys
D Conversational AI
at each entry point Backend robotics and
Self-service automation for straight- Frontline
E Frontline enablement with coaching channels through processing (STP) agents
for agents supported by a knowledge
repository and AI ~50–80% of >80% of all
contacts automated tasks automated
F Highly personalized, advisory interactions
drive relationship and value, with STP or
quick resolution of issues
G Performance measurement via a centrally
Performance management
managed nerve center that tracks
resolution accuracy and efficiency
McKinsey & Company
2 “The state of customer care in 2022,” McKinsey, July 8, 2022.
4 The next frontier of customer
needs and generate prompts for the agent. For self-service options while launching new,
example, the system might flag that the customer’s dedicated video and social-media channels.
credit-card bill is higher than usual, while also To drive a personalized experience, servicing
highlighting minimum-balance requirements and channels are supported by AI-powered decision
suggesting payment-plan options to offer. If the making, including speech and sentiment analytics
customer calls, the agent can not only address an to enable automated intent recognition and
immediate question, but also offer support that resolution. Enhanced measurement practices
deepens the relationship and potentially avoids an provide real-time tracking of performance
additional call from the customer later on. against customer engagement aspirations,
targets, and service level agreements, while new
AI service in the field: an Asian bank’s governance models and processes deal with
experience issues such as service request backlogs.
Put together, next-generation customer service
aligns AI, technology, and data to reimagine Underpinning the vision is an API-driven tech
customer service (Exhibit 2). That was the stack, which in the future may also include edge
approach a fast-growing bank in Asia took when technologies like next-best-action solutions
it found itself facing increasing complaints, slow and behavioral analytics. And finally, the entire
resolution times, rising cost-to-serve, and low transformation is implemented and sustained via
uptake of self-service channels. an integrated operating model, bringing together
service, business, and product leaders, together
Over a 12-month period, the bank reimagined with a capability-building academy.
engagement. It revamped existing channels,
improving straight-through processing in
Exhibit 2
AAII--eennaabbleledd c ucustsotmoemr esre rsveircvei cexec eelxlcenecllee nspcaen ssp nainnes cnriintiec aclr citoicmapl ocnoemntpso. nents.
Components
Reimagined engagement
1 New or upgraded self-service channels with automated journeys
2 Modernized assisted channels (contact centers, branches) with tech-enabled front-line
3 Preemptive, proactive end-to-end customer communications
4 Reimagined straight-through service journeys with standard operating procedures across all channels
5 Simplified, templatized service-to-sales interactions
AI-powered decisioning
6 AI-enabled automated intent recognition and resolution layer
7 Measurements and governance—nerve center for descriptive and predictive analytics
Core tech and data
8 Technologies including cloud-based telephony and integrated CRM are embedded into an API-driven tech stack
Operating model
9 Integrated service, business, and product operating models, with capability-building academy
McKinsey & Company
The next frontier of customer 5
The transformation resulted in a doubling to tripling — Maximize every customer service interaction, to
of self-service channel use, a 40 to 50 percent deepen customer relationships, build loyalty, and
reduction in service interactions, and a more than drive greater value over the customer’s lifetime.
20 percent reduction in cost-to-serve. Incidence
ratios on assisted channels fell by 20-30 percent, — Leverage AI and an end-to-end technology
improving both the customer and employee stack, to provide a more proactive and
experience. personalized customer service experience that
supports self-service and decision-making for
customers as well as employees .
Seizing the opportunity
To leapfrog competitors in using customer service to — Adapt agile and collaborative approaches to
foster engagement, financial institutions can start drive transformation, comprised of SMEs from
by focusing on a few imperatives. different business and support functions of the
organization.
— Envision the future of service, keeping
customers and their engagement at the core
while also defining the strategic value to be
attained—for example, a larger share of wallet
with existing customers? Expansion of particular
services, lines of business, or demographics? Holistically transforming customer service
into engagement through re-imagined, AI-led
— Rethink every customer touchpoint, whether capabilities can improve customer experience,
digital or assisted, together with opportunities reduce costs, and increase sales, helping
to enhance the experience while also increasing businesses maximize value over the customer
efficiencies. lifetime. For institutions, the time to act is now.
Avinash Chandra Das is an associate partner in McKinsey’s Bengaluru office, where Malcolm Gomes is a partner and Ishwar
Lal Patidar is an expert. Greg Phalin is a senior partner in the Charlotte office, Rakshit Sawhney is an associate partner in the
Gurugram office, and Renny Thomas is a senior partner in the Mumbai office.
The authors wish to thank Amit Gupta, John Larson, and Thomas Wind for their contributions to this article.
Copyright © 2023 McKinsey & Company. All rights reserved.
6 The next frontier of customer |
47 | mckinsey | time-to-place-our-bets-europes-ai-opportunity.pdf | QuantumBlack, AI by McKinsey
Time to place our bets:
Europe’s AI opportunity
Boosting Europe’s competitiveness across the AI value chain.
by Alexander Sukharevsky, Eric Hazan, Sven Smit, Marc-Antoine de la Chevasnerie, Marc de Jong,
Solveigh Hieronimus, Jan Mischke, and Guillaume Dagorret
October 2024
At a glance — Europe has made major progress in raising
AI awareness and setting commitments,
— A three-lens approach–on adoption,
but major bottlenecks persist. Policy makers
creation, and energy–is required to assess
and business leaders could explore several
Europe’s competitiveness in the emerging
levers, including increasing investments
generative AI (gen AI) economy. While much
(such as a public innovation procurement
of the current discourse centers around large
in AI applications for healthcare and
language models (LLMs), European policy
defense sectors), leapfrogging in emerging
makers and business leaders must look
semiconductor technologies (such as quantum
beyond LLMs. Adopting a holistic approach to
and neuromorphic computing), and addressing
capitalize fully on gen AI’s potential could boost
talent retention. Additionally, preparing the
European labor productivity by up to 3 percent
workforce through reskilling and mobility
annually through 2030.
programs will be crucial in fully leveraging
the benefits of gen AI adoption.
— On adoption, European organizations lag
behind their US counterparts by 45 to
70 percent. Yet this is where most of gen AI’s A holistic approach to help Europe
economic potential lies. With the technology still realize generative AI’s full potential
in its early stages and much of its productivity
For generative AI (gen AI),1 the blockbuster release
gains yet to be unlocked, the window of
of OpenAI’s ChatGPT in November 2022 marked
opportunity for Europe remains wide open.
the beginning of a boom.2 Since then, much of the
conversation around the technology has focused
— On creation, Europe leads in only one of the
on foundation models, particularly large language
eight segments of a simplified gen AI value
models (LLMs). In this field, Europe3 appears to be
chain: AI semiconductor equipment. Europe is
lagging behind its counterparts. However, LLMs are
a challenger in three other segments: foundation
just one part of the gen AI landscape. Engaging on
models, AI applications, and AI services. But
gen AI adoption, creation, and energy requirements
it has below 5 percent market share in the
can help capture a more complete picture of where
remaining four: raw materials, AI semiconductor
the region stands in the emerging gen AI economy.
design, AI semiconductor manufacturing, and
cloud infrastructure and supercomputers.
Most of the value generated by gen AI will stem
from organizations’ adoption and scaling of gen AI
— On energy, gen AI is expected to accelerate
solutions4—an important consideration in Europe,
data center power demand, potentially
where labor productivity has been slowing.5
accounting for more than 5 percent of
McKinsey Global Institute (MGI) research estimates
Europe’s total electricity consumption by
that gen AI could help Europe achieve an annual
2030. Without competitive electricity prices, it
productivity growth rate of up to 3 percent through
becomes less likely that European data centers
2030 (Exhibit 1).6 This potential additional growth
will host gen AI applications and services.
1 In this article, unless specified otherwise, “generative AI” (gen AI) encompasses all AI technologies, including the latest advancements in gen AI.
2 By January 2023, the company had already gained 100 million users and was valued at $29 billion ($80 billion today). This triggered massive
investments to fund gen AI companies ($25 billion in worldwide private investments in 2023) and spurred the release of multiple breakthrough
innovations and competing models (for example, Google’s Gemini and Meta’s Llama). Artificial Intelligence Index report 2024, Stanford
University, 2024; DigitalRank, Similarweb, accessed September 2024; Julia Boorstin, “Why OpenAI is the first company to be No. 1 on the
CNBC Disruptor 50 list two years in a row,” CNBC, May 14, 2024.
3 In this article, “Europe” refers to the 27 member states of the European Union plus Norway, Switzerland, and the United Kingdom.
4 Per academic research, innovators historically capture less than 5 to 10 percent of broader economic returns generated by their inventions.
Adopters of the technology and society at large generate the remaining returns. For more, see William D. Nordhaus, Schumpeterian profits in
the American economy: Theory and measurement, National Bureau of Economic Research working paper, number 10433, April 2004.
5 For example, from 2016 to 2022, annual growth was 0.5 percent in Western Europe and 1.2 percent in North America. From 2002 to 2007,
it was 1.1 percent and 1.9 percent, respectively. Chris Bradley, Jan Mischke, Marc Canal, Olivia White, Sven Smit, and Denitsa Georgieva,
“Investing in productivity growth,” McKinsey Global Institute (MGI), March 27, 2024.
6 Eric Hazan, Anu Madgavkar, Michael Chui, Sven Smit, Dana Maor, Gurneet Singh Dandona, and Roland Huyghues-Despointes, “A new future
of work: The race to deploy AI and raise skills in Europe and beyond,” MGI, May 21, 2024.
Time to place our bets: Europe’s AI opportunity 2
Web <2024>
E<Exuhroibpeit G 1enAI>
Exhibit <1> of <3>
Generative AI could add $575.1 billion to the European economy by 2030.
Generative AI productivity potential in Western Europe in 2030, by sector, $ billion1
575.1
Total potential value
Consumer goods and retail
101.9
56%
Construction Professional Transportation Advanced
and real estate services 53.9 manufacturing
of potential productivity 55.7 54.3 53.4
gains are from sectors
with high spending gaps and
high productivity potential
Healthcare and pharma
57.2
Banking and High tech Chemicals and materials
capital markets and software 29.2
44.8 44.0
Energy and utilities
27.2
Media and entertainment
27.0
Telecommunications 11.6 Insurance 9.8 Agriculture 5.1
1Western Europe: Austria, Belgium, Denmark, Finland, France, Germany, Greece, Ireland, Italy, Netherlands, Norway, Portugal, Spain, Sweden, Switzerland, and
UK. Potential value add from 2019 base period.
Source: “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023
McKinsey & Company
will be critical for financing the European model, In terms of creation of gen AI, since 2022, more
particularly in navigating the energy transition, than 90 percent of LLM-related funding has taken
solving the empowerment gap, and supporting an place outside of Europe.8 Moreover, European
aging population.7 It could also drive breakthrough companies represent only 25 of the 101 AI models
innovations that transform daily life, such as considered notable by the Stanford University AI
accelerated drug discovery, improved patient care, Index, far behind US companies (which boast 61
and personalized education. notable models). But the opportunities for capturing
the economic value resulting from the creation of
gen AI technologies extend well beyond LLMs.
7 For more, see Kweilin Ellingrud, Marco Piccitto, Tilman Tacke, Rebecca J. Anderson, Ishaa Sandhu, and Kevin Russell, “A better life
everyone can afford: Lifting a quarter billion people to economic empowerment,” MGI, May 20, 2024; Mekala Krishnan, Chris Bradley,
Humayun Tai, Tiago Devesa, Sven Smit, and Daniel Pacthod, “The hard stuff: Navigating the physical realities of the energy transition,” MGI,
August 14, 2024.
8 Artificial Intelligence Index report 2024, Stanford University, 2024.
Time to place our bets: Europe’s AI opportunity 3
They are spread across an eight-segment value stands relative to other regions, and provide a series
chain: raw materials, AI semiconductor equipment, of steps that leaders in Europe might consider if
AI semiconductor design, AI semiconductor they are to fully participate in—and tap into the
manufacturing, cloud infrastructure and value created by—this impressive new technology.
supercomputers, foundation models (including
LLMs), AI applications, and AI services.9
Adoption of gen AI: Opportunity
Finally, to power the creation and adoption of gen AI, remains wide open, but Europe is
Europe also needs to consider its energy capacity. starting from a disadvantage
This is a key consideration, given that Europe’s The vast majority of the economic value of gen AI
energy system will be forced by 2030 to manage is expected to come from its adoption by European
a rise in consumption of more than 5 percent, organizations. The technology is still in its early
triggered by the demand for data center power stages, and most productivity potential has yet to
(accelerated by gen AI).10 be captured, so the opportunities here remain wide
open. Yet European corporations are moving much
To realize the full potential of gen AI, Europe’s more slowly than those in other countries.11
business leaders and policy makers must embrace
a holistic view of the technology that encompasses How much is Europe lagging behind? The
the challenges and opportunities posed by creation, information here is incomplete, so we sought to
adoption, and energy (Exhibit 2). In this article, we quantify it by examining three indicators. First, we
describe those challenges, detailing where Europe
Web <2024>
E<Exuhroibpeit G 2enAI>
Exhibit <2> of <3>
To fully capture the value of generative AI, European leaders can embrace a
holistic approach that encompasses creation, adoption, and energy.
Creation Adoption
Creation of new technologies and applications across Deployment of gen AI technologies across
simplified 8-step generative AI (gen AI) value chain different use cases to increase labor productivity
1. Raw materials Potential high-impact use cases:
2. AI semiconductor equipment • Chatbots for customer service in retail
3. AI semiconductor design • AI-driven drug discovery in pharmaceuticals
4. AI semiconductor manufacturing • Supply chain optimization in logistics
5. Cloud infrastructure and supercomputers
6. Foundation models
7. AI applications
8. AI services
Energy
Power required to run gen AI applications, with low carbon emissions and competitive prices
McKinsey & Company
9 Simplified value chain of the most important segments (excludes other AI elements, such as distribution platforms and vector databases).
10 Electricity Data Explorer, Ember, accessed September 2024; McKinsey research and analysis.
11 For more, see Zach Meyers and John Springford, “How Europe can make the most of AI,” Centre for European Reform, September 14, 2023.
Time to place our bets: Europe’s AI opportunity 4
Western Europe lags behind the
United States on external spending
on AI by an average of 61 percent
for sectors of similar size.
looked at external AI spending of corporations, such chemicals and materials, and construction and real
as the purchase of AI software-as-a-service (SaaS) estate), we find that those in Europe lag behind by
solutions. Since not all AI spending is external— 45 to 55 percent. For sectors that are significantly
some, such as hiring AI engineers, is internal—we larger in the United States than in Western Europe
also examined general IT spending, of which AI is (for example, healthcare and pharma, high tech and
a component, as an indicator of IT readiness and software, and media and entertainment), the gap
a crucial foundation for AI adoption. Finally, we was even more pronounced, ranging from 50 to
factored in the responses of European executives to 70 percent (Exhibit 3).
the McKinsey Global Survey on the state of AI.12
When looking at external spending on AI
We analyzed the first two metrics both in absolute infrastructure, software, and services, Western
terms and relative to company sales, comparing Europe lags behind the United States by an
them with US figures when possible. This relative average of 61 percent for sectors of similar size
comparison helps account for differences in sector and 71 percent for sectors that are two or
size, which would otherwise skew the data because more times larger in the United States than in
of economies of scale. For instance, the high-tech Western Europe.
and software sector is 4.9 times larger in the United
States than in Western Europe,13 so we find an AI Looking at internal IT spend, we see that for sectors
external spend-to-sales ratio of 0.4 percent for of similar size, Western Europe lags behind the
the United States versus 0.7 percent for Western United States by an average of 43 percent, and by
Europe. But in AI external spend absolute value, 46 percent when sectors differ in size by at least
we find $8.7 billion versus $2.6 billion, respectively, two times.
leading to a 70 percent gap.
Per the 2023 McKinsey Global Survey on the
Additionally, with the two first metrics, figures show state of AI, Europe lags behind North America in
that companies in Western Europe lag behind their gen AI adoption by 30 percent, with 40 percent
US counterparts by 45 to 70 percent. This gap of surveyed North American companies reporting
exists across all sectors. When evaluating sectors having adopted gen AI in at least one business
of similar size14 in Western Europe and the United function, compared with about 30 percent for
States (for example, advanced manufacturing, surveyed European companies.15
12 The online survey was in the field from April 11 to April 21, 2023, and garnered responses from 1,684 participants representing the full range
of regions, industries, company sizes, functional specialties, and tenures.
13 Austria, Belgium, Denmark, Finland, France, Germany, Greece, Ireland, Italy, the Netherlands, Norway, Portugal, Spain, Sweden, Switzerland,
and the United Kingdom.
14 Sectors with a size ratio between Western Europe and the United States below 2:1.
15 Survey question, with 1,363 responses: Has the organization adopted AI in at least one business function?
Time to place our bets: Europe’s AI opportunity 5
Exhibit 3
Western Europe lags behind the United States in AI and IT spending across
sectors, with an average gap of 45–70 percent.
Spending gap between Western Europe1 AI external spending Western Europe US
and US in 2022, by sector
IT internal spending Western Europe US
Spending as share of sales in sectors of similar size,2 %
0 0.2 0.4 0.6 0.8 1.0
Construction and real estate
Chemicals and materials
Advanced manufacturing
Insurance
Energy and utilities
Telecommunications
Transportation
Agriculture
Professional services
55%
AI external spending Average gap in relative value to sales
45%
IT internal spending Average gap in relative value to sales
Absolute spending in sectors of differing size,3 $ billion Western Europe US
0 2 4 6 8 10 12 14
Consumer goods and retail
Banking and capital markets
Healthcare and pharma
High tech and software
Media and entertainment
70%
AI external spending Average gap in absolute value
50%
IT internal spending Average gap in absolute value
Note: AI external spending measured as external spending on AI infrastructure, software, and services. Sectors ordered from most similar in size to least similar. IT spending
used as proxy for AI internal spending. Sectors ordered from most similar in size to least similar.
1Austria, Belgium, Denmark, Finland, France, Germany, Greece, Ireland, Italy, Netherlands, Norway, Portugal, Spain, Sweden, Switzerland, and UK.
2Sectors with <2:1 size ratio between US and Western Europe or Western Europe and US.
3Sectors with ≥2:1 size ratio between US and Western Europe or Western Europe and US.
Source: Worldwide AI and Generative AI Spending Guide, IDC, February 2024; McKinsey analysis
McKinsey & Company
Time to place our bets: Europe’s AI opportunity 6
Creation of gen AI tech: Europe leads service), foundation models (for example, LLMs), AI
in one segment, is a challenger in applications (for example, AI-powered software),
three, but is almost absent in four and AI services (for example, advisory services
and implementation).
Beyond adoption, Europe’s ability to capitalize
on gen AI will depend on its ability to spur the
Europe is currently competitive in four of the eight
creation of gen AI technologies that spread across
segments of the value chain: AI semiconductor
the simplified eight-segment value chain: raw
equipment, foundation models, AI applications,
materials (for example, germanium and silicon), AI
and AI services. However, the region has less than
semiconductor equipment (for example, lithography
5 percent of global market share in the remaining
systems), AI semiconductor design (for example,
four segments: raw materials, AI semiconductor
development of high-end GPUs), AI semiconductor
design, AI semiconductor manufacturing, and cloud
manufacturing (for example, foundries), cloud
infrastructure and supercomputers (table):
infrastructure and supercomputers (for example,
infrastructure as a service and platform as a
Europe’s ability to capitalize on
gen AI will depend on its ability to
spur the creation of gen AI technologies
that spread across the value chain.
Time to place our bets: Europe’s AI opportunity 7
Table
Europe is strong in four segments of a simplified generative AI value chain and lags
in the remaining four.
Negligible (<5%) Moderate (5–15%) Fair (>15%)
Segment Description European market Historical Key data
share in 2023 European market
share, directional
Raw materials Materials needed to produce Stable Europe supplies ~5% of critical,
semiconductors and their strategic1 raw materials needed
machinery (eg, gallium to make for chip manufacturing and
lithography tools) semiconductors
AI semiconductor Goods needed for AI Increasing Europe has 80–90% market
equipment semiconductor production (eg, share for extreme ultraviolet
silicon wafers, lithography tools) lithography (allows for finer
patterns on semiconductor
wafers, essential for high-end AI
chips)
AI semiconductor Design, including intellectual Decreasing Europe has <2% share of design
design property, of semiconductors for AI of logic semiconductors used for
AI (eg, GPUs)
AI semiconductor Production of semiconductors Stable Europe has <1% of world’s
manufacturing for AI production capacity
of ≤7-nanometer logic
semiconductors used for AI
Cloud infrastructure Infrastructure, including basic Stable European cloud companies have
and supercomputers software layer, needed for <5% market share, compared with
computing power and data ~85% for US hyperscalers
hosting
Foundation models Design and training of foundation Increasing 25 notable models originate from
models Europe, compared with 61 from US
AI applications AI-based software needed to Increasing In 2023, European companies
perform specific tasks across raised ~12% of global venture
various industries capital and private equity funding
for system-as-a-service AI
companies
AI services Services needed to support Increasing Europe has ~15% share of global
design and deployment of AI use AI services market, compared with
cases US, which leads with >40%
1 “Critical” is based on economic importance and supply risk, and “strategic” is defined as important for the green and digital transition, defense, and aerospace.
Time to place our bets: Europe’s AI opportunity 8
— Raw materials. The chip-manufacturing and of AI-suitable semiconductors, a space led
semiconductor industries require more than by Nvidia.22 Nonetheless, some European
40 raw materials, 16 of which (for example, players are taking steps to bridge the gap.
gallium, magnesium, and silicon) the European Britain-based ARM has ambitions to launch AI
Union classifies as both critical and strategic.16 semiconductors in 2025.23 Europe also plays an
About 5 percent of these materials are supplied important, if indirect, role in AI semiconductor
by European companies. As a result, the region design through its strong position in the design
relies heavily on imports from countries such and manufacturing of power semiconductors
as China, which supplies about 75 percent (for example, through Infineon and
of the European Union’s needs in silicon STMicroelectronics).
and 90 percent of its needs in gallium and
magnesium.17 The Critical Raw Materials Act — AI semiconductor manufacturing. Europe
(CRMA) supports local production, streamlining produces only about 8 percent of the world’s
permitting processes and boosting the semiconductors and fewer than 1 percent of the
recycling of key materials.18 logic capacity semiconductors of up to seven
nanometers suitable for AI.24 Beyond that,
— AI semiconductor equipment. The Europe has no capacity for high-bandwidth
Netherlands–based ASML is the market memory (HBM) and advanced packaging.
leader for the lithography machines required Looking ahead, global capacity for advanced
to produce high-end semiconductors (up semiconductor manufacturing is expected to
to seven-nanometer logic) suitable for AI.19 continue to be fully owned by non-European
European companies also lead in other players, such as TSMC.25 In large part, that’s
equipment segments, such as atomic layer because fab payback time in Europe is higher
deposition (ASM International, also based than that of Southeast Asia, notably due to
in the Netherlands, with about a 50 percent higher labor and energy costs. In addition to
market share) and metal–organic chemical- higher costs, European companies also face
vapor deposition (Germany-based company complex administrative processes. It can take
AIXTRON, with 70 to 80 percent market up to four years to get a semiconductor plant up
share).20 Yet, in other key niches, like dry etchers and running in Europe, compared to one year
and dicing machines, European companies are in Taiwan.26
less present.
— Cloud infrastructure and supercomputers.
— AI semiconductor design. European Europe lags behind the United States
companies like Infineon Technologies, NXP in computing power. Europe is home to
Semiconductors, and STMicroelectronics 18 percent of global data-center-installed
play a global role in the semiconductor- capacity, compared with 37 percent in the
integrated-design-manufacturing space, with United States (while European and US GDPs
about 15 percent market share in 2023.21 But are comparable, with around $23 trillion and
Europe has less of a presence in the design $27 trillion, respectively)—and in most cases,
16 “Critical” is based on economic importance and supply risk, and “strategic” is defined as important for the green and digital transition,
defense, and aerospace. The 16 materials include gallium, germanium, rare earths, and silicon.
17 Study on the critical raw materials for the EU 2023, European Commission, March 16, 2023.
18 Emma Watkins, Emma Bergeling, and Eline Blot, “Circularity gaps of the European Critical Raw Materials Act,” Institute for European
Environmental Policy, October 30, 2023.
19 “Fitch affirms ASML at ‘A’; outlook stable,” Fitch Ratings, April 5, 2023.
20 AIXTRON annual reports; ASM annual reports; DataTrack, TrendForce, accessed September 2024.
21 Omdia, Informa, accessed September 2024.
22 Kif Leswing, “Nvidia dominates the AI chip market, but there’s more competition than ever,” CNBC, June 2, 2024.
23 Masayuki Shikata and Akira Yamashita, “SoftBank’s Arm plans to launch AI chips in 2025,” Nikkei Asia, May 23, 2024.
24 World Fab Forecast, SEMI (including discrete, analog, and memory semiconductors), accessed September 2024.
25 “Emerging resilience in the semiconductor supply chain,” Semiconductor Industry Association, May 8, 2024.
26 Florian Dèbes, “‘Il faut donner envie d’investir en Europe,’ plaide le patron d’ASML (“‘We need to make people want to invest in Europe,’
argues the boss of ASML”), Les Echos, June 6, 2024.
Time to place our bets: Europe’s AI opportunity 9
The operating costs of European data
centers are typically more than
50 percent higher than those in the
United States, largely driven by
Europe’s higher energy costs.
these European data centers are owned by AI, a leading open-source model provider,
US companies.27 In 2023, European cloud with $1 billion raised since 2023.34 Yet in the
companies (for example, OVH and UpCloud) technological race to constantly improve
had about 5 percent market share globally models’ performances, the company remains
(about 15 percent in Europe), while US players underfunded compared with its US competitors.
(for example, Amazon Web Services, Google, For example, OpenAI has raised $11.3 billion, and
and Microsoft) had more than 70 percent global Anthropic has raised $8.7 billion.35
market share.28 Furthermore, Europe has only
half the supercomputing capacity in flop/s,29 — AI applications. Europe has several emerging
which is increasingly necessary in basic and AI unicorns (for example, DeepL, Synthesia,
applied research.30 This is partially because and Wayve). The region also is home to
the United States has seen the emergence leading global software companies (such as
of private players specializing in this segment Dassault Systèmes, Hexagon, and SAP) that
(for example, CoreWeave), while Europe are increasingly building gen AI technologies
supercomputers mostly lie in research centers. into their solutions. For example, in 2023, SAP
What’s more, the operating costs of European pledged to invest more than $1 billion in gen
data centers are typically more than 50 percent AI companies.36 But Europe lags behind the
higher than those in the United States, largely United States, garnering only 12 percent of the
driven by Europe’s higher energy costs.31 global pool of private equity and venture capital
funding for SaaS AI companies as of 2023.37
— Foundation models. In 2023, 61 notable What’s more, several leading AI start-ups and
AI models32 originated from US-based scale-ups of European origin (for example,
organizations, far outpacing Europe’s 25.33 A Hugging Face, with a $4.5 billion valuation, and
few of the European models are competing Dataiku, with a $3.7 billion valuation38), have
globally. One such is France-based Mistral
27 IDC Global data, accessed September 2024; International Monetary Fund data, accessed September 2024; McKinsey analysis and research.
28 IDC Global data, accessed September 2024; McKinsey analysis and research.
29 Measured by total computing power of supercomputers in floating point operations per second.
30 TOP500 release, 62nd edition, TOP500, November 2023.
31 Jonathan Atkin et al., “RBC Datacenter download,” RBC Capital Markets, September 20, 2021.
32 “A notable model meets any of the following criteria: (i) state-of-the-art improvement on a recognized benchmark; (ii) highly cited (over 1000
citations); (iii) historical relevance; (iv) significant use. “What is a notable model,” Epoch AI, accessed September 2024.
33 Artificial Intelligence Index report 2024, Stanford University, 2024.
34 Crunchbase data, accessed September 2024.
35 PitchBook data, accessed September 2024.
36 “SAP advances vision of business AI with investments in Aleph Alpha, Anthropic and Cohere to complement $1+ billion AI commitment from
Sapphire Ventures,” PR Newswire, July 18, 2023.
37 PitchBook data, accessed September 2024.
38 Crunchbase data, accessed September 2024.
Time to place our bets: Europe’s AI opportunity 10
moved their headquarters from Europe to the installed capacity. Indeed, data centers are major
United States. energy consumers: a hyperscaler’s data center can
use as much power as 80,000 households.43
— AI services. Europe holds about a 15 percent
share of the global AI services market, These new demands will place additional pressure
positioning it just behind the United States, on a European power grid that’s already undergoing
which leads with approximately 40 percent.39 significant stresses. First, electricity demand is
This significant market presence provides expected to escalate in the region on the back of
Europe with a foundation for expanding growing decarbonization efforts and electrification
AI-related services. throughout various sectors, with absolute electricity
demand expected to increase by 20 to 25 percent
The near absence of European companies in by 2030 (from 3,200 terawatt-hours in 2023 to
four of the eight segments of the simplified value around 4,000 terawatt-hours in 2030, including
chain could result in missed opportunities for demand from data centers).44 Also, energy price
the region’s economy. The global market of gen competitiveness in Europe is low, with industrial-
AI technologies is expected to boom, with high electricity prices some 70 percent higher in Europe
double-digit annual growth anticipated over the than in the United States in May 2024.45 Finally,
next ten years.40 This situation could be a challenge Europe has the oldest power grid in the world (45 to
to the region’s strategic autonomy, ultimately 50 years, on average, versus 35 to 40 years in North
jeopardizing gen AI adoption and productivity gains. America and 15 to 20 years in China).46 This can lead
A semiconductor shortage in 2022, for example, to inefficiencies in electricity distribution.
hit the European auto industry especially hard,
resulting in an estimated €100 billion GDP loss.41 On the bright side, this significant increase in
Similarly, insufficient access to cloud infrastructure electricity consumption could serve as a positive
and supercomputers could limit development and incentive for energy operators to invest in new
operations of gen AI technologies. capacities. Additionally, Europe has an edge in clean
energy, with 61 percent of low-carbon sources in
its electricity mix, compared with 40 percent in the
Energy for gen AI: Expected to drive United States and 34 percent in China.47
increased electricity demand in
Europe amid already-high prices
How to boost Europe’s
McKinsey estimates that rising data center power
competitiveness in gen AI
demand could increase Europe’s electricity
consumption by at least 180 terawatt-hours by Europe clearly faces a host of challenges with gen
2030–equivalent to more than 5 percent of total AI, but they aren’t insurmountable. Policy makers
European electricity annual consumption in 2023.42 and business leaders in Europe can consider
This is driven by demand for data center computing several activities to increase the region’s ability to
power in Europe, which McKinsey expects to fully realize the potential economic gains of AI when
more than triple by 2030 to reach 35 gigawatts of it comes to adoption, creation, and energy.
39 Riccardo Righi et al., “EU in the global artificial intelligence landscape,” European Commission, 2021.
40 “Generative AI to become a $1.3 trillion market by 2032, research finds,” Bloomberg Intelligence, June 1, 2023.
41 “Missing chips cost EUR100bn to the European auto sector,” Allianz, September 13, 2022; International Organization of Motor Vehicle
Manufacturers data, accessed September 2024.
42 Electricity Data Explorer, Ember, accessed September 2024; McKinsey research and analysis.
43 “Investing in the rising data center economy,” McKinsey, January 17, 2023.
44 Electricity Data Explorer, Ember, accessed September 2024; Patrick Chen, Tamara Grünewald, Jesse Noffsinger, and Eivind Samseth,
“Global Energy Perspective 2023: Power outlook,” McKinsey, January 16, 2024.
45 Enerdata, Ember, US Energy Information Administration, Eurostat.
46 “Winds of change,” Nexans 2021 Capital Markets Day.
47 Total electricity generation mix with low-carbon energy, including biofuel and wastes, hydro, wind and solar, and other renewable sources.
International Energy Agency data, accessed September 2024.
Time to place our bets: Europe’s AI opportunity 11
Adoption of gen AI in Europe were two to four times higher than those of
To facilitate gen AI adoption, European leaders their European counterparts.53 This disparity
might consider the following actions: is likely attributable to the greater financial
resources of US companies, which benefit
— Reskill and upskill the workforce. Research from larger economies of scale and higher
from MGI indicates that to reap the full levels of venture capital and private equity
productivity dividends of gen AI, Europe funding. Europe also lags behind the United
would need to double its current pace of job States in AI-related research, with only two
transition—from the 0.4 percent per year seen universities in a key ranking of top institutions
in 2016–19, prior to the COVID-19 pandemic, for AI research in 2022, compared with 15 for
to an unprecedented 0.8 percent by 2030.48 the United States.54 European workers also
(The effort for the United States would be fall behind in gen AI awareness and use: the
lower, as transition rates have already been at latest McKinsey Global Survey on AI finds that
such levels.) That could require the reskilli |
48 | mckinsey | the-promise-and-the-reality-of-gen-ai-agents-in-the-enterprise.pdf | Technology, Media & Telecommunications Practice
The promise and the
reality of gen AI agents
in the enterprise
Generative AI technology is improving so quickly that a range of
new capabilities are rapidly coming online, but only for those who can
understand how to use them.
May 2024
The evolution of generative AI (gen AI) has opened For example, in customer services, recent
the door to great opportunities across organizations, developments in short- and long-term memory
particularly regarding gen AI agents—AI-powered structures enable these agents to personalize
software entities that plan and perform tasks or interactions with external customers and internal
aid humans by delivering specific services on their users, and help human agents learn. All of this
behalf. So far, adoption at scale across businesses means that gen AI agents are getting much closer
has faced difficulties because of data quality, to becoming true virtual workers that can both
employee distrust, and cost of implementation. In augment and automate enterprise services in
addition, capabilities have raced ahead of leaders’ all areas of the business, from HR to finance to
capacity to imagine how these agents could be customer service. That means we’re well on our way
used to transform work. to automating a wide range of tasks in many service
functions while also improving service quality.
However, as gen AI technologies progress and
the next-generation agents emerge, we expect Barr Seitz: Where do you see the greatest value
more use cases to be unlocked, deployment from gen AI agents?
costs to decrease, long-tail use cases to become
economically viable, and more at-scale automation Jorge Amar: We have estimated that gen AI
to take place across a wider range of enterprise enterprise use cases could yield $2.6 trillion to
processes, employee experiences, and customer $4.4 trillion annually in value across more than
interfaces. This evolution will demand investing 60 use cases.1 But how much of this value is realized
in strong AI trust and risk management practices as business growth and productivity will depend
and policies as well as platforms for managing and on how quickly enterprises can reimagine and
monitoring agent-based systems. truly transform work in priority domains—that is,
user journeys, processes across an entire chain of
In this interview, McKinsey Digital’s Barr Seitz activities, or a function.
speaks with senior partners Jorge Amar and
Lari Hämäläinen and partner Nicolai von Bismarck Gen-AI-enabled agents hold the promise of
to explore the evolution of gen AI agents and accelerating the automation of a very long tail of
how companies can and should implement the workflows that would otherwise require inordinate
technology, where the pools of value lie for amounts of resources to implement. And the
the enterprise as a whole. They particularly potential extends even beyond these use cases:
explore what these developments mean for 60 to 70 percent of the work hours in today’s
customer service. An edited transcript of the global economy could theoretically be automated
conversation follows. by applying a wide variety of existing technology
capabilities, including generative AI, but doing so
Barr Seitz: What exactly is a gen AI agent? will require a lot in terms of solutions development
and enterprise adoption.
Lari Hämäläinen: When we talk about gen AI
agents, we mean software entities that can Consider customer service. Currently, the value of
orchestrate complex workflows, coordinate gen AI agents in the customer service environment
activities among multiple agents, apply logic, and is going to come either from a volume reduction or
evaluate answers. These agents can help automate a reduction in average handling times. For example,
processes in organizations or augment workers in work we published earlier this year, we looked at
and customers as they perform processes. This is 5,000 customer service agents using gen AI and
valuable because it will not only help humans do found that issue resolution increased by 14 percent
their jobs better but also fully digitalize underlying an hour, while time spent handling issues went
processes and services. down 9 percent.2
1 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
2 Ibid.
The promise and the reality of gen AI agents in the enterprise 2
The other area for value is agent training. Typically, Nicolai von Bismarck: It’s worth emphasizing that
we see that it takes somewhere between six gen AI agents not only automate processes but
to nine months for a new agent to perform at also support human agents. One thing that gen AI
par with the level of more tenured peers. With agents are so good at, for example, is in helping
this technology, we see that time come down to customer service representatives get personalized
three months, in some cases, because new agents coaching not only from a hard-skill perspective but
have at their disposal a vast library of interventions also in soft skills like understanding the context
and scripts that have worked in other situations. of what is being said. We estimate that applying
generative AI to customer care functions could
Over time, as gen AI agents become more proficient, increase productivity by between 30 to 45 percent.3
I expect to see them improve customer satisfaction
and generate revenue. By supporting human Jorge Amar: Yes, and in other cases, gen AI
agents and working autonomously, for example, agents assist the customer directly. A digital sales
gen AI agents will be critical not just in helping assistant can assist the customer at every point in
customers with their immediate questions but also their decision journey by, for example, retrieving
beyond, be that selling new services or addressing information or providing product specs or cost
broader needs. As companies add more gen AI comparisons—and then remembering the context
agents, costs are likely to come down, and this if the customer visits, leaves, and returns. As those
will open up a wider array of customer experience capabilities grow, we can expect these gen AI
options for companies, such as offering more agents to generate revenue through upselling.
high-touch interactions with human agents as a
premium service. [For more on how companies are using gen AI
agents, see the sidebar, “A closer look at gen AI
Barr Seitz: What are the opportunities you are agents: The Lenovo experience.”]
already seeing with gen AI agents?
Barr Seitz: Can you clarify why people should
Jorge Amar: Customer care will be one of the first believe that gen AI agents are a real opportunity
but definitely not the only function with at-scale and not just another false technology promise?
AI agents. Over the past year, we have seen a lot
of successful pilots with gen AI agents helping to Jorge Amar: These are still early days, of course,
improve customer service functions. For example, but the kinds of capabilities we’re seeing from
you could have a customer service agent who is gen AI agents are simply unprecedented. Unlike
on the phone with a customer and receives help past technologies, for example, gen AI not
in real time from a dedicated gen AI agent that is, only can theoretically handle the hundreds of
for instance, recommending the best knowledge millions of interactions between employees and
article to refer to or what the best next steps are for customers across various channels but also can
the conversation. The gen AI agent can also give generate much higher-quality interactions, such
coaching on behavioral elements, such as tone, as delivering personalized content. And we know
empathy, and courtesy. that personalized service is a key driver of better
customer service. There is a big opportunity here
It used to be the case that dedicating an agent to because we found in a survey of customer care
an individual customer at each point of their sales executives we ran that less than 10 percent of
journey was cost-prohibitive. But, as Lari noted, respondents in North America reported greater-
with the latest developments in gen AI agents, now than-expected satisfaction with their customer
you can do it. service performance.4
3 Ibid.
4 “Where is customer care in 2024?,” McKinsey, March 12, 2024.
The promise and the reality of gen AI agents in the enterprise 3
A closer look at gen AI agents: The Lenovo experience
Three leaders at Lenovo—Solutions and Linda Yao: I was working with our much more effective. They can prepare
Services Group chief technology officer marketing and sales training teams sales people for customer interactions
Arthur Hu, COO and head of strategy Linda just this morning as part of a program or guide them during sales calls. This
Yao, and Digital Workplace Solutions to develop a learning curriculum for approach is having a much greater impact
general manager Raghav Raghunathan— our organization, our partners, and our than previous learning approaches. It
discuss with McKinsey senior partner key customers. We’re figuring out what gives them a safe space to learn. They can
Lari Hämäläinen and McKinsey Digital’s learning should be at all levels of the practice their pitches ahead of time and
Barr Seitz how the company uses business and for different roles. learn through feedback in live situations.
generative AI (gen AI) agents.
Arthur Hu: On the tech side, employees Barr Seitz: How do you see the future of
Barr Seitz: What existing gen AI agent need to understand what gen AI agents gen AI agents evolving?
applications has Lenovo been running are and how they can help. It’s critical
Linda Yao: In our use cases to date, we’ve
and what sort of impact have you seen to be able to build trust or they’ll resist
refined gen AI agents so they act as a
from them? adopting it. In many ways, this is a
good assistant. As we start improving the
demystification exercise.
Arthur Hu: We’ve focused on two main technology, gen AI agents will become
areas. One is software engineering. It’s Raghav Raghunathan: We see gen AI more like deputies that human agents
the low-hanging fruit to help our people as a way to level the playing field in new can deploy to do tasks. We’re hoping to
enhance speed and quality of code areas. You don’t need a huge talent base see productivity improvements, but we
production. Our people are already getting now to compete. We’re investing in tools expect this to be a big improvement for
10 percent improvements, and we’re and workflows to allow us to deliver the employee experience. These are tasks
seeing that increase to 15 percent as services with much lower labor intensity people don’t want to do.
teams get better at using gen AI agents. and better outcomes.
Arthur Hu: There are lots of opportunities,
The second one is about support. We Barr Seitz: What sort of learning programs but one area we’re exploring is how to
have hundreds of millions of interactions are you developing to upskill your people? use gen AI to capture discussions and
with our customers across online, chat, interactions, and feed the insights and
Linda Yao: The learning paths for
voice, and email. We’re applying LLM outputs into our development pipeline.
managers, for example, focus on building
[large language model]-enhanced bots to There are dozens of points in the customer
up their technical acumen, understanding
address customer issues across the entire interaction journey, which means we
how to change their KPIs because team
customer journey and are seeing some have tons of data to mine to understand
outputs are changing quickly. At the
great improvements already. We believe complex intent and even autogenerate new
executive level, it’s about helping leaders
it’s possible to address as much as 70 to knowledge to address issues.
develop a strong understanding of the tech
80 percent of all customer interactions
so they can determine what’s a good use
without needing to pull in a human.
case to invest in, and which one isn’t.
Linda Yao: With our gen AI agents helping
Arthur Hu: We’ve found that as our
Arthur Hu is chief technology officer of Lenovo’s
support customer service, we’re seeing
software engineers learn how to work Solutions and Services Group. Linda Yao is
double-digit productivity gains on call
with gen AI agents, they go from basically COO and head of strategy at Lenovo. Raghav
handling time. And we’re seeing incredible Raghunathan is general manager of Lenovo’s
just chatting with them for code snippets
gains in other places too. We’re finding that Digital Workplace Solutions. Lari Hämäläinen
to developing much broader thinking and is a senior partner in McKinsey’s Seattle office;
marketing teams, for example, are cutting
focus. They start to think about changing Barr Seitz is director of global publishing
the time it takes to create a great pitch for McKinsey Digital and is based in the New
the software workflow, such as working
book by 90 percent and also saving on York office.
with gen AI agents on ideation and other
agency fees.
parts of the value chain. Comments and opinions expressed by
interviewees are their own and do not represent
Barr Seitz: How are you getting ready for a
Raghav Raghunathan: Gen AI provides or reflect the opinions, policies, or positions of
world of gen AI agents?
an experiential learning capability that’s McKinsey & Company or have its endorsement.
The promise and the reality of gen AI agents in the enterprise 4
Lari Hämäläinen: Let me take the technology view. Finally, it’s worth mentioning that a lot of gen AI
This is the first time where we have a technology applications beyond chat have been custom-
that is fitted to the way humans interact and can be built in the past year by bringing different
deployed at enterprise scale. Take, for example, the components together. What we are now seeing
IVR [interactive voice response] experiences we’ve is the standardization and industrialization of
all suffered through on calls. That’s not how humans frameworks to become closer to “packaged
interact. Humans interact in an unstructured software.” This will speed up implementation
way, often with unspoken intent. And if you think and improve cost efficiency, making real-world
about LLMs [large language models], they were applications even more viable, including addressing
basically created from their inception to handle the long-tail use cases in enterprises.
unstructured data and interactions. In a sense, all
the technologies we applied so far to places like Barr Seitz: What sorts of hurdles are you seeing
customer service worked on the premise that the in adopting the gen AI agent technology for
customer is calling with a very structured set of customer service?
thoughts that fit predefined conceptions.
Nicolai von Bismarck: One big hurdle we’re seeing
Barr Seitz: How has the gen AI agent landscape is building trust across the organization in gen AI
changed in the past 12 months? agents. At one bank, for example, they knew they
needed to cut down on wrong answers to build
Lari Hämäläinen: The development of gen AI has trust. So they created an architecture that checks
been extremely fast. In the early days of LLMs, for hallucinations. Only when the check confirms
some of their shortcomings, like hallucinations that the answer is correct is it released. And if the
and relatively high processing costs, meant that answer isn’t right, the chatbot would say that it
models were used to generate pretty basic outputs, cannot answer this question and try to rephrase it.
like providing expertise to humans or generating The customer is then able to either get an answer
images. More complex options weren’t viable. For to their question quickly or decide that they want to
example, consider that in the case of an LLM with talk to a live agent. That’s really valuable, as we find
just 80 percent accuracy applied to a task with ten that customers across all age groups—even Gen
related steps, the cumulative accuracy rate would Z—still prefer live phone conversations for customer
be just 11 percent. help and support..
Today, LLMs can be applied to a wider variety of Jorge Amar: We are seeing very promising results,
use cases and more complex workflows because but these are in controlled environments with a
of multiple recent innovations. These include small group of customers or agents. To scale these
advances in the LLMs themselves in terms of their results, change management will be critical. That’s a
accuracy and capabilities, innovations in short- and big hurdle for organizations. It’s much broader than
long-term memory structures, developments simply rolling out a new set of tools. Companies are
in logic structures and answer evaluation, and going to need to rewire how functions work so they
frameworks to apply agents and models to complex can get the full value from gen AI agents.
workflows. LLMs can evaluate and correct “wrong”
answers so that you can have much higher accuracy. Take data, which needs to be in the right format
With an experienced human in the loop to handle and place for gen AI technologies to use them
cases that are identified as tricky, then the joint effectively. Almost 20 percent of most organizations,
human-plus-machine outcome can generate great in fact, see data as the biggest challenge to
quality and great productivity. capturing value with gen AI.5 One example of this
5 “The state of AI in 2023: Generative AI’s breakout year,” McKinsey, August 1, 2023.
The promise and the reality of gen AI agents in the enterprise 5
kind of issue could be a chatbot sourcing outdated Barr Seitz: Staying with customer service, how will
information, like a policy that was used during gen AI agents help enterprises?
COVID-19, in delivering an answer. The content
might be right, but it’s hopelessly out of date. Jorge Amar: This is a great question, because
Companies are going to need to invest in cleaning we believe the immediate impact comes from
and organizing their data. augmenting the work that humans do even as
broader automation happens. My belief is that gen
In addition, companies need a real commitment AI agents can and will transform various corporate
to building AI trust and governance capabilities. services and workflows. It will help us automate a lot
These are the principles, policies, processes, and of tasks that were not adding value while creating
platforms that assure companies are not just a better experience for both employees and
compliant with fast-evolving regulations—as customers. For example, corporate service centers
seen in the recent EU AI law and similar actions in will become more productive and have better
many countries—but also able to keep the kinds outcomes and deliver better experiences.
of commitments that they make to customers and
employees in terms of fairness and lack of bias. In fact, we’re seeing this new technology help
This will also require new learning, new levels of reduce employee attrition. As gen AI becomes
collaboration with legal and risk teams, and new more pervasive, we may see an emergence of more
technology to manage and monitor systems at scale. specialization in service work. Some companies
and functions will lead adoption and become fully
Change needs to happen in other areas as well. automated, and some may differentiate by building
Businesses will need to build extensive and tailored more high-touch interactions.
learning curricula for all levels of the customer
service function—from managers who will need to Nicolai von Bismarck: As an example, we’re seeing
create new KPIs and performance management this idea in practice at one German company, which
protocols to frontline agents who will need to is implementing an AI-based learning and coaching
understand different ways to engage with both engine. And it’s already seeing a significant
customers and gen AI agents. improvement in the employee experience as
measured while it’s rolling this out, both from a
The technology will need to evolve to be more supervisor and employee perspective, because the
flexible and develop a stronger life cycle capability employees feel that they’re finally getting feedback
to support gen AI tools, what we’d call MLOps that is relevant to them. They’re feeling valued,
[machine learning operations] or, increasingly, gen they’re progressing in their careers, and they’re also
AIOps [gen AI operations]. The operating model will learning new skills. For instance, instead of taking
need to support small teams working iteratively on just retention calls, they can now take sales calls.
new service capabilities. And adoption will require This experience is providing more variety in the work
sustained effort and new incentives so that people that people do and less dull repetition.
learn to trust the tools and realize the benefits.
This is particularly true with more tenured agents, Lari Hämäläinen: Let me take a broader view.
who believe their own skills cannot be augmented We had earlier modeled a midpoint scenario
or improved on with gen AI agents. For customer when 50 percent of today’s work activities could
operations alone, we’re talking about a broad effort be automated to occur around 2055. But the
here, but with more than $400 billion of potential technology is evolving so much more quickly than
value from gen AI at stake, it’s worth it.6 anyone had expected—just look at the capabilities
6 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
The promise and the reality of gen AI agents in the enterprise 6
of some LLMs that are approaching, and even a decade. And it’s going to keep getting faster, so
Find more content like this on the
surpassing, in certain cases, average human levels we can expect the adoption timeline to shrink even
McKinsey Insights App
of proficiency. The innovations in gen AI have further. That’s a crucial development that every
helped accelerate that midpoint scenario by about executive needs to understand.
Jorge Amar is a senior partner in McKinsey’s Miami office, Lari Hämäläinen is a senior partner in the Seattle office, and
Nicolai von Bismarck is a partner in the Boston office. Barr Seitz is director of global publishing for McKinsey Digital and is
based in the New York office.
Scan • Download • Personalize
Designed by McKinsey Global Publishing
Copyright © 2024 McKinsey & Company. All rights reserved.
The promise and the reality of gen AI agents in the enterprise 7 |
49 | mckinsey | tech-services-and-generative-ai-plotting-the-necessary-reinvention.pdf | Technology, Media & Telecommuni cations Practice
Tech services and
generative AI: Plotting
the necessary reinvention
The rapid emergence of generative AI has the potential to disrupt
a dynamic the sector has relied on for decades, but it also offers
an opportunity to tap a lucrative new market.
This article is a collaborative effort by Anuj Kadyan, Himanshu Pandey, Noshir Kaka, Pallav Jain,
Senthil Muthiah, and Vikash Daga, with Ruchika Dasgupta, representing views from McKinsey’s
Technology, Media & Telecommunications Practice.
June 2024
Through most advances and innovations in To help services providers reposition themselves
enterprise technology, IT or technology services to thrive in the gen AI era, we surveyed 100 top
providers (also known as system integrators1 [SIs] or industry executives and technology decision
managed services providers [MSPs]) have, for the makers,2 interviewed a number of experts in the
most part, been able to rely on one constant: their sector, and conducted an analysis of the state
customers continuing to look outside their four of gen AI adoption in a representative sample of
walls for help stitching together and overseeing the the Forbes Global 2000 ranking of the largest
ever-changing, complex web of hardware, software, enterprises. This article, which is also informed by
networking, and storage products that drives their our experience in the market, examines how the
businesses. Now, enterprises are funneling more of new technology is affecting enterprise technology
their technology spending into generative AI (gen spending patterns, what new gen AI services
AI) and leveraging its capabilities to streamline or providers can offer to enterprise customers at
automate some of these same IT management different stages of gen AI adoption, and what critical
services. Services providers could be forgiven for steps providers can take to position themselves for
wondering what the future holds for them. this new era.
As it turns out, the future could be quite bright. Gen
Gen AI’s impact on enterprise tech
AI is also increasing demand for a wide range of new
spending and provider economics
services, which represents a significant opportunity
for providers to reimagine and recharge their Most companies have been working to implement
business. Just how significant? We estimate the and scale traditional AI and automation solutions for
emerging market for services relating to gen AI/AI more than a decade. However, the launch of OpenAI’s
could be worth more than $200 billion by 2029. ChatGPT solution in late 2022 has led to a paradigm
If tech services providers can succeed in claiming shift in enterprise AI priorities. Organizations are
a decent share of that incremental value, their now turning to gen AI to help power and reinvigorate
profitability could grow by as much as 30 percent. traditional AI initiatives while launching entirely new
Reaching those heights will require providers to gen AI efforts in multiple functions. But after the
reinvent how they do business. That challenge will initial waves of excitement and hype that greeted
include transforming service offerings and how gen AI’s arrival, the enterprise customer base is
they are delivered, embracing new go-to-market now squarely focused on seeing the transformative
(GTM) and commercial models, and upskilling technology live up to its billing. The goal is to move
teams while finding new sources of talent. from piecemeal efforts, isolated pilots, and proofs of
concept (POCs) to scalable solutions that can be
The next 12 to 18 months will be pivotal. Enterprise deployed across organizations.
customers are already exploring new ways to
manage some core IT work themselves while As part of this gen AI reset, organizations have a
ramping up all manner of gen AI pilots and initiatives, better understanding of the strategic and financial
and a wide range of other tech players (from commitment required to create significant impact.
hyperscalers to hardware and software companies) As one executive told us, “Scaling AI is hard. It
are beginning to make or contemplate moves into requires new skills, new processes, and new ways
the burgeoning AI services market. Traditional of working. It’s a transformational challenge for
services providers that don’t begin to reimagine most organizations.”
their value proposition in this arena risk losing some
relevance—and potentially more than 15 percent in In the latest McKinsey state of AI survey3 of
revenue and profit. enterprise customers, 67 percent of respondents
1 System integrators (SIs), aka managed services providers (MSPs), focus on providing traditional IT services, including by building ecosystems
for end customers that combine hardware, software, networking, and storage products from multiple vendors.
2 M cKinsey Enterprise CXO Survey: Impact of Gen AI for Technology Services Providers, January 2024 (n = 100).
3 “The state of AI in early 2024: Gen AI adoption spikes and starts to generate value,” McKinsey, May 30, 2024.
Tech services and generative AI: Plotting the necessary reinvention 2
said they expect their organizations to spend more specialized and sensitive AI workloads (for
of their technology budgets on AI/gen AI over example, public sector, healthcare) may drive
the coming three years. Based on our analysis, we some spending growth.
estimate that overall tech budgets will grow at
a CAGR of about 4 to 6 percent over the next five At the same time, a wealth of new AI services
years. But where that is spent may change opportunities are developing thanks to increased
considerably, with traditional value pools changing spending across a number of categories. The
and new ones (and new competitors) fast appearing. largest of these include the following:
Gen AI is already causing various tech ecosystem
players to expand their range of offerings; for — Outsourced AI services. These services are
instance, hyperscalers are providing integrated expected to enjoy double-digit increases
development environments to build, train, as enterprises grappling with the scarcity—and
customize, and deploy large language models expense—of gen AI talent and their own
(LLMs), while some hardware vendors are inexperience developing and implementing gen
venturing into services that enable development AI solutions seek external help. This increased
of custom LLMs and microservices for faster spending will focus on AI foundational services
deployment of gen AI applications. (for example, AI for IT operations [AIOps]),
gen-AI-led productivity solutions (for example,
New competitors are just one aspect of the coding copilots), and vertical-industry solutions
disruption. With enterprises funneling a greater (for example, clinical trial acceleration in life
portion of tech budgets to AI/gen AI efforts, sciences, hyper-personalized B2C solutions
spending on services providers’ core offerings for telecom).
could drop or stagnate across a few traditional
areas of spending. The three main categories of — Outsourced digital services. Increased demand
tech services spending to feel this effect are for digital services like the cloud, legacy
as follows: modernization, and data and analytics will likely
drive growth by 8 to 12 percent as enterprises
— Outsourced traditional services. The long- leverage gen AI across existing digital initiatives.
standing foundation of tech services providers
will likely see a decline of 8 to 10 percent as — Enterprise applications. These applications
advancements in automation and AI from cloud should see solid growth as enterprises adopt a
platforms solve traditional IT challenges. new generation of gen AI apps and solutions
that solve traditional IT challenges.
— Insourced services. Although internal IT teams
will leverage low-code/no-code platforms, new — New AI stack solutions. This new spending
data/AI apps, and infrastructure-management- category (largely for LLMs and related spending)
automation tools to grow their portfolios, overall is likely to grow rapidly as enterprises increase
spending on this category will still likely stay flat, their adoption of gen-AI-native offerings
with the cost of additional workloads largely such as foundational models, tooling, and
offset by productivity gains. data architecture.
— On-prem, co-location (colo), and private cloud. — Public cloud and infrastructure as a service.
The secular shift to public cloud and cloud- Gen AI should drive increased enterprise
based graphics processing units (GPUs) is likely cloud migration and consumption (for example,
to cause a slow, steady decline in this area LLM training on the cloud), fueled by the rise of
across most workloads. However, a few AI-specialist cloud providers.
Tech services and generative AI: Plotting the necessary reinvention 3
— Computer hardware (for example, GPUs). opportunity for tech services providers in the next
This category is likely to experience growth as five years, primarily centered around AI foundational
enterprises use more advanced AI/gen AI services, AI-first horizontal solutions, and vertical-
custom chips, with some of this spending growth solutions. Companies are likely to overhaul
captured by public cloud providers making their their tech spending and reallocate their budgets
own investments in the advanced hardware. along the lines of the global enterprise macroshifts
laid out in Exhibit 1.
The full impact of gen AI on enterprise tech spending
could be dramatic. According to our analysis, the The alternative to seizing that potential opportunity
disruption could unlock a $200 billion-plus market may be even more daunting. Our analysis highlights
Web <2024>
<GenAITech>
Exhibit 1
Exhibit <1> of <5>
Generative AI is expected to fuel a fundamental shift in enterprise tech value
pools, as tech ecosystem actors make moves to claim their share.
Gen-AI-based shifts in global enterprise tech spending expected over next 3 years, by category
Services spend >$1.0 trillion
Consumption spend $0.5–$1.0 trillion
2024 spending
(total addressable Direction <$0.5 trillion
Tech spending categories market) of shift Important shifts expected
Outsourced New spending on AI-focused Net new outsourcing across three areas: gen AI
AI services outsourced services readiness, horizontal productivity solutions, and
vertical growth solutions
Outsourced Cloud implementation, legacy Growth in areas like the cloud, digital and analytics,
digital modernization, digital and and legacy modernization propelled by movement to
services analytics, customer experi- “AI-first stack”
ence (CX), security, IoT
Outsourced Application data Further deceleration in transitional tech spending
traditional management (ADM), business propelled by gen-AI-enabled automation and even-
services process outsourcing (BPO), tual redundancy
data center, inframanage-
ment services
Insourced In-house IT spend (eg, devel- Longer-term reduction expected, propelled by spe-
services opers, CX teams, etc) cialized, off-the-shelf solutions from both software
and services companies
Enterprise Software-as-a-service (SaaS) Steady growth likely to continue across areas like
applications applications and software enterprise resource planning (ERP), customer rela-
spending tionship management (CRM), and collaboration as
enterprises further modernize
Data and New SaaS spending on AI Significant uptick likely with the onset of LLM-led
AI solutions platforms, large language solutions from incumbents and new actors
models (LLMs), etc
Public Hyperscaler spending Adoption likely to sustain with growth of AI work-
cloud loads (including rise of AI-specialized cloud actors)
On-prem, Physical storage, on-prem - Spending likely to sustain, with specialized, sensi-
co-location, data centers, and spending tive, and edge workloads likely to be housed in
and private on private cloud private cloud
cloud
Source: McKinsey Enterprise CXO Survey: Impact of Gen AI for Technology Services Providers, Jan 2024 (n = 100); McKinsey analysis
McKinsey & Company
Tech services and generative AI: Plotting the necessary reinvention 4
the risk of inaction for both the top and bottom lines The enterprise gen AI journey
of companies in the sector (Exhibits 2 and 3),
In the relatively short period of time since enterprises
with a 15 percent cut in both a real possibility. The
started working with gen AI, they have already
growth in automation and insourcing of certain
begun to evolve how they navigate the technology.
workflows ushered in by gen AI is likely to spur a
For starters, they are now facing up to the myriad
sizable reduction in demand for providers’
challenges many have already experienced in
traditional services, while productivity gains and
attempting to adopt gen AI: high costs, particularly
added competition could lead to pricing pressure.
from trying to leverage LLMs on a large scale;
By contrast, embracing and adapting to the new
insufficient cloud and data readiness of the tech
technological era offers the prospect of not only
stack; the reliability of gen AI output; and uncertain
maintaining the industry’s 3 to 5 percent historical
risks related to regulation, intellectual property,
growth trend but also improving its financial
ethics, and more. Instead of relying on one vendor,
position, with a further 2 to 4 percent revenue boost
enterprises are increasingly using multiple model
and a potential 30 percent profit bump, based on
providers to develop their gen AI use cases. They’re
the provider’s starting point.
also turning to more affordable open-source models
Web <2024>
<EGxehniAbITiet c2h>
Exhibit <2> of <5>
Generative AI could affect tech services’ business models in many ways,
both positive and negative.
Impact of generative AI (gen AI) on tech services’ business models
Change in economics of existing business¹
1
Gains in
productivity
2 3
Pricing High gen
pressure AI costs
Reduction in the volume of contracts 4 5 6
Insourcing of
SaaS/CSP² workflows by Automation
substitution enterprise of workflows
Growth in services and offerings 7 8 9 10
Increased Reimagined New Increased
demand for existing services demand
existing service using gen AI from next
services lines applications tier of firms
Gains in SG&A³ 11 Improved win rate from Productivity gains in 12
M&S productivity gains internal processes
1Share of gains created and value retained by providers in time and material and in fixed-price contracts.
²Software as a service/cloud service provider.
³Selling, general, and administrative expenses.
McKinsey & Company
Tech services and generative AI: Plotting the necessary reinvention 5
Web <2024>
E<GxehniAbITite c3h>
Exhibit <3> of <5>
The impact of generative AI on services providers’ top and bottom lines will
depend on whether they take a passive or active approach to the new era.
Impact of generative AI (gen AI) on tech services’ sector profit and loss under different scenarios, %
Passive play (steady state) Offensive play (steady state) Baseline
Range by
102–104
scenario
100 100
83–85
80 80
60 60
46–48
37–41
40 40
43–44 30–32 12–15
9–11 19–21
20 20
13–14 19–21
17–18
0 0
Revenue Direct Other Gross SG&A/ EBITDA Revenue Direct Other Gross SG&A/ EBITDA
cost direct margin operating cost direct margin operating
FTE costs expenses FTE costs expenses
Revenue –15 to –17% Profit 0.85× Revenue +2 to +4% Profit 1.30×
Source: Expert interviews; McKinsey analysis
McKinsey & Company
that they can control and fine-tune rather than — Observers. The bulk of enterprises (50 to
attempting to build custom models from scratch, 60 percent) are “observers” focused on AI
taking the approach of what previous McKinsey readiness (setting up their data and cloud
research has dubbed a gen AI model “taker” foundations) and conducting small-scale POCs
or “shaper” rather than the more costly and primarily for internal use cases (for example,
complicated path of a “maker.” text summarization, knowledge management)
that are largely anchored on driving
While these types of shifts are widespread, large higher productivity.
enterprises are at very different stages of gen AI
adoption. Based on our analysis, organizations can — Front-runners. Another 30 to 40 percent are
be classified into the following three stages of “front-runners” with a clear vision for using AI/
gen AI readiness and adoption along their journey gen AI to reduce costs at scale through use
(Exhibit 4): cases such as AI-enabled service desks and
Tech services and generative AI: Plotting the necessary reinvention 6
legacy-code upgrades. These organizations — Innovators. Less than 10 percent are true AI-first
have already made changes to their organization “innovators” with an integrated strategy to achieve
and operating models, such as creating AI cost reductions and unlock the true potential
centers of excellence (COEs) and new roles like of gen AI through cutting-edge use cases like
chief AI officer. gen-AI-enabled product design and development
that can propel future business growth.
Web <2024>
E<GxehniAbITite c4h>
Exhibit <4> of <5>
AI/generative AI transformation is a multistep, multimodal journey, and
most large enterprises are still in the early stage of adoption.
Enterprise cloud, data, and AI value realization through technology transformation
Large enterprise AI/generative AI (gen AI) adoption stage, estimated share of Global 2000 companies
OBSERVERS FRONT-RUNNERS INNOVATORS
50–60% 30–40% <10%
15
14
New AI/gen 13
AI journey 12
11
Enterprises
10
want to derive
1 9 2–3×
Value 8 higher value
realization, $ through AI
6 7
5
Conventional digital
4
and cloud journey
3
1 2
The AI journey
Conventional cloud transformation, AI innovation on the cloud Long-term, end-to-end
at-scale migration of apps, followed over a “Data on Cloud” AI transformation
by modernization and native app foundation unlocked by building a
development modern AI tech stack
1 Cloud advisory and design 8 Data engineering 13 AI-first inframodern-
2 Cloud migration 9 Data migration to the cloud² ization⁴
3 Application modernization 10 AI-enabled IT moderniza- 14 AI use case scale-up
4 Native app development tion³ across functions
5 Cloud testing, financial operations, 11 AI use case development 15 AI operations and
and multihybrid management and strategic road map enablers⁵
6 Managed Cloud Services¹ 12 Data product design and
7 Cloud operations monetization
1For example, security. ²At scale. ³For example, legacy code upgrade, AI-enabled service desk. ⁴Custom LLM fine-tuning, etc. ⁵Including MLOps, shared use cases,
and data collaboration.
Source: Company annual reports; McKinsey Enterprise CXO Survey: Impact of Gen AI for Technology Services Providers, Jan 2024 (n = 100); McKinsey analysis
McKinsey & Company
Tech services and generative AI: Plotting the necessary reinvention 7
Just as companies are at different stages of their “new AI stack” of tooling/security, foundational
respective gen AI journeys, they also require a models, and data and databases sandwiched
range of tech services to propel them forward. To between the applications and infra/cloud layers,
satisfy that demand and launch their own gen AI which were previously the main focus areas of
journeys, providers should strongly consider rolling the traditional services providers’ play (Exhibit 5).
out three distinct types of AI services over an initial While services providers may encounter
12- to 18-month period. They are as follows: difficulty gaining ground as new entrants in
these areas, they are more likely to develop
— Reimagined traditional and digital services extensions that make existing solutions more
lines that leverage gen AI for improving delivery powerful, cost-effective, and easier to
productivity and innovating current services implement than to attempt building their own
offerings (for example, knowledge management, models or tools from scratch.
agent copilot).
— Vertical solutions that target product/process
— Foundational AI/gen AI offerings that prepare innovation and revenue growth initiatives of
the enterprise tech stack for cloud and gen AI enterprises through deep, vertical-specific use
readiness (for example, data on the cloud) and/or cases (for example, gen-AI-enabled connected
gen-AI-native services related to LLMs or tooling products and manufacturing ecosystems in the
(for example, building comprehensive, end-to- industrial segment, insurance claims processing
end services ecosystems related to new players platform in finance). Services providers’ strong
such as OpenAI, Cohere, and others). track record of targeting verticals with data and
analytics services should prove helpful.
Importantly, the second, foundational class of
services may provide a critical entry point Because of the relatively small number of enterprises
for providers to expand their relationships with that already qualify as gen AI innovators, the vast
enterprises and help shape their innovation majority (about 80 percent) of more than 10,000 AI
agendas. Services providers can now target the services deals4 expected over the next year
Given that cloud transformation has
been a key part of services providers’
growth in recent years, they should be
well positioned to guide customers to
the next fundamental digital overhaul
with AI and gen AI.
4 Extrapolating the number of proofs of concept/deals reported by services providers in the last quarter of 2023.
Tech services and generative AI: Plotting the necessary reinvention 8
Web <2024>
E<GxehniAbITite c5h>
Exhibit <5> of <5>
Generative AI has created new entry points for tech services providers to
shape enterprises’ innovation agendas and tap a dynamic new market.
AI services’ annual growth, by tech stack layer
New entry points <10% 10–20% >20%
Tech stack layer Emerging offerings for tech services providers CAGR, 2024–29
Enterprise applications Services focused on AI-first enterprise SaaS¹ applications (eg, AI-led ERP² solu-
tions, gen-AI-based CRM³ implementations), AI-powered virtual assistants,
personalized marketing and sales automation, predictive analytics for supply
chain agility
Tooling and security AI-based code analysis and testing automation, AI-based identity and access
management systems, intelligent DevSecOps⁴ for CI-CD,⁵ automated threat
detection and response tools
Foundational models Pretrained AI models for specific industries (eg, finance, healthcare); multimodal
AI models combining text, image, and audio data (including LLMOps⁶); trans-
former model integration for machine translation with other models
Data and databases Generative adversarial networks for synthetic data generation, modernizing data
architecture and managing multi-data structures (eg, vector databases with
traditional databases) to power LLMs, AI-based data cataloging and metadata
management
Public cloud AI-first code scanning and cloud readiness, AI-enabled code migration,
auto-generation of gen-AI-enabled cloud microservices, AI-based workload
optimization and resource management, augmented FinOps⁷ using ma-
chine-learning-enabled orchestration
On-prem, co-location, Intelligent workload orchestration and optimization, predictive maintenance for
and private cloud data center hardware, AI-based energy efficiency and cooling optimization ser-
vices, self-healing systems and automated fault detection
Chips and Embedded software engineering for advanced AI chips (with public and private
semiconductors cloud infrastructure), edge AI and on-device processing, custom chip design and
corresponding firmware development for AI-focused chips
1Software as a service. ²Enterprise resource planning. ³Customer relationship management. ⁴Development, security, operations. ⁵Continuous integration and continu-
ous delivery/deployment. ⁶Large language model operations. ⁷Financial operations.
Source: Company annual reports; expert interviews; HPE 2023 securities analyst meeting presentation, Oct 19, 2023; “IDC forecasts revenue for artificial intelli-
gence software will reach $307 billion worldwide in 2027,” IDC, Oct 31, 2023; “Worldwide software and public cloud services spending guide,” IDC, accessed
June 10, 2024; McKinsey analysis
McKinsey & Company
will probably fall in the first two categories of elements in place. Given that cloud transformation
services. They will likely be largely focused on has been a key part of services providers’ growth in
foundational AI readiness and cost reduction POCs recent years, they should be well positioned to
through horizontal use cases involving knowledge guide customers to the next fundamental digital
management, customer service, and text overhaul with AI and gen AI.
summarization. Our research shows that there is a
high degree of correlation between enterprise AI Still, the growth potential of these categories of
readiness and cloud readiness, so it will be critical services is limited. There is a strong possibility that
for services providers to position themselves as the market for productivity improvements and cost
end-to-end, holistic AI transformation partners, reduction will fast become commoditized as both
starting with getting the core data and cloud enterprises and providers increase investments in
Tech services and generative AI: Plotting the necessary reinvention 9
an area that lacks much room for differentiation. market. Providers have had success with this model
For a provider to thrive in this space, it will want to for the cloud, making implementation of other
seriously consider building ready-to-implement, vendors’ products faster, easier, and more affordable,
packaged AI-readiness offerings that enable rapid but it doesn’t happen overnight. It takes at least 15 to
and at-scale margin realization, modeled on the 20 individual client implementations to fine-tune
platform approach it has used successfully with the accelerators and equip them with the proper
cloud solutions over the past decade. functionality and systems as they evolve and mature
through repeated usage. Those players that can
As more organizations become comfortable and develop effective accelerators early on will likely
competent with implementing gen AI at scale over have a decided advantage as the gen-AI-services
the next couple of years, AI services deals will likely market starts to take off.
focus as much if not more on product innovation
and revenue growth. The providers that can build Rethink GTM and commercial models
full-stack, vertical-specific platform solutions The sector’s time-tested approaches to landing,
and lighthouse industry use cases focused on these structuring, and delivering on deals aren’t likely to
two areas will be best positioned to stand apart. have the same success in this burgeoning era.
Maintaining that advantage for the long term, Services providers may no longer be able to wait for
however, will demand more; providers will need sufficiently large deals to materialize. To stake
to prove that they can continually adapt and an early claim to the emerging gen-AI-services
respond to the accelerating pace of gen AI opportunity, they should strongly consider
innovation while enabling sustained impact for embracing volumetric deals—experimenting and
their enterprise customers. conducting small-scale POCs with a number of
clients, as leading providers have already begun to
do. Learning on the go will be key for both providers
Rewiring providers for the gen AI age and their customers as the technology (and use
The prospect of providers turning themselves into cases, solutions, implementations, et cetera) evolves
gen-AI-services-driven dynamos is compelling, but at a breakneck pace. At the same time, providers
turning that vision into a new reality will require will want to work with certain existing customers to
them to make a series of complex, challenging shifts create larger, pioneering gen-AI-led transformation
across their entire organizations. deals. Many if not most of these newfangled deals
will be outcome based with a significant gain-share
Build a new, broad-based AI-services catalog, component. As IT providers compete more with
including ready-to-deploy accelerators internal development teams and off-the-shelf
As stated earlier, service providers can jump-start software-as-a-service (SaaS) solutions, apps, and
their gen AI businesses by rolling out a wide array of low-code/no-code platforms, they will be forced
new offerings that include foundational-AI-readiness to prove their worth more than ever before. To win
solutions across both data and gen AI tools, deals and gain market share, services providers
packaged cost reduction solutions that can enable may need to embrace innovative commercial
rapid and at-scale margin realization, and vertical AI models; for instance, fees would be linked to the
use cases in pilot industries that focus on product number of tickets resolved by a customer-
innovation and revenue growth initiatives. The true support gen AI system, or to the time saved per
differentiator, however, is developing ready-to- salesperson through gen AI augmentation of
deploy accelerators or solutions (for example, customer relationship management tools.
prompt library, source attribution tools) across the Developing systems that can accurately measure
gen AI tech stack to accelerate the development the productivity gains attributable exclusively to
and adoption of existing gen AI solutions on the gen AI will be critical.
Tech services and generative AI: Plotting the necessary reinvention 10
Develop a new AI talent model across build, sell, Modernize delivery model through AI COEs to
and deliver functions enable higher efficiency for customers
Services providers will need to create a wide range Early evidence suggests that gen AI can enable
of new roles, such as a responsible AI lead to 20 to 40 percent5 productivity improvement in tech
establish policies, principles, operating models, and delivery across traditional service lines through new
controls to govern and ensure the ethical and safe solutions such as coding copilots or agent copilots
use of AI across the enterprise. Other new positions to aid knowledge management in application
may include AI product managers on large-app-build development and maintenance services. Still,
programs, while sales leaders will need to have services providers will need to develop a holistic
a broader technical and consultative skill set and approach to realize the full potential of gen AI on
be capable of answering customer inquiries on their delivery models. The linchpin of that approach
a range of topics, such as how to calculate the ROI will be a new COE to effectively coordinate and
of gen AI implementation and whether to scale cutting-edge AI services delivery efforts across
approach custom foundation model development the organization. Staffed with a mix of technical and
through prompt engineering, retrieval-augmented industry experts who collaborate with leaders in
generation (aka RAG) or fine-tuning. different functions and parts of the business, COEs
have typically been used for providers’ cloud and
Adopt a new partnership and M&A approach to digital and analytics initiatives. But gen AI’s rapid
bring together the emerging gen AI ecosystem pace of change and complexity mean that this new
Most enterprises access LLMs through APIs COE will require greater depths of expertise and
(leveraging cloud services providers, model levels of collaboration than previous similar efforts.
providers, or data cloud players) instead of hosting Most large providers have already launched
them themselves, which makes it critical for initiatives in this direction.
services providers to strengthen partnerships with
this growing roster of players. But while services Even if services providers manage to pull off these
providers have traditionally only formally linked up various transformations, there are still fundamental
with vendors once they have reached a certain risks to grapple with as they embrace gen AI.
scale with enterprise customers, the unusually fast Perhaps most important, as enterprises struggle
pace of gen AI adoption and experimentation to understand how to scale this fast-evolving
dictates that they take a different tack. If they want technology to fuel new growth, is that services
to play a key role in bringing “best of breed” providers will have to deal with the potential
ecosystems spanning the “chips to apps” tech stack, for significant scope creep and, as a result, possible
they will have to partner with smaller or fledgling reputational damage. Specific areas they will
software companies as well as the larger, more want to pay careful attention to include a lack of
established ones they are more used to working responsible AI controls as enterprise |
50 | mckinsey | the-case-for-human-centered-ai_final.pdf | The case for human-
centered AI
Maximizing generative AI’s promise while minimizing its misuse
requires an inclusive approach that puts humans first.
December 2024
Over the past two years, generative AI (gen AI) has been a rapidly evolving trend that has
touched the lives of many around the globe. Which is why the design of these formidable
systems must include experts from diverse backgrounds, says James Landay, a professor of
computer science at Stanford University. On this episode of the At the Edge podcast, Landay
talks with McKinsey senior partner Lareina Yee about how to develop safe, inclusive, and
effective AI.
The following transcript has been edited for clarity and length. For more conversations on
cutting-edge technology, follow the series on your preferred podcast platform.
Defining human-centered AI
Lareina Yee: You have been a champion of a human-centered approach to AI development for
many years. How do you define human-centered AI?
James Landay: To me, human-centered AI is not just about the applications of AI, which might
provide social value, whether in health or education. It’s also about how we create and design
those AI systems, who we involve in that development, and how we foster a process that’s more
human centered as we create and evaluate AI systems.
Lareina Yee: As the cofounder and codirector of the Stanford Institute for Human-Centered
Artificial Intelligence [HAI], you’re uniquely interdisciplinary. Can you tell us about how you bring
the community together at Stanford to look at and develop the future of AI?
James Landay: Interdisciplinarity was key to us from the start. It was also key to why we felt
Stanford was a special place for doing this kind of work because we have world-class technical
folks in AI, computer science, and other engineering disciplines.
But we also have a top medical school, a top law school, a top business school, and top social
sciences and humanities departments. And since AI is a society-changing technology that’s
going to be everywhere, we feel it needs to include every field—along with the different values
and outlooks inherent in those fields—to help shape it.
We give internal grants for research projects, and the sole funding criteria is, “Are you bringing
together people from different schools or different departments across the campus?” So we
encourage interdisciplinarity by how we fund projects.
We also encourage it by whom we highlight in our communications, as well as in our leadership.
Our two original codirectors were Fei-Fei Li, a famous AI computer scientist, and John
Etchemendy, a professor of philosophy.
The case for human-centered AI 2
Lareina Yee: Can you tell me how that interdisciplinary approach—combining philosophy,
computer science, law, and ethics—gives us a window into how that shapes the questions and
the types of research you’re doing at Stanford?
James Landay: For a start, it sometimes causes confusion, because people in different fields
speak different languages, so the same words can mean different things to different people. For
example, I’m working on a project with an English professor and someone from the medical
school. And what they call a pilot study is not what I would call a pilot study.
So you’ll experience confusion, but sometimes that confusion leads to new ideas and new ways
of looking at things. For example, we’ve had people working on large language models [LLMs]
who are looking at natural language processing [NLP]. And then they run into an ethicist with a
background in political science who questions some of the things they’re doing or how they’re
releasing their software without particular safeguards.
A technology with a mind of its own
Lareina Yee: Can you tell us why you think AI represents such a massive, profound change?
James Landay: Think about where computing itself has become part of our daily lives, like when
interacting with your doctor. Education is full of computer systems, and kids today could not
imagine being in high school, college, or even junior high without using a laptop or tablet for a lot
of their work.
AI is this general-purpose technology, and almost every application built in the future will
probably include some AI in it. But it’s a different kind of technology, and it is not as reliable in
some ways. AI systems aren’t deterministic, as we like to say in computer science, where the
same input always gives you the same output.
What’s different about AI systems is that they’re based on probabilistic models, these large
neural networks trained on billions or trillions of bits of data. And you can feed data into them
and receive different results, depending on how that data’s processed in that huge neural
network. That means they’re harder to design and it’s harder to protect against what they might
do when they do something wrong.
That’s why we need to think about designing AI systems differently, since they’re going to
become ubiquitous throughout our everyday lives, from health to education to government. We
want to understand them better than we do the existing computing systems.
The case for human-centered AI 3
‘We need to think about designing AI
systems differently, since they’re going
to become ubiquitous throughout our
everyday lives, from health to
education to government.’
Why it’s tough to build responsible AI
Lareina Yee: The training of AI is also so important, and it raises the problem of hallucinations.
Can you tell us a little bit about the science behind hallucinations, which underscores how we
think about responsible AI differently with these systems?
James Landay: Hallucinations occur when these probabilistic models essentially make up facts
that aren’t true. That’s a problem with these models that may even represent a fundamental
problem. We’re not even sure why they occur, and this is actually one of the bigger issues
concerning just who is building these models.
Right now, these models are controlled by a few large corporations, and academics don’t even
have the computing power to build models big enough to understand how they work. So we are
going to build large infrastructures of our societal systems on top of models that are very useful
but have properties that we don’t fully understand.
Responsible AI is a field that considers this situation and asks, “How do we try to make models
that don’t do harm? How do we put guardrails around them?” So responsible AI is trying to do
what it can, but it’s pretty hard without actually controlling the underlying data, the underlying
model, or even knowing what’s in the data.
Tread cautiously and test thoroughly
Lareina Yee: A lot of businesses are leveraging their data by combining it with a base LLM.
The proprietary piece is largely their data. How do you think about the right testing and
understanding in that context?
James Landay: There is a little more control because you’re feeding your data into the model to
fine-tune it or even just to look something up. So while there is a little more control, again, the
underlying model doing a lot of the work is using unknown data.
The case for human-centered AI 4
Companies are going to have to be very careful and really test things very thoroughly. That’s the
best bet they have right now, putting guardrails around things, essentially like blacklists that
look for certain words or phrases to never mention.
I also think we’re going to see a new business model selling those services, lists, or underlying
base LLMs that implement those kinds of things, depending on what a client wants.
Societal questions requiring answers
Lareina Yee: With the level of excitement over AI and kind of a call to action, what are some of
the questions that you believe need to be tackled at a societal level?
James Landay: One, we may need better design processes to include a broader set of
communities impacted by AI systems. That may help us get at some of the problems earlier on
that we can fix before they are released with negative consequences.
Two is education, making sure students going into computing and AI have more of an ethical
basis to think about their decisions. At Stanford, we’ve implemented something called
“embedded ethics.” So instead of requiring only one capstone ethics course, we embed ethical
lessons in different courses along the way. This is something we unabashedly borrowed from
Harvard.
But finally, there are going to be some things that happen that cause harm, because somebody
either had bad intentions or simply made a major mistake. And in that case, that’s where law and
policy come into play. We need to make sure that if you do something bad with AI, it carries a
cost.
Hopefully, that stops people with bad intentions in the first place. It will also cause companies
to make sure they’re being careful to avoid the downsides from legal risk and then also
reputational risk.
Good intentions aren’t enough
Lareina Yee: This is very much in line with something you once said that drew quite a lot of
attention, which is “‘AI for good’ isn’t good enough.”1 Can you expand on that?
James Landay: You can have good intentions and say, “I’m going to do AI for healthcare or
education.” But if you don’t do it in a human-centered way, if you just do it in a technology-
centered way, then you’re less likely to succeed in achieving that good you set out to do in the
first place.
1 James Landay, “‘AI for good’ isn’t good enough: A call for human-centered AI,” Stanford Institute for Human-Centered Artificial
Intelligence lecture, February 13, 2024.
The case for human-centered AI 5
‘You can have good intentions and
say, “I’m going to do AI for healthcare
or education.” But if you don’t do it in
a human-centered way, if you just do
it in a technology-centered way, then
you’re less likely to succeed in
achieving that good you set out
to do in the first place.’
So that is really the introduction to a design process that goes beyond designing for just users
because AI systems are different in that they have impacts beyond the immediate user. They
can impact a broader community around the user, so the design process should consider how to
bring those folks into the conversation around designing an AI system. And we might find that
some of those people should be our users as well.
Finally, if an AI system is really successful, it becomes fairly ubiquitous and may start to have
societal impacts. So designers of these popular systems might want to ask themselves, “If the
system I’m building is successful, are there any negative impacts it might have? How might I
mitigate them?”
And they should think about that in advance so they’re prepared to deal with any issues. It’s
much less expensive to fix some of these problems early in the design process than after you’ve
released a product.
The benefits of diverse and interdisciplinary teams
Lareina Yee: I think it’s neither here nor there. It’s actually more about asking people to change the
way they’ve done things, to redesign what product development looks like in today’s digital economy,
yes?
The case for human-centered AI 6
James Landay: Yes. It’s going to require changing processes and actually changing people as
well. Right now, we mainly have sets of engineers, like responsible AI groups or safety teams,
who are meant to check products before they’re released.
Unfortunately, there’s a lot of incentive to just push something out the door. And these teams
don’t quite have the social capital to stop it. A different way of doing this is to embed a lot of that
expertise in the original team.
So we need teams with these different disciplines—the social scientists, the humanists, the
ethicists—because then some of those problems will be found earlier. And as team members,
those people will have the social capital to make that change happen.
For example, we saw a lot of examples where computer vision systems could not recognize
Black women or people of color in general. Those problems weren’t that hard to fix in the end,
but they weren’t found until those companies released them and were publicly shamed.
And different companies dealt with it differently. Some immediately went and fixed it, while
some fought it. So part of this is changing the process, and part of it is changing the teams. They
need to be more diverse and interdisciplinary, and that will help solve a lot of these problems.
AI and the future of education
Lareina Yee: There is a lot to think about, but this is just a portion of your research. I was also
watching some pretty amazing work you and your PhD teams are doing around the future of
education. Are you optimistic or pessimistic about the impact of generative AI on education?
James Landay: I’m very optimistic. I think AI in education is going to be huge. Now, I don’t envy
anyone with young children right now, because I do think the next five years are going to be a
really rough time in education at all levels as the system tries to understand how to deal with this
technology. Educators are asking themselves, “Do we ban it, do we allow it, how do we change
how we teach, and how do we change how we evaluate?”
AI is going to force those questions, and some schools, teachers, and administrators are going
to be dragged kicking and screaming all the way, but some are going to embrace it and do
something smart with it from the beginning. So it’s going to take a while to figure it out, but in
the long run, it’s going to change the educational system in a lot of very positive ways.
The case for human-centered AI 7
Lareina Yee: Can you tell us about those positive ways and why you’re not one of the ones
kicking and screaming?
James Landay: AI is going to provide people with a personalized tutor that understands where
people are having difficulties and how best to motivate them. Because both kids and adults
respond better to different motivational strategies tailored to meet their needs. Imagine a tutor
who understands all that and helps you learn, as an addition to regular schooling.
In my research, I’ve found it’s also useful to target folks who maybe don’t fit in the traditional
educational system, who just don’t think that’s what they’re good at. How do we motivate those
folks, take advantage of their capabilities, and allow them to learn and eventually contribute to
society?
We’ve looked at how to make narratives and stories as a way to draw kids into learning, and my
“Smart Primer” project is based on that concept. We’ve written different stories where you have
to engage in learning activities as you read the story. And by engaging in the learning activity,
you get the story to move forward.
We use AI in many different ways, whether it’s using augmented reality to recognize objects in
the real world or even using AI to get a kid to write more.
From index cards to AI flash cards
Lareina Yee: One of your teams took a look at Quizlet’s online flash cards and made it a richer
experience. Flash cards are how I grew up, writing things out on index cards and sitting with my
friends and testing each other for a science exam the next day. How is the concept of an AI flash
card different from my good old index cards?
James Landay: We did a trial in China where we were trying to teach expats Chinese. And one
of the ideas we tried was using different flash cards tailored to the context of your location. So if
you’re in a taxi, they teach you how to talk to the driver. And if you’re in a restaurant, they teach
you how to order food. So we used AI technology to take advantage of the context and location
to drive the flash cards.
Lareina Yee: What’s interesting about those cases is that it’s starting to define a different
relationship children have with machines.
James Landay: Yes. And we should think about that. What does that mean? What kind of
relationships do we want? Do we want a kid’s AI agent to be their teacher, or do we want it to be
a tutor? Do we want it to be a companion? Do we want it to be a pet? None of the above?
The case for human-centered AI 8
That has to be thought about and designed, but we have to decide what we desire. I think we’re
still far off from really having all of that, but those are the kinds of research questions we need to
consider now. Because the technology will be there in a few years to allow these kinds of things.
Upheaval ahead for universities
Lareina Yee: James, let me ask you the contrarian question. The academic institutions you’ve
been a part of—UC Berkeley, Stanford, and Cornell—are all more than a century old, with a rich
tradition of traditional education excellence. To put it plainly, is the juice worth the squeeze,
considering how challenging AI is going to be?
James Landay: Higher education has worked, and these institutions have been successful. But
they’re not perfect, and they’ve changed in the past. The American university system was in
some ways a modified copy of the German system, which was a different version of the British
system.
So these institutions have transformed over time due to major societal and technological
changes. And I think AI is going to change the educational system because it can’t continue to
exist the way it does today, which is largely based on rote learning and certain ways of
evaluation, which is hard to do with the AI tools out there.
So that change due to AI is actually going to lead to other changes in the educational system.
And in the next five years, people are going to see a lot of upheaval. But in ten years, we will
look back and think, “Wow, we’re really educating people better than we were ten years ago.”
Lareina Yee: With all of that change, let me ask you some fun questions. I know that you enjoy
skiing, scuba diving, and many adventure sports. If you had your dream gen AI application
related to adventure sports, what would it help you do?
James Landay: Many of us have tried using gen AI to plan a vacation with some amount of
success and failure. But one of my students has a smart ski-boot insert that helps her make
better turns, with an agent that’s speaking into her ear as she’s skiing. So even while skiing, you
can have a personal coach who’s watching every turn and telling you what you need to do
better. I think for helping us get better at things we like to do, AI is going to be great.
Lareina Yee: Going way back, I read that your dissertation was one of the first to demonstrate
the use of sketching in user-interface-design tools. If you were to be a PhD student again, what
would you focus on?
James Landay: That’s interesting. Although I’m not a technical-AI expert, in that I don’t create
algorithms, going all the way back to that PhD dissertation to my research today, I’ve used AI in
the systems I’ve built probably 75 to 80 percent of the time. And with the AI capabilities we have
today, I could build them all way better.
The case for human-centered AI 9
A lot of computer science, at least PhD research, is time travel in the opposite direction. You’re
trying to imagine what something might look like in the future, simulating it with the technology
we have today but imagining it’s going to be faster, better, and cheaper.
And sometimes, we’re just too far ahead of ourselves. So in some ways, I was imagining
something in 1995 that I thought would only take five years. But it took 20 to 30 years for that
technology to become good enough to do what I was imagining at the time.
James Landay is a computer science professor at Stanford University and cofounder and codirector of the
Stanford Institute for Human-Centered Artificial Intelligence (HAI). Lareina Yee, a senior partner in McKinsey’s
Bay Area office, is the cohead of McKinsey ecosystems and alliances.
Comments and opinions expressed by interviewees are their own and do not represent or reflect the opinions,
policies, or positions of McKinsey & Company or have its endorsement.
Copyright © 2024 McKinsey & Company. All rights reserved.
The case for human-centered AI 10 |
51 | mckinsey | moving-past-gen-ais-honeymoon-phase-seven-hard-truths-for-cios-to-get-from-pilot-to-scale (1).pdf | Moving past gen AI’s honeymoon
phase: Seven hard truths for
CIOs to get from pilot to scale
Getting to scale requires CIOs to focus on fewer things but do them better.
This article is a collaborative effort by Aamer Baig, Douglas Merrill, and Megha Sinha, with Danesha Mead and
Stephen Xu, representing views from McKinsey Technology and QuantumBlack, AI by McKinsey.
© Getty Images
May 2024
The honeymoon phase of generative AI (gen AI) We explored many of the key initial technology
is over. As most organizations are learning, it is issues in a previous article.2 In this article, we want
relatively easy to build gee-whiz gen AI pilots, but to explore seven truths about scaling gen AI for the
turning them into at-scale capabilities is another “Shaper” approach, in which companies develop
story. The difficulty in making that leap goes a long a competitive advantage by connecting large
way to explaining why just 11 percent of companies language models (LLMs) to internal applications
have adopted gen AI at scale, according to our and data sources (see sidebar “Three approaches
latest tech trends research.1 to using gen AI” for more). Here are seven things
that Shapers need to know and do:
This maturing phase is a welcome development
because it gives CIOs an opportunity to turn gen 1. Eliminate the noise, and focus on the signal.
AI’s promise into business value. Yet while most Be honest about what pilots have worked.
CIOs know that pilots don’t reflect real-world Cut down on experiments. Direct your efforts
scenarios—that’s not really the point of a pilot, after toward solving important business problems.
all—they often underestimate the amount of work
that needs to be done to get gen AI production 2. It’s about how the pieces fit together, not the
ready. Ultimately, getting the full value from gen AI pieces themselves. Too much time is spent
requires companies to rewire how they work, and assessing individual components of a gen AI
putting in place a scalable technology foundation engine. Much more consequential is figuring
is a key part of that process. out how they work together securely.
1 “McKinsey Technology Trends Outlook 2024,” forthcoming on McKinsey.com.
2 “Technology’s generational moment with generative AI: A CIO and CTO guide,” McKinsey, July 11, 2023.
Three approaches to using gen AI
There are three primary approaches to take in using gen AI:
— In “Taker” use cases, companies use off-the-shelf, gen AI–powered software from third-party vendors such as GitHub
Copilot or Salesforce Einstein to achieve the goals of the use case.
— In “Shaper” use cases, companies integrate bespoke gen AI capabilities by engineering prompts, data sets, and connections
to internal systems to achieve the goals of the use case.
— In “Maker” use cases, companies create their own LLMs by building large data sets to pre-train models from scratch.
Examples include OpenAI, Anthropic, Cohere, and Mistral AI.
Most companies will turn to some combination of Taker, to quickly access a commodity service, and Shaper, to build a
proprietary capability on top of foundation models. The highest-value gen AI initiatives, however, generally rely on the Shaper
approach.1
1 For more on the three approaches, see “Technology’s generational moment with generative AI: A CIO and CTO guide,” McKinsey, July 11, 2023.
2 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
3. Get a handle on costs before they sink you. been deemed “successful,” but it was not applied
Models account for only about 15 percent to an important part of the business.
of the overall cost of gen AI applications.
Understand where the costs lurk, and apply the There are many reasons for failing to scale,
right tools and capabilities to rein them in. but the overarching one is that resources and
executive focus are spread too thinly across
4. Tame the proliferation of tools and tech. The dozens of ongoing gen AI initiatives. This is not a
proliferation of infrastructures, LLMs, and tools new development. We’ve seen a similar pattern
has made scaled rollouts unfeasible. Narrow when other technologies emerged, from cloud
down to those capabilities that best serve the to advanced analytics. The lessons from those
business, and take advantage of available innovations, however, have not stuck.
cloud services (while preserving your flexibility).
The most important decision a CIO will need to
5. Create teams that can build value, not just make is to eliminate nonperforming pilots and
models. Getting to scale requires a team with scale up those that are both technically feasible
a broad cross-section of skills to not only build and promise to address areas of the business that
models but also make sure they generate the matter while minimizing risk (Exhibit 1). The CIO will
value they’re supposed to, safely and securely. need to work closely with business unit leaders
on setting priorities and handling the technical
6. Go for the right data, not the perfect implications of their choices.
data. Targeting which data matters most and
investing in its management over time has a big
impact on how quickly you can scale. 2. It’s about how the pieces fit together,
not the pieces themselves
7. Reuse it or lose it. Reusable code can In many discussions, we hear technology leaders
increase the development speed of generative belaboring decisions around the component parts
AI use cases by 30 to 50 percent. required to deliver gen AI solutions—LLMs, APIs,
and so on. What we are learning, however, is that
solving for these individual pieces is relatively easy
1. Eliminate the noise, and focus on and integrating them is anything but. This creates
the signal a massive roadblock to scaling gen AI.
Although many business leaders acknowledge
the need to move past pilots and experiments, The challenge lies in orchestrating the range of
that isn’t always reflected in what’s happening on interactions and integrations at scale. Each use
the ground. Even as gen AI adoption increases, case often needs to access multiple models, vector
examples of its real bottom-line impact are few databases, prompt libraries, and applications
and far between. Only 15 percent of companies (Exhibit 2). Companies have to manage a variety
in our latest AI survey say they are seeing use of of sources (such as applications or databases
gen AI have meaningful impact on their companies’ in the cloud, on-premises, with a vendor, or a
EBIT.3 combination), the degree of fidelity (including
latency and resilience), and existing protocols (for
Exacerbating this issue is that leaders are drawing example, access rights). As a new component is
misleading lessons from their experiments. They added to deliver a solution, it creates a ripple effect
try to take what is essentially a chat interface pilot on all the other components in the system, adding
and shift it to an application—the classic “tech exponential complexity to the overall solution.
looking for a solution” trap. Or a pilot might have
3 That is, they attribute 5 percent or more of their organizations’ EBIT to gen AI use. McKinsey Global Survey on the state of AI in early 2024,
February 22 to March 5, 2024, forthcoming on McKinsey.com.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 3
Exhibit 1
Focus on use cases that are feasible and where business impact is clear.
Focus on use cases that are feasible and where business impact is clear.
Criteria for determining business impact and technical feasibility
Use cases Quick / high-impact wins
Category Criteria (illustrative) Second priority
High
Business Value Can we accurately quantify the value? Is it
impact creation incremental or a step function in performance?
Strategic How well does this align with or support the
alignment company’s primary strategic objectives?
Ease of Are end users enthusiastic about adopting
adoption the solution? Is there a demand for more
Business
features or capabilities?
impact
Business Are we introducing this solution at an
readiness appropriate time, considering ongoing
transformations or other projects?
Technical Data Is the data readily available, or do we need to
feasibility readiness create or synthesize it? Are there any special
considerations for handling sensitive data?
Low
Solution Does the solution require proven or nascent Low Technical High
readiness techniques? feasibility
Ability to Will the proposed business model remain
scale viable as number of users and cloud
consumption increase?
Reusability Can the components of the solution be
repurposed for other use cases?
McKinsey & Company
The key to effective orchestration is embedding The orchestration of the many interactions
the organization’s domain and workflow expertise required to deliver gen AI capabilities, however,
into the management of the step-by-step flow is impossible without effective end-to-end
and sequencing of the model, data, and system automation. “End-to-end” is the key phrase here.
interactions of an application running on a cloud Companies will often automate elements of the
foundation. The core component of an effective workflow, but the value comes only by automating
orchestration engine is an API gateway, which the entire solution, from data wrangling (cleaning
authenticates users, ensures compliance, logs and integration) and data pipeline construction to
request-and-response pairs (for example, to help model monitoring and risk review through “policy
bill teams for their usage), and routes requests to as code.” Our latest research has shown that gen
the best models, including those offered by third AI high performers are more than three times as
parties. The gateway also enables cost tracking likely as their peers to have testing and validation
and provides risk and compliance teams a way embedded in the release process for each model.4
to monitor usage in a scalable way. This gateway A modern MLOps platform is critical in helping to
capability is crucial for scale because it allows manage this automated flow and, according to
teams to operate independently while ensuring McKinsey analysis, can accelerate production by
that they follow best practices (see sidebar “Main ten times as well as enable more efficient use of
components for gen AI model orchestration”). cloud resources.
4 We define gen AI high performers as those who attribute more than 10 percent of their organizations’ EBIT to their use of gen AI.
McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
4 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
Exhibit 2
A gen AI solution needs to accommodate a complex set of integrations
A gen AI solution needs to accommodate a complex set of integrations across
across the entire tech stack.
the entire tech stack.
Illustrative tech stack with end-to-end automation Data Gen AI capabilities Cloud Models
Front-end application
User interface
Data enrichment
and processing Orchestration
Enhancing
Source data Query validation and intent routing Guardrails capabilities
Unstructured Structured Security Data Semantic Prompt LLM Conversation
data ETL¹ data ETL¹ and retrieval and engi- flow memory
access hybrid neering management
Databases (eg, control search and Prompt library
observability
vector stores)
Image Prompt
LLM agents
search enrichment
Structured Fallback External
data query runtime
search integration
Infrastructure and cloud services API gateway
Foundation models (eg, LLMs, multimodal
models, embedding generation models)
1Extract, transform, load.
McKinsey & Company
Gen AI models can produce inconsistent results, 3. Get a handle on costs before they
due to their probabilistic nature or the frequent sink you
changes to underlying models. Model versions can The sheer scale of gen AI data usage and model
be updated as often as every week, which means interactions means costs can quickly spiral out
companies can’t afford to set up their orchestration of control. Managing these costs will have a huge
capability and let it run in the background. They impact on whether CIOs can manage gen AI
need to develop hyperattentive observing and programs at scale. But understanding what drives
triaging capabilities to implement gen AI with costs is crucial to gen AI programs. The models
speed and safety. Observability tools monitor themselves, for example, account for only about 15
the gen AI application’s interactions with users percent of a typical project effort.5 LLM costs have
in real time, tracking metrics such as response dropped significantly over time and continue to
time, accuracy, and user satisfaction scores. If decline.
an application begins to generate inaccurate
or inappropriate responses, the tool alerts the CIOs should focus their energies on four realities:
development team to investigate and make any
necessary adjustments to the model parameters, — Change management is the biggest cost. Our
prompt templates, or orchestration flow. experience has shown that a good rule of thumb
for managing gen AI costs is that for every $1
5 “Generative AI in the pharmaceutical industry: Moving from hype to reality,” McKinsey, January 9, 2024.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 5
Main components for gen AI model orchestration
Orchestration is the process of coordinating various data, transformation, and AI components to manage complex AI workflows.
The API (or LLM) gateway layer serves as a secure and efficient interface between users or applications and underlying gen AI
models. The orchestration engine itself is made up of the following components:
— Prompt engineering and prompt library: Prompt engineering is the process of crafting input prompts or queries that guide
the behavior and output of AI models. A prompt library is a collection of predefined prompts that users can leverage as best
practices/shortcuts when they invoke a gen AI model.
— Context management and caching: Context management highlights background information relevant to a specific task or
interaction. Caching relates to storing previously computed results or intermediate data to accelerate future computations.
— Information retrieval (semantic search and hybrid search): Information-retrieval logic allows gen AI models to search for
and retrieve relevant information from a collection of documents or data sources.
— Evaluation and guardrails: Evaluation and guardrail tools help assess the performance, reliability, and ethical
considerations of AI models. They also provide input to governance and LLMOps. This encompasses tools and processes for
evaluating model accuracy, robustness, fairness, and safety.
spent on developing a model, you need to spend companies default to simply creating a chat
about $3 for change management. (By way of interface for a gen AI application), and second,
comparison, for digital solutions, the ratio has involving their best employees in training models
tended to be closer to $1 for development to $1 to ensure the models learn correctly and quickly.
for change management.6) Discipline in managing
the range of change actions, from training your — Run costs are greater than build costs for
people to role modeling to active performance gen AI applications. Our analysis shows that
tracking, is crucial for gen AI. Our analysis has it’s much more expensive to run models than to
shown that high performers are nearly three build them. Foundation model usage and labor
times more likely than others to have a strong are the biggest drivers of that cost. Most of
performance-management infrastructure, such the labor costs are for model and data pipeline
as key performance indicators (KPIs), to measure maintenance. In Europe, we are finding that
and track value of gen AI. They are also twice as significant costs are also incurred by risk and
likely to have trained nontechnical people well compliance management.
enough to understand the potential value and
risks associated with using gen AI at work.7 — Driving down model costs is an ongoing
process. Decisions related to how to engineer
Companies have been particularly successful in the architecture for gen AI, for example, can
handling the costs of change management by lead to cost variances of 10 to 20 times, and
focusing on two areas: first, involving end users sometimes more than that. An array of cost-
in solution development from day one (too often, reduction tools and capabilities are available,
6 Eric Lamarre, Kate Smaje, and Rodney Zemmel, “Rewired to outcompete,” McKinsey, June 20, 2023.
7 McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
6 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
such as preloading embeddings. This is analytics solutions. The goal here is to develop
not a one-off exercise. The process of cost a modeling discipline that instills an ROI focus
optimization takes time and requires multiple on every gen AI use case without getting lost in
tools, but done well, it can reduce costs from a endless rounds of analysis.
dollar a query to less than a penny (Exhibit 3).
— Investments should be tied to ROI. Not all 4. Tame the proliferation of tools
gen AI interactions need to be treated the and tech
same, and they therefore shouldn’t all cost Many teams are still pushing their own use cases
the same. A gen AI tool that responds to live and have often set up their own environments,
questions from customers, for example, is resulting in companies having to support multiple
critical to customer experience and requires infrastructures, LLMs, tools, and approaches
low-latency rates, which are more expensive. to scaling. In a recent McKinsey survey, in fact,
But code documentation tools don’t have to be respondents cited “too many platforms” as the
so responsive, so they can be run more cheaply. top technology obstacle to implementing gen AI
Cloud plays a crucial rule in driving ROI because at scale.8 The more infrastructures and tools, the
its prime source of value lies in supporting higher the complexity and cost of operations, which
business growth, especially supporting scaled in turn makes scaled rollouts unfeasible. This state
8 McKinsey survey on generative AI in operations, November 2023.
Exhibit 3
As solutions scale, organizations can optimize costs.
As solutions scale, organizations can optimize costs.
Cost per query by week,¹ $
1.0
0.8
0.6
0.4
0.2
0.0
Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Week 7 Backlog
Initial proof Add RAG,² Add intent Re-ranking Migrate from Migrate from Vendor price Batching,
of concept maxing out recognition and prompt paid GPT for risk reduction, and
prompt and routing, optimization embedding guardrails and semantic reevaluate
length reducing generation and intent cache need for
search space model to recognition to chatbot
and adding open-source open-source
LLM calls model models and
regular
expression
1Illustrative example pulling from multiple case studies.
2Retrieval-augmented generation.
McKinsey & Company
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 7
of affairs is similar to the early days of cloud and for example. But greater impact came only when
software as a service (SaaS), when accessing the other parts of the organization—such as risk and
tech was so easy—often requiring no more than a business experts—were integrated into the teams
credit card—that a “wild west” of proliferating tools along with product management and leadership.
created confusion and risk.
There are multiple archetypes for ensuring
To get to scale, companies need a manageable set this broader organizational integration. Some
of tools and infrastructures. Fair enough—but how companies have built a center of excellence to act
do you know which providers, hosts, tools, and as a clearinghouse to prioritize use cases, allocate
models to choose? The key is to not waste time on resources, and monitor performance. Other
endless rounds of analysis on decisions that don’t companies split strategic and tactical duties among
matter much (for example, the choice of LLMs is less teams. Which archetype makes sense for any
critical as they increasingly become a commodity) or given business will depend on its available talent
where there isn’t much of a choice in the first place— and local realities. But what’s crucial is that this
for example, if you have a primary cloud service centralized function enables close collaboration
provider (CSP) that has most of your data and your between technology, business, and risk leads, and
talent knows how to work with the CSP, you should is disciplined in following proven protocols for
probably choose that CSP’s gen AI offering. Major driving successful programs. Those might include,
CSPs, in fact, are rolling out new gen AI services for example, quarterly business reviews to track
that can help companies improve the economics of initiatives against specific objectives and key
some use cases and open access to new ones. How results (OKRs), and interventions to resolve issues,
well companies take advantage of these services reallocate resources, or shut down poor-performing
depends on many variables, including their own cloud initiatives.
maturity and the strength of their cloud foundations.
A critical role for this governing structure is to ensure
What does require detailed thinking is how to build that effective risk protocols are implemented and
your infrastructure and applications in a way that followed. Build teams, for example, need to map
gives you the flexibility to switch providers or models the potential risks associated with each use case;
relatively easily. Consider adopting standards widely technical and “human-in-the-loop” protocols need
used by providers (such as KFServing, a serverless to be implemented throughout the use-case life
solution for deploying gen AI models), Terraform for cycle. This oversight body also needs a mandate
infrastructure as code, and open-source LLMs. to manage gen AI risk by assessing exposures and
implementing mitigating strategies.
It’s worth emphasizing that overengineering for
flexibility eventually leads to diminishing returns. A One issue to guard against is simply managing the
plethora of solutions becomes expensive to maintain, flow of tactical use cases, especially where the
making it difficult to take full advantage of the volume is large. This central organization needs a
services providers offer. mandate to cluster related use cases to ensure large-
scale impact and drive large ideas. This team needs
to act as the guardians for value, not just managers
5. Create teams that can build value, of work.
not just models
One of the biggest issues companies are facing One financial services company put in place
is that they’re still treating gen AI as a technology clearly defined governance protocols for senior
program rather than as a broad business priority. management. A steering group, sponsored by
Past technology efforts demonstrate, however, that the CIO and chief strategy officer, focused on
creating value is never a matter of “just tech.” For gen enterprise governance, strategy, and communication,
AI to have real impact, companies have to build teams driving use-case identification and approvals. An
that can take it beyond the IT function and embed it enablement group, sponsored by the CTO, focused
into the business. Past lessons are applicable here, on decisions around data architecture, data science,
too. Agile practices sped up technical development, data engineering, and building core enabling
8 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale
capabilities. The CTO also mandated that at least engineering teams (tech sales/support teams)
one experienced architect join a use-case team developed their own version to find solutions for
early in their process to ensure the team used the unique client calls, commercialization teams had
established standards and tool sets. This oversight product descriptions, and customer support teams
and governance clarity was crucial in helping the had a set of specific product details to answer
business go from managing just five to more than queries. As each team updated its version of the
50 use cases in its pipeline. product information, conflicts emerged, making
it difficult for gen AI models to use the data. To
address this issue, the company is putting all
6. Go for the right data, not the relevant product information in one place.
perfect data
Misconceptions that gen AI can simply sweep up
7. Reuse it or lose it
the necessary data and make sense of it are still
widely held. But high-performing gen AI solutions Reusable code can increase the development
are simply not possible without clean and accurate speed of generative AI use cases by 30 to 50
data, which requires real work and focus. The percent.9 But in their haste to make meaningful
companies that invest in the data foundations to breakthroughs, teams often focus on individual use
generate good data aim their efforts carefully. cases, which sinks any hope for scale. CIOs need to
shift the business’s energies to building transversal
Take the process of labeling, which often oscillates solutions that can serve many use cases. In fact, we
between seeking perfection for all data and have found that gen AI high performers are almost
complete neglect. We have found that investing in three times as likely as their peers to have gen
targeted labeling—particularly for the data used for AI foundations built strategically to enable reuse
retrieval-augmented generation (RAG)—can have a across solutions.10
significant impact on the quality of answers to gen
AI queries. Similarly, it’s critical to invest the time to In committing to reusability, however, it is easy to
grade the importance of content sources (“authority get caught in building abstract gen AI capabilities
weighting”), which helps the model understand the that don’t get used, even though, technically, it
relative value of different sources. Getting this right would be easy to do so. A more effective way to
requires significant human oversight from people build up reusable assets is to do a disciplined
with relevant expertise. review of a set of use cases, typically three to five,
to ascertain their common needs or functions.
Because gen AI models are so unstable, companies Teams can then build these common elements
need to maintain their platforms as new data is as assets or modules that can be easily reused or
added, which happens often and can affect how strung together to create a new capability. Data
models perform. This is made vastly more difficult preprocessing and ingestion, for example, could
at most companies because related data lives in include a data-chunking mechanism, a structured
so many different places. Companies that have data-and-metadata loader, and a data transformer
invested in creating data products are ahead of as distinct modules. One European bank reviewed
the game because they have a well-organized data which of its capabilities could be used in a wide
source to use in training models over time. array of cases and invested in developing a
synthesizer module, a translator module, and a
At a materials science product company, for sentiment analysis module.
example, various teams accessed product
information, but each one had a different version. CIOs can’t expect this to happen organically. They
R&D had materials safety sheets, application need to assign a role, such as the platform owner,
9 Eric Lamarre, Alex Singla, Alexander Sukharevsky, and Rodney Zemmel, “A generative AI reset: Rewiring to turn potential into value in 2024,”
McKinsey, March 4, 2024.
10 McKinsey Global Survey on the state of AI in early 2024, February 22 to March 5, 2024, forthcoming on McKinsey.com.
Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale 9
Exhibit 4
A gen AI platform team needs an array of skills.
A gen AI platform team needs an array of skills.
Cross-functional platform team DataOps: Manages and optimizes the data pipeline, ensuring the
roles and skills availability and quality of data; supports training and deployment of
gen AI models
Site reliability engineer: Ensures reliability, availability, and perfor-
mance of software systems and applications
Data DataOps DevOps engineer: Establishes the CI/CD¹ pipeline and other auto-
engineer
mation needed for teams to rapidly develop and deploy code (eg,
chatbot, APIs) to production
Site
Data reliability Cloud architect: Ensures scalability, security, and cost optimization
scientist engineer of the cloud infrastructure; designs data storage and management
systems; facilitates integration and deployment of the AI models
Platform
Solution/data architect: Develops creative and efficient solutions
Full- team using engineering practices and software/web development
stack DevOps technologies
developer engineer
Platform owner: Acts like a product owner, oversees the build of a
gen AI platform
Full-stack developer: Writes clean and quality scalable code (eg,
Platform Cloud front-end/back-end APIs) that can be easily deployed with CI/CD¹
owner Solution/ architect p ipelines
data Data scientist: Fine-tunes foundational models to help
architect RAG²-based approach, ensures alignment of LLM outputs with
responsible AI guidelines
Data engineer: Architects data models to ingest data into vector
databases, creates and maintains automated pipelines, performs
closed-loop testing to validate responses and improve performance
1Continuous integration (CI) and continuous delivery (CD).
2Retrieval-augmented generation.
McKinsey & Company
and a cross-functional team with a mandate to The value gen AI could generate is
develop reusable assets for product teams transformational. But capturing the full extent of
(Exhibit 4), which can include approved tools, that value will come only when companies harness
code, and frameworks. gen AI at scale. That requires CIOs to not just
acknowledge hard truths but be ready to act on
them to lead their business forward.
Aamer Baig is a senior partner in McKinsey’s Chicago office, Douglas Merrill is a partner in the Southern California office,
Megha Sinha is a partner in the Bay Area office, Danesha Mead is a consultant in the Denver office, and Stephen Xu is
director of product management in the Toronto office.
The authors wish to thank Mani Gopalakrishnan, Mark Gu, Ankur Jain, Rahil Jogani, and Asin Tavakoli for their contributions
to this article.
Copyright © 2024 McKinsey & Company. All rights reserved.
10 Moving past gen AI’s honeymoon phase: Seven hard truths for CIOs to get from pilot to scale |
52 | mckinsey | strategic-alliances-for-gen-ai-how-to-build-them-and-make-them-work.pdf | McKinsey Digital Practice
Strategic alliances for gen
AI: How to build them and
make them work
Strategic alliances are a must for companies looking to build value from generative
AI. But approaching them like traditional vendor arrangements won’t work.
This article is a collaborative effort by Alex Singla, Alexander Sukharevsky, Ben Ellencweig, and Guilherme Cruz, with Carlo
Palermo and Joshan Cherian Abraham, representing views from QuantumBlack, AI by McKinsey, and McKinsey Digital.
May 2024
Generative AI’s (gen AI) transformative potential solutions will work with other components in a
promises to revolutionize business and propel up to company’s gen AI ecosystem.
$4.4 trillion in economic impact annually.
Unprecedented adoption rates from companies 3. Stay in control of your destiny. It is important to
across industries and sectors, as well as significant strike a balance between building on a
private investment, underscore this potential. provider’s capabilities and becoming overly
dependent on them. That means investing in a
Capturing the value from technology, however, is flexible infrastructure, monitoring provider
never just about the tech alone. Companies looking performance continually, and tying
to move beyond running gen AI experiments will compensation to outcomes while being clear
need to rewire how they work to achieve the full about intellectual property (IP) boundaries.
value of their efforts. One key component of this
rewiring is developing strategic alliances1 with gen
Go deeper on collaboration
AI providers. The unique challenges of working with
gen AI—from the lack of experience that many have As many companies are learning, the “build versus
in using the technology to gen AI’s instability and buy” approach to creating gen AI capabilities falls
risk to the technology’s rapid pace of change—have short when it comes to harnessing gen AI’s full
made collaborations increasingly vital. potential. Building solutions entirely in-house can
be time consuming and resource intensive,
While many companies are already working to some especially given the lack of gen AI talent at most
degree with gen AI providers, outdated notions of companies.2 And while buying existing gen AI
what to look for in a provider and how strategic products or services can provide quick access to
alliances should function are putting these efforts proven solutions, these solutions often require
at risk. To make the most of strategic alliances, experienced gen AI workers to customize them to
companies should focus on three areas: what the business really needs.
1. Go deeper on collaboration. Working with Collaborating with providers, on the other hand, can
providers on gen AI programs requires offer significant benefits in terms of access to the
a greater degree of trust and collaboration latest capabilities and expertise, development
than has been necessary with traditional speed, and tailored solutions. But effective
vendors, with thoughtful transparency, strategic gen AI alliances work differently from
frequent communications, and explicit traditional vendor relationships. The technology is
alignment across planning, development, and still rapidly maturing, implementation is complex,
ongoing management. and stability issues bedevil solutions, requiring
closer collaboration and higher degrees of trust.
2. Zero in on providers who provide scalability, Sharing data to fine-tune models, for example, can
interoperability, and reusability. No single happen only if client companies trust strategic allies
provider can offer companies everything they to protect it effectively. Similarly, the complexity of
need. Achieving scale with a range of providers addressing root cause issues in AI models, many of
means understanding not only how well which are not yet fully stable, necessitates both
providers can scale but also how well their clear lines of communication and alignment on
1 A strategic alliance typically has broad and long-term impact on corporate performance and valuation, often formed to create a competitive
advantage for the partners in their respective markets. Not all alliances need to be strategic; alliances can be established to achieve highly
operational or tactical objectives and can include working with large hyperscale providers or more niche organizations. (This definition is adapted
from the one created by the Association of Strategic Alliance Professionals. For more, see “Alliance management definitions,” Association of
Strategic Alliance Professionals, accessed May 6, 2024.)
2 “The state of AI in 2023: Generative AI’s breakout year,” McKinsey, August 1, 2023.
Strategic alliances for gen AI: How to build them and make them work 2
resolution protocols. This level of trust and This collaboration was instrumental in allowing
collaboration should be established on three the resulting model to surface the most
essential building blocks: appropriate products, even for complex or
ambiguous queries, with over 99 percent
— Cocreation of solutions. For most companies, accuracy. Early results indicate the solution could
the greatest value from gen AI will come from yield a 10 to 20 percent improvement in
adopting established capabilities, which the conversion rate from product discovery
providers offer, and tailoring these capabilities to purchase, a significant leap for the
to companies’ unique data. This requires a luxury industry.
highly iterative and collaborative process where
the company and provider work closely — Joint planning. It is essential for the gen AI
together to source and prepare the right data, provider to offer visibility into its product road
engineer relevant prompts, fine-tune models map, including upcoming features and
based on specific use case needs, and test and capabilities, and possibly grant access to alpha
iterate on the models in the field. To manage or beta releases. This allows the client company
the range of providers a company might need to both to anticipate how the provider’s offerings
work with, it will be important to institute might evolve to meet the company’s own future
frequent touchpoints to share updates, discuss needs and to possibly influence the direction of
challenges, and align on priorities across the road map. The road map can also be
providers. Dedicating time for in-person aligned when the company shares its strategic
workshops and co-innovation sessions, goals and relevant customer insights to
celebrating milestones, and sharing learnings help the provider better understand the
openly during this process is also critical for company’s needs.
building trust.
This level of communication and coordination is
When a luxury retail company, for instance, particularly important given that companies will
partnered with a gen AI provider to create a likely be working with different gen AI models
personalized product recommendation system, and applications—often developed by different
the company shared its vast catalog of product providers—that need to be closely integrated
information, including detailed specifications, for a solution to work well. Potential benefits of
features, and customer reviews. The company providing clarity and transparency include
also provided valuable insights into the nuances helping various vendors align their road maps
of customer preferences and behaviors, such as and identify dependencies (for example,
how they pose queries. This helped the provider between multiple models that need to work
engineer relevant prompts, fine-tune the gen AI together to deliver a specific gen AI solution).
models to understand and interpret this One area where we’ve seen big dividends is
domain-specific data, and comprehend the investing significant time together up
specific language, terminology, and attributes front—often meeting every couple of days for
used to describe luxury products. two to four weeks—to work out a mutual road
Strategic alliances for gen AI: How to build them and make them work 3
map and system dependencies. The output from — Risk and investment sharing. Gen AI programs
this effort should include a primary project plan often require sizable investments in specialized
that captures milestones and dependencies hardware, large-scale data acquisition and
between providers so the client company can tagging, and extensive computational resources
better manage and coordinate all parties. for model training. In addition, the risks
associated with adopting gen AI capabilities—
One leading technology company adopted this from hallucinating models to privacy issues—
approach. It engaged in joint planning sessions require close attention. For these reasons,
with its gen AI providers to identify high-impact companies should consider how best to distribute
use cases to strengthen its core product. The among providers financial, technological, and
company shared valuable customer analytics operational resources and risks associated with
insights and outlined its long-term vision for AI- gen AI development. Companies and providers,
driven innovation, which helped the gen AI for example, should be explicit in defining
providers develop a more aligned road map. For specific risks associated with the gen AI project,
their part, the gen AI providers offered early such as data privacy breaches, model biases, or
access to new gen AI features and models, IP infringement. These agreements will ideally
allowing the company to test and provide outline each party’s responsibilities for mitigating
feedback before general release. Through these and managing these risks, as well as any
collaborative-planning efforts and continual financial or legal liabilities.
communication about road map needs and
adjustments, the company was able to reduce The same technology company mentioned earlier
time to market for deploying at-scale solutions. shared risks with their gen AI providers by
For instance, it launched a personalized structuring contracts around outcomes instead
marketing campaign powered by gen AI of token usage. This approach allowed the
within six months of starting the strategic company to manage uncertainties and costs
alliance, resulting in a significant boost while aligning incentives and fostering a shared
in sales conversions. commitment to success.
Strategic alliances for gen AI: How to build them and make them work 4
Zero in on providers that offer a 50 percent increase in user queries over six
scalability, interoperability, and months without degradation. Providers should
reusability also be willing to regularly review and adjust
milestones and contracts to ensure alignment
A single provider that can provide all the best
with evolving goals.
components for an effective gen AI solution doesn’t
exist, at least not yet. The variety of components
and models needed to work together across — Reusability. Reusing code can accelerate the
the tech stack means that companies will need development of gen AI use cases by 30 to
to team up with a curated network of specialized 50 percent, so it’s critical that providers offer
tech providers. solutions that can be easily repurposed across
multiple projects.5 Companies should therefore
In developing an ecosystem of providers that can look for providers that offer flexible, modular
scale, the component parts working together are components and pretrained models (such as
more important than the parts individually. customizable natural-language-processing
Companies need to weigh those criteria that enable modules or configurable data pipelines that can
the overall gen AI system to work most effectively. be fine-tuned and adapted to various contexts.
Selecting the right providers has become They should also seek providers that offer tools
particularly challenging given the growth in the and frameworks (for example, intuitive APIs and
provider landscape. In fact, since the launch of software development kits for integrating and
ChatGPT in November 2022, the number of open- extending gen AI components or drag-and-drop
source large language models (LLMs) and interfaces for model fine-tuning) that can
commercial LLMs has quadrupled.3 Furthermore, enable the easy customization and extension
there are currently more than 1,000 AI vendors, of solutions.
with more than 600 new products introduced over
the previous year, mostly spurred by gen AI.4 To — Interoperability. Interoperability between
that end, companies should zero in on three key models and components is crucial for creating
criteria when selecting providers: a cohesive, efficient, and scalable gen AI
ecosystem. When evaluating model or solution
— Scalability. Given the mind-boggling scale of interoperability, companies should look for
gen AI—from the amount of data needed to providers that adhere to industry standards and
train and fine-tune models to the number of best practices for data exchange, API design,
queries models respond to—providers should and software development (for example,
have a proven track record of handling standard data formats such as Apache Avro and
increased volumes of complex traffic and user JavaScript Object Notation, established machine
queries without compromising performance. learning frameworks like PyTorch, or data
Companies should pressure test pilot programs, governance standards). Providers should use
which often do not replicate live conditions and widely adopted programming languages, offer
are typically not a good barometer for scaling well-documented and easy-to-use APIs, and
readiness. When evaluating scalability, it is support smooth integration with the company’s
important to look for providers that can commit data sources, applications, and platforms.
to specific milestones, such as handling
3 Sources included press search, Stanford University’s HELM (Holistic Evaluation of Language Models) leaderboard, and McKinsey analysis.
4 Maria Korolov, “Weighing risk and reward with gen AI vendor selection,” CIO, January 3, 2024.
5 Eric Lamarre, Alex Singla, Alexander Sukharevsky, and Rodney Zemmel, “A generative AI reset: Rewiring to turn potential into value in 2024,”
McKinsey Quarterly, March 4, 2024.
Strategic alliances for gen AI: How to build them and make them work 5
These three criteria are crucial for selecting gen AI should ensure that providers include proper
providers that can scale, but companies should also documentation and sufficient transparency
ensure that all providers meet a high bar on other during development. Robust monitoring and
criteria, such as ethical guidelines and adherence to testing capabilities are needed to track provider
local privacy and tech sovereignty regulations. performance and identify issues early (for
Establishing and aligning around clear data example, automated reporting capabilities to
governance and security protocols can go a long collect and aggregate relevant metrics, including
way toward building trust with providers. model inputs and outputs, latency and
throughput statistics, and user feedback). It’s
important to regularly conduct end-to-end tests
Stay in control of your destiny of the gen AI solution—from data ingestion to
model outputs—so as to track performance and
Finding the sweet spot between forging close
identify the source of a problem across the
strategic alliances and maintaining agency over the
provider ecosystem. Experience has shown
broader direction and vision of these collaborations
that involving all providers in establishing
presents a critical challenge for organizations.
a comprehensive testing strategy (joint
Companies looking to maintain independence and
integration testing and scenario testing, for
control of their destiny would do well to consider
instance) helps to set clear expectations
the following guidelines:
and responsibilities.
— Establish a flexible infrastructure. A flexible,
scalable gen AI infrastructure can serve as a — Establish clear IP boundaries. Difficult
foundation for quickly integrating different questions about IP are still being worked
providers. This “chassis” could be a centralized through with respect to gen AI, so it is important
platform or a set of well-defined APIs, to establish clear boundaries up front.
integration protocols, and data formats that Companies should specify, for example, the
enable different gen AI components to work existing IP that each party brings to the
together seamlessly. To ensure maximum collaboration, such as proprietary data sets,
flexibility, companies can adopt MLOps algorithms, or models. They should define how
(machine learning operations) best practices, IP that is created during the collaboration (for
such as containerization, automated testing, example, any patents, copyrights, or trade
and continuous-integration and continuous- secrets) will be owned and managed, including
delivery (CI/CD) pipelines. These practices help predefined terms for licensing, commercialization,
ensure the reliability and performance of the and revenue sharing. And they should outline a
gen AI stack and allow for rapid rollback of process for tracking and attributing individual
changes if issues arise. contributions to the codeveloped IP, which can
help prevent disputes and ensure proper
— Continually monitor model performance. recognition of each party’s contributions. Being
Companies need to maintain a clear transparent and assuring alignment during this
understanding of what providers are building to process can also help build trust.
avoid receiving a “black box” solution. They
Strategic alliances for gen AI: How to build them and make them work 6
— Tie compensation to outcomes. While following guidelines for assessing scalability, reusability,
best practices on contract structure (for and interoperability, as well as templates for
instance, including clear KPIs, service level contracts, service-level agreements, and
agreements, and licensing arrangements) and performance dashboards.
specifying risk-sharing provisions, it is critical to
tie a provider’s compensation to measurable
— Conduct a strategic gen-AI-alliance audit to
outcomes such as model accuracy, uptime, and
assess current strategic alliances and identify
user satisfaction. Companies should avoid
gaps, redundancies, or misalignments with the
minimum spend requirements and include clear
gen AI strategy. Determine which strategic
exit clauses and data portability requirements to
alliances to maintain, expand, or phase out
avoid limiting flexibility.
based on their potential to spur business value.
— Assign dedicated relationship managers to the
Getting started
gen AI alliance. The managers should have a
As the transformative potential of gen AI continues solid understanding of gen AI technologies,
to unfold, companies should act decisively to architectures, and best practices so they can
position themselves for success in this new era. To effectively communicate with providers, assess
get started, executives can consider the following their capabilities, and ensure alignment with the
actions: company’s technical requirements. They also
oversee the entire gen AI ecosystem and act as
— Establish a steering committee made up of key the “central authority” to help coordinate
stakeholders from business, IT, legal, and activities among providers, monitor progress,
procurement to oversee the gen-AI-alliance and resolve issues. In many cases, it will be
strategy. The committee should be tasked with useful to have a solution architect on board, as
defining strategic-alliance criteria, setting well as to regularly meet with providers to
performance metrics, and establishing understand exactly what they are doing and
governance guidelines. To do so, the team how they are progressing.
needs sufficient autonomy to make decisions
within strategic guidelines.
Building trust and fostering collaboration are just as
— Develop a strategic gen-AI-alliance playbook important as choosing the right technology.
that includes a standardized framework for Companies should start small, learn fast, and iterate
evaluating, onboarding, and managing new gen often to ensure that they are well on their way to
AI providers. This framework should include unlocking the full potential of gen AI.
Alex Singla is a senior partner in McKinsey’s Chicago office; Alexander Sukharevsky is a senior partner in the London office;
Ben Ellencweig is a senior partner in the Stamford, Connecticut, office; and Guilherme Cruz is a partner in the New York
office, where Carlo Palermo is a consultant and Joshan Cherian Abraham is an associate partner
The authors wish to thank Aaron Kovar, Doruk Caner, and Matias Navarro Crespo for their contributions to this article.
Copyright © 2024 McKinsey & Company. All rights reserved.
Strategic alliances for gen AI: How to build them and make them work 7 |
53 | mckinsey | scaling-gen-ai-in-the-life-sciences-industry.pdf | Life Sciences Practice
Scaling gen AI in the
life sciences industry
Gen AI pilots have shown promise, but for the technology to deliver
transformational business value in the life sciences industry,
organizations need to rethink how they scale it.
by Chaitanya Adabala Viswa, Dandi Zhu, Delphine Zurkiya, and Joachim Bleys
January 2025
Back in July 2023, researchers at the McKinsey Global Institute estimated that gen AI could
unlock between $60 billion and $110 billion a year in economic value for the pharmaceutical and
medical products industries, boosting productivity and innovation in domains across the
industry’s value chain—from the way new treatments are discovered to how they are marketed
and administered by physicians. Six months later, McKinsey experts dug deeper into those
numbers, uncovering more than 20 use cases with the greatest potential for near-term impact.
Now, with gen AI use cases proliferating across the business community, we decided to find out
how much progress life science organizations have made in capturing this value. In late summer
2024, we surveyed more than 100 pharma and medtech leaders responsible for driving their
organizations’ gen AI efforts. All respondents report having experimented with gen AI, and 32
percent say they have taken steps to scale the technology. But only 5 percent say they have
realized gen AI as a competitive differentiator that generates consistent and significant financial
value (Exhibit 1). Nonetheless, companies remain optimistic about gen AI, with more than two-
thirds of respondents saying they plan to significantly increase investment in the technology
(Exhibit 2).
Exhibit 1
Scaling gen AI in the life sciences industry 2
Exhibit 2
Why do so many life science organizations struggle to realize results from their gen AI
deployments? And what are the minority of top performers doing differently? This article reveals
the most common pitfalls life science companies are facing—and offers solutions that can help
organizations move from pilot purgatory to driving real business value at scale.
The key challenges to scaling gen AI in life sciences
Based on our survey and our experience, we have identified five key areas that pose challenges
for life science companies attempting to realize company-wide value from gen AI: gen AI
strategy, talent planning, operating model and governance structure, change management, and
risk (Exhibit 3).
Scaling gen AI in the life sciences industry 3
Exhibit 3
Challenge 1: Ambiguous, shortsighted, or nonexistent enterprise gen AI strategy
About 75 percent of respondents say that their organizations lack a comprehensive vision for
gen AI or an intentionally designed, strategic road map with clearly defined success measures
linked to business priorities. Instead, they tend to proceed in a decentralized manner, use case
by use case. This instinct to capture short-term value through experimentation, coupled with the
federated/function-led structure of many life science organizations, explains many of the
challenges organizations encounter when it comes to scaling.
McKinsey research has found that digital transformations seldom succeed unless C-suite
leaders are aligned around a business-led road map. Without an intentional strategic posture
toward gen AI—whether a top-down mandate or a coordinated enterprise road map driven by a
center of excellence—individual business units are left to navigate the ever-evolving technology
landscape on their own, pursuing a multitude of new use case ideas that, no matter how
compelling, often fail to add up to a strategy that delivers actual value.
Scaling gen AI in the life sciences industry 4
Challenge 2: Lack of talent planning and upskilling
At most life science companies, the existing pool of tech talent presents a traditional tool kit for
IT, data science, and product development. Unfortunately, traditional approaches to tech talent
are unable to deliver the quality and performance of enterprise-grade solutions needed for gen
AI, for example, agent-based architecture, model validation, large language model (LLM)
operations, and the fine-tuning of models. But only 6 percent of survey respondents report
having conducted a skills-based talent assessment to determine how to evolve their talent
strategy into one that considers gen AI priorities.
Prompt engineering has emerged as a key gap, especially for more complex gen AI applications.
One life science company, for example, was attempting to use gen AI to draft regulatory
documents, only to discover that prompt engineers required a unique combination of regulatory
domain knowledge and engineering rigor to craft scalable prompts that generate submission-
ready output—a specialized necessity that made the role especially challenging to fill.
Challenge 3: Loosely defined operating model and governance
One common challenge leaders face is creating the right operating model for gen AI
transformation, often choosing between one of two extremes. At one end of the spectrum is a
highly decentralized approach, in which the organization simultaneously launches multiple use
case pilots. While this allows companies to move fast, it also leads to quality, cost, and
sustainability challenges and creates operational silos that inhibit the sharing of knowledge and
the ability to capture cost synergies. At the opposite end is a top-down approach, with
centralized decision-making and a phased rollout of use cases. This approach can be slow and
often frustrating, destroying momentum.
One company swung between the two. It began its gen AI efforts by launching 1,500 different
use cases. When that proved unwieldy, company leaders imposed a top-down governance
structure that led to a different set of issues, constricting the innovation pipeline with projects
requiring an arduous approval process that stretched some two to three months.
Challenge 4: Underestimating the process rewiring required to drive scale
To succeed with gen AI, companies must integrate the technology across complex workflows to
promote adoption and impact—a reality that highlights the need for effective change
management. McKinsey has found that 70 percent of digital transformations fail not because of
technical issues but because leaders ignored the importance of managing change. In fact, for
every $1 spent on technology, $5 is required for change management to successfully drive
capability building, adoption, buy-in, and value capture over time.
One company launched a center of excellence function to initiate a broad gen AI platform for a
range of use cases but failed to communicate a compelling change story to accompany those
initiatives. That failure, coupled with the lack of holistic, end-to-end planning and thinking,
resulted in a collection of gen AI tools that almost no one ended up using.
Scaling gen AI in the life sciences industry 5
Challenge 5: Inadequate understanding of risk
Gen AI introduces unique risks, from hallucinations and accuracy to bias and intellectual
property protection. But 35 percent of survey respondents report that they spend fewer than
ten hours with their risk counterparts, limiting the degree of collaboration with these crucial
functions. This dynamic needs to evolve to scale gen AI. Successful scaling requires business
leaders, technology teams, and risk management professionals to communicate from the outset;
the absence of such collaboration can lead to issues being raised late in the game, when they
are much more difficult to fix, or a lack of adherence to the risk and compliance guardrails that
are critical to building trust in the organization.
One company, for example, spent several months developing an external-facing gen AI solution,
only to be forced to withdraw the launch due to a lack of alignment with its digital, medical, and
legal teams—which raised significant risk issues after the tool had been developed. This resulted
in a severe setback for the gen AI team’s agenda, morale, and momentum.
The solution: A five-point plan to realize value from gen AI
Successfully scaling gen AI and capturing its value potential requires more than just a
technological rollout. An effective gen AI strategy is fundamentally different from traditional tech
projects. Given the rapid pace of innovation, a gen AI strategy must be dynamic, scenario driven,
and focused on how to engage with the broader ecosystem. Scaling gen AI involves
comprehensive change across the organization, encompassing strategy, talent, governance,
and risk management.
Based on our experience, we have identified five key strategies to move from gen AI use cases
to enterprise-wide adoption. These actions ensure that organizations not only experiment with
the technology but also fully integrate it into their operations to drive measurable business
value.
— Adopt a domain-driven approach. Successful AI strategy cannot be based on a slew of
disconnected use cases, which often leads to fragmented efforts and missed opportunities.
Instead, the focus must shift to domain-driven transformations, where gen AI is applied to
fundamentally reshape critical areas of the business, such as the commercial, medical, or
R&D domains. Thirty-eight percent of the life science organizations surveyed cite research
as their leading strategic priority in their gen AI journey, followed by the commercial domain,
at 28 percent (Exhibit 4).
This domain-driven approach ensures that gen AI isn’t just another tech solution but a core
enabler of business transformation. Rather than focusing on technology for technology’s
sake, organizations that prioritize domain transformations are better positioned to capture
Scaling gen AI in the life sciences industry 6
the full value of AI. Crucially, there is no such thing as a stand-alone gen AI strategy. The real
focus should be on deploying gen AI to support broader business objectives, drive strategic
goals, and create differentiation in the market. Organizations that view the technology
through this business-first lens have found greater success in scaling AI initiatives.
Exhibit 4
Scaling gen AI in the life sciences industry 7
— AI transformation encompasses more than just tech. Scaling gen AI isn’t simply a matter of
implementing a new technology; it’s about rewiring the organization’s operating model and
culture to support new AI-driven ways of working. This extends to talent strategies: the
workforce must evolve beyond traditional IT data science roles to include new skills—AI
engineering, large language model fine-tuning, and business translation—to bridge the gap
between technical execution and business value capture. Without a comprehensive talent
realignment, organizations will be less successful in scaling their gen AI efforts. Further, gen
AI implementation needs to drive measurable value. This requires a clear up-front
agreement on how value will be captured, say, through acceleration of time to market,
productivity increase, or improved probability of success.
One life sciences company, for instance, launched an enterprise talent upskilling and planning
program, with targeted initiatives for business and technical roles. The program also
introduced dedicated gen-AI-focused leadership roles in critical functions to drive sustained
organizational change. With the appropriate talent—and leadership—in place, the company’s
gen AI initiatives proceeded much more smoothly than they would have otherwise.
— Adopt an ecosystem approach. In the rapidly evolving AI ecosystem, an externally focused
partnership strategy is critical. Given the speed at which AI technologies and methodologies
are advancing, life sciences organizations should consider cultivating a network of low-cost,
high-optionality partnerships. These partnerships can provide flexibility and give
organizations the ability to quickly pivot and seize opportunities as they arise. Organizations
should also establish clear “triggers” that indicate when it’s time to move from exploratory
partnerships to larger strategic bets. This ensures that the business remains agile and can
scale up or shift its AI investments based on real-time insights and market movements.
Engaging with the broader ecosystem—including academia, tech, and venture capital—is also
essential to staying on top of the latest developments. Relying solely on internal capabilities
is no longer enough to stay competitive in AI. A dynamic, externally focused lens ensures
that companies stay ahead of the curve and capture the full value of gen AI innovations.
— Deploy a platform-driven approach from the outset. A platform-driven approach is key to
ensuring that gen AI initiatives are scalable, sustainable, and reusable across various
business domains. A scalable AI platform allows organizations to standardize infrastructure,
data pipelines, and development processes, ensuring that each new use case builds on the
previous one. This can also help reduce duplication of effort, encourage collaboration across
business units, and foster consistency in AI performance across the organization. Moreover,
Scaling gen AI in the life sciences industry 8
a platform-driven approach ensures that AI models are not developed in isolation but are
integrated into a unified framework, allowing them to be adapted and reused across various
business domains. This not only reduces costs but also accelerates time to value, as insights
from one domain can be applied to another.
One life sciences company found success by adhering to a mantra: “Slow down to speed up.”
The company spent three months defining a detailed blueprint for insights and document
platforms. This enabled the reuse of components within each platform, enabling rapid
scaling across use cases.
— Embed risk management in the full product development life cycle. One of the common
mistakes organizations make with gen AI is treating risk management as an afterthought or
as an obstacle to innovation. In fact, risk management must be embedded throughout the
entire AI product life cycle. Gen AI introduces unique risks—such as hallucinations, bias, data
security, and intellectual property issues—which require careful oversight.
To ensure these risks are managed effectively, business leaders and risk and compliance
functions should collaborate regularly. Organizations should establish clear governance
frameworks early on and ensure that ethical guidelines are in place to address concerns about
AI fairness, transparency, and accountability.
Given the high regulatory requirements in life sciences, organizations should place greater
emphasis on risk management. One organization proactively identified the guardrails necessary
to address evolving regulations (for example, the EU AI Act) and technology limitations (for
example, the probabilistic nature of models). The organization established clear, responsible AI
requirements, including mandatory observability, validation protocols, and human-in-the-loop
guidelines, which were defined prior to the start of product development.
What a holistic transformation can look like
What does a successful gen AI initiative look like? Consider one life sciences company that
recognized the gen AI opportunity early and embarked on a holistic transformation across
domains. Company leaders convened a C-level task force to steer the overall gen AI strategy,
set up governing bodies across the R&D, commercial, medical, and operations domains, and
asked each domain to prioritize one use case with high-value potential for C-level sponsorship.
The company then ran proofs of concept with an eye toward scaling, using its early experiences
to organize reusable components into domain-specific platforms. The technology and business
Scaling gen AI in the life sciences industry 9
teams partnered from the outset, ensuring that all gen AI solutions addressed priority business
needs and helped drive the process changes needed to spark adoption and deliver value.
In the meantime, the company engaged ecosystem partners to bring in learnings and assets
from across the life sciences industry and beyond and built stage gates to focus resources on
partnered solutions that were ready to scale across therapeutic areas and geographies.
Leaders shaped a compelling change story focused on how gen AI solutions were intended to
augment rather than replace employees, for example, by helping them deal with increasing
workloads, and used change management teams to help drive a successful rollout. They
provided white-glove support for initial users and deployed these early adopters as change
ambassadors to build bottom-up momentum. Impact metrics were defined, tracked, and
reviewed at regular governance meetings to ensure gen AI initiatives remained on track to scale
and deliver business impact.
This kind of experience does not have to be an outlier. Leaders of life science organizations
should understand that capturing the potentially transformative value of gen AI requires more
than experimentation and individual use case deployment. It demands strategic integration into
the organizational fabric. In the next chapter of the gen AI story, organizations should take an
intentional approach to driving alignment with business strategy, scalability, and sustainability.
This pivotal moment is an opportunity for life sciences leaders to lead transformative change,
revolutionizing drug discovery and patient care, as well as driving meaningful bottom-line
results.
Chaitanya Adabala Viswa is a partner in McKinsey’s Boston office, where Delphine Zurkiya is a senior partner;
Dandi Zhu is a partner in the New York office; and Joachim Bleys is a senior partner in the Carolinas office.
The authors wish to thank Abhi Mukherjee, Lionel Jin, Natalia Dorogi, Nitisha Sharma, and Vasu Macherla for their
contributions to this article.
This article was edited by Larry Kanter, a senior editor in the New York office.
Copyright © 2025 McKinsey & Company. All rights reserved.
Scaling gen AI in the life sciences industry 10 |
54 | mckinsey | fortune-or-fiction-final-v3.pdf | Consumer Packaged Goods Practice
Fortune or fiction? The real
value of a digital and AI
transformation in CPG
A new McKinsey analysis quantifies the impact that digital and AI can have
on consumer goods businesses and where consumer-packaged-goods
executives should focus their efforts.
This article is a collaborative effort by Jessica Moulton, Rob Cain, and Roger Roberts, with Hannah Mayer and
Spurthi Gummadala, representing views from McKinsey’s Digital and Consumer Packaged Goods Practices.
October 2024
The narrative surrounding generative AI (gen AI), technology, media, and telecommunications. This
a moon shot, once-in-a-generation innovation, may be because leaders lack answers to questions
is that it could utterly reinvent how businesses— such as, “How much value will AI eventually create
consumer-packaged-goods (CPG) companies in CPG?” and “Where in the value chain will the value
among them—are run. be concentrated?”
CPG leaders are heeding the call. In a 2024 survey We sought fact-based answers to these questions
of CPG leaders,1 71 percent said they adopted AI in at to help CPGs figure out where to focus and how
least one business function of their organizations fast to move.
(up from 42 percent in 2023), while 56 percent said
they were regularly using gen AI. We found that the highest-impact investment
areas vary, depending on which subsector a CPG
However, no CPG player has truly scaled its gen AI company plays in. Our findings can help CPG
and traditional AI capabilities. So far, CPG leaders leaders determine their next moves in digital and AI
have reported adopting gen AI at a lower rate than (outlined in our article, “What it takes to rewire
other industries, such as advanced industries or a CPG company to outcompete in digital and AI”).
Quantifying the effects across
About the research the CPG value chain
After conducting a rigorous company-specific
Over the past two years, McKinsey has researched more than quantitative analysis of more than 140 use cases and
140 digital and AI use cases across the consumer packaged goods dozens of expert interviews (see sidebar, “About
(CPG) value chain to quantify the value at stake in each of the seven the research”), we have aggregated subsector-
value streams. After identifying use cases, we determined how each specific estimates to determine the value that CPG
one affects the profit-and-loss (P&L) statement for a standardized1 companies in the three major subsectors—food
CPG business. For example, we observed that use cases related to and beverage, personal care and home, and
trade promotion optimization could lead to reduced selling, general, beauty—can generate by committing to digital and
and administrative expenses, as well as growth in net revenue, both AI investments. (In this article, “digital and AI”
of which act together to expand operating margins. refers to all use cases across digital, analytics,
machine learning, traditional AI, and generative AI.)
We then simulated the effect on the P&L line items under conservative We quantified the value at stake in the main parts
and optimistic scenarios, based on a variety of assumptions about the of the CPG value chain: the core functions (including
ease of implementation and the pace of adoption. Every CPG subsector back-office support functions) and six innovation
will be affected differently by a digital and AI transformation, given the zones, as shown in Exhibit 1. Together, the core
different set of opportunities seen, for example, in beauty categories functions and the innovation zones make up a CPG
compared with grocery. Finally, we determined the cumulative impact company’s seven major value streams.
of these use cases for a composite CPG business to understand the
full value at stake. Enterprise and support functions, such as human
resources and finance departments, will surely
benefit from the use of new digital tools, and
1 To create a “standardized” CPG business, we identified a pool of players within each
CPG subsector, analyzed their P&Ls, and aggregated these results to create a sector partnerships and an ecosystem strategy can enable
composite that reflects the cost mix and performance of the subsector.
a CPG company to thrive (they can do this in
collaboration with suppliers and channel partners).
1 McKinsey Global Survey on AI, February 22–March 5, 2024; n = 63 CPG leaders.
Fortune or fiction? The real value of a digital and AI transformation in CPG 2
Web <2023>
<ECxPhGiDbiigti t1al>
Exhibit <1> of <5>
A digital transformation in consumer packaged goods should take place
across the entire value chain and with ecosystem partners.
Areas for digital Media and data partners
transformation
Consumer insights and
Value chain ecosystem: demand shaping
Rei
C
U
wn ov
n
ite
-
l
hoin
n
c
pt
n
k a
b
o
rno
v
tneau ewtn
e
r
d sina sr ii ge hs
ts Fulfillment
partn Die rr es
c ct ot no sumer
Enterprise-
i n n oP
v
ar o tid ou
nctI n ag nr
de
di
e nt p art
n
er
s
resource-planning-
Innovation zones:
based core
Put data to work
Enable agility Order to cash
Drive decision making Procure to pay
C d
C fuo
nrM t Sceo
it
o
m
a
ii onv
n
pe nn
d
l
io sf
f
r v
s
yo a um t pio pi nn os ri tght u st o m er
a n d
cc hh aa n nn ne el
l
mC
p
au
a
rs
n
tt
a
no
gm
ee mr ea nn
td
SuppH
aly
nir de
c h
lt oo
a gi
nr ie
s
pt ti ilr cae
snning
Manufact
our pi en rg
a
Ctia oon nn trs
act
manufacturers
Rationalize er
s
Modernize Logistics partners
McKinsey & Company
But the most significant value an organization will This domain can further benefit from generative AI
get from a digital and AI transformation happens in (gen AI) applications. We’ve already seen this
the six innovation zones. technology have an effect on CPG companies.
One beverage player, for instance, used gen AI to
Consider the product and innovation domain, where create prompts, images, and concepts that
digital and AI tools can be leveraged throughout informed product development, reducing the time
the entire cycle: social listening powered by natural- to introduce a new product to market by 60 percent.
language processing, feedback mining, and After conducting a gen-AI-powered sentiment
consumer-backed predictive trend sourcing can analysis based on customers’ online posts, the
lead to new product ideas or product improvements. team generated insights to understand how
AI can suggest new formulations for existing customers felt about the products that gen AI
products, while advanced analytics can improve helped to develop. The company’s gen AI efforts
packaging design. Automated, collaborative have yielded a portfolio of new products and
testing and experimentation can make launching experiences that have helped fuel growth and
a new product easier. expand market share.
Fortune or fiction? The real value of a digital and AI transformation in CPG 3
Our latest research estimates that gen AI use cases One notable exception is the beauty industry,
could increase the economic impact of traditional where the direct-to-consumer value stream takes
AI by 15 to 40 percent, unlocking an additional center stage. This reflects beauty companies’
$160 billion to $270 billion annually in profit ability to take advantage of their unique relationship
(measured by EBITDA) for CPG companies globally. with consumers and cater directly to their
That said, although gen AI is dazzling the business shoppers. Digitally enabled beauty companies
world and setting the media ablaze, it’s merely the can leverage new technologies to enhance
proverbial cherry on top: traditional AI’s potential the consumer experience, the e-commerce
impact is 2.5 to 7.0 times higher than that of gen AI. process, and fulfillment management.
This means that companies should invest in a broad
spectrum of AI capabilities and platforms to realize In the six domains, cooperation with ecosystem
a digital transformation’s full potential. partners unlocks the next level of value. Much of this
comes down to a data exchange with ecosystem
While the potential effects of digital and AI will partners, such as retailers, manufacturers, logistics
vary across CPG sectors, our analysis shows that providers, and media partners. CPG companies
the greatest value for most sectors is concentrated have historically been unable to collect and activate
most heavily in two value streams: consumer personalized, first-party data at scale. This lack of
insights and demand shaping and customer and data means they must decide either to rely on their
channel management (Exhibit 2). partners for third-party data or to invest in ways to
Web <2023>
<ECxPhGiDbiigti t2al>
Exhibit <2> of <5>
In consumer packaged goods, digital and AI could have the greatest impact
on consumer insights and customer and channel management innovation.
Distribution of digital and AI effects across innovation zones, %
2 2 1
Core
11
18
30
Direct to
consumer
30
23
Customer and
channel management
25 7
100% Supply chain
14 4
planning and logistics
10
11 Manufacturing
15
3 and operations
7
8 Product and
37 innovation
23
19 Consumer insights
and demand shaping
Food and Beauty Personal care,
beverage home, and
personal health
Note: Figures may not sum to 100%, because of rounding.
McKinsey & Company
Fortune or fiction? The real value of a digital and AI transformation in CPG 4
acquire “zero party” and first-party data. This data and $1.6 billion, driven by both top-line growth and
is key to being able to deliver the right message productivity gains (Exhibit 3). This translates into an
to the right customer at the right moment. CPG EBITDA margin increase of approximately seven to
companies must also invest in the right technology 13 percentage points for food and beverage players.
to enable the data exchange among ecosystem
partners. Adopting the cloud here can help. The largest potential impact—valued between
approximately $230 million and $470 million—lies in
customer and channel management, as food and
The value at stake in three beverage companies continually seek to optimize
CPG subsectors their presence across online and offline retailers.
Consider the effect that digital transformations
Specifically, retail trade promotions, which can
could have on the following types of CPG companies.
account for as much as 20 percent of revenue for
The three illustrative examples below offer case
a food and beverage company, are particularly
studies on how to realize these gains.
ripe for digital and analytics optimization. Retailers
typically have data about past promotion
Food and beverage companies can seize the
performance but may not have the tools to synthesize
customer and channel management opportunity
the data to build a clear picture of how to target
For a food and beverage company with $10.0 billion
promotions. Digital and analytics tools can leverage
in revenue, the value at stake from implementing
historical promotion and stock data to inform the
digital and AI successfully and comprehensively
extent and timing of future promotions. Because
across the full value chain is between $810.0 million
Web <2023>
E<CxPhGibDiigti t3al>
Exhibit <3> of <5>
A food and beverage company could mine half of its value from a digital and
AI transformation of the customer and channel management innovation zone.
Distribution of total value at stake across the full value chain,¹ $ million
230–470
A sample food and beverage player
with revenue of $10.0 billion could see
a value at stake of between
$810.0 million and $1.6 billion across
its full value chain
160–300
140–230
110–210
80–170
70–130
20–30
Consumer Product and Manufacturing Supply chain Customer Direct to Core
insights and innovation and operations planning and channel consumer
demand shaping and logistics management
1Numbers rounded to nearest $10 million.
McKinsey & Company
Fortune or fiction? The real value of a digital and AI transformation in CPG 5
updating and synthesizing data without advanced The personal-care market can be difficult to
analytics and AI tools can be expensive, navigate because businesses tend to offer frequent,
using these tools can help food and beverage widely varying promotions with high discounts,
companies reduce costs while simultaneously which can be inefficient. For this reason, enhanced
improving performance. consumer profiling (often referred to as “consumer
360”) can help to reduce this inefficiency. Supported
In personal care and home, consumer insights by AI, enhanced consumer profiling can help
and demand-shaping optimization can add to analyze the attributes, attitudes, and behaviors
billions of dollars in value consumers demonstrate. This allows the company
For one personal care and home brand with to construct granular, dynamic consumer profiles
$10.0 billion in revenue, the value at stake for a that inform how to target those consumers with
digital transformation is between approximately greater accuracy and efficiency.
$1.0 billion and $1.8 billion (Exhibit 4). This translates
into an EBITDA margin increase of approximately For instance, one personal-care player needed to
nine to 16 percentage points for personal care and increase EBITDA and decrease inventories. By
home players. Among the seven value streams, investing in its digital and AI suite, the company was
the consumer insights and demand-shaping domain able to incorporate internal and external data to
represents the biggest potential impact. improve forecast accuracy by 13 percent, decrease
Web <2023>
E<CxPhGibDiigti t4al>
Exhibit <4> of <5>
Consumer insights and demand is the innovation zone with the most value
at stake in an AI transformation for personal care and home brands.
Distribution of total value at stake across the full value chain,¹ $ million
380–680
A sample personal care and home
player with revenue of $10.0 billion
could see a value at stake of between
$1.0 billion–$1.8 billion across its full
value chain
200–420
190–340
110–180
60–120
50–70
10–20
Consumer Product and Manufacturing Supply chain Customer Direct to Core
insights and innovation and operations planning and channel consumer
demand shaping and logistics management
1Numbers rounded to nearest $10 million.
McKinsey & Company
Fortune or fiction? The real value of a digital and AI transformation in CPG 6
product shortages by 40 percent, and decrease beauty apps (which include virtual try-on tools)
inventory by 35 percent. By incorporating data and personalized product recommendations, both
about who consumers are, what they buy, where of which can increase sales. When it comes
they buy, and why they buy, companies can to personalization, AI-powered recommendation
gain better insights to inform decisions across engines use data about customers from various
messaging, branding, assortment, product touchpoints such as mobile, website, and
upgrades, new markets, and innovation. in the store to improve product search and
product suggestions.
Beauty brands have an opportunity to leverage
their direct-to-consumer advantage One beauty brand, for example, leveraged AI
A beauty brand with $3 billion in revenue could to launch a personalized lipstick-on-demand for
see between approximately $290 million its customers. The company developed an
and $500 million in added value from a digital AI-powered, at-home system that can recognize
transformation across its value chain. This color from any picture and prepare a lipstick
translates into an EBITDA margin increase of based on that color.
approximately eight to 14 percentage points
for beauty players (Exhibit 5). Consumers expect personalized brand experiences,
including at the time that they discover a product,
Nearly a third of this value can be mined from the buy it, and even after they make a purchase. Beauty
direct-to-consumer (DTC) value stream. Within DTC, brands that use advanced digital tools can integrate
AI has enabled use cases such as AI-powered data from multiple sources, including social media,
Web <2023>
E<CxPhGibDiigti t5al>
Exhibit <5> of <5>
Beauty brands can take advantage of their relationship with consumers by
using digital and AI to transform their direct-to-consumer channel.
Distribution of total value at stake across the full value chain,¹ $ million
90–150
A sample beauty player with revenue
of $3 billion could see a value at stake
of between $290 million– 70–120
60–110 $500 million across its full
value chain
30–50
20–40
5–10 5–10
Consumer Product and Manufacturing Supply chain Customer Direct to Core
insights and innovation and operations planning and channel consumer
demand shaping and logistics management
1Numbers rounded to nearest $10 million.
McKinsey & Company
Fortune or fiction? The real value of a digital and AI transformation in CPG 7
search engines, and hyperlocal data on consumer Consumer goods players will need to home in on
Find more content like this on the
behavior, to target consumers more accurately and the six innovation zones and prioritize the plays that
McKinsey Insights App
in ways they will be receptive to. best serve their business. Keep in mind: the full
impact of this transformation, one that will create
One beauty brand invested in developing unique competitive distance from challengers, will not
customer profiles through automated data come with a piecemeal approach.
clustering, a technique that helps to inform machine
learning models, to better identify and cater to “Rewired” companies, as we call them, take an all-
specific customers. This initiation not only better hands-on-deck approach across commercial,
met customer needs but also helped expedite operational, and support domains. This includes
Scan • Download • Personalize
the rollout of new marketing campaigns with faster, creating a digital road map, empowering talent,
targeted A/B testing. rethinking the CPG operating model, developing
and acquiring new technological tools, and building
out the data products necessary to implement
and scale their digital transformation.
CPG companies have an opportunity to take
advantage of a five- to 15-percentage-point impact Although in its earliest days, the next great
on EBITDA margins, which our analysis indicates technological revolution is here. The fruits of the
is on the table from digital transformations across revolution may take a while to ripen, but putting
their value chains. As alluring as those wins may their potential to work now will create more long-
be, they won’t come without a long-term, large- term value than could ever be contained within
scale, and iterative effort. a single earnings statement.
Jessica Moulton is a senior partner in McKinsey’s London office; Rob Cain is a partner in the Minneapolis office;
Roger Roberts is a partner in the Bay Area office, where Hannah Mayer is an associate partner; and Spurthi Gummadala
is an associate partner in the Seattle office.
The authors wish to thank Abhigna Antani, Monica Avakian, Miquel Ferrer, Warren Teichner, and Tim Usmanov for their
contributions to this article.
This article was edited by Alexandra Mondalek, an editor in the New York office.
Designed by McKinsey Global Publishing
Copyright © 2024 McKinsey & Company. All rights reserved.
Fortune or fiction? The real value of a digital and AI transformation in CPG 8 |
55 | mckinsey | superagency-in-the-workplace-empowering-people-to-unlock-ais-full-potential-v4.pdf | Superagency
in the Workplace
Empowering people to unlock AI’s full potential
Hannah Mayer
Lareina Yee
Michael Chui
Roger Roberts
January 2025
Contents
Introduction 2
Chapters:
1. An innovation as powerful as the steam engine 5
2. Employees are ready for AI; now leaders must step up 11
3. Delivering speed and safety 18
4. Embracing bigger ambitions 26
5. Technology is not the barrier to scale 35
Conclusion: Meeting the AI future 40
Acknowledgments 42
Methodology 43
Glossary 44
Introduction
Almost all companies invest in AI, but just 1 percent believe they are at
maturity. Our research finds the biggest barrier to scaling is not
employees—who are ready—but leaders, who are not steering fast enough.
A
rtificial intelligence has arrived in the workplace and has the potential to be as transformative
as the steam engine was to the 19th-century Industrial Revolution.1 With powerful and capable
large language models (LLMs) developed by Anthropic, Cohere, Google, Meta, Mistral, OpenAI,
and others, we have entered a new information technology era. McKinsey research sizes the
long-term AI opportunity at $4.4 trillion in added productivity growth potential from corporate use cases.2
Therein lies the challenge: the long-term potential of AI is great, but the short-term returns are unclear. Over
the next three years, 92 percent of companies plan to increase their AI investments. But while nearly all
companies are investing in AI, only 1 percent of leaders call their companies “mature” on the deployment
spectrum, meaning that AI is fully integrated into workflows and drives substantial business outcomes. The
big question is how business leaders can deploy capital and steer their organizations closer to AI maturity.
This research report, prompted by Reid Hoffman’s book Superagency: What Could Possibly Go Right with
Our AI Future,3 asks a similar question: How can companies harness AI to amplify human agency and unlock
new levels of creativity and productivity in the workplace? AI could drive enormous positive and disruptive
change. This transformation will take some time, but leaders must not be dissuaded. Instead, they must
advance boldly today to avoid becoming uncompetitive tomorrow. The history of major economic and
technological shifts shows that such moments can define the rise and fall of companies. Over 40 years ago,
the internet was born. Since then, companies including Alphabet, Amazon, Apple, Meta, and Microsoft have
attained trillion-dollar market capitalizations. Even more profoundly, the internet changed the anatomy of
work and access to information. AI now is like the internet many years ago: The risk for business leaders is
not thinking too big, but rather too small.
1 “Gen AI: A cognitive industrial revolution,” McKinsey, June 7, 2024.
2 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
3 Reid Hoffman and Greg Beato, Superagency: What Could Possibly Go Right with Our AI Future, Authors Equity, January 2025.
2 Superagency in the workplace: Empowering people to unlock AI’s full potential
Superagency: By the numbers
Employees are more ready for the change than their leaders imagine
3× 1.4×
more employees are using gen AI more likely for millennials to report
for a third or more of their work extensive familiarity with gen AI tools
than their leaders imagine; than peers in other age groups;
more than 70% of all employees they are also 1.2× more
believe that within 2 years gen AI will likely to expect workflows
change 30% or more of their work to change within a year
Companies need to move fast—employees trust their
leaders to balance speed and safety
of the C-suite say their companies are more likely for employees to trust their
47% 1.3×
developing gen AI tools too slowly, even though own companies to get gen AI deployment right
69% started investing more than a year ago than they are to trust other institutions
Companies are investing in gen AI but have not yet achieved maturity
92% 1%
of companies plan believe their
to invest more investments have
in gen AI over the reached maturity
next 3 years
Leaders need to recognize their responsibility in driving gen AI transformation
2.4× 48%
more likely for C-suite to cite employee readiness as of employees rank training as the
a barrier to adoption vs their own issues with leadership most important factor for gen AI adoption;
alignment, despite employees currently using yet nearly half feel they are receiving
gen AI 3× more than leaders expect moderate or less support
Superagency in the workplace: Empowering people to unlock AI’s full potential 3
This report explores companies’ technology and business readiness for AI adoption (see sidebar “About the
survey”). It concludes that employees are ready for AI. The biggest barrier to success is leadership.
Chapter 1 looks at the rapid advancement of technology over the past two years and its implications for
business adoption of AI.
Chapter 2 delves into the attitudes and perceptions of employees and leaders. Our research shows that
employees are more ready for AI than their leaders imagine. In fact, they are already using AI on a regular
basis; are three times more likely than leaders realize to believe that AI will replace 30 percent of their work
in the next year; and are eager to gain AI skills. Still, AI optimists are only a slight majority in the workplace; a
large minority (41 percent) are more apprehensive and will need additional support. This is where millennials,
who are the most familiar with AI and are often in managerial roles, can be strong advocates for change.
Chapter 3 looks at the need for speed and safety in AI deployment. While leaders and employees want to
move faster, trust and safety are top concerns. About half of employees worry about AI inaccuracy and
cybersecurity risks. That said, employees express greater confidence that their own companies, versus
other organizations, will get AI right. The onus is on business leaders to prove them right, by making bold and
responsible decisions.
Chapter 4 examines how companies risk losing ground in the AI race if leaders do not set bold goals. As the
hype around AI subsides, companies should put a heightened focus on practical applications that empower
employees in their daily jobs. These applications can create competitive moats and generate measurable
ROI. Across industries, functions, and geographies, companies that invest strategically can go beyond using
AI to drive incremental value and instead create transformative change.
Chapter 5 looks at what is required for leaders to set their teams up for success with AI. The challenge of AI
in the workplace is not a technology challenge. It is a business challenge that calls upon leaders to align
teams, address AI headwinds, and rewire their companies for change.
About the survey
To create our report, we surveyed 3,613 employees (managers and independent contributors) and 238
C-level executives in October and November 2024. Of these, 81 percent came from the United States,
and the rest came from five other countries: Australia, India, New Zealand, Singapore, and the United
Kingdom. The employees spanned many roles, including business development, finance, marketing,
product management, sales, and technology.
All the survey findings discussed in the report, aside from two sidebars presenting international nuances,
pertain solely to US workplaces. The findings are organized in this way because the responses from US
employees and C-suite executives provide statistically significant conclusions about the US workplace.
Analyzing global findings separately allows a comparison of differences between US responses and
those from other regions.
4 Superagency in the workplace: Empowering people to unlock AI’s full potential
1
An innovation as
powerful as the
steam engine
About the survey ‘ Scientific discoveries and technological
innovations are stones in the cathedral
of human progress.’
– Reid Hoffman, cofounder of LinkedIn and Inflection AI,
partner at Greylock Partners, and author
Superagency in the workplace: Empowering people to unlock AI’s full potential 5
I
magine a world where machines not only perform physical labor but also think, learn, and make
autonomous decisions. This world includes humans in the loop, bringing people and machines together
in a state of superagency that increases personal productivity and creativity (see sidebar “AI
superagency”). This is the transformative potential of AI, a technology with a potential impact poised to
surpass even the biggest innovations of the past, from the printing press to the automobile. AI does not just
automate tasks but goes further by automating cognitive functions. Unlike any invention before, AI-powered
software can adapt, plan, guide—and even make—decisions. That’s why AI can be a catalyst for
unprecedented economic growth and societal change in virtually every aspect of life. It will reshape
our interaction with technology and with one another.
Many breakthrough technologies, including the internet, smartphones, and cloud computing, have
transformed the way we live and work. AI stands out from these inventions because it offers more than
access to information. It can summarize, code, reason, engage in a dialogue, and make choices. AI can lower
skill barriers, helping more people acquire proficiency in more fields, in any language and at any time. AI
holds the potential to shift the way people access and use knowledge. The result will be more efficient and
effective problem solving, enabling innovation that benefits everyone.
Over the past two years, AI has advanced in leaps and bounds, and enterprise-level adoption has
accelerated due to lower costs and greater access to capabilities. Many notable AI innovations have
emerged (Exhibit 1). For example, we have seen a rapid expansion of context windows, or the short-term
memory of LLMs. The larger a context window, the more information an LLM can process at once. To
illustrate, Google’s Gemini 1.5 could process one million tokens in February 2024, while its Gemini 1.5 Pro
could process two million tokens by June of that same year.4 Overall, we see five big innovations for business
that are driving the next wave of impact: enhanced intelligence and reasoning capabilities, agentic AI,
multimodality, improved hardware innovation and computational power, and increased transparency.
AI superagency
What impact will AI have on humanity? Reid Hoffman and Greg Beato’s book Superagency: What
Could Possibly Go Right with Our AI Future (Authors Equity, January 2025) explores this question.
The book highlights how AI could enhance human agency and heighten our potential. It envisions a
human-led, future-forward approach to AI.
Superagency, a term coined by Hoffman, describes a state where individuals, empowered by AI, super-
charge their creativity, productivity, and positive impact. Even those not directly engaging with AI can
benefit from its broader effects on knowledge, efficiency, and innovation.
AI is the latest in a series of transformative supertools, including the steam engine, internet, and
smartphone, that have reshaped our world by amplifying human capabilities. Like its predecessors, AI
can democratize access to knowledge and automate tasks, assuming humans can develop and deploy
it safely and equitably.
4 The Keyword, “Our next-generation model: Gemini 1.5,” blog entry by Sundar Pichai and Demis Hassabis, Google, February 15, 2024; Google
for Developers, “Gemini 1.5 Pro 2M context window, code execution capabilities, and Gemma 2 are available today,” blog entry by Logan
Kilpatrick, Shrestha Basu Mallick, and Ronen Kofman, June 27, 2024.
6 Superagency in the workplace: Empowering people to unlock AI’s full potential
Web <2025>
<Superagency>
Exhibit 1
Exhibit <1> of <21>
Gen AI capabilities have evolved rapidly over the past two years.
Illustrative capabilities of gen AI platforms from select frontier labs, nonexhaustive
2022–231 Jan 20252
Anthropic
Google
Gemini
Meta
Microsoft
OpenAI
AI superagency
Note: Exhibit is not intended as an evaluation or comparison but as an illustration of the rapid progress in capabilities.
1Initial models released between Mar 2022 and Mar 2023.
2Latest models released between Nov and Dec 2024.
Source: Company websites and press releases; McKinsey analysis
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 7
Intelligence and reasoning are improving
AI is becoming far more intelligent. One indicator is the performance of LLMs on standardized tests.
OpenAI’s Chat GPT-3.5, introduced in 2022, demonstrated strong performance on high-school-level exams
(for example, scoring in the 70th percentile on the SAT math and the 87th percentile on the SAT verbal
sections). However, it often struggled with broader reasoning. Today’s models are near the intelligence level
of people who hold advanced degrees. GPT-4 can so easily pass the Uniform Bar Examination that it would
rank in the top 10 percent of test takers,5 and it can answer 90 percent of questions correctly on the US
Medical Licensing Examination.6
The advent of reasoning capabilities represents the next big leap forward for AI. Reasoning enhances AI’s
capacity for complex decision making, allowing models to move beyond basic comprehension to nuanced
understanding and the ability to create step-by-step plans to achieve goals. For businesses, this means they
can fine-tune reasoning models and integrate them with domain-specific knowledge to deliver actionable
insights with greater accuracy. Models such as OpenAI’s o1 or Google’s Gemini 2.0 Flash Thinking Mode
are capable of reasoning in their responses, which gives users a human-like thought partner for their
interactions, not just an information retrieval and synthesis engine.7
Agentic AI is acting autonomously
The ability to reason is growing more and more, allowing models to autonomously take actions and complete
complex tasks across workflows. This is a profound step forward. As an example, in 2023, an AI bot could
support call center representatives by synthesizing and summarizing large volumes of data—including voice
messages, text, and technical specifications—to suggest responses to customer queries. In 2025, an AI
agent can converse with a customer and plan the actions it will take afterward—for example, processing a
payment, checking for fraud, and completing a shipping action.
‘I’ve always thought of AI as the most
profound technology humanity is
working on . . . more profound than fire
or electricity or anything that we’ve
done in the past.’
– Sundar Pichai, CEO of Alphabet
5 GPT-4 technical report, OpenAI, March 27, 2023.
6 Dana Brin, Vera Sorin, Akhil Vaid, et al., “Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments,” Scientific Reports,
October 1, 2023.
7 “Learning to reason with LLMs,” OpenAI, September 12, 2024; “Gemini 2.09 Flash Thinking Mode,” Google, January 21, 2025.
8 Superagency in the workplace: Empowering people to unlock AI’s full potential
‘AI, like most transformative technologies,
grows gradually, then arrives suddenly.’
– Reid Hoffman, cofounder of LinkedIn and Inflection AI,
partner at Greylock Partners, and author
Software companies are embedding agentic AI capabilities into their core products. For example,
Salesforce’s Agentforce is a new layer on its existing platform that enables users to easily build and
deploy autonomous AI agents to handle complex tasks across workflows, such as simulating product
launches and orchestrating marketing campaigns.8 Marc Benioff, Salesforce cofounder, chair, and CEO,
describes this as providing a “digital workforce” where humans and automated agents work together to
achieve customer outcomes.9
Multimodality is bringing together text, audio, and video
Today’s AI models are evolving toward more advanced and diverse data processing capabilities across text,
audio, and video. Over the last two years, we have seen improvements in the quality of each modality. For
example, Google’s Gemini Live has improved audio quality and latency and can now deliver a human-like
conversation with emotional nuance and expressiveness.10 Also, demonstrations of Sora by OpenAI show its
ability to translate text to video.11
Hardware innovation is enhancing performance
Hardware innovation and the resulting increase in compute power continue to enhance AI performance.
Specialized chips allow faster, larger, and more versatile models. Enterprises can now adopt AI solutions that
require high processing power, enabling real-time applications and opportunities for scalability. For
example, an e-commerce company could significantly improve customer service by implementing AI-driven
chatbots that leverage advanced graphics processing units (GPUs) and tensor processing units (TPUs).
Using distributed cloud computing, the company could ensure optimal performance during peak traffic
periods. Integrating edge hardware, the company could deploy models that analyze photos of damaged
products to more accurately process insurance claims.
8 Sammy Spiegel, “The future of AI agents: Top predictions and trends to watch in 2025,” Salesforce, December 2024.
9 Marc Benioff, “How the rise of new digital workers will lead to an unlimited age,” Time, November 25, 2024.
10 Ivan Solovyev and Shrestha Basu Mallick, “Gemini 2.0: Level up your apps with real-time multimodal interactions,” Google, December 23, 2024.
11 “OpenAI releases AI video generator Sora but limits how it depicts people,” Associated Press, December 10, 2024.
Superagency in the workplace: Empowering people to unlock AI’s full potential 9
2
Transparency is increasing
AI is gradually becoming less risky, but it still lacks greater transparency and explainability. Both are critical
for improving AI safety and reducing the potential for bias, which are imperative for widescale enterprise
deployment. There is still a long way to go, but new models and iterations are rapidly improving. Stanford
University’s Center for Research on Foundation Models (CRFM) reports significant advances in model
performance. Its Transparency Index, which uses a scale of 1 to 100, shows that Anthropic’s transparency
score increased by 15 points to 51 and Amazon’s more than tripled to 41 between October 2023 and
May 2024.12
Beyond LLMs, other forms of AI and machine learning (ML) are improving explainability, allowing the outputs
of models that support consequential decisions (for example, credit risk assessment) to be traced back to
the data that informed them. In this way, critical systems can be tested and monitored on a near-constant
basis for bias and other everyday harms that arise from model drift and shifting data inputs, which happens
even in systems that were well calibrated before deployment.
All of this is crucial for detecting errors and ensuring compliance with regulations and company policies.
Companies have improved explainability practices and built necessary checks and balances, but they must
be prepared to evolve continuously to keep up with growing model capabilities.
Achieving AI superagency in the workplace is not simply about mastering technology. It is every bit as much
about supporting people, creating processes, and managing governance. The next chapters explore the
nontechnological factors that will help shape the deployment of AI in the workplace.
12 “The Foundation Model Transparency Index,” Stanford Center for Research on Foundation Models, May 2024.
10 Superagency in the workplace: Empowering people to unlock AI’s full potential
2
Employees are ready
for AI; now leaders
must step up
‘People are using [AI] to create amazing
things. If we could see what each of us
can do 10 or 20 years in the future, it
would astonish us today.’
– Sam Altman, cofounder and CEO of OpenAI
Superagency in the workplace: Empowering people to unlock AI’s full potential 11
E
mployees will be the ones to make their organizations AI powerhouses. They are more ready to
embrace AI in the workplace than business leaders imagine. They are more familiar with AI tools,
they want more support and training, and they are more likely to believe AI will replace at least a
third of their work in the near future. Now it’s imperative that leaders step up. They have more
permission space than they realize, so it’s on them to be bold and capture the value of AI. Now.
Beyond the tipping point
In our survey, nearly all employees (94 percent) and C-suite leaders (99 percent) report having some level of
familiarity with gen AI tools. Nevertheless, business leaders underestimate how extensively their employees
are using gen AI. C-suite leaders estimate that only 4 percent of employees use gen AI for at least 30
percent of their daily work, when in fact that percentage is three times greater, as self-reported by
employees (Exhibit 2). And while only a total of 20 percent of leaders believe employees will use gen AI for
more than 30 percent of their daily tasks within a year, employees are twice as likely (47 percent) to believe
they will (see sidebar “Who is using AI at work? Nearly everyone, even skeptical employees”).
The good news is that our survey suggests three ways companies can accelerate AI adoption and move
toward AI maturity.
Web <2025>
<ESxuhpeibraigt e2ncy>
Exhibit <2> of <21>
Employees are three times more likely to be using gen AI today than their
leaders expect.
US employees’ and C-suite’s C-suite Employees
timeline for employees using Already using 4
3×
gen AI for >30% of daily tasks, % 13
of respondents Less than a year 16
34
1–5 years 56
37
Over 5 years 11
5
Don’t anticipate it 10 7
Not sure 3 4
Note: Figures may not sum to 100%, because of rounding.
Source: McKinsey US CxO survey, Oct–Nov 2024 (n = 118) ; McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
12 Superagency in the workplace: Empowering people to unlock AI’s full potential
Our research looked at people who self-identify as “Zoomers,” “Bloomers,” “Gloomers,” and “Doomers” in their
attitudes toward AI—a set of archetypes introduced in Superagency. We find that 39 percent of employees
identify as Bloomers, who are AI optimists that want to collaborate with their companies to create responsible
solutions. Meanwhile, 37 percent identify as Gloomers, who are more skeptical about AI and want extensive
top-down AI regulations; 20 percent identify as Zoomers, who want AI to be quickly deployed with few guardrails;
and just 4 percent identify as Doomers, who have a fundamentally negative view of AI (exhibit).
Even those with a skeptical take on AI are familiar with it; 94 percent of Gloomers and 71 percent of Doomers say
they have some familiarity with gen AI tools. Furthermore, approximately 80 percent of Gloomers and about half
of Doomers say they are comfortable using gen AI at work.
Web <2025>
<Superagency>
Exhibit
Exhibit <3> of <21>
Employee segments differ, but all indicate a high familiarity with gen AI.
US employee sentiment on gen AI, by archetype, % of respondents
Doomer Gloomer Bloomer Zoomer
Gen AI will not align Above all else, gen AI Gen AI needs to be Gen AI development
with human values, needs to be closely developed iteratively should be trusted
regardless of monitored and with a diverse range to developers to
deployment method controlled of inputs maximize speed
Has extensive
familiarity
with gen AI1 16 42 55 67
Has at least
some familiarity
with gen AI2 71 94 96 96
Is comfortable using
results from gen AI 47 79 91 91
Believes gen AI will
have a net benefit in
the next 5 years 54 82 89 87
Plans to use gen AI
more in their
personal life 49 77 86 85
Expects 30% of
workflows to change
in the next year 19 38 50 64
Share of respondents
4 37 39 20
in archetype group, %
1Defined as those who have “extensive experience (use several tools for complex tasks)” and “experts.”
2Defined as those who have “some familiarity (use 1–2 tools a few times)” and “extensive experience (use several tools for complex tasks)” and “experts.”
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 13
Leaders can invest more in their employees
As noted at the beginning of this chapter, employees anticipate AI will have a dramatic impact on their work.
Now they would like their companies to invest in the training that will help them succeed. Nearly half of
employees in our survey say they want more formal training and believe it is the best way to boost AI
adoption. They also would like access to AI tools in the form of betas or pilots, and they indicate that
incentives such as financial rewards and recognition can improve uptake.
Yet employees are not getting the training and support they need. More than a fifth report that they have
received minimal to no support (Exhibit 3). Outside the United States, employees also want more training
(see sidebar “Global perspectives on training”).
Web <2025>
<ESxuhpeibraigt e3ncy>
Exhibit <4> of <21>
Employees long for more support and training on gen AI.
Share of US employees agreeing that a company initiative would make them more likely to
increase day-to-day usage of gen AI tools, %
Formal gen AI training from
48
my organization
Seamless integration into my
45
existing workflow
Access to gen AI tools 41
Incentives and rewards 40
Usage of gen AI being a requirement
30
for a certification program
Explicit instructions from my managers
30
to use gen AI
Being involved in the development
29
of the tools
OKRs¹/KPIs tied to gen AI usage 22
US employees’ perceived level of support for gen AI capability building at their organizations,
% of respondents
Not None/ Moderate to Fully
needed minimal significant supported
Current 6 22 44 29
In 3 years 4 10 56 31
Note: Figures do not sum to 100%, because of rounding.
¹Objectives and key results.
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
14 Superagency in the workplace: Empowering people to unlock AI’s full potential
Global perspectives on training
To get a clearer picture of global AI adoption trends, we looked at trends across five countries: Australia, India, New
Zealand, Singapore, and the United Kingdom. Broadly speaking, these employees and C-suite leaders—the “interna-
tional” group in this report—have similar views of AI as their US peers. In some key areas, however, including the topic
of training, their experiences differ.
Web <2025>
<Superagency>
Exhibit <5> of <21>
Many international employees are concerned about insufficient training, even though they report receiving far more
support than US employees. Some 84 percent of international employees say they receive significant or full organiza-
tional support to learn AI skills, versus just over half of US employees. International employees also have more
opportunities to participate in developing gen AI tools at work than their US counterparts, with differences of at least
ten percentage points in activities such as providing feedback, beta testing, and requesting specific features (exhibit).
Exhibit
International employees get more encouragement to use gen AI tools.
Sources encouraging employees’ use of gen AI tools at work, % of respondents reporting practice in
place at their organization
Australia and New Zealand India Singapore UK US
0 20 40 60 80 100
Use is mandated
Manager
Manager other than own
Peers
C-suite leadership
Developer of AI tool
Generic communications
Have not been encouraged
Employee involvement in developing gen AI tools, % of respondents
Australia and New Zealand India Singapore UK US
0 20 40 60 80 100
Provide feedback
in tool itself
Provide feedback via
other channels
Beta testing or
pilot program
Submit specific requests
for features
Not involved
Source: McKinsey international employee survey, Oct–Nov 2024 (Australia and New Zealand, n = 139; India, n = 134; Singapore, n = 140; UK, n = 201) ; McKinsey
US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Superagency in the workplace: Empowering people to unlock AI’s full potential 15
C-suite leaders can help millennials lead the way
Many millennials aged 35 to 44 are managers and team leaders in their companies. In our survey, they self-
report having the most experience and enthusiasm about AI, making them natural champions of
transformational change. Millennials are the most active generation of AI users. Some 62 percent of 35- to
44-year-old employees report high levels of expertise with AI, compared with 50 percent of 18- to 24-year-
old Gen Zers and 22 percent of baby boomers over 65 (Exhibit 4). By tapping into that enthusiasm and
expertise, leaders can help millennials play a crucial role in AI adoption.
Web <2025>
<ESxuhpeibraigt e4ncy>
Exhibit <6> of <21>
Millennials aged 35 to 44 are AI optimists, with 90 percent indicating
confidence in their gen AI abilities.
US employee sentiment on gen AI, by age group, % of respondents
18–24 25–34 35–44 45–54 55–64 65+
Has extensive
familiarity
with gen AI1
50 49 62 47 26 22
Is comfortable using
gen AI at work
80 87 90 82 70 71
Provides feedback
on gen AI tools
76 77 76 65 47 55
Wants to participate
in the design of
gen AI tools
70 76 81 77 73 76
1Defined as those who have “extensive experience (use several tools for complex tasks)” and “experts.”
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
16 Superagency in the workplace: Empowering people to unlock AI’s full potential
Web <2025>
E<Sxuhpiebraitg e5ncy>
Exhibit <7> of <21>
Two-thirds of managers regularly act as sounding boards for their teams on
gen AI.
Frequency of team inquiries about using new gen AI tools at work, % of US manager respondents
(n = 1,440)
Less than Once a Once a A few Once Multiple
quarterly Quarterly month week times a week a day times a day
10 5 5 12 15 28 9 16
Not at all
Use of gen AI tools to resolve a team member’s challenge, % of US manager respondents (n = 1,440)
Recommended Gen AI tool was
gen AI tool to successful in
solve team member’s resolving team
challenge in member’s challenge
the past month 86
68
Source: McKinsey US employee survey, Oct–Nov 2024 (n = 3,002)
McKinsey & Company
Since many millennials are managers, they can support their teams to become more adept AI users. This
helps push their companies toward AI maturity. Two-thirds of managers say they field questions from their
team about how to use AI tools at least once a week, and a similar percentage say they recommend AI tools
to their teams to solve problems (Exhibit 5).
Since leaders have the permission space, they can be bolder
In many transformations, employees are not ready for change, but AI is different. Employee readiness and
familiarity are high, which gives business leaders the permission space to act. Leaders can listen to
employees describe how they are using AI today and how they envision their work being transformed. They
also can provide employees with much-needed training and empower managers to move AI use cases from
pilot to scale.
It’s critical that leaders meet this moment. It’s the only way to accelerate the probability that their companies
will reach AI maturity. But they must move with alacrity, or they will fall behind.
Superagency in the workplace: Empowering people to unlock AI’s full potential 17
3
Delivering
speed and safety
‘Soon after the first automobiles were
on the road, there was the first car crash.
But we didn’t ban cars—we adopted
speed limits, safety standards, licensing
requirements, drunk-driving laws,
and other rules of the road.’
– Bill Gates, cofounder of Microsoft
18 Superagency in the workplace: Empowering people to unlock AI’s full potential
A
I technology is advancing at record speed. ChatGPT was released about two years ago; OpenAI
reports that usage now exceeds 300 million weekly users13 and that over 90 percent of Fortune
500 companies employ its technology.14 The internet did not reach this level of usage until the
early 2000s, nearly a decade after its inception.
The majority of employees describe themselves as AI optimists; Zoomers and Bloomers make up 59 percent
of the workplace. Even Gloomers, who are one of the two less-optimistic segments in our analysis, report
high levels of gen AI familiarity, with over a quarter saying they plan to use AI more next year.
Business leaders need to embrace this speed and optimism to ensure that their companies don’t get left
behind. Yet despite all the excitement and early experimentation, 47 percent of C-suite leaders say their
organizations are developing and releasing gen AI tools too slowly, citing talent skill gaps as a key reason for
the delay (Exhibit 6).
Web <2025>
<ESxuhpeibraigt e6ncy>
Exhib |
59 | mckinsey | AI-bank-of-the-future-Can-banks-meet-the-AI-challenge.pdf | Global Banking & Securities
AI-bank of the future: Can
banks meet the AI challenge?
Artificial intelligence technologies are increasingly integral to world we live
in, and banks need to deploy these technologies at scale to remain relevant.
Success requires a holistic transformation spanning multiple layers of the
organization.
by Suparna Biswas, Brant Carson, Violet Chung, Shwaitang Singh, and Renny Thomas
© Getty Images
September 2020
In 2016, AlphaGo, a machine, defeated 18-time 3. What obstacles prevent banks from deploying
world champion Lee Sedol at the game of AI capabilities at scale?
Go, a complex board game requiring intuition,
imagination, and strategic thinking—abilities 4. How can banks transform to become AI-first?
long considered distinctly human. Since then,
artificial intelligence (AI) technologies have
advanced even further,¹ and their transformative 1. Why must banks become AI-first?
impact is increasingly evident across Over several decades, banks have continually
industries. AI-powered machines are tailoring adapted the latest technology innovations to
recommendations of digital content to individual redefine how customers interact with them. Banks
tastes and preferences, designing clothing introduced ATMs in the 1960s and electronic,
lines for fashion retailers, and even beginning to card-based payments in the ’70s. The 2000s saw
surpass experienced doctors in detecting signs of broad adoption of 24/7 online banking, followed
cancer. For global banking, McKinsey estimates by the spread of mobile-based “banking on the go”
that AI technologies could potentially deliver up to in the 2010s.
$1 trillion of additional value each year.²
Few would disagree that we’re now in the
Many banks, however, have struggled to move AI-powered digital age, facilitated by falling costs
from experimentation around select use cases to for data storage and processing, increasing
scaling AI technologies across the organization. access and connectivity for all, and rapid
Reasons include the lack of a clear strategy for AI, advances in AI technologies. These technologies
an inflexible and investment-starved technology can lead to higher automation and, when deployed
core, fragmented data assets, and outmoded after controlling for risks, can often improve upon
operating models that hamper collaboration human decision making in terms of both speed
between business and technology teams. What and accuracy. The potential for value creation
is more, several trends in digital engagement is one of the largest across industries, as AI can
have accelerated during the COVID-19 pandemic, potentially unlock $1 trillion of incremental value
and big-tech companies are looking to enter for banks, annually (Exhibit 1).
financial services as the next adjacency. To
compete successfully and thrive, incumbent Across more than 25 use cases,³ AI technologies
banks must become “AI-first” institutions, can help boost revenues through increased
adopting AI technologies as the foundation for personalization of services to customers (and
new value propositions and distinctive customer employees); lower costs through efficiencies
experiences. generated by higher automation, reduced errors
rates, and better resource utilization; and uncover
In this article, we propose answers to four new and previously unrealized opportunities
questions that can help leaders articulate a clear based on an improved ability to process and
vision and develop a road map for becoming an generate insights from vast troves of data.
AI-first bank:
More broadly, disruptive AI technologies can
1. Why must banks become AI-first? dramatically improve banks’ ability to achieve
four key outcomes: higher profits, at-scale
2. What might the AI-bank of the future look like? personalization, distinctive omnichannel
1 AI can be defined as the ability of a machine to perform cognitive functions associated with human minds (e.g., perceiving, reasoning, learning, and
problem solving). It includes various capabilities, such as machine learning, facial recognition, computer vision, smart robotics, virtual agents, and
autonomous vehicles. See “Global AI Survey: AI proves its worth, but few scale impact,” November 2019, McKinsey.com.
2 “The executive’s AI playbook,” McKinsey.com.
3 For an interactive view, visit: www.mckinsey.com/business-functions/mckinsey-analytics/our-insights/the-executives-ai-
playbook?page=industries/banking/
2
Exhibit 1
PPootetnetnitaila al nannunaula vl avlauleu oef o Af IA aIn adn adn aanlyatliyctsi cfosr f oglro gblaolb baaln bkainnkgi cnogu cldo urelda crhe aacs hh iagsh as
$h1i gtrhil aliso n$.1 trillion.
Total potential annual value, $ billion
1,022.4 (15.4% of sales)
Traditional AI
Advanced AI
and analytics
660.9 361.5
% of value driven by advanced AI, by function
100
Finance and IT: 8.0 Other operations: $2.4 B
0.0 8.0 0.0 2.4
50
HR: 14.2
8.6 5.7
Marketing and sales: 624.8
Risk: 372.9
363.8 261.1
288.6 84.3
0
Source: "The executive's AI playbook," McKinsey.com. (See "Banking," under "Value & Assess.")
experiences, and rapid innovation cycles. Banks As consumers increase their use of digital
that fail to make AI central to their core strategy banking services, they grow to expect more,
and operations—what we refer to as becoming particularly when compared to the standards
“AI-first”—will risk being overtaken by competition they are accustomed to from leading consumer-
and deserted by their customers. This risk is internet companies. Meanwhile, these digital
further accentuated by four current trends: experience leaders continuously raise the bar
on personalization, to the point where they
— Rising customer expectations as adoption sometimes anticipate customer needs before
of digital banking increases. In the first few the customer is aware of them, and offer highly-
months of the COVID-19 pandemic, use of tailored services at the right time, through the
online and mobile banking channels across right channel.
countries has increased by an estimated 20
to 50 percent and is expected to continue at — Leading financial institutions’ use of advanced
this higher level once the pandemic subsides. AI technologies is steadily increasing. Nearly
Across diverse global markets, between 15 and 60 percent of financial-services sector
45 percent of consumers expect to cut back respondents in McKinsey’s Global AI Survey
on branch visits following the end of the crisis.⁴ report⁵ that their companies have embedded
4 John Euart, Nuno Ferreira, Jonathan Gordon, Ajay Gupta, Atakan Hilal, Olivia White, “A global view of financial life during COVID-19—an update,”
July 2020, McKinsey.com.
5 Arif Cam, Michael Chui, Bryce Hall, “Global AI Survey: AI proves its worth, but few scale impact,” November 2019, McKinsey.com.
AI-bank of the future: Can banks meet the AI challenge? 3
at least one AI capability. The most commonly but also to book a cab, order food, schedule
used AI technologies are: robotic process a massage, play games, send money to a
automation (36 percent) for structured contact, and access a personal line of credit.
operational tasks; virtual assistants or Similarly, across countries, nonbanking
conversational interfaces (32 percent ) for businesses and “super apps” are embedding
customer service divisions; and machine financial services and products in their
learning techniques (25 percent) to detect journeys, delivering compelling experiences
fraud and support underwriting and risk for customers, and disrupting traditional
management. While for many financial services methods for discovering banking products and
firms, the use of AI is episodic and focused on services. As a result, banks will need to rethink
specific use cases, an increasing number of how they participate in digital ecosystems,
banking leaders are taking a comprehensive and use AI to harness the full power of data
approach to deploying advanced AI, and available from these new sources.
embedding it across the full lifecycle, from the
front- to the back-office (Exhibit 2). — Technology giants are entering financial
services as the next adjacency to their
— Digital ecosystems are disintermediating core business models. Globally, leading
traditional financial services. By enabling technology giants have built extraordinary
access to a diverse set of services through market advantages: a large and engaged
a common access point, digital ecosystems customer network; troves of data, enabling a
have transformed the way consumers discover, robust and increasingly precise understanding
evaluate, and purchase goods and services. of individual customers; natural strengths
For example, WeChat users in China can use in developing and scaling innovative
the same app not only to exchange messages, technologies (including AI); and access to
Web <year>
<article slug>
EExxhhibiibt <itx 2> of <y>
Banks are expanding their use of AI technologies to improve customer
Banks are expanding their use of AI technologies to improve customer
experiences and back-office processes.
experiences and back-office processes.
Front office Back office
Smile-to-pay facial scanning Micro-expression analysis Biometrics (voice, video, Machine learning to detect
to initiate transaction with virtual loan officers print) to authenticate and fraud patterns,
authorize cybersecurity attacks
Conversational bots for Humanoid robots in branches Machine vision and natural- Real-time transaction
basic servicing requests to serve customers language processing to scan analysis for risk monitoring
and process documents
4 AI-bank of the future: Can banks meet the AI challenge?
low-cost capital. In the past, tech giants have digital era, the AI-first bank will offer propositions
aggressively entered into adjacent businesses and experiences that are intelligent (that
in search of new revenue streams and to is, recommending actions, anticipating and
keep customers engaged with a fresh stream automating key decisions or tasks), personalized
of offerings. Big-tech players have already (that is, relevant and timely, and based on a
gained a foothold in financial services in select detailed understanding of customers’ past
domains (especially in payments and, in some behavior and context), and truly omnichannel
cases, lending and insurance), and they may (seamlessly spanning the physical and online
soon look to press their advantages to deepen contexts across multiple devices, and delivering
their presence and build greater scale. a consistent experience) and that blend banking
capabilities with relevant products and services
beyond banking. Exhibit 3 illustrates how such a
2. What might the AI-bank of the bank could engage a retail customer throughout
future look like? the day. Exhibit 4 shows an example of the banking
To meet customers’ rising expectations and experience of a small-business owner or the
beat competitive threats in the AI-powered treasurer of a medium-size enterprise.
Exhibit 3
How AI transforms banking for a retail customer.
How AI transforms banking for a retail customer.
Name: Anya
Age: 28 years
Occupation: Working professional
Anya receives
App offers money- integrated portfolio
management and view and a set of
Anya uses smile- savings solutions, actions with the
Seamless to-pay to Analytics- prioritizes card Aggregated potential to
integration with initiate payment backed payments overview of daily augment returns
nonbanking apps personalized offers
activities
Bank app Facial recognition Anya gets 2% off Personalized Anya receives Savings and
investment recom-
recognizes Anya's for frictionless on health money-management end-of-day
mendations
spending patterns payment insurance solutions overview of her
and suggests premiums based activities, with
coffee at nearby on her gym augmented reality,
cafes activity and and reminders to
sleep habits pay bills
Intelligent Personalized Omnichannel Banking and beyond banking
AI-bank of the future: Can banks meet the AI challenge? 5
Exhibit 4
How AI transforms banking for a small- or medium-size-enterprise customer.
How AI transforms banking for a small- or medium-size-enterprise customer.
Name: Dany
Age: 36 years
Occupation: Treasurer of a small manufacturing unit
Dany answers
short questionnaire;
app scans his facial
An AI-powered
movements
Dany is assisted virtual adviser
Firm is credited in sourcing and resolves queries
with funds after selecting the Dany seeks
Customized application Seamless right vendors Beyond- professional advice
lending solutions approval inventory and receiv- and partners banking support on a lending offer
ables management services
Bank is integrated Micro-expression App suggests SME platform to Dany gets prefilled Serviced by an AI-
with client analysis to review loan items to reorder, source suppliers tax documents to powered virtual
business applications gives visual reports and buyers review and adviser
management on receivables approve; files with
systems management a single click
Dany receives
Dany gets loan
customized
offer based on
solutions for
company projected
invoice discounting,
cash flows
factoring, etc.
Intelligent Personalized Omnichannel Banking and beyond banking
Internally, the AI-first institution will be optimized The AI-first bank of the future will also enjoy
for operational efficiency through extreme the speed and agility that today characterize
automation of manual tasks (a “zero-ops” mindset) digital-native companies. It will innovate
and the replacement or augmentation of human rapidly, launching new features in days or
decisions by advanced diagnostic engines in weeks instead of months. It will collaborate
diverse areas of bank operations. These gains extensively with partners to deliver new
in operational performance will flow from broad value propositions integrated seamlessly
application of traditional and leading-edge AI across journeys, technology platforms, and
technologies, such as machine learning and data sets.
facial recognition, to analyze large and complex
reserves of customer data in (near) real time.
6 AI-bank of the future: Can banks meet the AI challenge?
cases. Without a centralized data backbone, it is
3. What obstacles prevent banks from
practically impossible to analyze the relevant data
deploying AI capabilities at scale?
and generate an intelligent recommendation or
Incumbent banks face two sets of objectives,
offer at the right moment. If data constitute the
which on first glance appear to be at odds. On
bank’s fundamental raw material, the data must be
the one hand, banks need to achieve the speed,
governed and made available securely in a manner
agility, and flexibility innate to a fintech. On the
that enables analysis of data from internal and
other, they must continue managing the scale,
external sources at scale for millions of customers,
security standards, and regulatory requirements
in (near) real time, at the “point of decision” across
of a traditional financial-services enterprise.
the organization. Lastly, for various analytics and
advanced-AI models to scale, organizations need
Despite billions of dollars spent on change-
a robust set of tools and standardized processes
the-bank technology initiatives each year, few
to build, test, deploy, and monitor models, in a
banks have succeeded in diffusing and scaling
repeatable and “industrial” way.
AI technologies throughout the organization.
Among the obstacles hampering banks’ efforts,
Banks’ traditional operating models further
the most common is the lack of a clear strategy
impede their efforts to meet the need for
for AI.⁶ Two additional challenges for many
continuous innovation. Most traditional banks
banks are, first, a weak core technology and data
are organized around distinct business lines,
backbone and, second, an outmoded operating
with centralized technology and analytics
model and talent strategy.
teams structured as cost centers. Business
owners define goals unilaterally, and alignment
Built for stability, banks’ core technology
with the enterprise’s technology and analytics
systems have performed well, particularly in
strategy (where it exists) is often weak or
supporting traditional payments and lending
inadequate. Siloed working teams and “waterfall”
operations. However, banks must resolve
implementation processes invariably lead
several weaknesses inherent to legacy systems
to delays, cost overruns, and suboptimal
before they can deploy AI technologies at scale
performance. Additionally, organizations lack
(Exhibit 5). First and foremost, these systems
a test-and-learn mindset and robust feedback
often lack the capacity and flexibility required
loops that promote rapid experimentation and
to support the variable computing requirements,
iterative improvement. Often unsatisfied with the
data-processing needs, and real-time analysis
performance of past projects and experiments,
that closed-loop AI applications require.⁷ Core
business executives tend to rely on third-party
systems are also difficult to change, and their
technology providers for critical functionalities,
maintenance requires significant resources.
starving capabilities and talent that should ideally
What is more, many banks’ data reserves are
be developed in-house to ensure competitive
fragmented across multiple silos (separate
differentiation.
business and technology teams), and analytics
efforts are focused narrowly on stand-alone use
6 Michael Chui, Sankalp Malhotra, “AI adoption advances, but foundational barriers remain,” November 2018, McKinsey.com.
7 “Closed loop” refers to the fact that the models’ intelligence is applied to incoming data in near real time, which in turn refines the content presented
to the user in near real time.
AI-bank of the future: Can banks meet the AI challenge? 7
Exhibit 5
IInnvveessttmmeentnst sin i nco croer tee cthe cahre a crrei tcicraitli ctoa lm teoe mt ienecrte ianscinrega dseinmga nddesm foarn ds for
ssccaalalabbiliiltiyty, ,fl flexeixbiibliitliyt,y a, nadn dsp sepede.e d.
Cloud
Data API1
Challenges How cloud computing can help
Core/legacy systems can’t scale sufficiently Enables higher scalability, resilience of services and
(eg, 150+ transactions/second) platforms through virtualization of infrastructure
Significant time, effort, and team sizes Reduces IT overhead, enables automation of several
required to maintain infrastructure infrastructure-management tasks, and allows development
teams to “self-serve”
Long time required to provision environments
for development and testing (eg, 40+ days in Enables faster time to market; dramatically reduces time by
some cases) providing managed services (e., setting up new environments
in minutes vs days)
Challenges How best-in-class data management can help
High error rates; poor refresh rates; lack of Ensures high degree of accuracy and single source of truth
golden source of truth in a cost-effective manner
Hard to access in a timely fashion for various Enables timely and role-appropriate access for various use
use cases cases (eg, regulatory, business intelligence at scale, advanced
analytics and machine learning, exploratory)
Data trapped in silos across multiple units and
hard to integrate with external sources Enables a 360-degree view across the organization to enable
generation of deeper insights by decision-making algorithms
and models
Challenges How APIs can help
Longer time to market, limited reusability of Promote reusability and accelerate development by enabling
code and software across internal teams access to granular services (internal and external)
Hard to partner or collaborate with external Reduce complexity and enable faster collaboration with
partners; long time to integrate external partners
Suboptimal user experience—hard to stitch Enhance customer experience by enabling timely access to
data and services across multiple functional data and services across different teams; faster time to market
siloes for an integrated proposition due to limited coordination, cross-team testing
1Application programming interface.
8 AI-bank of the future: Can banks meet the AI challenge?
4. How can banks transform to First, banks will need to move beyond highly
become AI-first? standardized products to create integrated
To overcome the challenges that limit propositions that target “jobs to be done.”⁸ This
organization-wide deployment of AI requires embedding personalization decisions
technologies, banks must take a holistic (what to offer, when to offer, which channel
approach. To become AI-first, banks must invest to offer) in the core customer journeys and
in transforming capabilities across all four layers designing value propositions that go beyond the
of the integrated capability stack (Exhibit 6): the core banking product and include intelligence
engagement layer, the AI-powered decisioning that automates decisions and activities on
layer, the core technology and data layer, and the behalf of the customer. Further, banks should
operating model. strive to integrate relevant non-banking
products and services that, together with the
core banking product, comprehensively address
As we will explain, when these interdependent
the customer end need. An illustration of the
layers work in unison, they enable a bank to
“jobs-to-be-done” approach can be seen in the
provide customers with distinctive omnichannel
way fintech Tally helps customers grapple with
experiences, support at-scale personalization,
the challenge of managing multiple credit cards.
and drive the rapid innovation cycles critical
The fintech’s customers can solve several pain
to remaining competitive in today’s world.
points—including decisions about which card to
Each layer has a unique role to play—under-
pay first (tailored to the forecast of their monthly
investment in a single layer creates a weak link
income and expenses), when to pay, and how
that can cripple the entire enterprise.
much to pay (minimum balance versus retiring
principal)—a complex set of tasks that are often
The following paragraphs explore some of the
not done well by customers themselves.
changes banks will need to undertake in each
layer of this capability stack.
The second necessary shift is to embed
customer journeys seamlessly in partner
Layer 1: Reimagining the customer
ecosystems and platforms, so that banks
engagement layer
engage customers at the point of end use and
Increasingly, customers expect their bank to be
in the process take advantage of partners’
present in their end-use journeys, know their
data and channel platform to increase higher
context and needs no matter where they interact
engagement and usage. ICICI Bank in India
with the bank, and to enable a frictionless
embedded basic banking services on WhatsApp
experience. Numerous banking activities
(a popular messaging platform in India) and
(e.g., payments, certain types of lending) are
scaled up to one million users within three
becoming invisible, as journeys often begin and
months of launch.⁹ In a world where consumers
end on interfaces beyond the bank’s proprietary
and businesses rely increasingly on digital
platforms. For the bank to be ubiquitous in
ecosystems, banks should decide on the
customers’ lives, solving latent and emerging
posture they would like to adopt across multiple
needs while delivering intuitive omnichannel
ecosystems—that is, to build, orchestrate, or
experiences, banks will need to reimagine how
partner—and adapt the capabilities of their
they engage with customers and undertake
engagement layer accordingly.
several key shifts.
8 Clayton M. Christensen, Taddy Hall, Karen Dillon and David S. Duncan, “Know your customers ‘jobs to be done,” Harvard Business Review,
September 2016, hbr.org.
9 “ICICI Bank crosses 1 million users on WhatsApp platform,” Live Mint, July 7, 2020, livemint.com.
AI-bank of the future: Can banks meet the AI challenge? 9
Exhibit 6
TToo b beeccoomme ean a nA IA-fiI-rfistr sitn sintistutittiuotni,o an b, aan bka mnku smt ustsrte asmtrelianme iltisn eca iptsa bcialiptya bstialictky sfotra ck
vfaolru ve aclrueea tciorena. tion.
AI bank of the future
Personalization Omnichannel Speed and
Profitability
at scale experience innovation
Intelligent products, Within-bank channels and Beyond-bank channels
Reimagined tools, experiences journeys (eg, web, apps, and journeys (eg, Smart service and
engagement for customers and mobile, smart devices, ecosystems, partners, operations
employees branches, Internet of Things) distributors)
1 2 3 4
5
Digital marketing
6
Retention
Credit Monitoring Servicing
Advanced Customer and cross-
decision and and
analytics acquisition selling,
AI-powered making collections engagement
upselling
decision
making
Natural-
Voice- Virtual Facial Behav-
7 language script agents, Computer recog- Block- Robotics ioral
AI capabilities process- analysis bots vision nition chain analytics
ing
A. Tech-forward strategy (in-house build of differential capabilities
vs buying offerings; in-house talent plan)
Core 8 B. Data C. Modern D. Intelligent E. Hollow- F. Cyber-
manage- API archi- infrastructure ing the security
technology Core technology
ment for tecture (AI operations core (core and
and data and data
AI world command, moderniza- control
hybrid cloud tion) tiers
setup, etc)
A. Autonomous business + tech teams
9
Operating B. Agile way C. Remote D. Modern talent E. Culture and
Platform operating
model model of working collaboration strategy (hiring, capabilities
reskilling)
10 Value capture
10 AI-bank of the future: Can banks meet the AI challenge?
Third, banks will need to redesign overall and stronger risk management (e.g., earlier
customer experiences and specific journeys for detection of likelihood of default and
omnichannel interaction. This involves allowing fraudulent activities).
customers to move across multiple modes (e.g.,
web, mobile app, branch, call center, smart To establish a robust AI-powered decision
devices) seamlessly within a single journey layer, banks will need to shift from attempting
and retaining and continuously updating the to develop specific use cases and point
latest context of interaction. Leading consumer solutions to an enterprise-wide road map for
internet companies with offline-to-online deploying advanced-analytics (AA)/machine-
business models have reshaped customer learning (ML) models across entire business
expectations on this dimension. Some banks domains. As an illustration, in the domain of
are pushing ahead in the design of omnichannel unsecured consumer lending alone, more
journeys, but most will need to catch up. than 20 decisions across the life cycle can be
automated.¹¹ To enable at-scale development
Reimagining the engagement layer of the of decision models, banks need to make the
AI bank will require a clear strategy on how development process repeatable and thus
to engage customers through channels capable of delivering solutions effectively and
owned by non-bank partners. Banks will on-time. In addition to strong collaboration
need to adopt a design-thinking lens as they between business teams and analytics
build experiences within and beyond the talent, this requires robust tools for model
bank’s platform, engineering engagement development, efficient processes (e.g., for
interfaces for flexibility to enable tailoring and re-using code across projects), and diffusion
personalization for customers, reengineering of knowledge (e.g., repositories) across teams.
back-end processes, and ensuring that data- Beyond the at-scale development of decision
capture funnels (e.g., clickstream) are granularly models across domains, the road map should
embedded in the bank’s engagement layer. All also include plans to embed AI in business-
of this aims to provide a granular understanding as-usual process. Often underestimated,
of journeys and enable continuous this effort requires rewiring the business
improvement.10 processes in which these AA/AI models will be
embedded; making AI decisioning “explainable”
Layer 2: Building the AI-powered decision- to end-users; and a change-management plan
making layer that addresses employee mindset shifts and
Delivering personalized messages and skills gaps. To foster continuous improvement
decisions to millions of users and thousands beyond the first deployment, banks also
of employees, in (near) real time across the full need to establish infrastructure (e.g., data
spectrum of engagement channels, will require measurement) and processes (e.g., periodic
the bank to develop an at-scale AI-powered reviews of performance, risk management of AI
decision-making layer. Across domains within models) for feedback loops to flourish.
the bank, AI techniques can either fully replace
or augment human judgment to produce Additionally, banks will need to augment
significantly better outcomes (e.g., higher homegrown AI models, with fast-evolving
accuracy and speed), enhanced experience capabilities (e.g., natural-language processing,
for customers (e.g., more personalized computer-vision techniques, AI agents
interaction and offerings), actionable insights and bots, augmented or virtual reality) in
for employees (e.g., which customer to contact their core business processes. Many of
first with next-best-action recommendations), these leading-edge capabilities have the
10Jennifer Kilian, Hugo Sarrazin, and Hyo Yeon, “Building a design-driven culture,” September 2015, McKinsey.com.
11 Renny Thomas, Vinayak HV, Raphael Bick, and Shwaitang Singh, “Ten lessons for building a winning retail and small-business digital lending
franchise,” November 2019, McKinsey.com.
AI-bank of the future: Can banks meet the AI challenge? 11
potential to bring a paradigm shift in customer technology backbone, starved of the investments
experience and/or operational efficiency. While needed for modernization, can dramatically
many banks may lack both the talent and the reduce the effectiveness of the decision-making
requisite investment appetite to develop these and engagement layers.
technologies themselves, they need at minimum
to be able to procure and integrate these The core-technology-and-data layer has six key
emerging capabilities from specialist providers elements (Exhibit 7):
at rapid speed through an architecture enabled
by an application programming interface (API), — Tech-forward strategy. Banks should have
promote continuous experimentation with these a unified technology strategy that is tightly
technologies in sandbox environments to test and aligned to business strategy and outlines
refine applications and evaluate potential risks, strategic choices on which elements, skill
and subsequently decide which technologies to sets, and talent the bank will keep in-house
deploy at scale. and those it will source through partnerships
or vendor relationships. In addition, the
To deliver these decisions and capabilities and to tech strategy needs to articulate how each
engage customers across the full life cycle, from component of the target architecture will both
acquisition to upsell and cross-sell to retention support the bank’s vision to be an AI-first
and win-back, banks will need to establish institution and interact with each layer of the
enterprise-wide digital marketing machinery. This capability stack.
machinery is critical for translating decisions and
insights generated in the decision-making layer — Data management for the AI-enabled world.
into a set of coordinated interventions delivered The bank’s data management must ensure
through the bank’s engagement layer. This data liquidity—that is, the ability to access,
machinery has several critical elements, which ingest, and manipulate the data that serve as
include: the foundation for all insights and decisions
generated in the decision-making layer.
— Data-ingestion pipelines that capture a range Data liquidity increases with the removal of
of data from multiple sources both within the functional silos and allows multiple divisions
bank (e.g., clickstream data from apps) and to operate off the same data, with increased
beyond (e.g., third-party partnerships with coordination. The data value chain begins with
telco providers) seamless sourcing of data from all relevant
internal systems and external platforms. This
— Data platforms that aggregate, develop, and includes ingesting data into a lake, cleaning
maintain a 360-degree view of customers and and labeling the data required for diverse use
enable AA/ML models to run and execute in cases (e.g., regulatory reporting, business
near real time intelligence at scale, AA/ML diagnostics),
segregating incoming data (from both existing
— Campaign platforms that track past actions and prospective customers) to be made
and coordinate forward-looking interventions available for immediate analysis from data to
across th |
60 | mckinsey | Global-AI-Survey-AI-proves-its-worth-but-few-scale-impact.pdf | McKinsey Analytics
Global AI Survey:
AI proves its worth,
but few scale impact
Most companies report measurable benefits from AI where it has
been deployed; however, much work remains to scale impact,
manage risks, and retrain the workforce. A group of high performers
shows the way.
© Sylverarts/Getty Images
November 2019
Adoption of artificial intelligence (AI) continues to Further, our results suggest that workforce retraining
increase, and the technology is generating returns.1 will need to ramp up. While the findings indicate
The findings of the latest McKinsey Global Survey on that AI adoption has generally had modest overall
the subject show a nearly 25 percent year-over- effects on organizations’ workforce size in the
year increase in the use of AI2 in standard business past year, about one-third of respondents say they
processes, with a sizable jump from the past year expect AI adoption to lead to a decrease in their
in companies using AI across multiple areas of their workforce in the next three years, compared with
business.3 A majority of executives whose com- one-fifth who expect an increase, and AI high
panies have adopted AI report that it has provided performers are doing more retraining.
an uptick in revenue in the business areas where it is
used, and 44 percent say AI has reduced costs.
Most respondents are seeing returns
The results also show that a small share of from AI
companies—from a variety of sectors—are attaining In this year’s survey, we asked respondents about
outsize business results from AI, potentially widen- 33 AI use cases across eight business functions,
ing the gap between AI power users and adoption including how adoption of AI for each of these activ-
laggards. Respondents from these high-performing ities has affected revenue and cost in the business
companies (or AI high performers) report that they units where AI is used. The results suggest that AI is
achieve greater scale and see both higher revenue delivering meaningful value to companies.
increases and greater cost decreases than other
companies that use AI.4 The findings, however, pro- Aggregating across all of the use cases, 63 percent
vide a potential road map for laggards, showing of respondents report revenue increases from AI
that the AI high performers are more likely to apply adoption in the business units where their companies
core practices for using AI to drive value across use AI, with respondents from high performers
the organization, mitigate risks associated with the nearly three times likelier than those from other com-
technology, and retrain workers to prepare them panies to report revenue gains of more than
for AI adoption. 10 percent. Respondents are most likely to report
The results suggest that AI is delivering
meaningful value to companies.
1 We define artificial intelligence (AI) as the ability of a machine to perform cognitive functions that we associate with human minds (such as
perceiving, reasoning, learning, and problem solving) and to perform physical tasks using cognitive functions (for example, physical robotics,
autonomous driving, and manufacturing work).
2 W e define AI use in standard business processes as embedded AI in at least one product or business process for at least one function or
business unit.
3 The online survey was in the field from March 26 to April 5, 2019, and garnered responses from 2,360 participants representing the full range
of regions, industries, company sizes, functional specialties, and tenures. Of these respondents, 1,872 work at companies they say have piloted
AI in at least one function or business unit, embedded at least one AI capability in at least one product or business process for at least one
function or business unit, or embedded at least one AI capability in products or business processes across multiple functions or business units.
To adjust for differences in response rates, the data are weighted by the contribution of each respondent’s nation to global GDP.
4 We define an AI high performer as a company that, according to respondents, has adopted AI in five or more business activities (is in the top
quartile for the number of activities using AI), seen an average revenue increase of 5 percent or more from AI adoption in the business units
where AI is used, and seen an average cost decrease of 5 percent or more from AI adoption in the business units where AI is used. The survey
results include 54 respondents from high-performing companies, which is 3 percent of all respondents reporting AI use by their companies.
2 Global AI Survey: AI proves its worth, but few scale impact
revenue growth from AI use cases in marketing and Overall, 44 percent of respondents report cost
sales, product and service development, and savings from AI adoption in the business units where
supply-chain management (Exhibit 1). In marketing it’s deployed, with respondents from high per-
and sales, respondents most often report formers more than four times likelier than others
revenue increases from AI use in pricing, prediction to say AI adoption has decreased business
of likelihood to buy, and customer-service units’ costs by at least 10 percent, on average. The
analytics. In product and service development, two functions in which the largest shares of
revenue-producing use cases include the respondents report cost decreases in individual AI
Survey 2019 creation of new AI-based products and new AI-based use cases are manufacturing and supply-chain
AI enhancements. And in supply-chain manage- management. In manufacturing, responses suggest
Exhibit 1 of 6 ment, respondents often cite sales and demand some of the most significant savings come from
forecasting and spend analytics as use cases optimizing yield, energy, and throughput. In supply-
that generate revenue. chain management, respondents are most likely to
Exhibit 1
Revenue increases from adopting AI are reported most often in marketing and sales,
and cost decreases most often in manufacturing.
Cost decrease and revenue increase from AI adoption, by function,¹ % of respondents2
Average cost decrease Average revenue increase
Decrease Decrease Decrease Increase Increase Increase
by ≥20% by 10–19% by <10% by ≤5% by 6–10% by >10%
4 13 19 Marketing and sales 40 30 10
6 10 13 Product and service development 31 21 19
14 16 31 Supply-chain management 28 22 13
13 14 37 Manufacturing 34 13 14
11 17 23 Service operations 31 14 15
15 11 24 Strategy and corporate finance 27 24 8
7 16 31 Risk 28 16 13
6 22 27 HR 20 23 12
1 Marketing and sales includes the following use cases: customer-service analytics, customer segmentation, channel management, prediction of likelihood to
buy, pricing and promotion, closed-loop marketing, marketing-budget allocation, churn reduction, and next product to buy. For product and service development:
product-feature optimization, product-development-cycle optimization, creation of new AI-based enhancements, and creation of new AI-based products. For
supply-chain management: logistics-network optimization, sales and parts forecasting, warehouse optimization, inventory and parts optimization, spend analytics,
and sales and demand forecasting. For manufacturing: predictive maintenance and yield, energy, and throughput optimization. For service operations:
service-operations optimization, contact-center automation, and predictive service and intervention. For strategy and corporate finance: capital allocation,
treasury management, and M&A support. For risk: risk modeling/analytics, and fraud/debt analytics. For HR: performance management and organization-
design, workforce-deployment, and talent-management optimization.
2 Question asked only of respondents who said their companies adopted AI in given use case. Figures were calculated after removing respondents who said “don’t know”
or “not applicable; we are not tracking revenue related to AI”; respondents who said “no change” are not shown.
Global AI Survey: AI proves its worth, but few scale impact 3
report savings from spend analytics and logistics- of capabilities. And telecom respondents report
network optimization. their companies using virtual agents—which can be
used in customer-service applications—more than
other capabilities (Exhibit 2). High-performing
AI adoption is increasing in nearly all companies, however, are far more likely to adopt AI
industries, but capabilities vary in business functions that this survey and past
As in last year’s survey, we asked respondents about research link to greater value creation more broadly.6
their companies’ use of nine AI capabilities.5 Fifty- For example, more than 80 percent of respondents
eight percent of respondents report that their organi- from high performers say they have adopted AI in
zations have embedded at least one AI capability marketing and sales, compared with only one-quarter
into a process or product in at least one function or from those of other companies that use AI.
business unit, up from 47 percent in 2018—a
sign that AI adoption in general is becoming more On a regional level, the survey shows significant
mainstream. What’s more, responses show an increases in adoption levels in developed Asia–
increase in the share of companies using AI in Pacific,7 Europe, Latin America, and North America.
products or processes across multiple business In Asia–Pacific and Latin America, the shares of
units and functions: 30 percent of this year’s respondents who say their companies have
respondents report doing so, compared with embedded AI across multiple functions or business
21 percent in the previous survey. While this seems units have nearly doubled since the previous
to indicate that more companies are beginning survey. However, the increases put all of these
to scale AI, high performers are much further along regions, as well as China, at similar aggregate
in these efforts, averaging 11 reported AI use reported levels of adoption, suggesting that while
cases across the organization versus about three there is considerable variation at the level
among other companies. of individual companies, the adoption of AI is a
global phenomenon.8
By sector, the results indicate increases in AI adop-
tion in nearly every industry in the past year. The results indicate that the pace of adoption will
Retail has seen the largest increase, with 60 percent likely continue in the near term, with 74 percent
of respondents saying their companies have of respondents whose companies have adopted or
embedded at least one AI capability in one or more plan to adopt AI saying their organizations will
functions or business units, a 35-percentage- increase their AI investment in the next three years.
point increase from 2018. More than half of these respondents expect an
increase of 10 percent or more. But the survey results
The results show companies applying AI capabilities indicate that AI high performers plan to invest
that help them perform the functions that create more, with nearly 30 percent of respondents from
value in their industries. For example, respondents these companies saying their organizations will
from consumer-packaged-goods companies are increase investment in AI by 50 percent or more in
more likely to report using physical robotics—which the next three years, compared with just 9 percent
can aid in assembly tasks—than most other types of others who say the same.
5 “AI adoption advances, but foundational barriers remain,” November 2018, McKinsey.com. Respondents were asked to describe their
organizations’ use of the following AI capabilities: natural language text understanding, natural language speech understanding,
natural language generation, virtual agents or conversational interfaces, computer vision, robotic process automation, machine learning,
physical robotics, and autonomous vehicles.
6 M ichael Chui, Rita Chung, Nicolaus Henke, Sankalp Malhotra, James Manyika, Mehdi Miremadi, and Pieter Nel, “Notes from the AI frontier:
Applications and value of deep learning,” McKinsey Global Institute, April 2018, McKinsey.com.
7 Includes Australia, Hong Kong, Japan, New Zealand, the Philippines, Singapore, South Korea, and Taiwan.
8 In each region, about three in ten respondents say their organizations have embedded AI across multiple functions or business units. In China,
the base size is below the baseline for statistical significance. For more on what AI means for China, see Dominic Barton, Jeongmin Seong,
Qinzheng Tian, and Jonathan Woetzel, “Artificial intelligence: Implications for China,” McKinsey Global Institute, April 2017, McKinsey.com.
4 Global AI Survey: AI proves its worth, but few scale impact
Survey 2019
AI
Exhibit 2 of 6
Exhibit 2
High tech leads in AI adoption, and industries are generally using the AI capabilities most
relevant to their value chains.
Organizations’ AI capabilities,1 % of respondents,2 by industry
Computer Natural Physical Natural language ≥1 AI capability
vision language text robotics generation embedded, %/
understanding change since 2018,
percentage points
Robotic process Machine Virtual agents or Natural Autonomous
automation learning conversational language speech vehicles
interfaces understanding
High tech 35 33 54 38 35 9 24 22 4 78/+17
Automotive
46 42 31 28 17 44 19 18 25 76/+11
and assembly
Telecom 30 36 45 38 45 20 23 26 3 72/+8
Travel, transport,
33 26 19 24 29 10 12 12 7 64/+26
and logistics
Financial
36 24 25 28 32 7 19 16 6 62/+6
services
Consumer
17 14 12 13 11 47 7 7 15 62/+12
packaged goods
Retail 21 24 23 34 27 25 18 16 9 60/+35
Electric power
26 31 30 9 22 22 8 6 4 60/+16
and natural gas
Healthcare systems
23 32 23 30 20 14 22 16 4 58/+9
and services
Pharma and
21 19 15 10 6 31 7 8 5 48/–2
medical products
Professional services 17 20 22 22 17 7 12 13 6 43/+10
Infrastructure 20 17 15 10 4 14 5 5 2 36/+8
1 Embedded in ≥1 product and/or business process for ≥1 function or business unit.
2 Respondents who said “don’t know” or “none of the above” are not shown. For high tech, n = 277; for automotive and assembly, n = 128; for telecom, n = 93; for travel,
transport, and logistics, n = 83; for financial services, n = 396; for consumer packaged goods, n = 72; for retail, n = 94; for electric power and natural gas, n = 82; for
healthcare systems and services, n = 78; for pharma and medical products, n = 96; for professional services, n = 331; and for infrastructure, n = 91.
Global AI Survey: AI proves its worth, but few scale impact 5
AI high performers tend to engage in frontline employees use AI insights in real time for
value-capturing practices daily decision making, and just 42 percent
According to our experience and past research on systematically track a comprehensive set of well-
analytics, some core practices are necessary defined key performance indicators for AI—
to capture value at scale.9 These include, among two practices, in our experience, that are crucial for
achieving end-user adoption and value. Likewise,
others, aligning business, analytics, and IT leaders
only 35 percent of respondents from AI high
on the potential value at stake from AI across
performers report having an active continuous-
each business domain; investing in talent, such as
learning program on AI for employees.
translator expertise; and ensuring that business
staff and technical teams have the skills necessary
for successful scaling.10
A minority of companies acknowledge
The survey results suggest these core practices most AI risks—fewer mitigate them
hold true for scaling AI, given that respondents Despite extensive dialogue across industries about
at AI high performers are far more likely than others the potential risks of AI and highly publicized
to say their organizations apply these practices incidents of privacy violations, unintended bias, and
(Exhibit 3). For example, 72 percent of respondents other negative outcomes,11 the survey findings
from AI high performers say their companies’ suggest that a minority of companies recognize
AI strategy aligns with their corporate strategy, com- many of the risks of AI use. Even fewer are taking
pared with 29 percent of respondents from action to protect against the risks.
other companies. Similarly, 65 percent from the
high performers report having a clear data Fewer than half of respondents (41 percent) say
strategy that supports and enables AI, compared their organizations comprehensively identify and
with 20 percent from other companies. prioritize their AI risks. The survey also asked
specifically about ten of the most widely recognized
Even the AI high performers have work to do in risks. Of them, respondents most often cite
several key areas. For example, only 36 percent of cybersecurity and regulatory compliance as the
respondents from these companies say their AI-related risks their companies consider
Fewer than half of respondents
(41 percent) say their organizations
comprehensively identify and
prioritize their AI risks.
9 Peter Bisson, Bryce Hall, Brian McCarthy, and Khaled Rifai, “Breaking away: The secrets to scaling analytics,” May 2018, McKinsey.com.
1 0 Brian McCarthy, Chris McShea, and Marcus Roth, “Rebooting analytics leadership: Time to move beyond the math,” November
2018, McKinsey.com; Nicolaus Henke, Jordan Levine, and Paul McInerney, “Analytics translator: The new must-have role,” February 2018,
McKinsey.com; Solly Brown, Darshit Gandhi, Louise Herring, and Ankur Puri, “The analytics academy: Bridging the gap between human
and artificial intelligence,” McKinsey Quarterly, September 2019, McKinsey.com.
11 Benjamin Cheatham, Kia Javanmardian, and Hamid Samandari, “Confronting the risks of artificial intelligence,” McKinsey Quarterly,
April 2019, McKinsey.com.
6 Global AI Survey: AI proves its worth, but few scale impact
Survey 2019
AI
Exhibit 3 of 6
Exhibit 3
Respondents at AI high performers are much more likely than others to report that their
organizations apply core practices for scaling AI.
Share of respondents saying given statement is true of At high performers2
their organizations, %1 At all other companies3
Aligning AI strategy We have an AI strategy with a clear enterprise-level 58
to business goals road map of use cases 15 3.9×
The AI strategy aligns with our broader 72
corporate strategy 29 2.5×
Investing in AI talent We have in place an active continuous-learning 35
and training program on AI for our employees 10 3.5×
We have people in translator roles who
49
communicate with employees across the analytics
21 2.3×
and business functions
Collaborating Cross-functional teams, including AI professionals
62
across functions and people in the business, work together on
23 2.7×
specific problems
Applying strong We have a clear data strategy that supports 65
data practices and enables AI 20 3.3×
Well-defined governance processes are in place 55
for key data-related decisions 20 2.8×
Establishing We have standard AI tool sets for data and 76
standard protocols analytics professionals to use 18 4.2×
and repeatable
methodologies
We know how frequently our AI models 43
need to be updated 11 3.9×
We have techniques and processes in place to
54
ensure that our models are explainable to people
17 3.2×
across the organization
Ensuring adoption Our frontline employees use AI insights in real 36
and value time to enable their daily decision making 8 4.5×
We systematically track a comprehensive set of 42
well-defined key performance indicators for AI 10 4.2×
1 Question asked only of respondents who said their companies had embedded or piloted ≥1 AI capability.
2 Respondents who said companies have adopted AI in ≥5 business activities (ie, top quartile for the number of activities using AI), seen an average revenue
increase of ≥5% from AI adoption in the business units where AI is used, and seen an average cost decrease of ≥5% from AI adoption in the business units where
AI is used, n = 54.
3 n = 1,818.
Global AI Survey: AI proves its worth, but few scale impact 7
relevant (Exhibit 4). These two risks are the only Respondents at AI high performers are likelier than
ones that at least half of respondents cite as those from other companies to say their organiza-
relevant. Furthermore, the share of respondents tions both recognize and work to reduce risks. Take
saying their companies are mitigating each risk personal-privacy risk, which is squarely in regulators’
is smaller than the share citing it as relevant. For line of sight. Eighty percent of respondents at
example, while 39 percent of respondents say high-performing companies say their companies
their companies recognize risk associated with consider personal-privacy risk to be relevant,
“e xplainability” (the ability to explain how AI compared with less than half of respondents from
Survey 2019 models come to their decisions), only 21 percent say other companies. When asked about internal
AI they are actively addressing this risk. At the controls aimed at reducing privacy risks, 89 percent
Exhibit 4 of 6 companies that reportedly do mitigate AI risks, the of respondents at high-performing companies
most frequently reported tactic is conducting say their organizations adopt and enforce enterprise-
internal reviews of AI models. wide privacy policies, compared with 68 percent
Exhibit 4
Respondents at AI high performers are more likely than average to say their companies identify
AI-related risks—and work to mitigate them.
Risks that organizations consider relevant and are working to mitigate, Relevant risk
% of respondents1 Mitigated risk
All respondents Respondents at AI high performers
62 89
Cybersecurity
48 86
50 69
Regulatory compliance
35 55
45 80
Personal privacy
30 76
39 47
“Explainability”2
19 42
35 36
Workforce/labor displacement
17 23
34 44
Organizational reputation
19 41
26 36
Equity and fairness
13 23
16 25
Physical safety
11 23
9 18
National security
4 9
7 15
Political stability
2 7
9 0
Don’t know/not applicable
12 0
1 Question asked only of respondents who said their companies had embedded or piloted ≥1 AI capability; n = 1,872.
2 Ability to explain how AI models come to their decisions.
8 Global AI Survey: AI proves its worth, but few scale impact
of other respondents. Similarly, 80 percent of adopt AI expect it to drive a decrease in the number
respondents at AI high performers report that their of employees, versus 21 percent who expect an
organizations implement tech-enabled access increase—although most predict the change to be
restrictions to sensitive data, versus 59 percent of less than 10 percent in either direction.13 Another
those at other companies. 28 percent foresee AI adoption having little impact
on workforce size, with any expected change
being less than 3 percent.
More expect AI to cause workforce
decreases than increases, with Respondents also expect AI adoption to cause shifts
variances across functions in their workforce across functions. Respondents
are more likely to predict a decrease than an increase
Generally, there has been increasing concern that
AI will lead to workforce reduction.12 The survey in employment levels in HR, manufacturing, supply-
chain management, and service operations. They
findings suggest that, thus far, this concern has
more often predict an increase than a decrease in the
largely not been realized. More than one-third
number of employees in product development
of respondents report less than a 3 percent change
and marketing and sales.
in their companies’ workforce size because of
AI deployment, and only 5 percent of respondents
report a change, whether decrease or increase,
Greater emphasis on workforce
of greater than 10 percent. While respondents from
a handful of industries, including automotive and retraining is likely
assembly, are more likely to report a workforce The results indicate that a majority of respondents’
reduction than an increase in the past year because companies are preparing for AI-related work-
of AI (Exhibit 5), more respondents overall report force changes. When asked about retraining workers
job increases of 3 percent or more at their in response to AI adoption, nearly six in ten
companies in the past year than report decreases respondents at companies using AI say at least
of the same magnitude (17 percent and some of their workforce has been retrained
13 percent, respectively). in the past year. In addition, 83 percent of respon-
dents expect at least some of their workforce
But the outlook for the next three years could be to be retrained in the next three years because of
shifting. Thirty-four percent of respondents AI adoption, and 38 percent expect more than
from organizations that have adopted or plan to a quarter to be retrained.
Respondents are more likely to predict
a decrease than an increase in
employment levels in HR, manufacturing,
supply-chain management, and
service operations.
12 For more information on how AI is expected to affect the workforce, see James Manyika and Kevin Sneader, “AI, automation, and the future of
work: Ten things to solve for,” McKinsey Global Institute, June 2018, McKinsey.com.
13 Respondents reporting that their companies have piloted or embedded one or more AI capabilities, or plan to do so in the next three years, were
asked how they expect the adoption of AI to affect the number of employees relative to the number if the organizations had not adopted AI.
Global AI Survey: AI proves its worth, but few scale impact 9
Survey 2019
AI
Exhibit 5 of 6
Exhibit 5
Respondents in automotive and telecom report the deepest AI-related workforce cuts to date
and predict the most going forward.
Change in workforce due to AI adoption, Decrease >10% Decrease 3–10% Increase 3–10% Increase >10%
% of respondents
Little or Little or
Past year1 no change2 Next 3 years3 no change2
Automotive
8 15 10 1 32 18 28 16 1 25
and assembly
Telecom 2 21 12 4 20 18 37 8 5 13
Infrastructure 1 19 8 3 38 5 21 18 13 21
Retail 2 16 23 4 18 4 35 21 2 25
Financial services 4 13 14 1 37 14 25 12 3 30
Professional
1 12 15 6 40 8 20 22 7 26
services
1
High tech 1 12 21 6 26 9 16 15 15 26
Pharma and
12 6 3 39 11 13 19 2 32
medical products
Consumer
11 13 2 48 3 42 7 41
packaged goods
Travel, transport,
9 11 44 19 25 6 7 32
and logistics
Electric power
6 10 48 12 23 22 1 18
and natural gas
Healthcare systems
5 15 2 36 11 12 17 3 36
and services
1 Change in workforce in past year because of AI adoption. Question only asked of respondents who say their companies have piloted or embedded ≥1 AI capability.
Respondents who said “don’t know” are not shown. For automotive and assembly, n = 111; for telecom, n = 81; for infrastructure, n = 63; for retail, n = 74; for financial
services, n = 333; for professional services, n = 235; for high tech, n = 246; for pharma and medical products, n = 71; for consumer packaged goods, n = 55; for
travel, transport, and logistics, n = 69; for healthcare systems and services, n = 60.
2 A decrease or increase of ≤2%.
3 Expected change in workforce in next 3 years because of AI adoption, relative to size if AI had not been adopted. Question was asked only of respondents who say
their companies have piloted or embedded ≥1 AI capability, or plan to do so in the next 3 years. Respondents who said “don’t know” are not shown. For automotive and
assembly, n = 113; for telecom, n = 85; for infrastructure, n = 65; for retail, n = 76; for financial services, n = 341; for professional services, n = 245; for high tech,
n = 253; for pharma and medical products, n = 78; for consumer packaged goods, n = 58; for travel, transport, and logistics, n = 70; and for healthcare systems and
services, n = 67.
10 Global AI Survey: AI proves its worth, but few scale impact
Survey 2019
AI
Exhibit 6 of 6
Exhibit 6
Respondents at high performers report larger retraining efforts as a result of AI than others do.
Share of workforce 2 Share of workforce
7 3 8
retrained in past year 6 expected to be retrained
because of AI adoption, in next 3 years because 9
29
% of respondents1 of AI adoption, % of
26
respondents2
19
46
13
12
27
45
76–100% 51 26
51–75%
26–50% 29
7
1–25%
17
0% 11
1
Don’t know 2 2
At AI high At all other At AI high At all other
performers companies performers companies
Note: Figures may not sum to 100%, because of rounding.
1 Question was asked only of respondents who say their companies have piloted or embedded one or more AI capabilities. For respondents at high performers,
n = 54; for all others, n = 1,818.
2 Question was asked only of respondents who say their companies have piloted or embedded one or more AI capabilities, or plan to do so in the next three years. For
respondents at high performers, n = 54; for all others, n = 1,892.
Respondents at AI high performers report retraining With the research showing that companies now use
much greater shares of employees in the past AI more often than not, the technology appears to
year because of AI, compared with respondents at have reached another stepping stone in its ascent in
other companies that have adopted AI (Exhibit 6). business. Along with it comes a ratcheting up of
Respondents at high performers also predict that the urgency to scale AI among those still early in their
their companies will retrain larger shares of their adoption journeys. However, while the survey
workforce in the next three years. results indicate that some companies are further
ahead in realizing AI’s impact, they also suggest a
path for lagging companies to catch up.
The survey content and analysis were developed by Arif Cam, a consultant in McKinsey’s Silicon Valley office; Michael Chui,
a partner of the McKinsey Global Institute and a partner in the San Francisco office; and Bryce Hall, an associate partner in
the Washington, DC, office.
They wish to thank David DeLallo for his contributions to this article.
Designed by Global Editorial Services
Copyright © 2019 McKinsey & Company. All rights reserved.
Global AI Survey: AI proves its worth, but few scale impact 11 |
61 | mckinsey | Global-survey-The-state-of-AI-in-2021.pdf | The state of AI in 2021
As business’s adoption of AI continues to grow, the companies reaping
the biggest bottom-line benefits are differentiating themselves through
their use of more sophisticated tools and practices.
© Getty Images
December 2021
The results of our latest McKinsey Global Survey on AI indicate that AI adoption¹ continues to grow and that the
benefits remain significant—though in the COVID-19 pandemic’s first year, they were felt more strongly on the cost-
savings front than the top line. As AI’s use in business becomes more common, the tools and best practices to make
the most out of AI have also become more sophisticated.
We looked at the practices of the companies seeing the biggest earnings boost from AI and found that they are
not only following more of both the core and advanced practices, including machine-learning operations (MLOps),
that underpin success but also spending more efficiently on AI and taking more advantage of cloud technologies.
Additionally, they are more likely than other organizations to engage in a range of activities to mitigate their AI-related
risks—an area that continues to be a shortcoming for many companies’ AI efforts.
AI adoption and impact
Findings from the 2021 survey indicate that AI adoption is continuing its steady rise: 56 percent of all respondents
report adoption in at least one function, up from 50 percent in 2020. The newest results suggest that AI adoption
since last year has increased most at companies headquartered in emerging economies, which includes China, the
Middle East and North Africa: 57 percent of respondents report adoption, up from 45 percent in 2020. And across
regions, the adoption rate is highest at Indian companies, followed closely by those in Asia–Pacific.
About the research
The online survey was in the field from May 18 to June 29, 2021, and garnered responses from 1,843
participants representing the full range of regions, industries, company sizes, functional specialties, and
tenures. Of those respondents, 1,013 said their organizations had adopted AI in at least one function and were
asked questions about their organizations’ AI use. To adjust for differences in response rates, the data are
weighted by the contribution of each respondent’s nation to global GDP.
As we saw in the past two surveys, the business functions where AI adoption is most common are service operations,
product and service development, and marketing and sales, though the most popular use cases span a range
of functions. The top three use cases are service-operations optimization, AI-based enhancement of products,
and contact-center automation, with the biggest percentage-point increase in the use of AI being in companies’
marketing-budget allocation and spending effectiveness (Exhibit 1).
The results also suggest that AI’s impact on the bottom line is growing. The share of respondents reporting at least
5 percent of earnings before interest and taxes (EBIT) that’s attributable to AI has increased year over year to 27
percent, up from 22 percent in the previous survey.
1 We define “adoption” as the use of AI capabilities (for example, machine learning, computer vision, natural-language processing) in at least one business function.
2 The state of AI in 2021
Exhibit 1
The most popular AI use cases span a range of functional activities.
TToopp uussee ccaasseess Use cases by function
Most commonly adopted AI use cases,¹ by function, % of respondents
Service-operations optimization 27 Service operations
Product and/or service development
New AI-based enhancements of products 22
Marketing and sales
Risk
Contact-center automation 22
Product-feature optimization 20
Predictive service and intervention 18
Customer-service analytics 17
Creation of new AI-based products 17
Customer segmentation 16
Risk modeling and analytics 16
Fraud and debt analytics 14
The most popular AI use cases span a range of functional activities.
Top use cases UUssee ccaasseess bbyy ffuunnccttiioonn
¹ Out of 39 use cases. Question was asked only of respondents who said their organizations have adopted AI in at least 1 business function.
Most commonly adopted AI use cases within each business function,¹ % of respondents
Service operations² Product and/or service development
New AI-based enhancements
Service-operations optimization 27 22
of products
Contact-center automation 22 Product-feature optimization 20
Marketing and sales Supply-chain management
Customer-service analytics 17 Logistics-network optimization 11
Customer segmentation 16 Sales and demand forecasting 11
Risk Manufacturing
Risk modeling and analytics 16 Predictive maintenance 12
Yield, energy, and/or
Fraud and debt analytics 14 throughput optimization 11
Strategy and corporate finance Human resources
Capital allocation 7 Optimization of talent management 8
Treasury management 6 Performance management 8
¹ Question was asked only of respondents who said their organizations have adopted AI in a given function.
² Eg, field services, customer care, back office.
The state of AI in 2021 3
And while AI’s revenue benefits have held steady or even decreased since the previous survey—especially for supply-
chain management, where AI was unlikely to compensate for the pandemic era’s global supply-chain challenges—the
opposite is true of costs (Exhibit 2). Respondents report significantly greater cost savings from AI than they did
previously in every function, with the biggest year-over-year changes in the shares reporting cost takeout from using
AI in product and service development, marketing and sales, and strategy and corporate finance.
Exhibit 2
Across functions, respondents report higher levels of cost decreases from AI adoption in the pandemic’s
first year, while revenue increases held steady.
CCoosstt ddeeccrreeaassee Revenue increase
Cost decrease from AI adoption by function, % of respondents¹ Decrease by <10% Decrease by 10–19% Decrease ≥20%
Fiscal year 2019 Fiscal year 2020
Service operations 54 30 17 7 87 12 24 51
Manufacturing 52 28 16 8 87 23 27 37
Human resources 52 33 8 11 86 20 26 40
Marketing and sales 41 25 9 7 83 21 35 27
Risk 46 16 18 12 78 17 20 41
Supply-chain management 56 44 6 6 78 15 27 36
Product and/or service development 26 12 7 7 69 22 24 23
Strategy and corporate finance 35 20 3 12 68 10 28 30
AcroAsvse rfaugen acctroisosn asll ,a crteivsitpiesondents rep4o4rt hig2h5er leve11ls o8f cost decreases fr7o9m A1I8 adoptio2n8 in the pand33emic’s
first year, while revenue increases held steady.
¹Question was asked only of respondents who said their organizations have adopted AI in a given function. Respondents who said “no change,” “cost increase,” “not applicable,” or “don’t know” are not shown.
Cost decrease RReevveennuuee iinnccrreeaassee
Revenue increase from AI adoption by function, % of respondents¹ Increase by ≤ 5% Increase by 6–10% Increase by >10%
Fiscal year 2019 Fiscal year 2020
Service operations 25 19 13 57 34 16 15 65
Manufacturing 43 18 10 71 38 15 10 63
Human resources 35 11 10 56 30 18 15 63
Marketing and sales 43 26 10 79 38 25 11 74
Risk 33 16 19 68 26 25 13 64
Supply-chain management 38 26 8 72 27 15 12 54
Product and/or service development 30 19 16 65 30 25 15 70
Strategy and corporate finance 36 24 13 73 33 32 2 67
Average across all activities 36 20 10 66 33 21 13 67
¹Question was asked only of respondents who said their organizations have adopted AI in a given function. Respondents who said “no change,” “revenue decrease,” “not applicable,” or “don’t know” are not shown.
4 The state of AI in 2021
Finally, respondents say AI’s prospects remain strong. Nearly two-thirds say their companies’ investments in AI will
continue to increase over the next three years, similar to the results from the 2020 survey.
The differentiators of AI outperformance
We sought to understand more about the factors and practices that differentiate the best AI programs from all others:
specifically, at the organizations at which respondents attribute at least 20 percent of EBIT to their use of AI—our “AI
high performers.” With adoption becoming ever more commonplace, we asked new questions about more advanced
AI practices, particularly those involved in MLOps, a best-practice approach to building and deploying machine-
learning-based AI that has emerged over the past few years.
While organizations seeing lower returns from AI are increasingly engaging in core AI practices, AI high performers
are still more likely to engage in most of the core practices. High performers also engage in most of the advanced AI
practices more often than others do (Exhibit 3).
Exhibit 3
Organizations seeing the highest returns from AI are more likely to follow
both core and more advanced best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
CCoorree Advanced data Advanced models, tools, and technology User enablement
AI high performers² All other respondents
Use design thinking when developing AI tools 60 46
Test the performance of our AI models internally before deployment 57 43
Track the performance of AI models to ensure that process outcomes
46 35
and/or models improve over time
Have well-defined processes for data governance 45 37
Have protocols in place to ensure good data quality 40 42
Have a clear framework for AI governance that covers the model-
38 20
development process
AI-development teams follow standard protocols for building and
36 33
delivering AI tools
Have well-defined capability-building programs to develop technology
36 20
personnel’s AI skills
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
The state of AI in 2021 5
Exhibit 3 cont.
Organizations seeing the highest returns from AI are more likely to follow
both core and more advanced best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Core AAddvvaanncceedd ddaattaa Advanced models, tools, and technology User enablement
AI high performers² All other respondents
Have a data dictionary that is accessible across the enterprise 53 29
Rapidly integrate internal structured data to use in our AI initiatives 51 32
Have scalable internal processes for labeling AI training data 48 22
Have well-defined processses for data governance 45 37
Generate synthetic data to train AI models when
27 27
we lack sufficient natural data sets
Organizations seeing the highest returns from AI are more likely to follow
both core and more advanced best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Core Advanced data AAddvvaanncceedd mmooddeellss,, ttoooollss,, aanndd tteecchhnnoollooggyy User enablement
AI high performers² All other respondents
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
Take a full life-cycle approach to developing and deploying AI models 57 26
Regularly refresh our AI models, based on clearly defined criteria for
49 23
when and why to do so
Have techniques and processes in place to ensure that our models
45 31
are explainable
Refresh our AI/ML tech stack at least annually to take advantage of the
45 16
latest technological advances
Design AI models with a focus on ensuring they are reusable 43 27
Use external third-party services to test, validate, verify, and monitor the
35 28
performance of our AI models
Use a standardized end-to-end platform for AI-related data science, data
32 21
engineering, and application development
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
6 The state of AI in 2021
Exhibit 3 cont.
Organizations seeing the highest returns from AI are more likely to follow
both core and more advanced best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Core Advanced data Advanced models, tools, and technology UUsseerr eennaabblleemmeenntt
AI high performers² All other respondents
Users are taught the basics of how the models work 57 35
Users are consulted throughout the design, development, training, and
50 50
deployment phases
Users are taught how to use the model 46 45
There are designated channels of communications and touchpoints
39 20
between AI users and the organization’s data science team
A dedicated training center develops nontechnical personnel’s AI skills
34 14
through hands-on learning
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
There’s evidence that engaging in such practices is helping high performers industrialize and professionalize their
AI work, which leads to better results and greater efficiency and predictability in their AI spending. Three-quarters
of AI high performers say the cost to produce AI models has been on par with or even less than they expected,
whereas half of all other respondents say their companies’ AI project costs were higher than expected (Exhibit 4).
Going forward, the AI high performers’ work could push them farther ahead of the pack, since both groups plan to
increase their spending on AI by roughly the same amount.
The survey results also suggest that AI high performers could be gaining some of their efficiency by using the cloud.
Most companies—whether they are high performers or not—tend to use a mix of cloud and on-premises platforms
for AI similar to what they use for overall IT workloads. But the high performers use cloud infrastructure much more
than their peers do: 64 percent of their AI workloads run on public or hybrid cloud, compared with 44 percent at
other companies. This group is also accessing a wider range of AI capabilities and techniques on a public cloud. For
example, they are twice as likely as the rest to say they tap the cloud for natural-language-speech understanding
and facial-recognition capabilities.
The state of AI in 2021 7
Exhibit 4
Compared with their peers, the high performers’ AI spending is more efficient and predictable.
Typical costs for AI model production, compared with expected,¹ % of respondents
More than About the Less than Don’t
expected same expected know
AI high performers² 23 55 20 2
All other respondents
51 34 8 8
¹Figures may not sum to 100%, because of rounding.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
Managing AI risks
No matter a company’s AI performance, risk management remains an area where many have room to improve—
which we have seen in previous survey results. Cybersecurity remains the most recognized risk among respondents,
yet a smaller share says so than did in 2020, despite the rising threat of cyberincidents seen throughout the COVID-
19 pandemic. On a positive note, respondents report increasing focus on equity and fairness as a relevant risk and
one that their companies are mitigating.
Across regions, survey respondents report some notable changes since the previous survey and very different
opinions on cybersecurity risks (Exhibit 5). In developed economies, their views on the biggest risks have held
relatively steady since 2020, though 57 percent (versus 63 percent last year) cite cybersecurity as a relevant AI risk.
In emerging economies, respondents report a more dramatic decline in the relevance and mitigation of several of
the top risks. Yet, they also report personal and individual privacy as a relevant AI risk more often.
When asked why companies aren’t mitigating all relevant risks, respondents most often say it’s because they lack
capacity to address the full range of risks they face and have had to prioritize. Notably, the second-most common
response from those seeing lower returns from AI adoption is that they are unclear on the extent of their exposure
to AI risks (29 percent versus only 17 percent of AI high performers). And by geography, respondents in emerging
economies are more likely than others to report that they are waiting until clearer regulations for risk mitigation are
in place, and that they know from formal assessments that mitigation is more costly than the consequences of a
risk-related incident.
8 The state of AI in 2021
Exhibit 5
The management of AI risks remains an area for significant improvement, as respondents
report a waning focus on cyber—especially in emerging economies.
Relevant risks Mitigated risks
AI risks that organizations consider relevant, % of respondents by office headquarters¹ In emerging economies
In developed economies
2020 2021
Cybersecurity 59 47
63 57
Regulatory compliance 37 40
51 50
Explainability² 31 34
43 44
Personal/individual privacy 33 45
41 41
Organizational reputation 26 24
32 37
Equity and fairness 22 30
24 30
Workforce/labor displacement 35 31
29 24
Physical safety 19 18
19 22
National security 12 18
16 12
Political stability 11 16
8 7
¹ “EmeTrghinge e cmonoamnieas”g ineclumdese rnestpo ondfe nAtsI i nr AisSEkAsN , rCehinma, Iandiina, sLa atinn A maerriecaa, M fidodlre Esaisgt, nNoirfithc Aafrincat, S iomuthp Asrioa, vaned msube-Snahta,r aan sAf rricea,s apndo “dnevdeleopnedt esc onomies” includes respondents in
developed Asia, Europe, and North America. Question was asked only of respondents who said their organizations have adopted AI in at least 1 business function; those who answered “don’t know” are
not srheowpn.ort a waning focus on cyber—especially in emerging economies.
² That is, the ability to explain how AI models come to their decisions.
Relevant risks Mitigated risks
AI risks that organizations are working to mitigate, % of respondents by office headquarters¹ In emerging economies
In developed economies
2020 2021
Cybersecurity 50 36
51 50
Regulatory compliance 28 24
41 39
Explainability² 19 20
27 30
Personal/individual privacy 24 28
32 29
Organizational reputation 17 15
23 24
Equity and fairness 10 16
15 21
Workforce/labor displacement 14 19
20 14
Physical safety 13 14
15 17
National security 6 8
11 8
Political stability 5 3
4 4
¹ “Emerging economies” includes respondents in Association of Southeast Asian Nations, China, India, Latin America, Middle East, North Africa, South Asia, and sub-Saharan Africa, and “developed
economies” includes respondents in developed Asia, Europe, and North America. Question was asked only of respondents who said their organizations have adopted AI in ≥1 business function. Those
who answered “don’t know” are not shown.
² That is, the ability to explain how AI models come to their decisions.
The state of AI in 2021 9
Additional survey results suggest a way forward for companies that continue to struggle with risk management in
AI. We asked about a range of risk-mitigation practices related to model documentation, data validation, and checks
on bias. And in most cases, AI high performers are more likely than other organizations to engage in these practices
(Exhibit 6).
Exhibit 6
Organizations seeing the highest returns from AI engage in risk-mitigation
practices more often than others.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
TTrraaiinniinngg aanndd tteessttiinngg ddaattaa Measuring model bias and accuracy Model documentation
AI high performers² All other respondents
Scan training and testing data to detect the underrepresentation of
47 33
protected characteristics and/or attributes
Data professionals actively check for skewed or biased data during
47 27
data ingestion
Increase the representation of protected characteristics and/or attributes
43 23
in our training and testing data as needed
Data professionals actively check for skewed or biased data at several
36 24
stages of model development
Legal and risk professionals work with data-science teams to help them
24 26
understand definitions of bias & protected classes
Organizations seeing the highest returns from AI engage in risk-mitigation
pHraavcet ai cdeedsic amtedo groeve ornfatnecen c otmhmaintte oe tthhate inrcslu.des risk
23 17
and legal professionals
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Training and testing data MMeeaassuurriinngg mmooddeell bbiiaass aanndd aaccccuurraaccyy Model documentation
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
AI high performers² All other respondents
Retrain our models when issues are detected 43 27
Regularly monitor for data drift and/or concept drift 42 25
Have a human-in-the-loop verification phase of model deployment that
39 30
expressly tests and controls for model bias
Model users are taught how to monitor for issues 39 21
Test for different outcomes based on a change to protected
36 21
characteristics
Refresh our models based on clearly defined criteria for how frequently
36 20
they need to be updated
Have mechanisms in place to monitor for model bias specifically 31 19
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
10 The state of AI in 2021
Organizations seeing the highest returns from AI engage in risk-mitigation
practices more often than others.
Exhibit 6 cont.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Training and testing data Measuring model bias and accuracy MMooddeell ddooccuummeennttaattiioonn
AI high performers² All other respondents
Document model performance on an ongoing basis 59 43
Document model architecture 53 43
Record information about both the training data set and the model-
52 34
training process
Document data flows 52 42
Document known issues and/or trade-offs with the model 43 30
Document the risk-mitigation strategies applied to both the model and its
30 28
underlying data
Documentation enables a clear understanding of the relative weight that
17 11
our data’s inputs have on the model’s output
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2020 was attributable to their use of AI.
The survey content and analysis were developed by Michael Chui, a partner of the McKinsey Global Institute and a
partner in McKinsey’s Bay Area office; Bryce Hall, an associate partner in the Washington, DC, office; Alex Singla, a
senior partner in the Chicago office; and Alex Sukharevsky, a senior partner in the Moscow office.
They wish to thank Jacomo Corbo, David DeLallo, Liz Grennan, Heather Hanselman, and Kia Javanmardian for their
contributions to this article.
Copyright © 2021 McKinsey & Company. All rights reserved.
The state of AI in 2021 11 |
63 | mckinsey | building-the-ai-bank-of-the-future.pdf | Global Banking Practice
Building the AI bank
of the future
May 2021
© Getty Images
Global Banking Practice
Building the AI bank of
the future
To thrive in the AI-powered digital age, banks will need an AI-and-analytics
capability stack that delivers intelligent, personalized solutions and
distinctive experiences at scale in real time.
May 2021
Contents
4 AI bank of the future: Can banks meet the
AI challenge?
Artificial intelligence technologies are increasingly
integral to the world we live in, and banks need
to deploy these technologies at scale to remain
relevant. Success requires a holistic transformation
spanning multiple layers of the organization.
18 Reimagining customer engagement for the
AI bank of the future
Banks can meet rising customer expectations by
applying AI to offer intelligent propositions and smart
servicing that can seamlessly embed in partner
ecosystems.
29 AI-powered decision making for the bank of
the future
Banks are already strengthening customer relationships
and lowering costs by using artificial intelligence to
guide customer engagement. Success requires that
capability stacks include the right decisioning elements.
41 Beyond digital transformations: Modernizing
core technology for the AI bank of the future
For artificial intelligence to deliver value across the
organization, banks need core technology that is scalable,
resilient, and adaptable. Building that requires changes in
six key areas.
52 Platform operating model for the AI bank of
the future
Technology alone cannot define a successful AI bank;
the AI bank of the future also needs an operating
model that brings together the right talent, culture, and
organizational design.
Introduction
Banking is at a pivotal moment. Technology leaders recognize that the economies of scale
disruption and consumer shifts are laying the basis afforded to organizations that efficiently deploy AI
for a new S-curve for banking business models, technologies will compel incumbents to strengthen
and the COVID-19 pandemic has accelerated customer engagement each day with distinctive
these trends. Building upon this momentum, experiences and superior value propositions. This
the advancement of artificial-intelligence (AI) value begins with intelligent, highly personalized
technologies within financial services offers banks offers and extends to smart services, streamlined
the potential to increase revenue at lower cost by omnichannel journeys, and seamless embedding
engaging and serving customers in radically new of trusted bank functionality within partner
ways, using a new business model we call “the AI ecosystems. From the customer’s point of view,
bank of the future.” The articles collected here these are key features of an AI bank.
outline key milestones on a path we believe can lead
banks to deeper customer relationships, expanded
market share, and stronger financial performance. The building blocks of an AI bank
Our goal in this compendium is to give banking
The opportunity for a new business model comes as leaders an end-to-end view of an AI bank’s full stack
banks face daunting challenges on multiple fronts. capabilities and examine how these capabilities
In capital markets, many banks trade at a 50 percent cut across four layers: engagement, AI-powered
discount to book, and approximately three-quarters decision making, core technology and data
of banks globally earn returns on equity that do not infrastructure, and a platform-based operating
cover their cost of equity.¹ Traditional banks also model.
face diverse competitive threats from neobanks and
nonbank challengers. Leading financial institutions In our first article, “AI-bank of the future: Can banks
are already leveraging AI for split-second loan meet the challenge?” we take a closer look at the
approvals, biometric authentication, and virtual trends and challenges leading banks to take an
assistants, to name just a few examples. Fintech AI-first approach as they define their core value
and other digital-commerce innovators are steadily proposition. We continue by considering a day in the
disintermediating banks from crucial aspects of life of a retail consumer and small-business owner
customer relationships, and large tech companies transacting with an AI bank. Then we summarize the
are incorporating payments and, in some cases, requirements for each layer of the AI-and-analytics
lending capabilities to attract more users with capability stack.
an ever-broader range of services. Further, as
customers conduct a growing share of their daily The second article, “Reimagining customer
transactions through digital channels, they are engagement for the AI bank of the future,” examines
becoming accustomed to the ease, speed, and the capabilities that enable a bank to provide
personalized service offered by digital natives, and customers with intelligent offers, personalized
their expectations of banks are rising. solutions, and smart servicing within omnichannel
journeys across bank-owned platforms and partner
To compete and thrive in this challenging ecosystems.
environment, traditional banks will need to build a
new value proposition founded upon leading-edge In our third article, “AI-powered decision making for
AI-and-analytics capabilities. They must become the bank of the future,” we examine how machine-
“AI first” in their strategy and operations. Many bank learning models can significantly enhance customer
1 “A test of resilience: Banking through the crisis, and beyond,” Global Banking Annual Review, December 2020, McKinsey.com.
2 Building the AI bank of the future
experiences and bank productivity, and we outline Once bank leaders have established their AI-first
the steps banks can follow to build the architecture vision, they will need to chart a road map detailing
required to generate real-time analytical insights and the discrete steps for modernizing enterprise
translate them into messages addressing precise technology and streamlining the end-to-end stack.
customer needs. Joint business-technology owners of customer-
facing solutions should assess the potential of
The fourth article, “Beyond digital transformations: emerging technologies to meet precise customer
Modernizing core technology for the AI bank of needs and prioritize technology initiatives with the
the future,” discusses the key elements required greatest potential impact on customer experience
for the backbone of the capability stack, including and value for the bank. We also recommend that
automated cloud provisioning and an API and banks consider leveraging partnerships for non-
streaming architecture to enable continuous, differentiating capabilities while devoting capital
secure data exchange between the centralized data resources to in-house development of capabilities
infrastructure and the decisioning and engagement that set the bank apart from the competition.
layers.
As we discuss in our final article, “Platform operating
model for the AI bank of the future,” deploying these Building the AI bank of the future will allow
AI-and-analytics capabilities efficiently at scale institutions to innovate faster, compete with digital
requires cross-functional business-technology natives in building deeper customer relationships
platforms comprising agile teams and new at scale, and achieve sustainable increases in
technology talent. profits and valuations in this new age. We hope
the following articles will help banks establish their
vision and craft a road map for the journey.
Starting the journey
To get started on the transformation, bank leaders
should formulate the organization’s strategic goals
for the AI-enabled digital age and evaluate how AI
technologies can support these goals.
Renny Thomas
Senior Partner
McKinsey & Company
Building the AI bank of the future 3
Global Banking & Securities
AI bank of the future: Can
banks meet the AI challenge?
Artificial intelligence technologies are increasingly integral to the world we
live in, and banks need to deploy these technologies at scale to remain
relevant. Success requires a holistic transformation spanning multiple layers
of the organization.
by Suparna Biswas, Brant Carson, Violet Chung, Shwaitang Singh, and Renny Thomas
© Getty Images
September 2020
4
In 2016, AlphaGo, a machine, defeated 18-time 3. What obstacles prevent banks from deploying
world champion Lee Sedol at the game of AI capabilities at scale?
Go, a complex board game requiring intuition,
imagination, and strategic thinking—abilities 4. How can banks transform to become AI first?
long considered distinctly human. Since then,
artificial intelligence (AI) technologies have
advanced even further,¹ and their transformative 1. Why must banks become AI first?
impact is increasingly evident across Over several decades, banks have continually
industries. AI-powered machines are tailoring adapted the latest technology innovations to
recommendations of digital content to individual redefine how customers interact with them. Banks
tastes and preferences, designing clothing introduced ATMs in the 1960s and electronic,
lines for fashion retailers, and even beginning to card-based payments in the ’70s. The 2000s saw
surpass experienced doctors in detecting signs of broad adoption of 24/7 online banking, followed
cancer. For global banking, McKinsey estimates by the spread of mobile-based “banking on the go”
that AI technologies could potentially deliver up to in the 2010s.
$1 trillion of additional value each year.²
Few would disagree that we’re now in the
Many banks, however, have struggled to move AI-powered digital age, facilitated by falling costs
from experimentation around select use cases to for data storage and processing, increasing
scaling AI technologies across the organization. access and connectivity for all, and rapid
Reasons include the lack of a clear strategy for AI, advances in AI technologies. These technologies
an inflexible and investment-starved technology can lead to higher automation and, when deployed
core, fragmented data assets, and outmoded after controlling for risks, can often improve upon
operating models that hamper collaboration human decision making in terms of both speed
between business and technology teams. What and accuracy. The potential for value creation
is more, several trends in digital engagement is one of the largest across industries, as AI can
have accelerated during the COVID-19 pandemic, potentially unlock $1 trillion of incremental value
and big-tech companies are looking to enter for banks, annually (Exhibit 1).
financial services as the next adjacency. To
compete successfully and thrive, incumbent Across more than 25 use cases,³ AI technologies
banks must become “AI-first” institutions, can help boost revenues through increased
adopting AI technologies as the foundation for personalization of services to customers (and
new value propositions and distinctive customer employees); lower costs through efficiencies
experiences. generated by higher automation, reduced errors
rates, and better resource utilization; and uncover
In this article, we propose answers to four new and previously unrealized opportunities
questions that can help leaders articulate a clear based on an improved ability to process and
vision and develop a road map for becoming an generate insights from vast troves of data.
AI-first bank:
More broadly, disruptive AI technologies can
1. Why must banks become AI first? dramatically improve banks’ ability to achieve
four key outcomes: higher profits, at-scale
2. What might the AI bank of the future look like? personalization, distinctive omnichannel
1 AI can be defined as the ability of a machine to perform cognitive functions associated with human minds (e.g., perceiving, reasoning, learning, and
problem solving). It includes various capabilities, such as machine learning, facial recognition, computer vision, smart robotics, virtual agents, and
autonomous vehicles. See “Global AI Survey: AI proves its worth, but few scale impact,” November 2019, McKinsey.com.
2 “The executive’s AI playbook,” McKinsey.com.
3 For an interactive view, visit: www.mckinsey.com/business-functions/mckinsey-analytics/our-insights/the-executives-ai-
playbook?page=industries/banking/
5 AI bank of the future: Can banks meet the AI challenge?
Exhibit 1
PPootetnetnitaila al nannunaula vl avlauleu oef o Af IA aIn adn adn aanlyatliyctsi cfosr f oglro gblaolb baaln bkainnkgi cnogu cldo urelda crhe aacs hh iagsh as
$h1i gtrhil aliso n$.1 trillion.
Total potential annual value, $ billion
1,022.4 (15.4% of sales)
Traditional AI
Advanced AI
and analytics
660.9 361.5
% of value driven by advanced AI, by function
100
Finance and IT: 8.0 Other operations: $2.4 B
0.0 8.0 0.0 2.4
50
HR: 14.2
8.6 5.7
Marketing and sales: 624.8
Risk: 372.9
363.8 261.1
288.6 84.3
0
Source: "The executive's AI playbook," McKinsey.com. (See "Banking," under "Value & Assess.")
experiences, and rapid innovation cycles. Banks As consumers increase their use of digital
that fail to make AI central to their core strategy banking services, they grow to expect more,
and operations—what we refer to as becoming particularly when compared to the standards
“AI-first”—will risk being overtaken by competition they are accustomed to from leading consumer-
and deserted by their customers. This risk is internet companies. Meanwhile, these digital
further accentuated by four current trends: experience leaders continuously raise the bar
on personalization, to the point where they
— Rising customer expectations as adoption sometimes anticipate customer needs before
of digital banking increases. In the first few the customer is aware of them, and offer highly-
months of the COVID-19 pandemic, use of tailored services at the right time, through the
online and mobile banking channels across right channel.
countries has increased by an estimated 20
to 50 percent and is expected to continue at — Leading financial institutions’ use of advanced
this higher level once the pandemic subsides. AI technologies is steadily increasing. Nearly
Across diverse global markets, between 15 and 60 percent of financial-services sector
45 percent of consumers expect to cut back respondents in McKinsey’s Global AI Survey
on branch visits following the end of the crisis.⁴ report⁵ that their companies have embedded
4 John Euart, Nuno Ferreira, Jonathan Gordon, Ajay Gupta, Atakan Hilal, Olivia White, “A global view of financial life during COVID-19—an update,”
July 2020, McKinsey.com.
5 Arif Cam, Michael Chui, Bryce Hall, “Global AI Survey: AI proves its worth, but few scale impact,” November 2019, McKinsey.com.
AI bank of the future: Can banks meet the AI challenge? 6
at least one AI capability. The most commonly but also to book a cab, order food, schedule
used AI technologies are: robotic process a massage, play games, send money to a
automation (36 percent) for structured contact, and access a personal line of credit.
operational tasks; virtual assistants or Similarly, across countries, nonbanking
conversational interfaces (32 percent ) for businesses and “super apps” are embedding
customer service divisions; and machine financial services and products in their
learning techniques (25 percent) to detect journeys, delivering compelling experiences
fraud and support underwriting and risk for customers, and disrupting traditional
management. While for many financial services methods for discovering banking products and
firms, the use of AI is episodic and focused on services. As a result, banks will need to rethink
specific use cases, an increasing number of how they participate in digital ecosystems,
banking leaders are taking a comprehensive and use AI to harness the full power of data
approach to deploying advanced AI, and available from these new sources.
embedding it across the full lifecycle, from the
front- to the back-office (Exhibit 2). — Technology giants are entering financial
services as the next adjacency to their
— Digital ecosystems are disintermediating core business models. Globally, leading
traditional financial services. By enabling technology giants have built extraordinary
access to a diverse set of services through market advantages: a large and engaged
a common access point, digital ecosystems customer network; troves of data, enabling a
have transformed the way consumers discover, robust and increasingly precise understanding
evaluate, and purchase goods and services. of individual customers; natural strengths
For example, WeChat users in China can use in developing and scaling innovative
the same app not only to exchange messages, technologies (including AI); and access to
Web <year>
<article slug>
EExxhhibiibt <itx 2> of <y>
Banks are expanding their use of AI technologies to improve customer
Banks are expanding their use of AI technologies to improve customer
experiences and back-office processes.
experiences and back-office processes.
Front office Back office
Smile-to-pay facial scanning Micro-expression analysis Biometrics (voice, video, Machine learning to detect
to initiate transaction with virtual loan officers print) to authenticate and fraud patterns,
authorize cybersecurity attacks
Conversational bots for Humanoid robots in branches Machine vision and natural- Real-time transaction
basic servicing requests to serve customers language processing to scan analysis for risk monitoring
and process documents
7 AI bank of the future: Can banks meet the AI challenge?
low-cost capital. In the past, tech giants have digital era, the AI-first bank will offer propositions
aggressively entered into adjacent businesses and experiences that are intelligent (that
in search of new revenue streams and to is, recommending actions, anticipating and
keep customers engaged with a fresh stream automating key decisions or tasks), personalized
of offerings. Big-tech players have already (that is, relevant and timely, and based on a
gained a foothold in financial services in select detailed understanding of customers’ past
domains (especially in payments and, in some behavior and context), and truly omnichannel
cases, lending and insurance), and they may (seamlessly spanning the physical and online
soon look to press their advantages to deepen contexts across multiple devices, and delivering
their presence and build greater scale. a consistent experience) and that blend banking
capabilities with relevant products and services
beyond banking. Exhibit 3 illustrates how such a
2. What might the AI bank of the bank could engage a retail customer throughout
future look like? the day. Exhibit 4 shows an example of the banking
To meet customers’ rising expectations and experience of a small-business owner or the
beat competitive threats in the AI-powered treasurer of a medium-size enterprise.
Exhibit 3
How AI transforms banking for a retail customer.
How AI transforms banking for a retail customer.
Name: Anya
Age: 28 years
Occupation: Working professional
Anya receives
App offers money- integrated portfolio
management and view and a set of
Anya uses smile- savings solutions, actions with the
Seamless to-pay to Analytics- prioritizes card Aggregated potential to
integration with initiate payment backed payments overview of daily augment returns
nonbanking apps personalized offers
activities
Bank app Facial recognition Anya gets 2% off Personalized Anya receives Savings and
investment recom-
recognizes Anya's for frictionless on health money-management end-of-day
mendations
spending patterns payment insurance solutions overview of her
and suggests premiums based activities, with
coffee at nearby on her gym augmented reality,
cafes activity and and reminders to
sleep habits pay bills
Intelligent Personalized Omnichannel Banking and beyond banking
AI bank of the future: Can banks meet the AI challenge? 8
Exhibit 4
How AI transforms banking for a small- or medium-size-enterprise customer.
How AI transforms banking for a small- or medium-size-enterprise customer.
Name: Dany
Age: 36 years
Occupation: Treasurer of a small manufacturing unit
Dany answers
short questionnaire;
app scans his facial
An AI-powered
movements
Dany is assisted virtual adviser
Firm is credited in sourcing and resolves queries
with funds after selecting the Dany seeks
Customized application Seamless right vendors Beyond- professional advice
lending solutions approval inventory and receiv- and partners banking support on a lending offer
ables management services
Bank is integrated Micro-expression App suggests SME platform to Dany gets prefilled Serviced by an AI-
with client analysis to review loan items to reorder, source suppliers tax documents to powered virtual
business applications gives visual reports and buyers review and adviser
management on receivables approve; files with
systems management a single click
Dany receives
Dany gets loan
customized
offer based on
solutions for
company projected
invoice discounting,
cash flows
factoring, etc.
Intelligent Personalized Omnichannel Banking and beyond banking
Internally, the AI-first institution will be optimized The AI-first bank of the future will also enjoy
for operational efficiency through extreme the speed and agility that today characterize
automation of manual tasks (a “zero-ops” mindset) digital-native companies. It will innovate
and the replacement or augmentation of human rapidly, launching new features in days or
decisions by advanced diagnostic engines in weeks instead of months. It will collaborate
diverse areas of bank operations. These gains extensively with partners to deliver new
in operational performance will flow from broad value propositions integrated seamlessly
application of traditional and leading-edge AI across journeys, technology platforms, and
technologies, such as machine learning and data sets.
facial recognition, to analyze large and complex
reserves of customer data in (near) real time.
9 AI bank of the future: Can banks meet the AI challenge?
cases. Without a centralized data backbone, it is
3. What obstacles prevent banks from
practically impossible to analyze the relevant data
deploying AI capabilities at scale?
and generate an intelligent recommendation or
Incumbent banks face two sets of objectives,
offer at the right moment. If data constitute the
which on first glance appear to be at odds. On
bank’s fundamental raw material, the data must be
the one hand, banks need to achieve the speed,
governed and made available securely in a manner
agility, and flexibility innate to a fintech. On the
that enables analysis of data from internal and
other, they must continue managing the scale,
external sources at scale for millions of customers,
security standards, and regulatory requirements
in (near) real time, at the “point of decision” across
of a traditional financial-services enterprise.
the organization. Lastly, for various analytics and
advanced-AI models to scale, organizations need
Despite billions of dollars spent on change-
a robust set of tools and standardized processes
the-bank technology initiatives each year, few
to build, test, deploy, and monitor models, in a
banks have succeeded in diffusing and scaling
repeatable and “industrial” way.
AI technologies throughout the organization.
Among the obstacles hampering banks’ efforts,
Banks’ traditional operating models further
the most common is the lack of a clear strategy
impede their efforts to meet the need for
for AI.⁶ Two additional challenges for many
continuous innovation. Most traditional banks
banks are, first, a weak core technology and data
are organized around distinct business lines,
backbone and, second, an outmoded operating
with centralized technology and analytics
model and talent strategy.
teams structured as cost centers. Business
owners define goals unilaterally, and alignment
Built for stability, banks’ core technology
with the enterprise’s technology and analytics
systems have performed well, particularly in
strategy (where it exists) is often weak or
supporting traditional payments and lending
inadequate. Siloed working teams and “waterfall”
operations. However, banks must resolve
implementation processes invariably lead
several weaknesses inherent to legacy systems
to delays, cost overruns, and suboptimal
before they can deploy AI technologies at scale
performance. Additionally, organizations lack
(Exhibit 5). First and foremost, these systems
a test-and-learn mindset and robust feedback
often lack the capacity and flexibility required
loops that promote rapid experimentation and
to support the variable computing requirements,
iterative improvement. Often unsatisfied with the
data-processing needs, and real-time analysis
performance of past projects and experiments,
that closed-loop AI applications require.⁷ Core
business executives tend to rely on third-party
systems are also difficult to change, and their
technology providers for critical functionalities,
maintenance requires significant resources.
starving capabilities and talent that should ideally
What is more, many banks’ data reserves are
be developed in-house to ensure competitive
fragmented across multiple silos (separate
differentiation.
business and technology teams), and analytics
efforts are focused narrowly on stand-alone use
6 Michael Chui, Sankalp Malhotra, “AI adoption advances, but foundational barriers remain,” November 2018, McKinsey.com.
7 “Closed loop” refers to the fact that the models’ intelligence is applied to incoming data in near real time, which in turn refines the content presented
to the user in near real time.
AI bank of the future: Can banks meet the AI challenge? 10
Exhibit 5
IInnvveessttmmeentnst sin i nco croer tee cthe cahre a crrei tcicraitli ctoa lm teoe mt ienecrte ianscinrega dseinmga nddesm foarn ds for
ssccaalalabbiliiltiyty, ,fl flexeixbiibliitliyt,y a, nadn dsp sepede.e d.
Cloud
Data API1
Challenges How cloud computing can help
Core/legacy systems can’t scale sufficiently Enables higher scalability, resilience of services and
(eg, 150+ transactions/second) platforms through virtualization of infrastructure
Significant time, effort, and team sizes Reduces IT overhead, enables automation of several
required to maintain infrastructure infrastructure-management tasks, and allows development
teams to “self-serve”
Long time required to provision environments
for development and testing (eg, 40+ days in Enables faster time to market; dramatically reduces time by
some cases) providing managed services (e., setting up new environments
in minutes vs days)
Challenges How best-in-class data management can help
High error rates; poor refresh rates; lack of Ensures high degree of accuracy and single source of truth
golden source of truth in a cost-effective manner
Hard to access in a timely fashion for various Enables timely and role-appropriate access for various use
use cases cases (eg, regulatory, business intelligence at scale, advanced
analytics and machine learning, exploratory)
Data trapped in silos across multiple units and
hard to integrate with external sources Enables a 360-degree view across the organization to enable
generation of deeper insights by decision-making algorithms
and models
Challenges How APIs can help
Longer time to market, limited reusability of Promote reusability and accelerate development by enabling
code and software across internal teams access to granular services (internal and external)
Hard to partner or collaborate with external Reduce complexity and enable faster collaboration with
partners; long time to integrate external partners
Suboptimal user experience—hard to stitch Enhance customer experience by enabling timely access to
data and services across multiple functional data and services across different teams; faster time to market
siloes for an integrated proposition due to limited coordination, cross-team testing
1Application programming interface.
11 AI bank of the future: Can banks meet the AI challenge?
4. How can banks transform to First, banks will need to move beyond highly
become AI-first? standardized products to create integrated
To overcome the challenges that limit propositions that target “jobs to be done.”⁸ This
organization-wide deployment of AI requires embedding personalization decisions
technologies, banks must take a holistic (what to offer, when to offer, which channel
approach. To become AI-first, banks must invest to offer) in the core customer journeys and
in transforming capabilities across all four layers designing value propositions that go beyond the
of the integrated capability stack (Exhibit 6): the core banking product and include intelligence
engagement layer, the AI-powered decisioning that automates decisions and activities on
layer, the core technology and data layer, and the behalf of the customer. Further, banks should
operating model. strive to integrate relevant non-banking
products and services that, together with the
core banking product, comprehensively address
As we will explain, when these interdependent
the customer end need. An illustration of the
layers work in unison, they enable a bank to
“jobs-to-be-done” approach can be seen in the
provide customers with distinctive omnichannel
way fintech Tally helps customers grapple with
experiences, support at-scale personalization,
the challenge of managing multiple credit cards.
and drive the rapid innovation cycles critical
The fintech’s customers can solve several pain
to remaining competitive in today’s world.
points—including decisions about which card to
Each layer has a unique role to play—under-
pay first (tailored to the forecast of their monthly
investment in a single layer creates a weak link
income and expenses), when to pay, and how
that can cripple the entire enterprise.
much to pay (minimum balance versus retiring
principal)—a complex set of tasks that are often
The following paragraphs explore some of the
not done well by customers themselves.
changes banks will need to undertake in each
layer of this capability stack.
The second necessary shift is to embed
customer journeys seamlessly in partner
Layer 1: Reimagining the customer
ecosystems and platforms, so that banks
engagement layer
engage customers at the point of end use and
Increasingly, customers expect their bank to be
in the process take advantage of partners’
present in their end-use journeys, know their
data and channel platform to increase higher
context and needs no matter where they interact
engagement and usage. ICICI Bank in India
with the bank, and to enable a frictionless
embedded basic banking services on WhatsApp
experience. Numerous banking activities
(a popular messaging platform in India) and
(e.g., payments, certain types of lending) are
scaled up to one million users within three
becoming invisible, as journeys often begin and
months of launch.⁹ In a world where consumers
end on interfaces beyond the bank’s proprietary
and businesses rely increasingly on digital
platforms. For the bank to be ubiquitous in
ecosystems, banks should decide on the
customers’ lives, solving latent and emerging
posture they would like to adopt across multiple
needs while delivering intuitive omnichannel
ecosystems—that is, to build, orchestrate, or
experiences, banks will need to reimagine how
partner—and adapt the capabilities of their
they engage with customers and undertake
engagement layer accordingly.
several key shifts.
8 Clayton M. Christensen, Taddy Hall, Karen Dillon and David S. Duncan, “Know your customers ‘jobs to be done,” Harvard Business Review,
September 2016, hbr.org.
9 “ICICI Bank crosses 1 million users on WhatsApp platform,” Live Mint, July 7, 2020, livemint.com.
AI bank of the future: Can banks meet the AI challenge? 12
Exhibit 6
TToo b beeccoomme ean a nA IA-fiI-rfistr sitn sintistutittiuotni,o an b, aan bka mnku smt ustsrte asmtrelianme iltisn eca iptsa bcialiptya bstialictky sfotra ck
vfaolru ve aclrueea tciorena. tion.
AI bank of the future
Personalization Omnichannel Speed and
Profitability
at scale experience innovation
Intelligent products, Within-bank channels and Beyond-bank channels
Reimagined tools, experiences journeys (eg, web, apps, and journeys (eg, Smart service and
engagement for customers and mobile, smart devices, ecosystems, partners, operations
employees branches, Internet of Things) distributors)
1 2 3 4
5
Digital marketing
6
Retention
Credit Monitoring Servicing
Advanced Customer and cross-
decision and and
analytics acquisition selling,
AI-powered making collections engagement
upselling
decision
making
Natural-
Voice- Virtual Facial Behav-
7 language script agents, Computer recog- Block- Robotics ioral
AI capabilities process- analysis bots vision nition chain analytics
ing
A. Tech-forward strategy (in-house build of differ |
65 | mckinsey | How-to-make-AI-work-for-your-business.pdf | REPLACE IMAGE
Photo credit: Getty Images
How to make AI work for your
business
Jacques Bughin, Michael Chui, and Brian McCarthy
A survey of more than 3,000 executives sheds light on how
businesses are using AI, offering lessons for CEOs, as we
explain in this article for Harvard Business Review.
The buzz over artificial intelligence (AI) has While it’s clear that CEOs need to consider
grown loud enough to penetrate the C-suites AI’s business implications, the technology’s
of organizations around the world, and for nascence in business settings makes it less
good reason. Investment in AI is growing and is clear how to profitably employ it. Through a
increasingly coming from organizations outside study of AI that included a survey of 3,073
the tech space. And AI success stories are executives and 160 case studies across 14
becoming more numerous and diverse, from sectors and ten countries, and through a
Amazon reaping operational efficiencies using separate digital research program, we have
its AI-powered Kiva warehouse robots, to GE identified ten key insights CEOs need to know
keeping its industrial equipment running by to embark on a successful AI journey.
leveraging AI for predictive maintenance.
1 McKinsey Analytics
Don’t believe the hype—not every Believe the hype that AI can potentially
business is using AI … yet. boost your top and bottom line.
While investment in AI is heating up, corporate Thirty percent of early AI adopters in our
adoption of AI technologies is still lagging. survey—those using AI at scale or in core
Total investment (internal and external) in processes—say they’ve achieved revenue
AI reached somewhere in the range of increases, leveraging AI in efforts to gain
$26 billion to $39 billion in 2016, with external market share or expand their products and
investment tripling since 2013. Despite this services. Furthermore, early AI adopters are
level of investment, however, AI adoption 3.5 times more likely than others to say they
is in its infancy, with just 20 percent of our expect to grow their profit margin by up to
survey respondents using one or more AI five points more than industry peers. While
technologies at scale or in a core part of their the question of correlation versus causation
business, and only half of those using three can be legitimately raised, a separate analysis
or more. (Our results are weighted to reflect uncovered some evidence that AI is already
the relative economic importance of firms of directly improving profits, with return on AI
different sizes. We include five categories of AI investment in the same range as that for
technology systems: robotics and autonomous associated digital technologies such as big
vehicles, computer vision, language, virtual data and advanced analytics.
agents, and machine learning.)
Without support from leadership, your AI
For the moment, this is good news for those transformation might not succeed.
companies still experimenting with or piloting Successful AI adopters have strong
AI (41 percent). Our results suggest there’s still executive-leadership support for the new
time to climb the learning curve and compete technology. Survey respondents from
using AI. firms that have successfully deployed an
AI technology at scale tend to rate C-suite
However, we are likely at a key inflection point support as being nearly twice as high as that
of AI adoption. AI technologies such as neural- at those companies that have not adopted
based machine learning and natural-language any AI technology. They add that strong
processing are beginning to mature and prove support comes not only from the CEO and
their value, quickly becoming centerpieces IT executives but also from all other C-level
of AI technology suites among adopters. And officers and the board of directors.
we expect at least a portion of current AI
piloters to fully integrate AI in the near term. You don’t have to go it alone on AI—
Finally, adoption appears poised to spread, partner for capability and capacity.
albeit at different rates, across sectors and With the AI field recently picking up its pace of
domains. Telecom and financial services are innovation after the decades-long “AI winter,”
poised to lead the way, with respondents in technical expertise and capabilities are in
these sectors planning to increase their AI tech short supply. Even large digital natives such as
spend by more than 15 percent a year—seven Amazon and Google have turned to companies
percentage points higher than the cross- and talent outside their confines to beef up
industry average—in the next three years. their AI skills. Consider, for example, Google’s
How to make AI work for your business 2
acquisition of DeepMind, which is using its Long-term: Work with academia or a
machine-learning chops to help the tech giant third party to solve a high-impact use case
improve even core businesses such as search (augmented human decision making in a key
optimization. Our survey, in fact, showed that knowledge-worker role, for example) with
early AI adopters have primarily bought the bleeding-edge AI technology to potentially
right fit-for-purpose technology solutions, with capture a sizable first-mover advantage.
only a minority of respondents both developing
and implementing all AI solutions in-house. Machine learning is a powerful tool, but
it’s not right for everything.
Resist the temptation to put technology Machine learning and its most prominent
teams solely in charge of AI initiatives. subfield, deep learning, have attracted a lot
Compartmentalizing accountability for AI with of media attention and received a significant
functional leaders in IT, digital, or innovation share of the financing that has been pouring
can result in a hammer-in-search-of-a-nail into the AI universe, garnering nearly 60
outcome: technologies being launched without percent of all investments from outside the
compelling use cases. To ensure a focus on industry in 2016.
the most valuable use cases, AI initiatives
should be assessed and co-led by both But while machine learning has many
business and technical leaders, an approach applications, it is just one of many AI-related
that has proved successful in the adoption of technologies capable of solving business
other digital technologies. problems. There’s no one-size-fits-all AI
solution. For example, the AI techniques
Take a portfolio approach to accelerate implemented to improve customer-call-
your AI journey. center performance could be very different
AI tools today vary along a spectrum ranging from the technology used to identify credit-
from tools that have been proven to solve card-payments fraud. It’s critical to look for
business problems (for example, pattern the right tool to solve each value-creating
detection for predictive maintenance) to those business problem at a particular stage in an
with low awareness and currently limited but organization’s digital and AI journey.
high-potential utility (for example, application
of AI to develop a competitive strategy). This Digital capabilities come before AI.
distribution suggests that organizations could We found that industries leading in AI
consider a portfolio-based approach to AI adoption—such as high tech, telecom, and
adoption across three time horizons: automotive—are also the ones that are the
most digitized. Likewise, within any industry,
Short-term: Focus on use cases where there the companies that are early adopters of AI
are proven technology solutions today, and have already invested in digital capabilities,
scale them across the organization to drive including cloud infrastructure and big data. In
meaningful bottom-line value. fact, it appears that companies can’t easily
leapfrog to AI without digital-transformation
Medium-term: Experiment with technology experience. Using a battery of statistics, we
that’s emerging but still relatively immature found that the odds of generating profit from
(deep-learning video recognition) to prove its using AI are 50 percent higher for companies
value in key business use cases before scaling. that have strong experience in digitization.
3 McKinsey Analytics
Be bold. technical AI implementation challenges. As
In a separate study on digital disruption, we leaders determine the tasks that machines
found that adopting an offensive digital strategy should handle, versus those that humans
was the most important factor in enabling perform, both new and traditional, it will be
incumbent companies to reverse the curse critical to implement programs that allow
of digital disruption. An organization with an for constant reskilling of the workforce. And
offensive strategy radically adapts its portfolio as AI continues to converge with advanced
of businesses, developing new business visualization, collaboration, and design thinking,
models to build a growth path that is more businesses will need to shift from a primary
robust than before digitization. So far, the same focus on process efficiency to a focus on
seems to hold true for AI: early AI adopters decision-management effectiveness, which
with a very proactive, strictly offensive strategy will further require leaders to create a culture of
report a much better profit outlook than those continuous improvement and learning.
without one.
Make no mistake: the next digital frontier is
The biggest challenges are people and here, and it’s AI. While some firms are still
processes. reeling from previous digital disruptions, a new
In many cases, the change-management one is taking shape. But it’s early days. There’s
challenges of incorporating AI into employee still time to make AI a competitive advantage.
processes and decision making far outweigh
Jacques Bughin is a senior partner in McKinsey’s Brussels office and a director of the McKinsey Global
Institute (MGI); Michael Chui is an MGI partner and is based in the San Francisco office; and Brian
McCarthy is a partner in the Atlanta office.
This article first ran in Harvard Business Review.
Copyright © 2018 McKinsey & Company. All rights reserved.
How to make AI work for your business 4 |
66 | mckinsey | driving-impact-at-scale-from-automation-and-ai.pdf | Driving impact
at scale from
automation
and AI
February 2019
Contents
Introduction 2
Part 1: Why automation and AI?
Harnessing automation for a future that works 6
Notes from the AI frontier: Applications and value of deep learning 10
Artificial intelligence is getting ready for business, but are businesses ready for AI? 26
Part 2: How to make transformation successful
Burned by the bots: Why robotic automation is stumbling 44
Ten red flags signaling your analytics program will fail 48
The automation imperative 56
How to avoid the three common execution pitfalls that derail automation programs 64
The new frontier: Agile automation at scale 72
Part 3: Understanding functional nuances
How bots, algorithms, and artificial intelligence are reshaping the future of corporate 78
support functions
A CIO plan for becoming a leader in intelligent process automation 86
Introduction
Automation, leveraging artificial intelligence (AI) and other technologies, has
opened up new possibilities. The pace of adoption has been rapid. Institutions
of all sizes globally are leveraging automation to drive value. According to the
McKinsey Automation Survey in 2018, 57 percent of 1,300 institutions have
already started on this journey, with another 18 percent planning to kick off
something within the next year.
When done right, automation has proven to deliver real benefits, including the
following:
• Distinctive insights: Hundreds of new factors to predict and improve drivers
of performance
• Faster service: Processing time reduced from days to minutes
• Increased flexibility and scalability: Ability to operate 24/7 and scale up or
down with demand
• Improved quality: From spot-checking to 100 percent quality control
through greater traceability
• Increased savings and productivity: Labor savings of 20 percent or more
However, success is far from guaranteed. According to our Automation Survey,
only 55 percent of institutions believe their automation program has been
successful to date. Moreover, a little over half of respondents also say that the
program has been much harder to implement than they expected.
In this collection of articles, we explore why automation and AI are so
important, how to transform, and what the functional nuances are that can
be the difference between success and failure. At a high level, these articles delve into the four most
important practices that are strongly correlated with success in automation:
• Understand the opportunity and move early: Start taking advantage of automation and AI by
assessing the opportunity, identifying the high-impact use cases, and laying out the capability and
governance groundwork.
• Balance quick tactical wins with long-term vision: Identify quick wins to automate activities
with the highest automation potential and radiate out, freeing up capital; in parallel, have a long-
term vision for comprehensive transformation, with automation at the core.
• Redefine processes and manage organizational change: Since 60 percent of all jobs have at least
30 percent technically automatable activities, redefining jobs and taking an end-to-end process
view are necessary to capture the value.
• Integrate technology into core business functions: Build AI and other advanced technologies
into the operating model to create transformative impact and lasting value, support a culture
of collecting and analyzing data to inform decisions, and build the muscle for continuous
improvement.
We hope this curated collection will be helpful to you in realizing the full value potential from your
own automation transformation.
Alex Edlich Greg Phalin Rahil Jogani Sanjay Kaniyar
Senior partner, New York Senior partner, New York Partner, Chicago Partner, Boston
We wish to thank Keith Gilson, Vishal Koul, and Christina Yum for their contributions to this collection.
Introduction 3
Part
01
Why automation and AI?
4 Making a secure transition to cloud
POhloi tSoc carreffd/Git/eGtteyt tIym Iamgaegse Nsews
Harnessing automation for a future
that works
Jacques Bughin, Michael Chui, Martin Dewhurst, Katy George, James Manyika, Mehdi
Miremadi, and Paul Willmott
Automation is happening, and it will bring substantial benefits to
businesses and economies worldwide, but it won’t arrive overnight.
A new McKinsey Global Institute report finds realizing automation’s
full potential requires people and technology to work hand in hand.
Recent developments in robotics, artificial and CEOs. But how quickly will these automation
intelligence, and machine learning have put us technologies become a reality in the workplace?
on the cusp of a new automation age. Robots and And what will their impact be on employment and
computers can not only perform a range of routine productivity in the global economy?
physical work activities better and more cheaply
than humans, but they are also increasingly The McKinsey Global Institute has been conducting
capable of accomplishing activities that include an ongoing research program on automation
cognitive capabilities once considered too difficult technologies and their potential effects. A new MGI
to automate successfully, such as making tacit report, A future that works: Automation, employment,
judgments, sensing emotion, or even driving. and productivity, highlights several key findings.
Automation will change the daily work activities
The automation of activities can enable businesses
of everyone, from miners and landscapers to
to improve performance by reducing errors
commercial bankers, fashion designers, welders,
6 Digital/McKinsey
and improving quality and speed, and in some Still, automation will not happen overnight. Even
cases achieving outcomes that go beyond human when the technical potential exists, we estimate it
capabilities. Automation also contributes to will take years for automation’s effect on current
productivity, as it has done historically. At a time work activities to play out fully. The pace of
of lackluster productivity growth, this would give automation, and thus its impact on workers, will
a needed boost to economic growth and prosperity. vary across different activities, occupations, and
It would also help offset the impact of a declining wage and skill levels. Factors that will determine
share of the working-age population in many the pace and extent of automation include the
countries. Based on our scenario modeling, we ongoing development of technological capabilities,
estimate automation could raise productivity the cost of technology, competition with labor
growth globally by 0.8 to 1.4 percent annually. including skills and supply and demand dynamics,
performance benefits including and beyond labor
The right level of detail at which to analyze the cost savings, and social and regulatory acceptance.
potential impact of automation is that of individual Our scenarios suggest that half of today’s work
activities rather than entire occupations. Every activities could be automated by 2055, but this
occupation includes multiple types of activity, each could happen up to 20 years earlier or later
of which has different requirements for automation. depending on various factors, in addition to other
Given currently demonstrated technologies, economic conditions.
very few occupations—less than 5 percent—are
candidates for full automation. However, almost The effects of automation might be slow at a macro
every occupation has partial automation potential, level, within entire sectors or economies, for
as a proportion of its activities could be automated. example, but they could be quite fast at a micro
We estimate that about half of all the activities level, for individual workers whose activities are
people are paid to do in the world’s workforce could automated or for companies whose industries are
potentially be automated by adapting currently disrupted by competitors using automation.
demonstrated technologies. That amounts to
almost $15 trillion in wages. While much of the current debate about
automation has focused on the potential for mass
The activities most susceptible to automation are unemployment, people will need to continue
physical ones in highly structured and predictable working alongside machines to produce the growth
environments, as well as data collection and in per capita GDP to which countries around the
processing. In the United States, these activities world aspire. Thus, our productivity estimates
make up 51 percent of activities in the economy, assume that people displaced by automation will
accounting for almost $2.7 trillion in wages. find other employment. Many workers will have
They are most prevalent in manufacturing, to change, and we expect business processes to be
accommodation and food service, and retail trade. transformed. However, the scale of shifts in the
And it’s not just low-skill, low-wage work that could labor force over many decades that automation
be automated; middle-skill and high-paying, high- technologies can unleash is not without precedent.
skill occupations, too, have a degree of automation It is of a similar order of magnitude to the long-
potential. As processes are transformed by the term technology-enabled shifts away from
automation of individual activities, people will agriculture in developed countries’ workforces
perform activities that complement the work that in the 20th century. Those shifts did not result
machines do, and vice versa. in long-term mass unemployment, because they
Harnessing automation for a future that works 7
were accompanied by the creation of new types of come about if people work alongside machines. That
work. We cannot definitively say whether things in turn will fundamentally alter the workplace,
will be different this time. But our analysis shows requiring a new degree of cooperation between
that humans will still be needed in the workforce: workers and technology.
the total productivity gains we estimate will only
Jacques Bughin and James Manyika are directors of the McKinsey Global Institute, and Michael Chui is
an MGI partner; Martin Dewhurst and Paul Willmott are senior partners in McKinsey’s London office; Katy
George is a senior partner in the New Jersey office; and Mehdi Miremadi is a partner in the Chicago office.
Copyright © 2017 McKinsey & Company. All rights reserved.
8 Digital/McKinsey
A global force that will transform economies and the workforce
Technical automation potential by adapting currently demonstrated technologies
Wages associated with technically
automatable activities
While few occupations are fully automatable, 60 percent of all occupations
$ trillion
have at least 30 percent technically automatable activities
Remaining China
Share of roles countries 4.7 3.6
ACTIVITIES WITH HIGHEST 100% = 820 roles
AUTOMATION POTENTIAL:
About 60% of occupations 100% =
have at least 30% of 100 $14.6T
Predictable physical activities 81% their activities that 91 1.0 2.3 United
Processing data 69% are automatable
Japan 1.1 1.9 States
Collecting data 64% 73
India
Big 5 in Europe1
62
Labor associated with technically
51 automatable activities
<5% of occupations consist 42 Million full-time equivalents (FTEs)
of activities that are 34
100% automatable 26 Remaining
18 countries 367 China
395
8 100% =
1 1.2B
36
Japan 61
100 >90 >80 >70 >60 >50 >40 >30 >20 >10 >0 235 62 U Stn ait te ed s
Technical automation potential, % India Big 5 in Europe1
1 France, Germany, Italy, Spain, and the United Kingdom.
Five factors affecting pace and Automation will boost global
extent of adoption productivity and raise GDP
G19 plus Nigeria
1 2 3 4 5
TECHNICAL COST OF LABOR ECONOMIC REGULATORY Productivity growth, %
FEASIBILITY DEVELOPING MARKET BENEFITS AND SOCIAL Automation can help provide some of the productivity needed
Technology AND DYNAMICS Include higher ACCEPTANCE to achieve future economic growth
has to be DEPLOYING The supply, throughput Even when
invented, SOLUTIONS demand, and and increased automation Employment growth, %
integrated, Hardware costs of quality, makes will slow drastically because of aging
and adapted and software human labor alongside business
into solutions costs affect which labor cost sense,
for specific activities will savings adoption can
Last 50 years Next 50 years Next 50 years
case use be automated take time
Growth aspiration Potential impact of automation
Scenarios around time spent on current work activities, %
Adoption, Adoption, Technical automation Technical automation 1.8
Early scenario Late scenario potential, Early scenario potential, Late scenario
2.8
100 Technical
automation
80 potential 1.7 1.4
must precede 0.8
60 adoption 0.1 0.1 0.1
40 Technical, 3.5 2.9 1.5 0.9
economic,
and social Historical Required to Early Late
20 factors affect achieve scenario scenario
pace of projected growth
0 adoption
2020 2030 2040 2050 2060 2065 in GDP per capita
Harnessing automation for a future that works 9
Notes from the AI frontier:
Applications and value of deep
learning
Michael Chui, Rita Chung, Nicolaus Henke, Sankalp Malhotra, James Manyika, Mehdi Miremadi,
and Pieter Nel
An analysis of more than 400 use cases across 19 industries
and nine business functions highlights the broad use and
significant economic potential of advanced AI techniques.
Artificial intelligence (AI) stands out as a and the problems they can solve to more
transformational technology of our digital than 400 specific use cases in companies and
age—and its practical application throughout organizations.1 Drawing on McKinsey Global
the economy is growing apace. In our discussion Institute research and the applied experience
paper Notes from the AI frontier: Insights from with AI of McKinsey Analytics, we assess both the
hundreds of use cases, we mapped both traditional practical applications and the economic potential
analytics and newer “deep learning” techniques of advanced AI techniques across industries and
1 For the full McKinsey Global Institute discussion paper, see “Notes from the AI frontier: Applications and value of deep
learning,” April 2018, on McKinsey.com.
10 Digital/McKinsey
business functions. Our findings highlight the We analyzed the applications and value of three
substantial potential of applying deep learning neural network techniques:
techniques to use cases across the economy, but we
also see some continuing limitations and obstacles— Feed-forward neural networks: The
along with future opportunities as the technologies simplest type of artificial neural network.
continue their advance. Ultimately, the value of AI In this architecture, information moves
is not to be found in the models themselves, but in in only one direction, forward, from the
companies’ abilities to harness them. input layer, through the “hidden” layers, to
the output layer. There are no loops in the
It is important to highlight that, even as we see network. The first single-neuron network
economic potential in the use of AI techniques, the was proposed already in 1958 by AI pioneer
use of data must always take into account concerns Frank Rosenblatt. While the idea is not
including data security, privacy, and potential new, advances in computing power, training
issues of bias. algorithms, and available data led to higher
levels of performance than previously
Mapping AI techniques to problem possible.
types
As artificial intelligence technologies advance, so Recurrent neural networks (RNNs): Artificial
does the definition of which techniques constitute neural networks whose connections
AI.2 For the purposes of this article, we use AI as between neurons include loops; RNNs are
shorthand for deep learning techniques that use well suited for processing sequences of
artificial neural networks. We also examined inputs. In November 2016, Oxford University
other machine learning techniques and traditional researchers reported that a system based on
analytics techniques (Exhibit 1). recurrent neural networks (and convolutional
neural networks) had achieved 95 percent
Neural networks are a subset of machine learning accuracy in reading lips, outperforming
techniques. Essentially, they are AI systems based experienced human lip readers, who tested at
on simulating connected “neural units,” loosely 52 percent accuracy.
modeling the way that neurons interact in the
brain. Computational models inspired by neural Convolutional neural networks (CNNs):
connections have been studied since the 1940s Artificial neural networks in which the
and have returned to prominence as computer connections between neural layers are
processing power has increased and large training inspired by the organization of the animal
data sets have been used to successfully analyze visual cortex, the portion of the brain that
input data such as images, video, and speech. AI processes images; CNNs are well suited for
practitioners refer to these techniques as “deep perceptual tasks.
learning,” since neural networks have many
(“deep”) layers of simulated interconnected For our use cases, we also considered two other
neurons. techniques—generative adversarial networks and
reinforcement learning—but did not include them
2 For more on AI techniques, including definitions and use cases, see “An executive’s guide to AI,” February 2018,
McKinsey.com.
Notes from the AI frontier: Applications and value of deep learning 11
Web <2018>
<MGI AI Impact>
Exhibit 1
Exhibit <1> of <6>
We examined artificial intelligence (AI), machine learning, and other
We examined artificial intelligence (AI), machine learning, and other
analytics techniques for our research.
analytics techniques for our research.
Considered AI for our research
MORE
Transfer
learning
Reinforcement
Deep learning
learning
(feed-forward networks,
CNNs1, RNNs2, GANs3)
Dimensionality
reduction
Likelihood to Ensemble
be used in AI Instance-based Decision-tree learning
applications learning learning
Monte Linear Clustering
Carlo classifiers
methods
Statistical Markov Regression
inference process analysis
Descriptive Naive Bayes
statistics classifiers
LESS
TRADITIONAL Complexity of technique ADVANCED
1 Convolutional neural networks.
2 Recurrent neural networks.
3 Generative adversarial networks.
Source: McKinsey Global Institute analysis
12 Digital/McKinsey
in our potential value assessment of AI, since they Following are examples of where AI can be used to
remain nascent techniques that are not yet widely improve the performance of existing use cases:
applied:
Predictive maintenance: The power of
Generative adversarial networks (GANs) machine learning to detect anomalies. Deep
use two neural networks contesting one learning’s capacity to analyze very large
another in a zero-sum game framework (thus amounts of high-dimensional data can take
“adversarial”). GANs can learn to mimic existing preventive maintenance systems to
various distributions of data (for example, a new level. Layering in additional data, such
text, speech, and images) and are therefore as audio and image data, from other sensors—
valuable in generating test data sets when including relatively cheap ones such as
these are not readily available. microphones and cameras—neural networks
can enhance and possibly replace more
Reinforcement learning is a subfield of traditional methods. AI’s ability to predict
machine learning in which systems are failures and allow planned interventions
trained by receiving virtual “rewards” or can be used to reduce downtime and
“punishments,” essentially learning by trial operating costs while improving production
and error. Google’s DeepMind has used yield. For example, AI can extend the life
reinforcement learning to develop systems of a cargo plane beyond what is possible
that can play games, including video games using traditional analytics techniques by
and board games such as Go, better than combining plane model data, maintenance
human champions. history, and Internet of Things (IoT) sensor
data such as anomaly detection on engine-
In a business setting, these analytic techniques vibration data, and images and video of
can be applied to solve real-life problems. The engine condition.
most prevalent problem types are classification,
continuous estimation, and clustering (see sidebar, AI-driven logistics optimization can reduce
“Problem types and their definitions”). costs through real-time forecasts and
behavioral coaching. Application of AI
Insights from use cases techniques such as continuous estimation
We collated and analyzed more than 400 use cases to logistics can add substantial value across
across 19 industries and nine business functions. sectors. AI can optimize routing of delivery
They provided insight into the areas within traffic, thereby improving fuel efficiency
specific sectors where deep neural networks can and reducing delivery times. One European
potentially create the most value, the incremental trucking company has reduced fuel costs by
lift that these neural networks can generate 15 percent, for example, by using sensors
compared with traditional analytics (Exhibit 2), that monitor both vehicle performance and
and the voracious data requirements—in terms of driver behavior; drivers receive real-time
volume, variety, and velocity—that must be met coaching, including when to speed up or slow
for this potential to be realized. Our library of use down, optimizing fuel consumption and
cases, while extensive, is not exhaustive and may reducing maintenance costs.
overstate or understate the potential for certain
sectors. We will continue refining and adding to it.
Notes from the AI frontier: Applications and value of deep learning 13
EWxebh <ib20it1 82>
<MGI AI Impact>
AExdhibvit a<2n> cofe <6d> deep learning artificial intelligence techniques can be
applied across industries, alongside more traditional analytics.
Advanced deep learning artificial intelligence techniques can be applied across industries,
alongside more traditional analytics.
Technique relevance1 heatmap by industry Frequency of use Low High
Focus of report Traditional analytics techniques
Feed- Recurrent Convolutional Generative Tree-based
forward neural neural adversarial Reinforcement ensemble Regression Statistical
networks networks networks networks learning learning Classifiers Clustering analysis inference
Advanced electronics/
semiconductors
Aerospace and
defense
Agriculture
Automotive and
assembly
Banking
Basic materials
Chemicals
Consumer
packaged goods
Healthcare systems
and services
High tech
Insurance
Media and
entertainment
Oil and gas
Pharmaceuticals and
medical products
Public and
social sectors
Retail
Telecommunications
Transport and
logistics
Travel
1Relevance refers to frequency of use in our use case library, with the most frequently found cases marked as high
relevance and the least frequently found as low relevance. Absence of circles indicates no or statistically insignificant
number of use cases.
Note: List of techniques is not exhaustive.
Source: McKinsey Global Institute analysis
14 Digital/McKinsey
Problem types and their definitions
Classification: Based on a set of training data, categorize new inputs as belonging to one of a set of categories. An example of
classification is identifying whether an image contains a specific type of object, such as a cat or a dog, or a product of acceptable
quality coming from a manufacturing line.
Continuous estimation: Based on a set of training data, estimate the next numeric value in a sequence. This type of problem
is sometimes described as “prediction,” particularly when it is applied to time-series data. One example of continuous estimation
is forecasting the sales demand for a product, based on a set of input data such as previous sales figures, consumer sentiment,
and weather.
Clustering: These problems require a system to create a set of categories, for which individual data instances have a set of
common or similar characteristics. An example of clustering is creating a set of consumer segments, based on a set of data
about individual consumers, including demographics, preferences, and buyer behavior.
All other optimization: These problems require a system to generate a set of outputs that optimize outcomes for a specific
objective function (some of the other problem types can be considered types of optimization, so we describe these as “all other”
optimization). Generating a route for a vehicle that creates the optimum combination of time and fuel utilization is an example of
optimization.
Anomaly detection: Given a training set of data, determine whether specific inputs are out of the ordinary. For instance, a
system could be trained on a set of historical vibration data associated with the performance of an operating piece of machinery,
and then determine whether a new vibration reading suggests that the machine is not operating normally. Anomaly detection can
be considered a subcategory of classification.
Ranking: Ranking algorithms are used most often in information-retrieval problems where the results of a query or request
needs to be ordered by some criterion. Recommendation systems suggesting next product to buy use these types of algorithms
as a final step, sorting suggestions by relevance, before presenting the results to the user.
Recommendations: These systems provide recommendations based on a set of training data. A common example of
recommendations are systems that suggest “next product to buy” for an individual buyer, based on the buying patterns of similar
individuals and the observed behavior of the specific person.
Data generation: These problems require a system to generate appropriately novel data based on training data. For instance,
a music composition system might be used to generate new pieces of music in a particular style, after having been trained on
Notes from the AI frontier: Applications and value of deep learning 15
AI can be a valuable tool for customer Greenfield AI solutions are prevalent in business
service management and personalization areas such as customer-service management, as
challenges. Improved speech recognition in well as among some industries where the data are
call center management and call routing as rich and voluminous and at times integrate human
a result of the application of AI techniques reactions. Among industries, we found many
allows a more seamless experience for greenfield use cases in healthcare, in particular.
customers—and more efficient processing. Some of these cases involve disease diagnosis
The capabilities go beyond words alone. For and improved care and rely on rich data sets
example, deep learning analysis of audio incorporating image and video inputs, including
allows systems to assess a customer’s from MRIs.
emotional tone; in the event a customer is
responding badly to the system, the call On average, our use cases suggest that modern
can be rerouted automatically to human deep learning AI techniques have the potential
operators and managers. In other areas to provide a boost in additional value above and
of marketing and sales, AI techniques can beyond traditional analytics techniques—ranging
also have a significant impact. Combining from 30 percent to 128 percent, depending on
customer demographic and past transaction industry.
data with social media monitoring can
help generate individualized product In many of our use cases, however, traditional
recommendations. Next-product-to-buy analytics and machine learning techniques
recommendations that target individual continue to underpin a large percentage of the
customers—as companies such as Amazon value-creation potential in industries including
and Netflix have successfully been doing— insurance, pharmaceuticals and medical products,
can lead to a twofold increase in the rate of and telecommunications, with the potential of AI
sales conversions. limited in certain contexts. In part this is due to
the way data are used by these industries and to
Two-thirds of the opportunities to use AI are regulatory issues.
in improving the performance of existing
analytics use cases Data requirements for deep learning
In 69 percent of the use cases we studied, deep are substantially greater than for other
neural networks can be used to improve analytics
performance beyond that provided by other Making effective use of neural networks in most
analytics techniques. Cases in which only neural applications requires large labeled training data
networks can be used, which we refer to here as sets alongside access to sufficient computing
“greenfield” cases, constituted just 16 percent of infrastructure. Furthermore, these deep learning
the total. For the remaining 15 percent, artificial techniques are particularly powerful in extracting
neural networks provided limited additional patterns from complex, multidimensional data
performance over other analytics techniques, types such as images, video, and audio or speech.
because, among other reasons, of data limitations
that made these cases unsuitable for deep learning Deep learning methods require thousands of
(Exhibit 3). data records for models to become relatively
16 Digital/McKinsey
Web <2018>
<MGI AI Impact>
Exhibit 3
Exhibit <3> of <6>
In more than two-thirds of our use cases, artificial intelligence (AI)
cIna nm imorpe rtohvaen ptwerof-otrhmirdasn coef obuery uosned c tahsaets p, raorvtiifidceiadl binyt eoltlihgeern acen a(AlyIt) iccasn
tiemcphrnoivqeu epse.rformance beyond that provided by other analytics techniques.
Breakdown of Potential incremental value from AI over other analytics techniques, %
use cases by
applicable
Travel 128
techniques, %
Transport and logistics 89
Full value can Retail 87
be captured
15
using non-AI Automotive and assembly 85
techniques
High tech 85
AI necessary
Oil and gas 79
to capture
16
value
Chemicals 67
(“greenfield”)
Media and entertainment 57
Basic materials 56
Agriculture 55
Consumer packaged goods 55
AI can
Banking 50
improve
performance
Healthcare systems and services 44
over that
69
provided Public and social sectors 44
by other
analytics Telecommunications 44
techniques
Pharmaceuticals and medical products 39
Insurance 38
Advanced electronics/semiconductors 36
Aerospace and defense 30
Source: McKinsey Global Institute analysis
Notes from the AI frontier: Applications and value of deep learning 17
good at classification tasks and, in some cases, Realizing AI’s full potential requires a
millions for them to perform at the level of diverse range of data types, including
humans. By one estimate, a supervised deep images, video, and audio
learning algorithm will generally achieve Neural AI techniques excel at analyzing image,
acceptable performance with around 5,000 video, and audio data types because of their
labeled examples per category and will match or complex, multidimensional nature, known
exceed human-level performance when trained by practitioners as “high dimensionality.”
with a data set containing at least ten million Neural networks are good at dealing with high
labeled examples.3 In some cases where advanced dimensionality, as multiple layers in a network
analytics are currently used, so much data are can learn to represent the many different features
available—millions or even billions of rows per present in the data. Thus, for facial recognition,
data set—that AI usage is the most appropriate the first layer in the network could focus on raw
technique. However, if a threshold of data volume pixels, the next on edges and lines, another on
is not reached, AI may not add value to traditional generic facial features, and the final layer might
analytics techniques. identify the face. Unlike previous generations
of AI, which often required human expertise to
These massive data sets can be difficult to obtain do “feature engineering,” these neural network
or create for many business use cases, and labeling techniques are often able to learn to represent
remains a challenge. Most current AI models these features in their simulated neural networks
are trained through “supervised learning,” as part of the training process.
which requires humans to label and categorize
the underlying data. However, promising new Along with issues around the volume and variety of
techniques are emerging to overcome these data data, velocity is also a requirement: AI techniques
bottlenecks, such as reinforcement learning, require models to be retrained to match potential
generative adversarial networks, transfer learning, changing conditions, so the training data must
and “one-shot learning,” which allows a trained be refreshed frequently. In one-third of the cases,
AI model to learn about a subject based on a the model needs to be refreshed at least monthly,
small number of real-world demonstrations or and almost one in four cases requires a daily
examples—and sometimes just one. refresh; |
67 | mckinsey | gen-ai-opportunities-in-m-and-a.pdf | M&A Practice
Gen AI: Opportunities
in M&A
Generative AI is already making its way into the day-to-day world of
M&A, and more use cases are emerging. How should companies
approach the opportunity?
by Ben Ellencweig, Mieke Van Oostende, and Rui Silva
with Julia Berbel
May 2024
Generative AI (gen AI) is making its mark across a M&A that any deal, small or large, requires real work
gamut of industries and functions. Yet as and real people capacity to successfully execute it.
companies seek to capture the immense economic Gen AI, like many other technologies, exists to help
potential from gen AI and traditional AI, they’re leaders do more with less, make better decisions,
finding that it will take time to identify and prioritize and ultimately help their organizations create value
the most impactful and economically sound use in the long term. More specifically, four categories
cases, understand what is and isn’t—yet— of use cases for gen AI can materially improve the
achievable, and train employees for a broad range M&A process: faster and better-quality sourcing of
of applications and initiatives. potential targets; expediting the diligence and
negotiation process; executing the integration or
M&A is no exception. There are significant separation with excellence; and strengthening in-
opportunities for gen AI across the end-to-end house M&A capabilities.
M&A process, from defining an M&A strategy to
conducting due diligence to executing integrations Faster and better-quality sourcing of targets
or separations. Delivering successful transactions There is a surfeit of potential companies to acquire,
and building an effective M&A program is a sell to, or partner with. A huge amount of data
resource-intensive process with numerous pain about these companies is obtainable. In fact, there’s
points, and it’s clear that new technologies can so much information that organizations’ M&A teams
help. In fact, gen AI solutions are already being can get bogged down sorting through and
successfully applied. processing it all. The most successful M&A programs
look beyond their core business, into adjacencies
The goal of this article is not to reel off big and potential step-outs, and this is where gen AI
numbers; suffice to say, the potential is enormous. can be most impactful. Companies are in a race
As dealmakers prepare for what’s to come, we want because their competitors are searching for targets,
to share our real-time perspective. We’ll explore too. They also have to be thorough: target
some potential M&A use cases, provide examples of assessment needs to encompass several dimensions
solutions that are already being deployed, and offer to identify the highest-value potential targets with
practical steps on how organizations can use gen AI the right strategic and cultural fit. Deal scanning is a
to enhance their M&A capabilities. prominent, proven use case for traditional AI, but
when coupled with gen AI it can go further to find
and interpret broader sets of structured and
How gen AI is gaining traction unstructured data, synthesize results to answer
in M&A quantitative and qualitative prompts, and highlight
key elements of strategic, financial, and cultural fit
For years, our research has shown that taking a
of all potential targets. With gen AI, companies can
programmatic approach to M&A in the long term
identify and pursue targets they wouldn’t otherwise
can significantly boost an organization’s
have on their radar (exhibit).
performance compared with its peers. Yet M&A
execution is a very labor-intensive activity, requiring
thoughtful allocation of resources and a balanced For example, a North American–based company in
focus between integration activities and core the consumer-packaged-goods industry used
business continuity. It is inherent to the nature of McKinsey’s proprietary tool DealScan.AI to search
Gen AI: Opportunities in M&A 2
Exhibit
Gen AI: Opportunities in M&A 3
and evaluate potential investments. First, the tool Tools powered by gen AI can do a lot of the heavy
identified approximately 1,600 viable targets lifting. In fact, a wide range of time- and resource-
according to initial prompts. Then, it applied consuming tasks can be accelerated and, in some
bespoke quantitative and qualitative prioritization cases, almost fully automated. One striking use
criteria, including whether there was a direct-to- case is to have a gen AI “coach,” trained on M&A
consumer operating model, information about best practices and on the organization’s specific
subscription-based product assortments, and M&A playbook, that delivers fast and smart answers
details about recent fundings. This led to the to questions from integration and separation
prioritization of 40 targets—most of which the leaders and team members. Applications are rapidly
company had not considered before—that matched evolving, including McKinsey’s myIMO, which is
all requirements. powered by gen AI to help improve team
capabilities and efficiency. For example, a team
Expediting the diligence and negotiation process could ask the tool, “What are the right steps to
Gen AI can expedite the diligence and negotiation integrate the acquired company’s brand with our
process. For example, it can summarize key own, and what is the best timing to do that?” Or a
diligence documents, surface risks, draft initial team could give it the following prompt: “Draft a
memoranda based on a deal’s specific parameters, memo about upcoming changes in employee
source applicable statutes and regulations, identify benefits considering the following changes.” The
helpful case law to ease friction in the negotiations application is trained on a vast repository of M&A
phase, and generate other highly accurate outputs playbooks and best practices to help companies
(such as first drafts of the deal announcement and make well-informed decisions about their
regulatory filings). As one can imagine, these use integrations or separations. Other uses being
cases can save a significant portion of the time developed include post-day-one value creation
currently required to perform the different legal recommendations, such as identifying real-time
tasks involved in deal negotiations, signing, synergy opportunities based on a company’s
and closing. available data; automated summaries and
comparisons of internal policies that need to be
Executing the integration or separation harmonized between the two organizations; the
with excellence quick comparison and harmonization of job title and
Seasoned dealmakers know that deal synergies hierarchy structures, cost center, and general
need to be captured quickly—and that sometimes, ledger definitions; and the automation of change
by taking too long, companies can squander management activities. The list goes on.
significant value. Organizations going through
sizeable M&A events are particularly likely to get Strengthening in-house M&A capabilities
diverted and see organic momentum decline, with Gen AI can strengthen a company’s internal
an average decrease in excess revenue growth of capabilities by drawing on companies’ proprietary
seven percentage points compared with peers.1 data from past deals to assess performance
Sluggish integrations can frustrate customers, patterns and find insights about untapped
demotivate employees, and sometimes cause opportunities. For example, it could assess a
organizations to stall. company’s portfolio of acquisitions and calculate
the impact brought by each deal. It could also
generate postmortem insight about how deals
1 Based on the 1,000 largest companies in McKinsey’s annual Global 2,000 analysis. For more on the methodology of the Global 2,000, see “The
seven habits of programmatic acquirers,” August 24, 2023.
Gen AI: Opportunities in M&A 4
affect the business (for example, how and when the decision to either use in-house resources or
company’s organic revenue growth is typically outsource, leaders should consider their team’s
affected after closing a deal). It could update the existing expertise, the size of the required
company’s proprietary playbook with recipes, investment, the extent of the potential return
nuances, and lessons learned (for example, “Deals (including how sustainable any competitive
of up to $1 billion typically require an integration advantage would be), and the actions that the
team of five people, focused on the following company’s peers are or could be taking.
tasks”). It could even generate personalized training
programs in line with the specific function of an — Ensure that the right guardrails are in place.
integration team member, as well as with the Gen AI is distinct from most existing
acquisition type and the deal timing (based on the technologies because it heightens certain
following prompt, for example: “I am new to the risks—for example, security breaches, given its
team. I will be leading the HR integration for our ease of access; reputational risks from quality
acquisition of X company. What do I need to know? control missteps; and potential intellectual
Where do I start?”). property infringement. Legal and regulatory
developments are fast moving, even as gen AI
races forward. And the better the AI models are,
How to get started
the greater the potential risk that humans will
Gen AI will not fix a broken approach to M&A; it simply disengage and not catch issues until it’s
might even exacerbate it. The first step for senior too late. It’s essential that organizations keep
leaders is to frankly assess their current level of human beings at the forefront of the work,
M&A capabilities and to consider where in the M&A proactively identify and mitigate risks in
process technology can be used to materially partnership with their legal and technology
improve the M&A engine. teams, and maintain rigorous ethical standards.
The next steps are just as foundational: Gen AI is a predictive language model, not a human
being. As companies navigate the gen AI transition,
— Prioritize the gen AI use cases that create the they should consider how to use their newly freed-
most value. If your M&A strategy is focused on up time to focus on more strategic, high-value
acquiring dozens of very small players, gen AI activities such as relationship building and eureka-
will have the greatest impact on opportunity moment problem solving, which technology cannot
scanning and assessment. Conversely, if you do (yet) replace.
one to two larger deals a year, gen AI may also
help you streamline and accelerate the
execution processes. Commercial applications of gen AI in M&A are
already gaining traction and will almost certainly
— Drill down on whether to develop or to adopt. accelerate in the next few years. The greatest
There is a full spectrum of choices for how a question is not whether gen AI will affect
company can bring its prioritized use cases to dealmaking—it already is—but to what degree, how
life, and off-the-shelf solutions have recently quickly, and to what consequence. We’ll be
been brought to market—with more expected monitoring these developments in real time as
over the next one to two years. As with any they proceed.
Ben Ellencweig is a senior partner in McKinsey’s Stamford, Connecticut, office; Mieke Van Oostende is a senior partner in the
Brussels office; and Rui Silva is a partner in the New York office, where Julia Berbel is a consultant.
Copyright © 2024 McKinsey & Company. All rights reserved.
Gen AI: Opportunities in M&A 5 |
68 | mckinsey | four-essential-questions-for-boards-to -ask-about-generative-ai.pdf | Four essential questions
for boards to ask about
generative AI
Boards are responsible for how generative AI is used at the companies they
oversee. Asking company leaders the right questions will help unlock the
technology’s value while managing its risk.
by Frithjof Lund, Dana Maor, Nina Spielmann, and Alexander Sukharevsky
© Getty Images
July 2023
Company executives are scrambling to applications with relative ease, even if users lack
understand and respond to generative AI. This deep AI and data science know-how.
technology is still nascent, but of those who have
used it, few doubt its power to disrupt operating Board members can equip their C-suite to harness
models in all industries. this potential power thoughtfully but decisively by
asking the following four broad questions.
We recently provided a view of how CEOs might
start preparing for what lies ahead.¹ But what is How will generative AI affect our industry and
the role of the board? Many board members tell us company in the short and longer term?
they aren’t sure how to support their CEOs as they Forming any sensible generative AI strategy will
grapple with the changes that generative AI has require an understanding of how the technology
unleashed, not least because the technology seems might affect an industry and the businesses within it
to be developing and getting adopted at lightning in the short and longer term. Our research suggests
speed. that the first wave of applications will be in software
engineering, marketing and sales, customer service,
The early use cases are awe inspiring. A software and product development.² As a result, the early
developer can use generative AI to create entire impact of generative AI will probably be in the
lines of code. Law firms can answer complex industries that rely particularly heavily on these
questions from reams of documentation. Scientists functions—for example, in media and entertainment,
can create novel protein sequences to accelerate banking, consumer goods, telecommunications, life
drug discovery. But the technology still poses real sciences, and technology companies.
risks, leaving companies caught between fear of
getting left behind—which implies a need to rapidly Even so, companies in other industries should not
integrate generative AI into their businesses—and delay in assessing the potential value at stake for
an equal fear of getting things wrong. The question their company. The technology and its adoption
becomes how to unlock the value of generative AI are moving too fast. Recall that the public-facing
while also managing its risks. version of ChatGPT reached 100 million users in
just two months, making it the fastest-growing
Board members can help their management teams app ever. And our research finds that generative AI
move forward by asking the right questions. In this can increase worker productivity across industries,
article, we provide four questions boards should adding up to $7.9 trillion in value globally from
consider asking company leaders, as well as a adoption of specific use cases and the myriad
question for members to ask themselves. ways workers can use the technology in everyday
activities.³ Each company will want to explore
immediate opportunities to improve efficiency and
Questions for management effectiveness. Those that don’t may quickly find
Generative AI models—deep learning models themselves trailing behind competitors that answer
trained on extremely large sets of unstructured customer queries more accurately and faster or
data—have the potential to increase efficiency launch new digital products more rapidly because
and productivity, reduce costs, and generate new generative AI is helping write the code. They risk
growth. The power of these “foundation” models falling behind on the learning curve, too.
lies in the fact that, unlike previous deep learning
models, they can perform not just one function but Simultaneously, companies will want to begin
several, such as classifying, editing, summarizing, looking further out. No one can predict the full
answering questions, and drafting new content. This implications of generative AI, but considering
enables companies to use them to launch multiple them is important. How might the competitive
1 “What every CEO should know about generative AI,” McKinsey, May 12, 2023.
2 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
3 Ibid.
2 Four essential questions for boards to ask about generative AI
environment change? How might the business frameworks for the knowable generative AI
benefit, and where does it look vulnerable? And risks assumed across the company and that AI
are there ways to future-proof the strategy and activities within the company are continually
business model? reviewed, measured, and audited. They will
also want to ensure mechanisms are in place to
Are we balancing value creation with adequate continually explore and assess risks and ethical
risk management? concerns that are not yet well understood or even
An assessment of the new frontiers opened by apparent. How, for example, will companies stand
generative AI will rightly make management teams up processes to spot hallucination and mitigate
eager to begin innovating and capturing its value. the risk of wrong information eliciting incorrect
But that eagerness will need to be accompanied by or even harmful action? How will the technology
caution, as generative AI, if not well managed, has affect employment? And what of the risks posed
the potential to destroy value and reputations. It by third parties using the technology? A clear-eyed
poses the same—and more—risks as traditional AI. early view on where problems might lie is the key to
addressing them.
Like traditional AI, generative AI raises privacy
concerns and ethical risks, such as the potential The bottom line is that AI must always be subject
to perpetuate bias hidden in training data. And it to the effective oversight of those designing
heightens the risk of a security breach by opening and using it. Support for the effort can come
up more areas of attack and new forms of attack. from government regulatory frameworks and
For example, deepfakes simplify the impersonation guidance being developed on how to use and apply
of company leaders, raising reputation risks. There generative AI. It will be important for companies to
are also new risks, such as the risk of infringing keep abreast of these.
copyrighted, trademarked, patented, or otherwise
legally protected materials by using data collected How should we organize for generative AI?
by a generative AI model. Many companies took an experimental approach
to implementing previous generations of AI
Generative AI also has a propensity to hallucinate— technology, with those keenest to explore its
that is, generate inaccurate information, expressing possibilities launching pilots in pockets of the
it in a manner that appears so natural and organization. But given the speed of developments
authoritative that the inaccuracies are difficult within generative AI and the risks it raises,
to detect. This could prove dangerous not just companies will need a more coordinated approach.
for companies but for society at large. There is Getting stuck in pilot mode really isn’t an option.
widespread concern that generative AI could Indeed, the CEO of one multinational went as far
stoke misinformation, and some industry experts as to ask each of his 50 business leaders to fully
have said it could be as dangerous to society as implement two use cases without delay, such was
pandemics or nuclear war if not properly regulated.⁴ his conviction that generative AI would rapidly lend
competitive advantage.
Companies will therefore need to understand the
value and the risks of each use case and determine Company leaders should consider appointing a
how these align with the company’s risk tolerance single senior executive to take responsibility for the
and other objectives. For example, with regard oversight and control of all generative AI activities.
to sustainability objectives, they might consider A smart second step is to establish a cross-
generative AI’s implications for the environment functional group of senior people representing
because it requires substantial computing capacity. data science, engineering, legal, cybersecurity,
marketing, design, and other business functions.
From there, boards need to be satisfied that the Such a team can collaborate to formulate and
company has established legal and regulatory implement a strategy quickly and widely.
4 Cristina Criddle, “AI executives warn its threat to humanity rivals ‘pandemics and nuclear war,’” Financial Times, May 30, 2023.
Four essential questions for boards to ask about generative AI 3
Bear in mind too that a foundation model can Talent
underpin multiple use cases across an organization, The introduction of generative AI, like any change,
so board members will want to ask the appointed also requires a reassessment of the organization’s
generative AI leader to ensure that the organization talent. Companies are aware they need to reskill the
takes a coordinated approach. This will promote workforce to compete in a world where data and
the prioritization of use cases that deliver fast, AI play such a big role, though many are struggling
high-impact results. More complex use cases to attract and retain the people they need. With
can be developed thereafter. Importantly, a generative AI, the challenge just got harder. Some
coordinated approach will also help ensure a full roles will disappear, others will be radically different,
view of any risks assumed. and some will be new. Such changes will likely affect
more people in more domains and faster than has
The board will also want to check that there’s a been the case with AI to date.
strategy for establishing what is likely to be a
wide range of partnerships and alliances—with The precise new skills required will vary by use
providers that customize models for a specific case. For example, if the use case is relatively
sector, for example, or with infrastructure providers straightforward and can be supported by an off-
that offer capabilities such as scalable cloud the-shelf foundation model, a generalist may be
computing. The right partnerships with the right able to lead the effort with the help of a data and
experts will help companies move quickly to create software engineer. But with highly specialized data—
value from generative AI, though they will want to as might be the case for drug development—the
take care to prevent vendor lock-in and oversee company may need to build a generative AI model
possible third-party risks. from scratch. In that case, the company may need to
hire PhD-level experts in machine learning.
Do we have the necessary capabilities?
To keep pace with generative AI, companies may The board will therefore want to query leadership
need to review their organizational capabilities on as to whether it has a dynamic understanding of
three fronts. its AI hiring needs and a plan for fulfilling them.
Also, the existing workforce will need to be trained
Technology to integrate generative AI into their day-to-day
The first front is technology. A modern data and work and to equip some workers to take on new
tech stack will be the key to success in using roles. But tech skills are not the only consideration,
generative AI. While foundation models can as generative AI arguably puts a premium on
support a wide range of use cases, many of the more advanced analytical and creative skills to
most impactful models will be those fed with supplement the technology’s capabilities. The
additional, often proprietary, data. Therefore, talent model may therefore need to change—but
companies that have not yet found ways to with consideration of a caution raised recently at
harmonize and provide ready access to their the World Economic Forum: using AI as a substitute
data will be unable to unlock much of generative for the work of junior-level talent could endanger
AI’s potentially transformative power. Equally the development of the next generation of creators,
important is the ability to design a scalable data leaders, and managers.⁵
architecture that includes data governance and
security procedures. Depending on the use case, Organizational culture
the existing computing and tooling infrastructure Finally, a company’s culture shapes how well it
might also need upgrading. Is the management will succeed with generative AI. Companies that
team clear about the computing resources, data struggle with innovation and change will likely
systems, tools, and models required? And does it struggle to keep pace. It’s a big question, but does
have a strategy for acquiring them? the company have the learning culture that will be
5 Ravin Jesuthasan, “Here’s how companies should navigate generative AI in the world of work,” World Economic Forum, April 14, 2023.
4 Four essential questions for boards to ask about generative AI
a key to success? And does the company have a full board and all its committees can properly
shared sense of responsibility and accountability? consider its implications.
Without this shared sense, it is more likely to
run afoul of the ethical risks associated with the Second, the board can improve its members’
technology. understanding of generative AI. Training
sessions run by the company’s own experts
Both questions involve cultural issues that boards and by external experts on the front line of
should consider prompting their management developments can give board members an
teams to examine. Depending on what they find, understanding of how generative AI works, how
reformulating a company’s culture could prove to be it might be applied in the business, the potential
an urgent task. value at stake, the risks, and the evolution of the
technology.
A question for the board Third, the board can incorporate generative
As boards try to support their CEOs in creating value AI into its own work processes. Hands-on
from generative AI and managing its risks, they experience in the boardroom can build familiarity
will also want to direct a preliminary, fundamental with the technology and appreciation of its value
question to themselves: Are we equipped to provide and risks. Moreover, because generative AI can
that support? improve decision making, it would be remiss of
boards not to explore its potential to help them
Unless board members understand generative AI perform their duties to the best of their ability. For
and its implications, they will be unable to judge example, they might use it to surface additional
the likely impact of a company’s generative AI critical questions on strategic issues or to deliver
strategy and the related decisions regarding an additional point of view to consider when
investments, risk, talent, technology, and more making a decision.
on the organization and its stakeholders. Yet, our
conversations with board members revealed that
many of them admit they lack this understanding.
When that is the case, boards can consider three
ways to improve matters. Generative AI is developing fast, and companies
will have to balance pace and innovation with
The first option is to review the board’s composition caution. The board’s role is to constructively
and adjust it as necessary to ensure sufficient challenge the management team to ensure
technological expertise is available. In the past, this happens, keeping the organization at the
when companies have struggled to find technology forefront of this latest technological development
experts with the broader business expertise yet intensely mindful of the risks. The questions
required of a board member, some have obtained posed here are not, of course, exhaustive, and
additional support by setting up technology more will arise as the technology progresses. But
advisory boards that include generative AI experts. they are a good place to start. Ultimately, board
However, generative AI will likely have an impact members hold responsibility for how generative
on every aspect of a company’s operations—risk, AI is used in the companies they oversee, and the
remuneration, talent, cybersecurity, finance, and answers they receive should help them meet that
strategy, for example. Arguably, therefore, AI responsibility wisely.
expertise needs to be widespread so that the
Frithjof Lund is a senior partner in McKinsey’s Oslo office, Dana Maor is a senior partner in the Tel Aviv office, Nina Spielmann
is a senior expert in the Zurich office, and Alexander Sukharevsky is a senior partner in the London office.
Copyright © 2023 McKinsey & Company. All rights reserved.
Four essential questions for boards to ask about generative AI 5 |
69 | mckinsey | ai-for-social-good-improving-lives-and-protecting-the-planet-v2.pdf | AI for social good:
Improving lives and
protecting the planet
This report is a collaborative effort by
Medha Bankhwal, Ankit Bisht, Michael Chui,
Roger Roberts, and Ashley van Heteren,
representing views from McKinsey Digital.
May 2024
Table of contents
CHAPTER 1
How AI can accelerate progress
toward reaching all of the SDGs 2
CHAPTER 2
How funding for AI initiatives
supports SDGs 13
CHAPTER 3
Challenges of scaling AI
for social good 16
CHAPTER 4
How stakeholders can accelerate
the deployment of AI for social good 21
Methodology 26
Acknowledgments 26
AI is already being used to further all 17 SDGs—from the goal of eliminating poverty to establishing
sustainable cities and communities and providing quality education for all—and generative AI has
opened new possibilities. As we look to the future, we see exciting potential for acceleration, with new
tools and platforms putting ever-greater power in the hands of social entrepreneurs, public sector
innovators, and private sector players to create effective solutions. But that power also brings with it
the need to assure it is harnessed in trusted and responsible ways and that risks are monitored and
managed actively to avoid unintended harms.
Six years ago, it was becoming clear that AI could play a major role globally in promoting not just
productivity and economic growth but also social good. In a 2018 report, we outlined how AI
capabilities, from natural language processing to sound recognition and tracking, could be used in
about 170 use cases to benefit society1—to promote equality and inclusion, improve crisis response,
protect the environment, and deliver impact in many more ways.2
Today’s AI R&D is not just confirming our initial assessments but showing promise for further gains in
the future. A series of improvements in AI techniques and progress on key enablers have substantially
expanded the universe of problems that AI may be able to address. Much of this progress is centered
on generative AI, which is enabling natural language interfaces; rapid language translation; synthesis
of vast document repositories; creation of stories in text, images, and video; and much more.3
In this report, we take another look at how AI can become a key part of solutions to benefit people
and the planet—and how it already has. One way to assess this is by mapping innovations and impact
to the UN Sustainable Development Goals, or SDGs (see sidebar “Methodology,” found at the end of
the report). The SDGs comprise 17 goals and 169 targets that aim to improve lives around the world
and protect the planet. But the UN’s 2023 update on progress toward the SDGs indicates the world
is on track to meet only 15 percent of SDG targets.4 In real terms, this means that 2.2 billion people
lack access to safe water and hygiene, and 3.5 billion lack access to safely managed sanitation5;
roughly 3.3 billion people live in environments that are highly vulnerable to climate change6; and about
750 million people are facing hunger.7
Below, we illustrate the potential of AI to catalyze progress on these pressing social issues, and we
highlight the challenges in the domains of data quality and governance, as well as access to AI talent
(particularly for not-for-profits), that are hindering AI from scaling. We then outline some actions that
stakeholders—including governments, foundations, universities, and businesses—could take to
overcome these challenges. While the opportunities have associated risks, such as embedded biases
and data privacy and security threats, thoughtful action could accelerate the deployment of AI-based
solutions to advance progress on the SDGs and improve lives across the globe.
1 “Applying artificial intelligence for social good,“ McKinsey Global Institute, November 28, 2018. Additional research in 2023 yielded
discovery of 13 more use cases piloted in 2018 that were not originally accounted for in our 2018 report, bringing the 2018 total up to
about 170.
2 “‘Tech for Good’: Using technology to smooth disruption and improve well-being,” McKinsey Global Institute, May 15, 2019; Amine
Aït-Si-Selmi, Eric Hazan, Hamza Khan, and Tunde Olanrewaju, “Tech for Good: Helping the United Kingdom improve lives and
livelihoods,” McKinsey, July 31, 2020.
3 For more on generative AI, see “What is generative AI?,” McKinsey, April 2, 2024.
4 The Sustainable Development Goals report 2023: Special edition, United Nations, July 10, 2023.
5 “The 17 goals,” United Nations Department of Economic and Social Affairs, accessed April 24, 2024.
6 “Protecting people from a changing climate: The case for resilience,” McKinsey, November 8, 2021.
7 “122 million more people pushed into hunger since 2019 due to multiple crises, reveals UN report,” World Health Organization,
July 12, 2023.
AI for social good: Improving lives and protecting the planet 1
Chapter 1
How AI can accelerate
progress toward reaching
all of the SDGs
AI for social good: Improving lives and protecting the planet 2
AI is not a magic bullet, and many risks need to be managed to harness its potential (see sidebar
“Managing the risks of adopting AI”). But the universe of problems that AI can address is broad.
Current applications of AI are applicable to all the SDGs, including modeling proteins, screening
drugs, designing vaccines, targeting aid and public services, solving supply chain problems such as
route optimization for last mile delivery of food in remote geographies, forecasting the long-term
impacts of climate change or giving early warning for natural disasters, and bringing expertise to
frontline aid workers.
Additionally, adoption of generative AI could significantly increase and democratize access to
new capabilities. AI tools now allow remote users to complete tasks that once required specific
expertise, such as language translation, fact checking, identification of human or plant diseases,
and identification of harmful online content. In a recent survey of more than 4,000 not-for-profits
conducted by Google for Nonprofits, 75 percent of respondents said that generative AI had the
potential to transform their marketing efforts by enhancing their translation and fact-checking
capabilities.8
The experts we interviewed noted that AI could address or help solve social or environmental
challenges in two circumstances: 1) when the AI solution could solve problems that bottleneck other
efforts in the field—for example, a solution for water leakage in residential pipes requires predictions
about the likelihood of leaks based on analysis of data such as pipe age and location; and 2) when
data required for the model to work is (or will soon be) available and accessible.
To map the breadth of AI’s applicability, we have developed a database of AI use cases, each of
which highlights a type of meaningful problem whose solution could be enabled by one or more AI
capabilities. At the time of our 2018 report, this database contained about 170 high-potential use
cases. It now contains about 600—more than a threefold increase. This number is growing as more
innovative uses come to light, as social impact leaders continue to experiment boldly, and as AI tools
become more accessible and easier to use.
The number of real-life AI deployments has also increased significantly over the past six years. In
2018, only a small fraction of the about 170 use cases had been deployed. Today, about 490 of the
600 use cases, or more than 80 percent, have been implemented in at least one instance (Exhibit 1).9
Adoption of generative AI could
significantly increase and
democratize access to new capabilities.
AI tools now allow remote users to
complete tasks that once required
specific expertise.
8 The Keyword, “3 insights from nonprofits about generative AI,” blog entry by Annie Lewin, March 28, 2024.
9 Our library contains approximately 600 use cases, and our analysis of deployments is based on publicly available data. Neither is
comprehensive or exhaustive, and both will continue to evolve.
AI for social good: Improving lives and protecting the planet 3
Web <2024>
E<MxChKib23it7 2111 Perspective on AI For Social Good Report>
Exhibit <1> of <6>
About 600 AI-enabled use cases have the potential to support the UN
Sustainable Development Goals.
Number of AI-enabled use cases identified per Included in the library created in 2018 Number of use
UN Sustainable Development Goal (SDG),1 2023 Additions since 2018 cases with at
least one deploy-
ment in 2023
82% SDG 3: Good Health and
43 122 165 128
Well-Being
of all use cases
have at least SDG 16: Peace, Justice, and
28 27 55 40
one deployment Strong Institutions
(492 out of 600)
SDG 15: Life on Land 10 30 40 38
600
SDG 4: Quality Education 13 27 40 37
SDG 13: Climate Action 7 25 32 31
SDG 2: Zero Hunger 8 24 32 29
SDG 11: Sustainable Cities and 11 20 31 26
Communities
SDG 9: Industry, Innovation, 9 21 30 21
429 and Infrastructure
SDG 8: Decent Work and 7 20 27 17
Economic Growth
1
SDG 14: Life Below Water 25 26 24
3
SDG 12: Responsible 18 21 19
Consumption and Production
2
SDG 7: Affordable and Clean 19 21 18
Energy
SDG 10: Reduced Inequalities 613 19 15
2
SDG 6: Clean Water and 16 18 16
Sanitation
171
SDG 1: No Poverty 107 17 12
SDG 17: Partnerships for the 88 16 13
Goals
3
Total SDG 5: Gender Equality 7 10 8
Note: Our library of 600 use cases and our analysis of deployments are based on publicly available data, are not comprehensive, and will continue to evolve; this
library is a starting point and should thus not be treated as exhaustive. Many AI use cases are relevant for more than one SDG, which means that successful
deployments of these use cases can spur progress on multiple fronts. Additional research in 2023 led to the discovery of 13 use cases piloted in 2018 that were
not accounted for in our 2018 report.
1Each use case is mapped to primary UN SDGs only.
Source: AI for Sustainable Development Goals academy; Candid database 2018–23; IRCAI global top 100 2022 report, International Research Centre on
Artificial Intelligence (IRACAI), 2022; United Nations activities on artificial intelligence (AI) 2021, International Telecommunication Union, 2021; United Nations
Statistics Division; United Nations University Institute for Water, Environment and Health reports
McKinsey & Company
AI for social good: Improving lives and protecting the planet 4
The experts we surveyed agreed that AI has particularly high potential to make a difference for five
SDG goals: Good Health and Well-Being (SDG 3), Quality Education (SDG 4), Affordable and Clean
Energy (SDG 7), Sustainable Cities and Communities (SDG 11), and Climate Action (SDG 13). In fact,
60 percent of not-for-profit AI for social good deployments were in these areas. Relative to their
perceived AI potential, the goals for Zero Hunger (SDG 2), Life on Land (SDG 15), and Peace, Justice,
and Strong Institutions (SDG 16) have many use case deployments, whereas Quality Education
(SDG 4), Affordable and Clean Energy (SDG 7), and Climate Action (SDG 13) have fewer (Exhibit 2).
We excluded Decent Work and Economic Growth (SDG 8); Industry, Innovation, and Infrastructure
(SDG 9); and Partnerships for Goals (SDG 17) from the analysis of not-for-profit deployment,
foundation grants, and private capital, because most projects can be tagged to these areas given
their broad applicability.10
Web <2024>
E<MxChKib23it7 2211 Perspective on AI For Social Good Report>
Exhibit <2> of <6>
The number of not-for-profit deployments does not necessarily reflect the
perceived AI potential for each Sustainable Development Goal.
Bubble size reflects Relatively high number of Lower level of deployment
number of AI-enabled use cases identified given than expected based on higher
use cases identified low perceived AI potential perceived AI potential
Well-recognized
potential 3
4
13
30
7
Perceived AI 20 11
potential1
12
10 2 10
6 15
5
Not yet 0 14 16 1
recognized2
0 100 200 300 400
Low Number of not-for-profit deployments3 High
1 No Poverty 10 Reduced Inequalities
2 Zero Hunger 11 Sustainable Cities and Communities
3 Good Health and Well-Being 12 Responsible Consumption and Production
4 Quality Education 13 Climate Action
5 Gender Equality 14 Life Below Water
6 Clean Water and Sanitation 15 Life on Land
7 Affordable and Clean Energy 16 Peace, Justice, and Strong Institutions
Note: We excluded Decent Work and Economic Growth (SDG 8); Industry, Innovation, and Infrastructure (SDG 9); and Partnerships for the Goals (SDG 17) from
our analysis of not-for-profit deployment, grants, and private capital. This is because most projects can be tagged to these areas given broad applicability.
1AI potential determined through survey of ~60 experts representing 48 organizations (incl not-for-profits, foundations, technology companies, start-ups,
academic institutions, and government) and 17 countries in response to the following question: “What are the top 5 Sustainable Development Goals (SDGs) in
the list below where you think AI has the highest potential to accelerate progress toward the SDG targets?”
2There may be potential for AI use, but the surveyed experts are unaware of it at this point.
3Not-for-profit deployment determined from number of sample deployments in a collection of 1,121 AI applications largely deployed in not-for-profits.
Source: AI for Sustainable Development Goals academy; Candid database 2018–23; IRCAI global top 100 2022 report, International Research Centre on
Artificial Intelligence (IRACAI), 2022; United Nations activities on artificial intelligence (AI) 2021, International Telecommunication Union, 2021; United Nations
Statistics Division; United Nations University Institute for Water, Environment and Health reports
McKinsey & Company
10 In our analysis of 600 use cases, each use case was tagged to a single primary SDG and SDG target.
AI for social good: Improving lives and protecting the planet 5
Additionally, several SDGs that are behind on progress have relatively untapped AI potential.
Consider the following examples:
— No Poverty (SDG 1): machine learning could be used to direct cash aid to those most in need or
provide alternative credit scores to financially excluded individuals.
— Zero Hunger (SDG 2): AI could be used to help develop new crops, better select crop regions to
minimize crop risks, and provide early warning for nutrition crises.
— Peace, Justice, and Strong Institutions (SDG 16): machine learning could be used to detect and
curb the spread of misinformation, provide access to information that enables advocacy for policy
change, and improve measurement of specific policy interventions.
Below, we explore potential and existing deployments in three of the SDGs with the most widely
recognized potential: Good Health and Well-Being (SDG 3), Quality Education (SDG 4), and Climate
Action (SDG 13). We also explore two SDGs where AI does not have widely recognized potential but
has had an impact in select areas: No Poverty (SDG 1) and Zero Hunger (SDG 2).
We explore potential and existing
deployments in three of the SDGs
with the most widely recognized
potential. We also explore two
SDGs where AI does not have widely
recognized potential but has had an
impact in select areas.
AI for social good: Improving lives and protecting the planet 6
Managing the risks of adopting AI
Risks are inherent to the use of AI. With generative AI (gen AI), risks include inaccurate outputs,
biases embedded in the underlying training data, the potential for large-scale misinformation, and
malicious influence on politics and personal well-being.1 As we have noted in multiple recent articles,2
AI tools and techniques can be misused, even if they were originally designed for social good.
Respondents to our survey of about 60 experts identified the top risks as impaired fairness,
malicious use, and privacy and security concerns, followed by explainability (exhibit).3 Respondents
from not-for-profits expressed relatively more concern about misinformation, talent issues such as
job displacement, and effects of AI on economic stability compared with their counterparts at for-
profits, who were more often concerned with intellectual property infringement.
Web <2024>
E<MxChKib23it7211 Perspective on AI For Social Good Report>
Exhibit <6> of <6>
Experts say impaired fairness and malicious use are the top risks in using AI
to address the Sustainable Development Goals.
AI risks presenting the largest challenges in deploying AI for achieving Delta between not-for-
SDG targets, % of respondents including this topic in their top 5 profits and others
Not-for-profits Others1 Negative Positive
73
Impaired fairness –3 p.p.2
76
68
Malicious use 76 –8 p.p.
68
Data privacy 74 –6 p.p.
68
Security threats 74 –6 p.p.
55
Performance and explainability 45 +10 p.p.
45
Talent issues 32 +13 p.p.
32
Political stability 24 +8 p.p.
27
Economic stability 11 +16 p.p.
18
National security 26 –8 p.p.
18
Environmental impact 21 –3 p.p.
9
Intellectual property infringement 32 –23 p.p.
Note: “Impaired fairness” was framed as “bias and fairness” in the survey; “performance and explainability” was framed as “explainability”; “data privacy” and
“security threats” were combined in the survey.
1“Others” includes for-profits, think tanks, academic institutions, and consultancies.
2Percentage points.
Source: Survey of ~60 experts representing 48 organizations (incl not-for-profits, foundations, technology companies, start-ups, academic institutions, and
government) and 17 countries
McKinsey & Company
1 “Implementing generative AI with speed and safety,” McKinsey Quarterly, March 13, 2024.
2 Ibid.; “The state of AI in 2023: Generative AI’s breakout year,” McKinsey, August 1, 2023; New at McKinsey Blog, “An inside look at
how businesses are—or are not—managing AI risk,” blog entry by Liz Grennan and Bryce Hall, August 31, 2023; “What is generative
AI?,” McKinsey, April 2, 2024.
3 Our AI risks framework for social impact builds on McKinsey’s gen AI risks framework (see “Implementing generative AI with speed
and safety,” McKinsey Quarterly, March 13, 2024). It includes additional categories such as political stability and environmental
impact and excludes risks such as strategic risks that can be more relevant to for-profit enterprises.
AI for social good: Improving lives and protecting the planet 7
Impaired fairness. Algorithmic systems can inherit biases from their creators or from the data sets on
which they are trained. When these algorithms are deployed in decision-making capabilities, these
biases can reinforce preexisting prejudices and social inequalities, with potentially negative impacts
on marginalized communities. One organization, Data Science for Social Good, builds bias detection
tools that allow developers to audit data science systems for bias and equity.4
Malicious use. Malicious use includes creating and disseminating false information or fake content,
scams, phishing attempts, hate speech, and activities that harm individuals and national security.
A 2022 UN report found that misinformation had been used to incite hatred against marginalized
groups and to prevent civilians from finding humanitarian corridors during conflicts, such as the one
in Ukraine.5 According to a recent report by the World Economic Forum, “growing misinformation and
disinformation could further increase vaccine hesitancy, which has already led to the re-emergence
of locally eradicated diseases.”6 The Global Disinformation Index uses models based on large
language models (LLMs) to detect disinformation with the goal of tracking news sites supported by
hostile states.7 Similarly, Full Fact is an independent fact checking organization that deploys a range
of AI and machine learning methodologies to detect and curb the proliferation of misinformation
across the evolving landscape of information-spreading platforms.
Data privacy and security threats. Many of the UN Sustainable Development Goals use cases require
access to health or financial data of vulnerable populations. While organizations are well aware
of the harm that could result from breaches in their data systems, many social enterprises have
resource constraints that may limit their ability to use the latest cybersecurity capabilities. Several
organizations have developed data privacy guidelines, tool lists, and custom security frameworks for
not-for-profits with limited resources.8
Performance and explainability. Many AI solutions employ complex algorithms that can make it
difficult to identify the data or logic used to arrive at a decision. This is particularly relevant for gen
AI solutions, which may provide inaccurate or toxic answers. Explainable AI models have several
advantages for not-for-profits: they may make it easier to verify the correctness and fairness of
results, to assign credit to data providers, and to assign accountability for model outcomes. The
Allen Institute for AI recently released a platform for comparing large text data sets to measure the
prevalence of toxic, low-quality, duplicate, or personally identifiable information used to train various
LLMs.9
To mitigate the risks of AI, organizations must first understand and prioritize the risks they are most
likely to face, both from inbound AI threats such as disinformation and from developing and deploying
their AI solutions. While risks such as data privacy may be addressed through traditional software
tools, emerging risks, such as bias in systems driven by LLMs, may require the development of new
monitoring systems and guardrails.
4 “The bias and fairness audit toolkit for machine learning: Aequitas,” Center for Data Science and Public Policy, accessed
April 24, 2024.
5 A/77/288: Disinformation and freedom of opinion and expression during armed conflicts - Report of the Special Rapporteur on the
promotion and protection of the right to freedom of opinion and expression, Office of the High Commissioner for Human Rights,
United Nations, August 12, 2022.
6 The global risks report 2023: 18th edition, World Economic Forum, 2023.
7 “What we do,” Global Disinformation Index, accessed April 24, 2024.
8 “Online privacy for nonprofits: A guide to better practices,” Electronic Frontier Foundation, accessed April 24, 2024; “Learn,” Digital
Defense Fund, accessed April 24, 2024; website of SOAP, accessed April 24, 2024; “Frontline policies,” Open Briefing Ltd, accessed
April 24, 2024.
9 Akshita Bhagia et al., “What’s in my big data?,” arXiv:2310.20707, March 2024.
AI for social good: Improving lives and protecting the planet 8
Existing deployments related to SDG 3: Good Health and Well-Being
SDG 3 aims to promote well-being and ensure people live healthy lives.11 Specific targets for this SDG
include reducing maternal mortality; fighting communicable diseases such as AIDS, tuberculosis,
and malaria; and establishing universal access to sexual and reproductive care, family planning, and
education.
AI is now well integrated into many medical research pipelines. Key AI applications in this area include
protein modeling, genome sequencing, computerized tomography (CT) analysis, vision support,
and vaccine design. Health is relatively accessible for AI work compared with many SDGs: the field
is technology-forward, data availability is high (relative to other SDGs), and health outcomes are
frequently measurable. Yet major opportunities remain to support SDG 3 targets that have received
less attention, such as treating neglected communicable diseases and preventing substance abuse.
Sample use case: Addressing maternal and newborn health in Kenya. Jacaranda Health provides
AI-enabled solutions that improve the quality of care for women with the goal of reducing the number
of maternal deaths in Kenya. For example, PROMPTS is an SMS exchange that sends personalized
messages to women, empowering them to seek care. An accompanying free digital healthcare
platform uses natural language processing to categorize user questions in real time and connects
those who need urgent care with a help desk agent. More than two million new and expectant
mothers have enrolled with PROMPTS. Mothers who use the services are 20 percent more likely to
attend more than four prenatal visits; women who adopt the service are also twice as likely to use
postpartum family planning services as women who do not.12 Jacaranda Health shares feedback from
PROMPTS users with governments and facilities to improve their services.13
Sample use case: Addressing maternal and newborn health in India. More than 1.3 million women
in India have died in pregnancy or childbirth over the past two decades, mostly from preventable
causes.14 ARMMAN was founded in 2008 to address systematic problems that prevent at-risk
women from accessing care.15 The organization developed numerous interventions, including
mMitra, an automated voice messaging system that delivers key information on preventive care.
These messages have a high correlation with positive health outcomes, such as improved rates of
taking iron supplements and better knowledge of family planning. However, 40 percent of women
drop out of the program before giving birth.16 ARMMAN has resources to call some women and
encourage them to stay in the program. The organization partnered with Google Research India to
develop an AI-based prediction model for this intervention that selects women to receive service
calls. The solution is a resource optimization model based on a restless multi-armed bandit approach
to optimize resource allocation in a changing world. In a randomized controlled trial, dropout rates
were 32 percent lower for women called according to the algorithm than women called using a round
robin control group method.17 Using mMitra, ARMMAN has reached roughly 3.6 million women in nine
states, many of whom would likely have dropped out without the AI-targeted intervention. ARMMAN
has now developed a similar AI model for use with Kilkari, a voice technology program that brings
time-sensitive care information to families.18
11 “3: Good Health and Well-Being,” Global Goals, accessed April 24, 2024.
12 PROMPTS, Jacaranda Health, 2023.
13 “Impact at a glance,” Jacaranda Health, accessed April 25, 2024.
14 R. Begum et al., “Trends in maternal mortality in India over two decades in nationally representative surveys,” British Journal of
Obstetrics and Gynaecology, March 2022, Volume 129, Number 4.
15 “ARMMAN: About us,” LinkedIn, accessed April 25, 2024.
16 Google Research Blog, “Using ML to boost engagement with a maternal and child health program in India,” blog entry by Milind
Tambe and Aparna Taneja, August 24, 2022.
17 Aparna Hegde et al., “Field study in deploying restless multi-armed bandits: Assisting non-profits in improving maternal and child
health,” Proceedings of the AAAI Conference on Artificial Intelligence, June 2022, Volume 36, Number 11.
18 “Kilkari,” ARMMAN, accessed April 25, 2024.
AI for social good: Improving lives and protecting the planet 9
Sample use case: Predicting the structure of proteins to aid drug discovery. DeepMind developed
AlphaFold 2 in 2020 and AlphaFold 3 in 2024 to tackle a challenge that had plagued scientists
for more than 50 years: the protein-folding problem. This problem involves three related puzzles,
as defined by a National Library of Medicine paper: What is the folding code? What is the folding
mechanism? And can we predict the native structure of a protein from its amino acid sequence?19
AlphaFold2 is an attention-based deep learning system that predicts protein structures with a
higher degree of accuracy than was previously possible. The DeepMind team released a database
of more than 200 million protein structure predictions that is now widely used in structural biology
research.20 A million researchers have accessed the protein structure database since its launch,
using the predictions to solve real-world problems, including developing treatments for neglected
diseases and fighting antibiotic resistance.21 AlphaFold 3 extends beyond proteins to include a wide
range of biomolecules impacting life sciences and medical research, agriculture, materials sciences,
and more.
Existing deployments related to SDG 4: Quality Education
SDG 4 aims to ensure inclusive and equitable quality education and promote lifelong learning
opportunities.22 Targets include establishing free primary and secondary education, ensuring equal
access to quality preprimary education, and achieving universal literacy and numeracy.
AI algorithms are already being used in this space, such as predictive
One in 20 school-age tools that help identify a student’s likelihood of completing high school
or dropping out and that enable at-risk students to get early intervention
children from low- and support.23 AI can be used to create more-inclusive educational
platforms for young children, teenagers, adults, and people with
income countries disabilities; increase student enrollment; and formulate lesson plans
for teachers—including creating materials tailored to students’ unique
development areas and interests.
has internet access at
Yet implementation has proved challenging, partly because of limited
home, while nearly infrastructure—including internet access and data records—in
developing countries. Roughly one in 20 school-age children from low-
nine in ten from high- income countries has internet access at home, while nearly nine in ten
from high-income countries do.24 Parents are unable to engage with
schools using digital platforms due to factors such as digital literacy and
income countries do.
internet access, so use cases that focus on parent engagement are not
yet an option.
Sample use case: Enabling people who are nonverbal or experiencing learning disabilities to
communicate. Livox uses intelligent algorithms and machine learning to adapt content for students
with a variety of disabilities, including verbal, motor, cognitive, and visual.25 The Livox interface adapts
to the student’s needs, and its software tracks improvements in visual, auditory, cognitive, and
behavioral function, making it easier for teachers to monitor students’ progress. More than 25,000
people with disabilities have used this service, which is available in 25 languages.
19 Ken A. Dill et al., “The protein folding problem,” Annual Review of Biophysics, June 2008, Volume 37.
20 “AlphaFold: Protein structure database,” EMBL’s European Bioinformatics Institute, accessed April 25, 2024.
21 Oana Stroe, “Case study: AlphaFold uses open data and AI to discover the 3D protein universe,” EMBL, February 9, 2023.
22 “4: Quality Education,” Global Goals, accessed April 25, 2024.
23 IDeas Blog, “Rebuilding the Educate Girls machine learning model,” blog entry by Sid Ravinutala, April 29, 2019.
24 “How many children and young people have internet access at home? Estimating digital connectivity during the COVID-19 pandemic,”
UNICEF, December 2020.
25 “About us,” Livox, accessed April 25, 2024.
AI for social good: Improving lives and protecting the planet 10
Sample use case: Bolstering girls’ enrollment in school. Educate Girls is a not-for-profit organization
that works to educate girls in India’s rural and educationally underresourced areas. The organization
uses a machine learning model to reduce the operational cost of locating girls who are not attending
school. Before developing this model, Educate Girls staff members had to travel from village to
village to gather the required data, which they would then manually compile and analyze to identify
areas where their services could have the most impact. The machine learning model uses census
data, which is manually cleaned and updated where necessary, and district-level out-of-school data
to recommend target areas, allowing Educate Girls staff to reach a greater number of prospective
students faster and target interventions more accurately.26 Educate Girls aims to enroll 1.6 million
girls—or 40 percent of the population of out-of-school girls—into grades one through ten.27
Existing deployments related to SDG 13: Climate Action
SDG 13 focuses on combating climate change and its impacts, including strengthening resilience and
adaptive capacity to climate-related disasters and integrating climate change measures into policies
and planning.28
AI can be used to analyze large climate data sets and model the impact of specific variables, improve
the yield of agriculture, and reduce emissions from transportation and industrial processes, to name
a few applications. Not-for-profit deployments are lower than perceived potential for this SDG. In the
past few years, AI has been used to provide detailed climate information to improve climate change
education and awareness, and to track emissions and improve the sustainability of operations
acr |
70 | mckinsey | ai-powered-marketing-and-sales-reach-new-heights-with-generative-ai.pdf | Growth, Marketing & Sales Practice
AI-powered
marketing and sales
reach new heights
with generative AI
May 2023
by Richelle Deveau, Sonia Joseph Griffin, and Steve Reis
AI technology has
revolutionized marketing
and sales; now, generative
AI promises to disrupt the
wayB2B and B2C players think
about customer experience,
productivity and growth.
Artificial intelligence (AI) and machine learning (ML) continue to push the boundaries of what is
possible in marketing and sales. And now, with the ongoing step-change evolution of generative
AI (gen AI), we’re seeing the use of open-source platforms penetrating to the sales frontlines,
along with rising investment by sales-tech players in gen AI innovations. Given the accelerating
complexity and speed of doing business in a digital-first world, these technologies are becoming
essential tools.
Our research suggests that a fifth of current
sales-team functions could be automated.
Inevitably, this will impact how you operate—and how you connect with and serve your
customers. In fact, it’s probably already doing so. Forward-thinking C-suite leaders are
considering how to adjust to this new landscape. Here, we outline the marketing and sales
opportunities (and risks) in this dynamic field and suggest productive paths forward.
2 AI-powered sales and marketing reach new heights with generative AI
How AI is reshaping
marketing and sales
AI is poised to disrupt marketing and sales in every sector. This is the result
of shifts in consumer sentiment alongside rapid technological change.
Omnichannel is table stakes Step changes are occurring in
Across industries, engagement models are changing: digitization and automation
today’s customers want everything, everywhere, AI technology is evolving at pace. It is becoming
and all the time. While they still desire an even mix of increasingly easy and less costly to implement, while
traditional, remote, and self-service channels (including offering ever-accelerating complexity and speed that
face-to-face, inside sales, and e-commerce), we see far exceeds human capacity. Our research suggests
continued growth in customer preference for online that a fifth of current sales-team functions could be
ordering and reordering. automated. In addition, new frontiers are opening with
the rise of gen AI (see sidebar, “What is generative AI?”).
Winning companies—those increasing their market
share by at least 10 percent annually—tend to utilize Furthermore, venture capital investment in AI has
advanced sales technology; build hybrid sales teams grown 13-fold over the last ten years.1 This has led to
and capabilities; tailor strategies for third-party and an explosion of “usable” data (data that can be used to
company-owned marketplaces; achieve e-commerce formulate insights and suggest tangible actions) and
excellence across the entire funnel; and deliver hyper- accessible technology (such as increased computation
personalization (unique messages for individual power and open-source algorithms). Vast, and growing,
decision makers based on their needs, profile, amounts of data are now available for foundation-model
behaviors, and interactions—both past and predictive). training, and since 2012 there’s been a millionfold
increase in computation capacity—doubling every three
to four months.2
What is generative AI?
Many of us are already familiar with online AI chatbots and image generators, using them to create
convincing pictures and text at astonishing speed. This is the great power of generative AI, or gen AI: it
utilizes algorithms to generate new content—writing, images, or audio—from training data.
To do this, gen AI uses deep-learning models called foundation models (FMs). FMs are pre-trained
on massive datasets and the algorithms they support are adaptable to a wide variety of downstream
tasks, including content generation. Gen AI can be trained, for example, to predict the next word in
a string of words and can generalize that ability to multiple text-generation tasks, such as writing
articles, jokes, or code.
In contrast, “traditional” AI is trained on a single task with human supervision, using data specific
to that task; it can be fine-tuned to reach high precision, but must be retrained for each new use
case. Thus gen AI represents an enormous step change in power, sophistication, and utility—and a
fundamental shift in our relationship to artificial intelligence.
1 Nestor Maslej et al., “The AI Index 2023 annual report,” AI Index Steering Committee, Institute for Human-Centered AI, Stanford University, April 2023.
2 Cliff Saran, “Stanford University finds that AI is outpacing Moore’s Law,” Computer Weekly, December 12, 2019; Risto Miikkulainen, “Creative AI
through evolutionary computation: Principles and examples,” SN Computer Science, 2(3): 163, March 23, 2001.
rabediS
AI-powered sales and marketing reach new heights with generative AI 3
What does gen AI mean for
marketing and sales?
The rise of AI, and particularly gen AI, has potential for impact in three areas
of marketing and sales: customer experience (CX), growth, and productivity.
For example, in CX, hyper-personalized content and offerings can be based on individual
customer behavior, persona, and purchase history. Growth can be accelerated by leveraging AI
to jumpstart top-line performance, giving sales teams the right analytics and customer insights
to capture demand. Additionally, AI can boost sales effectiveness and performance by offloading
and automating many mundane sales activities, freeing up capacity to spend more time with
customers and prospective customers (while reducing cost to serve).
In all these actions, personalization is key. AI coupled with company-specific data and context
has enabled consumer insights at the most granular level, allowing B2C lever personalization
through targeted marketing and sales offerings. Winning B2B companies go beyond account-
based marketing and disproportionately use hyper-personalization in their outreach.
Dynamic audience targeting and segmentation
Gen AI can combine and analyze large amounts of data—such as demographic information, existing
customer data, and market trends—to identify additional audience segments. Its algorithms then
enable businesses to create personalized outreach content, easily and at scale.
Instead of spending time researching and creating audience segments, a marketer can leverage gen
AI’s algorithms to identify segments with unique traits that may have been overlooked in existing
customer data. Without knowing every detail about these segments, they can then ask a gen AI tool
to draft automatically tailored content such as social media posts and landing pages. Once these have
been refined and reviewed, the marketer and a sales leader can use gen AI to generate further content
such as outreach templates for a matching sales campaign to reach prospects.
Embracing these techniques will require some openness to change. Organizations will require a
comprehensive and aggregated dataset (such as an operational data lake that pulls in disparate
sources) to train a gen AI model that can generate relevant audience segments and content. Once
trained, the model can be operationalized within commercial systems to streamline workflows while
being continuously refined by agile processes.
Lastly, the commercial organizational structure and operating model may need to be adjusted to
ensure appropriate levels of risk oversight are in place and performance assessments align to the new
ways of working.
selas
IA
neg
A
esac
esu
4 AI-powered sales and marketing reach new heights with generative AI
Bringing gen AI to life in the customer journey
There are many gen AI-specific use cases across the customer journey that can drive impact:
— At the top of the funnel, gen AI — Within the sales motion, gen AI — There are many gen AI use cases
surpasses traditional AI-driven goes beyond initial sales-team after the customer signs on the
lead identification and targeting engagement, providing continuous dotted line, including onboarding
that uses web scraping and simple critical support throughout the entire and retention. When a new customer
prioritization. Gen AI’s advanced sales process, from proposal to deal joins, gen AI can provide a warm
algorithms can leverage patterns closure. welcome with personalized
in customer and market data training content, highlighting
to segment and target relevant With its ability to analyze customer relevant best practices. A chatbot
audiences. With these capabilities, behavior, preferences, and functionality can provide immediate
businesses can efficiently analyze demographics, gen AI can generate answers to customer questions and
and identify high-quality leads, personalized content and messaging. enhance training materials for future
leading to more effective, tailored From the beginning, it can assist customers.
lead-activation campaigns with hyper-personalized follow-
(see “A gen AI sales use case: up emails at scale and contextual Gen AI can also offer sales
Dynamic audience targeting and chatbot support. It can also act leadership with real-time next-step
segmentation”). as a 24/7 virtual assistant for each recommendations and continuous
team member, offering tailored churn modeling based on usage
Additionally, gen AI can optimize recommendations, reminders, trends and customer behavior.
marketing strategies through and feedback, resulting in higher Additionally, dynamic customer-
A/B testing of various elements engagement and conversion rates. journey mapping can be utilized to
such as page layouts, ad copy, identify critical touchpoints and drive
and SEO strategies, leveraging As the deal progresses, gen AI can customer engagement.
predictive analytics and data- provide real-time negotiation
driven recommendations to ensure guidance and predictive insights
maximum return on investment. based on comprehensive analysis of
These actions can continue through historical transaction data, customer
the customer journey, with gen behavior, and competitive pricing.
AI automating lead-nurturing
campaigns based on evolving
customer patterns.
This revolutionary approach is transforming
the landscape of marketing and sales, driving
greater effectiveness and customer engagement
from the very start of the customer journey.
AI-powered sales and marketing reach new heights with generative AI 5
Commercial leaders are optimistic—and reaping benefits
We asked a group of commercial leaders to provide their perspective on use cases and the role
of gen AI in marketing and sales more broadly. Notably, we found cautious optimism across the
board: respondents anticipated at least moderate impact from each use case we suggested.
In particular, these players are most enthusiastic about use cases in the early stages of the
customer journey lead identification, marketing optimization, and personalized outreach
(Exhibit 1).
Exhibit 1
Commercial leaders are cautiously optimistic about gen AI use cases,
anticipating moderate to significant impact.
Estimated impact of use cases,¹ % respondents answering “significant” or “very significant”
Lead identification
(real time, based on customer trends) 60
Marketing optimization
(A/B testing, SEO strategies) 55
Personalized outreach
(chatbots, virtual assistants) 53
Dynamic content
(websites, marketing collateral) 50
Up/cross-selling recs
(via usage patterns, support tickets) 50
Success analytics
45
(continuous churn modeling)
Marketing analytics
(dynamic audience targeting) 45
Dynamic customer-journey mapping
(identifying critical touchpoints) 45
Automated marketing workflows
(nurturing campaigns) 35
Sales analytics
(predictive pricing, negotiation) 30
Sales coaching
(hyper-personalized training) 25
1Senior executives in significant global B2B and B2C sales and marketing organizations across a wide range of industries and company maturity levels were
asked: Please share your estimated ROI / impact these tools would have if implemented in your organization.
Source: McKinsey analysis
McKinsey & Company
6 AI-powered sales and marketing reach new heights with generative AI
These top three use cases are all focused on prospecting
Our research found that
and lead generation, where we’re witnessing significant
early momentum. This comes as no surprise, considering the
vast amount of data on prospective customers available for
90 percent
analysis and the historical challenge of personalizing initial
marketing outreach at scale.
Various players are already deploying gen AI use cases,
but this is undoubtedly only scratching the surface. Our
of commercial leaders expect to utilize gen AI solutions “often” over
research found that 90 percent of commercial leaders
the next two years.
expect to utilize gen AI solutions “often” over the next two
years (Exhibit 2).
Web <year>
<Title>
Exhibit 2
Exhibit <x> of <x>
Commercial leaders are already leveraging gen AI use cases—but most feel the
technology is underutilized.
Extent to which commercial leaders feel their organizations are using machine learning / gen AI,¹
% of responses
Machine learning Gen AI
55
40
25
20 20 20
15
5
0 0
Almost never Rarely Sometimes Often Almost always
Extent to which commercial leaders think their organizations should be using machine learning /
gen AI,² % of responses
65
50
40
25
10 10
0 0 0 0
Almost never Rarely Sometimes Often Almost always
1Senior executives in significant global B2B and B2C sales and marketing organizations across a wide range of industries and company maturity levels were
asked: To what extent is your organization using ML / gen AI solutions?
2Q: How much do you think your organization should be using ML / gen AI solutions?
Source: McKinsey analysis
McKinsey & Company
AI-powered sales and marketing reach new heights with generative AI 7
Overall, the most effective companies are prioritizing and deploying advanced sales tech,
building hybrid teams, and enabling hyper-personalization. And they’re maximizing their use of
e-commerce and third-party marketplaces through analytics and AI. At successful companies,
we’ve found:
— There is a clearly defined AI vision and strategy.
— More than 20 percent of digital budgets are invested in AI-related technologies.
— Teams of data scientists are employed to run algorithms to inform rapid pricing strategy and
optimize marketing and sales.
— Strategists are looking to the future and outlining simple gen AI use cases.
Such trailblazers are already realizing the potential of gen AI to elevate their operations.
Our research indicates that players
that invest in AI are seeing a revenue
uplift of 3 to 15 percent and a sales
ROI uplift of 10 to 20 percent.
Anticipating and mitigating risks in gen AI
While the business case for artificial intelligence is compelling, the rate of change in AI
technology is astonishingly fast—and not without risk. When commercial leaders were asked
about the greatest barriers limiting their organization’s adoption of AI technologies, internal and
external risk were at the top of the list.
From IP infringement to data privacy and security, there are a number of issues that require
thoughtful mitigation strategies and governance. The need for human oversight and
accountability is clear, and may require the creation of new roles and capabilities to fully
capitalize on opportunities ahead.
88 AI-powered sales and marketing reach new heights with generative AI
The way forward:
Six “no regrets”
AI strategies
There are six actions you can take in your company today to chart
an AI transformation in sales and marketing.
2.
3.
Form a commercial
gen AI taskforce
Identify low-hanging fruit in
Create a cross-functional team (including, your customer journey
for example, marketing, sales, pricing, and
Look for simple, high-impact, low-cost,
1. IT) to explore gen AI opportunities and
low-risk use cases (such as automating
pressure test applicability of commercial
prospecting outreach emails) and put
Conduct a gen AI audit of use cases.
guardrails in place to limit risk.
commercial activities
Evaluate marketing and sales tech
infrastructure and skill sets; explore
how open-source or low-cost tech
players could help you implement gen
AI use cases.
6.
Establish gen AI guidelines for
your sales team
5.
Prohibit input of sensitive customer data
Train your sales team on gen AI into gen AI tools and set a high bar for
4. basics to fuel experimentation verifying outputs, especially where content
will be externally facing.
Launch a gen AI experiment Ofer workshops on gen AI fundamentals
(or three) to give the team a better sense of potential
applications and the con—dence to begin
Pilot two or three exciting use cases in a experimenting.
targeted portion of the sales cycle (such as
top-of-funnel). Track results and re—ne for
broader implementation.
AI-powered sales and marketing reach new heights with generative AI 9
In addition to immediate actions, leaders can start thinking strategically about how to invest in AI
commercial excellence for the long term. It will be important to identify which use cases are table
stakes, and which can help you differentiate your position in the market. Then prioritize based on
impact and feasibility.
The AI landscape is evolving very quickly, and winners today may not be viable tomorrow. Small start-
ups are great innovators but may not be able to scale as needed or produce sales-focused use cases
that meet your needs. Test and iterate with different players, but pursue partnerships strategically
based on sales-related innovation, rate of innovation versus time to market, and ability to scale.
v v v
AI is changing at breakneck speed, and while it’s hard to predict the course of this revolutionary tech,
it’s sure to play a key role in future marketing and sales. Leaders in the field are succeeding by turning
to gen AI to maximize their operations, taking advantage of advances in personalization and internal
sales excellence. How will your industry react?
Richelle Deveau is a partner in McKinsey’s Southern California office, and Sonia Joseph Griffin is an associate partner
in the Atlanta office, where Steve Reis is a senior partner.
The authors wish to thank Michelle Court-Reuss, Will Godfrey, Russell Groves, Maxim Lampe, Siamak Sarvari, and Zach
Stone for their contributions to this article.
10 AI-powered sales and marketing reach new heights with generative AI
McKinsey Growth, Marketing & Sales
May 2023
Copyright 2023 © McKinsey & Company
Designed by Darby
www.mckinsey.com
@McKinsey
@McKinsey |
74 | mckinsey | the-state-of-ai-in-2022-and-a-half-decade-in-review.pdf | The state of AI in 2022—and
a half decade in review
December 2022
The results of this year’s McKinsey Global Survey on AI show the expansion of the
technology’s use since we began tracking it five years ago, but with a nuanced
picture underneath.1 Adoption has more than doubled since 2017, though the pro-
portion of organizations using AI has plateaued between 50 and 60 percent for
the past few years. A set of companies seeing the highest financial returns from AI
continue to pull ahead of competitors. The results show these leaders making larger
investments in AI, engaging in increasingly advanced practices known to enable
scale and faster AI development, and showing signs of faring better in the tight
market for AI talent. On talent, for the first time, we looked closely at AI hiring and
upskilling. The data show that there is significant room to improve diversity on AI
teams, and, consistent with other studies, diverse teams correlate with outstanding
performance.
Five years in
review: AI adoption,
impact, and spend
This marks the fifth consecutive year we’ve conducted research globally on AI’s role in business, and we
have seen shifts over this period.
First, AI adoption has more than doubled.² In 2017, 20 percent of respondents reported adopting AI in
at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in
2019 at 58 percent.
Meanwhile, the average number of AI capabilities that organizations use, such as natural-language
generation and computer vision, has also doubled—from 1.9 in 2018 to 3.8 in 2022. Among these
1 In the survey, we defined AI as the ability of a machine to perform cognitive functions that we associate with human minds (for example,
natural-language understanding and generation) and to perform physical tasks using cognitive functions (for example, physical robotics,
autonomous driving, and manufacturing work).
2 In 2017, the definition for AI adoption was using AI in a core part of the organization’s business or at scale. In 2018 and 2019, the definition
was embedding at least one AI capability in business processes or products. In 2020, 2021, and 2022, the definition was that the
organization has adopted AI in at least one function.
2 The state of AI in 2022—and a half decade in review
capabilities, robotic process automation and computer vision have remained the most commonly deployed each
year, while natural-language text understanding has advanced from the middle of the pack in 2018 to the front of the
list just behind computer vision.
Responses show an increasing number of AI capabilities embedded in
organizations over the past ve years.
Average number of AI capabilities that Share of respondents who say their organizations
respondents’ organizations have embedded have adopted AI in at least one function, %
within at least one function or business unit¹
3.9 3.8 47 58 50 56 50
3.1
2.3
20
1.9
2018 2019 2020 2021 2022 2017 2018 2019 2020 2021 2022
% of respondents who say given AI capability is embedded in products or business processes in
at least one function or business unit²
Robotic process automation 39
Computer vision 34
Natural-language text understanding 33
Virtual agents or conversational interfaces 33
Deep learning 30
Knowledge graphs 25
Recommender systems 25
Digital twins 24
Natural-language speech understanding 23
Physical robotics 20
Reinforcement learning 20
Facial recognition 18
Natural-language generation 18
Transfer learning 16
Generative adversarial networks (GAN) 11
Transformers 11
¹The number of capabilities included in the survey has grown over time, from 9 in 2018 to 15 in the 2022 survey.
²Question was asked only of respondents who said their organizations have adopted AI in at least one function.
McKinsey & Company
The state of AI in 2022—and a half decade in review 3
The top use cases, however, have remained relatively stable: optimization of service operations has taken
the top spot each of the past four years.
Second, the level of investment in AI has increased alongside its rising adoption. For example, five years
ago, 40 percent of respondents at organizations using AI reported more than 5 percent of their digital
budgets went to AI, whereas now more than half of respondents report that level of investment. Going
forward, 63 percent of respondents say they expect their organizations’ investment to increase over the
next three years.
The most popular AI use cases span a range of functional activities.
Top use cases Use cases by function
Most commonly adopted AI use cases, by function, % of respondents¹
Service operations² Product and/or service development Marketing and sales Risk
Service operations optimization 24
Creation of new AI-based products 20
Customer service analytics 19
Customer segmentation 19
New AI-based enhancements of products 19
Customer acquisition and lead generation 17
Contact-center automation 16
Product feature optimization 16
Risk modeling and analytics 15
Predictive service and intervention 14
¹Out of 39 use cases. Question was asked only of respondents who said their organizations have adopted AI in at least one function.
²Eg, eld services, customer care, back o ce.
McKinsey & Company
4 The state of AI in 2022—and a half-decade in review
The most popular AI use cases span a range of functional activities.
Top use cases Use cases by function
Most commonly adopted AI use cases within each business function,¹ % of respondents¹
Service operations² Product and/or service development
Service operations Creation of new AI-based
24 20
optimization products
Contact-center New AI-based enhancements
16 19
automation of products
Marketing and sales Supply chain management
Customer service Sales and demand
19 10
analytics forecasting
Logistics network
Customer segmentation 19 9
optimization
Risk Human resources
Risk modeling and Optimization of talent
15 10
analytics management
Fraud and debt Optimization of workforce
11 5
analytics deployment
Strategy and corporate finance Manufacturing
Capital allocation 7 Predictive maintenance 13
Yield, energy, and/or
Treasury management 4 11
throughput optimization
Simulations (eg, using digital
M&A support 4 11
twins, 3 D modeling)
¹Question was asked only of respondents who said their organizations have adopted AI in at least one function.
²Eg, eld services, customer care, back o ce.
McKinsey & Company
Third, the specific areas in which companies see value from AI have evolved. In 2018, manufacturing and
risk were the two functions in which the largest shares of respondents reported seeing value from AI
use. Today, the biggest reported revenue effects are found in marketing and sales, product and service
development, and strategy and corporate finance, and respondents report the highest cost benefits
from AI in supply chain management. The bottom-line value realized from AI remains strong and largely
consistent. About a quarter of respondents report this year that at least 5 percent of their organizations’
EBIT was attributable to AI in 2021, in line with findings from the previous two years, when we’ve also
tracked this metric.
Lastly, one thing that has remained concerningly consistent is the level of risk mitigation organizations
engage in to bolster digital trust. While AI use has increased, there have been no substantial increases in
reported mitigation of any AI-related risks from 2019—when we first began capturing this data—to now.
The state of AI in 2022—and a half decade in review 5
AI-related cost decreases are most often reported in supply chain
management and revenue increases in product development and marketing
and sales.
Cost decrease and revenue increase from AI adoption in 2021, by function, % of respondents¹
Decrease Decrease Decrease Increase Increase Increase
by <10% by 10–19% by ≥20% by >10% by 6–10% by ≤5%
Service operations 45 29 10 6 10 10 37 57
Manufacturing 42 32 7 3 10 18 33 61
Human resources 29 25 3 1 14 13 31 58
Marketing and sales 28 21 43 9 20 41 70
Risk 43 30 8 5 10 11 27 48
Supply chain management 52 41 7 4 14 17 28 59
Product and/or service development 30 20 4 6 13 24 33 70
Strategy and corporate finance 43 31 8 4 8 16 41 65
Average across all activites 32 23 6 3 8 19 36 63
1Question was asked only of respondents who said their organizations have adopted AI in a given function. Respondents who said “no change,”
“cost increase,” “not applicable,” or “don’t know” are not shown.
McKinsey & Company
6 The state of AI in 2022—and a half decade in review
McKinsey commentary
Michael Chui
Partner, McKinsey Global Institute
Over the past half decade, during which we’ve been conducting our global survey, we have seen
the “AI winter” turn into an “AI spring.” However, after a period of initial exuberance, we appear to
have reached a plateau, a course we’ve observed with other technologies in their early years of
adoption. We might be seeing the reality sinking in at some organizations of the level of organiza-
tional change it takes to successfully embed this technology.
In our work, we’ve encountered companies that get discouraged because they went into AI
thinking it would be a quick exercise, while those taking a longer view have made steady prog-
ress by transforming themselves into learning organizations that build their AI muscles over time.
These companies gradually incorporate more AI capabilities and stand up increasingly more
applications progressively faster and more easily thanks to lessons from past successes as well
as failures. They not only invest more, but they also invest more wisely, with the goal of creating a
veritable AI factory that enables them to incorporate more AI in more areas of the business, first in
adjacent ones where some existing capabilities can be repurposed and then into entirely
new ones.
There is, at a high level, an emerging playbook for getting maximum value from AI. Each year that
we conduct our research, we see a group of leaders engaging in the types of practices that help
execute AI successfully. It’s paying off in the form of actual bottom-line impact at significant levels.
We also see it every day as we guide others on their AI journeys. It’s not easy work, but as has
been the case with previous technologies, the gains will go to those who stay the course.
Those taking a longer view
have made steady progress by
transforming themselves into
learning organizations that build
their AI muscles over time.
The state of AI in 2022—and a half decade in review 7
AI use and sustainability efforts
The survey findings suggest that many organizations are more commonly seen at organizations based in
that have adopted AI are integrating AI capabilities into Greater China, Asia–Pacific, and developing markets,
their sustainability efforts and are also actively seeking while respondents in North America are least likely to
ways to reduce the environmental impact of their AI report them.
use (exhibit). Of respondents from organizations that
have adopted AI, 43 percent say their organizations are When asked about the types of sustainability efforts
using AI to assist in sustainability efforts, and 40 per- using AI, respondents most often mention initiatives
cent say their organizations are working to reduce the to improve environmental impact, such as optimiza-
environmental impact of their AI use by minimizing the tion of energy efficiency or waste reduction. AI use
energy used to train and run AI models. As companies is least common in efforts to improve organizations’
that have invested more in AI and have more mature social impact (for example, sourcing of ethically made
AI efforts than others, high performers are 1.4 times products), though respondents working for North
more likely than others to report AI-enabled sustain- American organizations are more likely than their
ability efforts as well as to say their organizations are peers to report that use.
working to decrease AI-related emissions. Both efforts
Exhibit
Organizations are using AI within sustainability e orts and are working to
reduce the environmental impact of their AI use.
Organizations using AI in their sustainability Organizations taking steps to reduce carbon
efforts, % of respondents¹ emissions from their AI use, % of respondents¹
Greater China² 61 Developing markets³ 53
Asia–Paci c 54 Asia–Paci c 47
Developing markets³ 44 Greater China² 46
Europe 39 Europe 36
North America 30 North America 31
Types of sustainability e orts in which respondents’ organizations are using AI⁴
Improving the organization’s environmental impact (eg,
62
improving energy e ciency, optimizing transportation)
Evaluating sustainability e orts (eg, benchmarking) 51
Improving the organization’s governance
45
(eg, regulatory compliance, risk management)
Improving the organization’s social
34
impact (eg, sourcing ethical products)
¹Only asked of respondents whose organizations have adopted AI in at least one function. For organizations based in Greater China, n = 102; for
Asia–Paci c, n = 74; for developing markets, n = 118; for Europe, n = 260; and for North America, n = 190.
²Includes respondents in Hong Kong SAR and Taiwan China.
³Includes respondents in India, Latin America, Middle East, North Africa, and sub-Saharan Africa.
⁴Only asked of respondents whose organizations have adopted AI in at least one function who said that their organizations are using AI in
sustainability e orts; n = 302.
McKinsey & Company
8 The state of AI in 2022—and a half decade in review
Mind the gap: AI
leaders pulling ahead
Over the past five years, we have tracked the leaders in AI—we refer to them as AI high performers—and
examined what they do differently. We see more indications that these leaders are expanding their
competitive advantage than we find evidence that others are catching up.
First, we haven’t seen an expansion in the size of the leader group. For the past three years, we have
defined AI high performers as those organizations that respondents say are seeing the biggest
bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of
respondents falling into that group has remained steady at about 8 percent. The findings indicate that
this group is achieving its superior results mainly from AI boosting top-line gains, as they’re more likely
to report that AI is driving revenues rather than reducing costs, though they do report AI decreasing
costs as well.
Next, high performers are more likely than others to follow core practices that unlock value, such
as linking their AI strategy to business outcomes.³ Also important, they are engaging more often
in “frontier” practices that enable AI development and deployment at scale, or what some call the
“industrialization of AI.” For example, leaders are more likely to have a data architecture that is modular
enough to accommodate new AI applications rapidly. They also often automate most data-related
processes, which can both improve efficiency in AI development and expand the number of applications
they can develop by providing more high-quality data to feed into AI algorithms. And AI high performers
are 1.6 times more likely than other organizations to engage nontechnical employees in creating AI
applications by using emerging low-code or no-code programs, which allow companies to speed up
the creation of AI applications. In the past year, high performers have become even more likely than
other organizations to follow certain advanced scaling practices, such as using standardized tool sets
to create production-ready data pipelines and using an end-to-end platform for AI-related data science,
data engineering, and application development that they’ve developed in-house.
High performers might also have a head start on managing potential AI-related risks, such as personal
privacy and equity and fairness, that other organizations have not addressed yet. While overall, we
have seen little change in organizations reporting recognition and mitigation of AI-related risks since
we began asking about them four years ago, respondents from AI high performers are more likely
than others to report that they engage in practices that are known to help mitigate risk. These include
ensuring AI and data governance, standardizing processes and protocols, automating processes such
as data quality control to remove errors introduced through manual work, and testing the validity of
models and monitoring them over time for potential issues.
3All questions about AI-related strengths and practices were asked only of the 744 respondents who said their organizations had adopted
AI in at least one function, n = 744.
The state of AI in 2022—and a half decade in review 9
Organizations seeing the highest returns from AI are more likely to follow
strategy, data, models, tools, technology, and talent best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Strategy Data Models, tools, and tech TTTaaallleeennnttt aaannnddd wwwaaayyysss ooofff wwwooorrrkkkiiinnnggg
All other respondents AI high performers²
Have a road map that clearly prioritizes AI initiatives
linked to business value across organization
Have an AI strategy that is aligned with the broader
corporate strategy and goals
Senior management that is fully aligned and committed
to organization’s AI strategy
Have a clearly de ned AI vision and strategy
Appointed a credible leader of AI initiatives who is
empowered to move them forward in collaboration with
peers across business units and functions
Systematically track a comprehensive set of well-
defined KPIs to measure the incremental impact of
AI initiatives
Have a clear framework for AI governance that
Orgcaovnerisz eavteriyo sntesp osfe thee imnogde tl hdeeve hloipgmhenet sprto creessturns from AI are more likely to follow
Organizations seeing the highest returns from AI are more likely to follow
strategy, data, models, tools, technology, and talent best practices.
strategy, data, models, tools, technology, and talent best practices.
0 20 40 60 80 100
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
SSttrraatteeggyy DDaattaa Models, tools, and techTalentTTT aaaalllneeednnn tttw aaaannnyddds wwwofaaa wyyyssso roookfff iwwwngooorrrkkkiiinnnggg
¹PrSacttriacetes gshyown heDrea taare repreMseondtaetilvse, toof othlso,s ea nwdit ht ethceh highesTTTtaaa dllleeeelnnntattts aaa bnnnedddtw wwweaaaenyyy sssA Iooo hfffi gwwwhooo prrrekkkriiifnnnogggrmers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ earnings before interest and taxes (EBIT) in 2021 was attributable to their use of AI.
³ All other respondents AI high performers²
All other respondents AI high performers²
McKinsey T&a Ckoem apa fnuyll life cycle approach to developing and
Have ability to integrate data intod AeIp mlooydinegls A aI sm qoudiceklsly
as needed (eg, in near real time)
InItnetgergartaet eA Is tterucchtnuorelodg iienste irnntaol bduastain (eesgs, pa rdoacteas slaekse ( ethga, t
contains cduasyt-otmo-edra dya otap earcartoiossn sb, uesminpelsosy euen iwtso) rtko uoswes i)n
AI initiatives
Teams for data science and AI design and development
Integcoralltaeb eoxratetern taol bduatilad (aengd, oimpepnro svoeu ArcI ea,p ppulirccahtaiosnesd)
to use in AI initiatives
Have well-de ned capability-building programs to
Integrate undsetvrueclotpur teedc hinntoelrongayl dpaetras o(engn,e tlesx’ tAuIa sl kciallsll-
center logs) to use in AI initiatives
Train nontechnical personnel to use AI to improve
Generate synthetic data to train AI mdoedceilssi ownh mena kthinegre
are insu cient natural data sets
AI development teams follow standard protocols
(eg, tool frameworks, development processes) for
Have a modular enough data architecture to
building and delivering AI tools
rapidly accommodate the needs of new AI use cases
Automate most data-related processes (eg, data 0 20 40 60 80 100
labeling, data quality control)
Have scalable internal processes for labeling AI training
data
0 20 40 60 80 100
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²R¹Persapcotnicdeesn sths owwhno hsearide tahrea tr eatp lreeassetn 2ta0t ipvee rocfe tnhto osfe t hweitirh otrhgea hniigzahteiostn sd’e EltBasIT b ient 2w0e2e1n w AaI sh iagthtr ipbeurtfaobrmlee tros t ahnedir outshee or fr eAsI.pondents. Not all practices are shown.
³²Respondents who said that at least 20 percent of their organizations’ EBIT in 2021 was attributable to their use of AI.
³
McKinsey & Company
McKinsey & Company
10 The state of AI in 2022—and a half decade in review
Organizations seeing the highest returns from AI are more likely to follow
strategy, data, models, tools, technology, and talent best practices.
Share of respondents reporting their organizations engage in each practice,¹ % of respondents
Strategy Data MMMooodddeeelllsss,,, tttoooooolllsss , aaannnddd ttteeeccchhh TTTaaallleeennnttt aaannnddd wwwaaayyysss ooofff wwwooorrrkkkiiinnnggg
All other respondents AI high performers²
Develop AI models that can provide accurate,
usable results leveraging smaller amounts of data
(ie, “small data”)
Regularly refresh AI models based on clearly de ned
criteria for when and why to do so
Developed in-house the end-to-end platform used for
AI-related data science, data engineering, and
application development
Use a standardized tool set to create production-ready
data pipelines
Develop modular components (eg, data model layers,
data pipelines) so they can be reused in AI applications
Refresh AI/machine learning tech stack at
least annually to take advantage of the latest
technological advances
Organizations seeing the highest returns from AI are more likely to follow
Automate the full life cycle for AI model development
str(eagt, ferogmy d,a tda aingteas,t iomn aondd qeulaslit,y tcoonotrolsl t,h rtoeugchh nology, and talent best practices.
model monitoring)
Share oUf sree tshpeo onrgdaenniztasti orne’sp oowrtni nhgig ht-hpeeirrf oormrgaannceiz ations engage in each practice,¹ % of respondents
computing cluster for AI workloads
Organizations seeing the highest returns from AI are more likely to follow
strategy, data, models, tools, technology, and talent best practices.
SSttrraatteeggyy DDaattaa Models, tools, and techTalentTTT aaaalllneeednnn tttw0 aaaannnyddds wwwofaaa wyyyssso roookfff2 iwwwn0gooorrrkkkiiinnnggg 40 60 80 100
¹SPhraactricees oshfo wren shepreo anred reeprnestesn trateivpe oof rthtoisneg w itthh theei hri gohersgt daenltaisz baettwioeenn sA I ehinghg paergfoerm ienrs aenad cothhe rp rersapcontdiecnets,. ¹N %ot a lol pfr arceticseps oarne sdheownnt.s
²Respondents who said that at least 20 percent of their organizations’ EBIT in 2021 was attributable to theirA uslle ootf hAIe.r respondents AI high performers²
³
Take a full life cycle approach to developing and
McKSSittnrrsaaettyee &gg CyyompanDDyaattaa Models, tools, an dd
e
t pe lc oh yTa inle gn AtTTT aaaa
I
llln meeednnn
o
tttw
d
aaaa ennny lddds
s
wwwofaaa wyyyssso roookfff iwwwngooorrrkkkiiinnnggg
Integrate AI technologies into business processes (eg, All other respondents AI high performers²
day-to-day operations, employee work ows)
Take a full life cycle approach to developing and
Teams for data science and AI dedsiegpnl oaynindg d AevI emloopdmelesnt
collaborate to build and improve AI applications
Integrate AI technologies into business processes (eg,
Havdea wy-etlol--ddeayn oepde craatpioanbsil,i teym-bpulioldyieneg wpororkgraomwss )to
develop technology personnels’ AI skills
Teams for data science and AI design and development
Tcroallianb noornatteec thon bicuailld p aenrsdo inmnperlo tvoe u AsIe a ApIp tloic iamtipornosve
decision making
Have well-de ned capability-building programs to
AI devedleovpemloepn tte tcehanmosl ofoglylo pwe rsstoannndealrsd’ AprI ostkoicllsols
(eg, tool frameworks, development processes) for
building and delivering AI tools
Train nontechnical personnel to use AI to improve
decision making
0 20 40 60 80 100
AI development teams follow standard protocols
(eg, tool frameworks, development processes) for
building and delivering AI tools
0 20 40 60 80 100
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ EBIT in 2021 was attributable to their use of AI.
³
McKinsey & Company
¹Practices shown here are representative of those with the highest deltas between AI high performers and other respondents. Not all practices are shown.
²Respondents who said that at least 20 percent of their organizations’ EBIT in 2021 was attributable to their use of AI.
³
McKinsey & Company
The state of AI in 2022—and a half decade in review 11
Investment is yet another area that could contribute to the widening of the gap: AI high performers are
poised to continue outspending other organizations on AI efforts. Even though respondents at those
leading organizations are just as likely as others to say they’ll increase investments in the future, they’re
spending more than others now, meaning they’ll be increasing from a base that is a higher percentage of
revenues. Respondents at AI high performers are nearly eight times more likely than their peers to say their
organizations spend at least 20 percent of their digital-technology budgets on AI-related technologies.
And these digital budgets make up a much larger proportion of their enterprise spend: respondents at AI
high performers are over five times more likely than other respondents to report that their organizations
spend more than 20 percent of their enterprise-wide revenue on digital technologies.
Finally, all of this may be giving AI high performers a leg up in attracting AI talent. There are indications
that these organizations have less difficulty hiring for roles such as AI data scientist and data engineer.
Respondents from organizations that are not AI high performers say filling those roles has been “very
difficult” much more often than respondents from AI high performers do.
The bottom line: high performers are already well positioned for sustained AI success, improved efficiency
in new AI development, and a resultingly more attractive environment for talent. The good news for
organizations outside the leader group is that there’s a clear blueprint of best practices for success.
Respondents at AI high performers are nearly
eight times more likely than their peers to say their
organizations spend at least 20 percent of their
digital-technology budgets on AI-related technologies.
12 The state of AI in 2022—and a half-decade in review
McKinsey commentary
Bryce Hall
Associate partner
Over the years of our research, we’ve continued to refine our understanding of the specific
practices that leading companies are doing well and the capabilities they have in place to capture
value from AI. Recently, a new set of “frontier” practices has emerged as organizations shift from
experimenting with AI to industrializing it. These include machine learning operations (MLOps)
practices such as assetization, or turning elements like code into reusable assets that can be
applied over and over in different business applications.
But over the years, we’ve also consistently seen a set of foundational practices that these
organizations are getting right. Through our work, we’ve learned not to describe these as “basic”
practices, because they are some of the most difficult to implement. Many of these involve the
people elements that need to be in place for companies to adopt AI successfully, such as having
a clear understanding of what specific tech talent roles are needed and successfully integrating
AI into business processes and decision making. As proven in many cases, AI engines and people
together can create much more value than either can individually.
As the AI frontier advances, we continue to be inspired by some truly innovative applications of
AI, such as the use of AI to identify new drugs, create hyperpersonalized recommendations for
consumers, and power AI simulations in digital twins to optimize performance across a variety
of settings. As individual AI capabilities, such as natural-language processing and generation,
continue to improve and democratize, we’re excited to see a wave of new applications emerge and
more companies capture value from AI at scale.
The state of AI in 2022—and a half decade in review 13
AI talent tales: New
hot roles, continued
diversity woes
Our first detailed look at the AI talent picture signals the maturation of AI, surfaces the most common
strategies organizations employ for talent sourcing and upskilling, and shines a light on AI’s diversity
problem—while showing yet again a link between diversity and success.
Hiring is a challenge, but less so for high performers
Software engineers emerged as the AI role that survey responses show organizations hired most
often in the past year, more often than data engineers and AI data scientists. This is another clear sign
that many organizations have largely shifted from experimenting with AI to actively embedding it in
enterprise applications.
Unfortunately, the tech talent shortage shows no sign of easing, threatening to slow that shift for
some companies. A majority of respondents report difficulty in hiring for each AI-related role in the
Web <year>
<Title>
Exhibit <x> of <x>
Responses suggest that organizations are most often hiring software
engineers, data engineers, and AI data scientists.
AI-related roles that respondents’ organizations hired, past year, % of respondents¹
Software engineers 39
Data engineers 35
AI data scientists 33
Machine learning engineers 30
Data architects 28
AI product owners/managers 22
Design specialists 22
Data visualization specialists 21
Translators 8
None of the above 14
1Only asked of respondents whose organizations have adopted AI in at least one function. For respondents at AI high performers, n = 51. For all other
respondents, n = 413.
McKinsey & Company
14 The state of AI in 2022—and a half decade in review
past year, and most say it either wasn’t any easier or was more difficult to acquire this talent than in years
past. AI data scientists remain particularly scarce, with the largest share of respondents rating data
scientist as a role that has been difficult to fill, out of the roles we asked about.
As mentioned earlier, we see some signs that AI high performers have a slightly easier time hiring than
other organizations, but they still report difficulty more often than not. What’s more evident from the
survey findings is their focus on hiring for AI industrialization and business value optimization. For
example, they’re more than twice as likely to have hired a ML engineer in the past year—a role focused on
optimizing the ML models built by data scientists for performance and scalability, as well as automating
the machine learning pipeline, from data ingestion to prediction generation. Respondents at high
performers are also nearly twice as likely as others to say they have hired an AI product manager to
oversee AI application development and adoption and more than three times as likely to have hired an
analytics translator, two roles that ensure that AI applications deliver business value.
Most respondents say that hiring for each AI-related role has been difficult
in the past year and hasn’t become easier over time.
Difficulty in organizations’ hiring of AI-related roles, past year, % of respondents¹
Very Somewhat Neither easy Somewhat Very
difficult difficult nor difficult easy easy
Software engineers 20 45 17 13 1
Data engineers 20 49 20 6 1
AI data scientists 32 46 9 6 1
Machine learning engineers 28 42 18 9 1
Data architects 25 47 18 5 1
AI product owners/managers 20 42 27 5 1
Design specialists 15 44 24 10 1
Data visualization specialists 15 46 21 12 1
Translators 27 43 14 11 2
Change of difficulty in organizations’ hiring of AI-related roles, past 3 years, % of respondents¹
Much Somewhat Neither easier Somewhat Much
more difficult more difficult nor more difficult easier easier
Software engineers 18 31 24 10 7
Data engineers 22 35 16 15 3
AI data scientists 22 25 19 18 3
Machine learning engineers 20 28 14 22 3
Data architects 21 31 16 14 6
AI product owners/managers 16 27 21 16 3
Design specialists 17 28 20 15 7
Data visualization specialists 17 25 22 23 4
Translators 22 34 19 11 5
1Only asked of respondents whose organizations have adopted AI in at least |
75 | mckinsey | the-state-of-ai-in-2023-generative-ais-breakout-year_vf.pdf | The state of AI in
2023: Generative AI’s
breakout year
As organizations rapidly deploy generative AI tools, survey respondents
expect significant effects on their industries and workforces.
August 2023
The state of AI in 2023: Generative AI’s breakout year
The latest annual McKinsey Global Survey on the current
state of AI confirms the explosive growth of generative AI
(gen AI) tools. Less than a year after many of these tools debuted,
one-third of our survey respondents say their organizations are
using gen AI regularly in at least one business function. Amid
recent advances, AI has risen from a topic relegated to tech
employees to a focus of company leaders: nearly one-quarter
of surveyed C-suite executives say they are personally using
gen AI tools for work, and more than one-quarter of respondents
from companies using AI say gen AI is already on their boards’
agendas. What’s more, 40 percent of respondents say their
organizations will increase their investment in AI overall because
of advances in gen AI. The findings show that these are still early
days for managing gen AI–related risks, with less than half of
respondents saying their organizations are mitigating even the
risk they consider most relevant: inaccuracy.
The organizations that have already embedded AI capabilities
have been the first to explore gen AI’s potential, and those seeing
the most value from more traditional AI capabilities—a group we
call AI high performers—are already outpacing others in their
adoption of gen AI tools.1
The expected business disruption from gen AI is significant, and
respondents predict meaningful changes to their workforces. They
anticipate workforce cuts in certain areas and large reskilling
efforts to address shifting talent needs. Yet while the use of gen AI
might spur the adoption of other AI tools, we see few meaningful
increases in organizations’ adoption of these technologies. The
percent of organizations adopting any AI tools has held steady since
2022, and adoption remains concentrated within a small number of
business functions.
1 We define AI high performers as organizations that, according to respondents, attribute at least 20 percent of their EBIT
to AI adoption.
The state of AI in 2023: Generative AI’s breakout year 1
It’s early days still,
but use of gen AI is
already widespread
The findings from the survey—which was in the field in mid-April 2023—show that, despite
gen AI’s nascent public availability, experimentation with the tools is already relatively common,
and respondents expect the new capabilities to transform their industries. Gen AI has captured
interest across the business population: individuals across regions, industries, and seniority
levels are using gen AI for work and outside of work. Seventy-nine percent of all respondents say
they’ve had at least some exposure to gen AI, either for work or outside of work, and 22 percent
say they are regularly using it in their own work. While reported use is quite similar across
seniority levels, it is highest among respondents working in the technology sector and those
in North America.
2 The state of AI in 2023: Generative AI’s breakout year
Web <2023>
<State of AI 2023>
Exhibit <1PDF> of <11>
Respondents across regions, industries, and seniority levels say they are
already using generative AI tools.
Reported exposure to generative AI tools, % of respondents
Regularly use Regularly use for work Regularly use Have tried at No Don’t
for work and outside of work outside of work least once exposure know
By office location Asia–Pacific 4 18 19 36 19 3
Developing markets 9 11 20 34 23 3
Europe 10 14 11 45 15 6
Greater China 9 10 18 46 14 3
North America 6 22 13 38 19 3
By industry Advanced industries 5 11 16 47 15 5
Business, legal, and professional services 7 16 13 41 21 2
Consumer goods/retail 7 11 12 40 26 4
Energy and materials 6 8 15 50 19 3
Financial services 8 16 18 41 14 4
Healthcare, pharma, and medical products 6 10 17 44 15 7
Technology, media, and telecom 14 19 17 37 9 3
By job title C-suite executives 8 16 13 42 18 2
Senior managers 10 14 16 42 15 3
Midlevel managers 7 16 20 35 19 4
By age Born in 1964 or earlier 6 17 21 30 18 9
Born 1965–80 7 18 18 37 17 3
Born 1981–96 5 22 24 36 11 3
By gender identity Men 8 16 16 37 19 4
Women 12 15 6 46 18 3
Note: Figures may not sum to 100%, because of rounding. In Asia–Pacific, n = 164; in Europe, n = 515; in North America, n = 392; in Greater China (includes
Hong Kong and Taiwan), n = 337; and in developing markets (includes India, Latin America, and Middle East and North Africa), n = 276. For advanced industries
(includes automotive and assembly, aerospace and defense, advanced electronics, and semiconductors), n = 96; for business, legal, and professional services,
n = 215; for consumer goods and retail, n = 128; for energy and materials, n = 96; for financial services, n = 248; for healthcare, pharma, and medical products,
n = 130; and for technology, media, and telecom, n = 244. For C-suite respondents, n = 541; for senior managers, n = 437; and for middle managers, n = 339.
For respondents born in 1964 or earlier, n = 143; for respondents born between 1965 and 1980, n = 268; and for respondents born between 1981 and 1996,
n = 80. Age details were not available for all respondents. For respondents identifying as men, n = 1,025; for respondents identifying as women, n = 156.
The survey sample also included respondents who identified as “nonbinary” or “other” but not a large enough number to be statistically meaningful.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
Organizations, too, are now commonly using gen AI. One-third of all respondents say their
organizations are already regularly using generative AI in at least one function—meaning that
60 percent of organizations with reported AI adoption are using gen AI. What’s more, 40 percent
of those reporting AI adoption at their organizations say their companies expect to invest more in
AI overall thanks to generative AI, and 28 percent say generative AI use is already on their board’s
agenda. The most commonly reported business functions using these newer tools are the same
as those in which AI use is most common overall: marketing and sales, product and service
development, and service operations, such as customer care and back-office support. This
suggests that organizations are pursuing these new tools where the most value is. In our previous
research, these three areas, along with software engineering, showed the potential to deliver
about 75 percent of the total annual value from generative AI use cases.
The state of AI in 2023: Generative AI’s breakout year 3
Web <2023>
<State of AI 2023>
Exhibit <2> of <11>
The most commonly reported uses of generative AI tools are in marketing
and sales, product and service development, and service operations.
Share of respondents reporting that their organization is regularly using generative AI in given
function, %1
Product and/ Strategy and
Marketing or service Service corporate Supply chain
and sales development operations Risk finance HR management Manufacturing
14 13 10 4 4 3 3 2
Most regularly reported generative AI use cases within function, % of respondents
Marketing and sales Product and/or service development Service operations
Crafting first drafts of text documents Identifying trends in customer needs Use of chatbots (eg, for customer service)
9 7 6
Personalized marketing Drafting technical documents Forecasting service trends or anomalies
8 5 5
Summarizing text documents Creating new product designs Creating first drafts of documents
8 4 5
1Questions were asked of respondents who said their organizations have adopted AI in at least 1 business function. The data shown were rebased to
represent all respondents.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
In these early days, expectations for gen AI’s impact are high: three-quarters of all respondents
expect gen AI to cause significant or disruptive change in the nature of their industry’s
competition in the next three years. Survey respondents working in the technology and financial-
services industries are the most likely to expect disruptive change from gen AI. Our previous
research shows that, while all industries are indeed likely to see some degree of disruption, the
level of impact is likely to vary.2 Industries relying most heavily on knowledge work are likely to
see more disruption—and potentially reap more value. While our estimates suggest that tech
companies, unsurprisingly, are poised to see the highest impact from gen AI—adding value
equivalent to as much as 9 percent of global industry revenue—knowledge-based industries
such as banking (up to 5 percent), pharmaceuticals and medical products (also up to 5 percent),
and education (up to 4 percent) could experience significant effects as well. By contrast,
manufacturing-based industries, such as aerospace, automotives, and advanced electronics,
could experience less disruptive effects. This stands in contrast to the impact of previous
technology waves that affected manufacturing the most and is due to gen AI’s strengths in
language-based activities, as opposed to those requiring physical labor.
2 “The economic potential of generative AI: The next productivity frontier,” McKinsey, June 14, 2023.
4 The state of AI in 2023: Generative AI’s breakout year
McKinsey commentary
Alex Singla
Senior partner and global leader of QuantumBlack, AI by McKinsey
It’s amazing how quickly the conversation around generative AI has evolved. Just a few
months ago, the conversation in the C-suite was pretty rudimentary, focused on trying to
understand what it was and seeing what was hype versus what was reality. Now in just about
six months, business leaders are having much more sophisticated conversations. As we can
see from the survey results, almost a third of companies are using generative AI in at least one
business function. This underscores the degree to which companies understand and accept
that generative AI is viable in business.
The next question will be how companies will take the next step, and whether generative
AI will follow the same pattern we observed with AI more generally, where adoption has
plateaued at around the 50 percent mark. We see from the data that the promise of
generative AI is leading almost half of companies already using AI to plan on increasing their
investments in AI, driven in part by the understanding that broader capabilities are needed to
take full advantage of generative AI.
Taking that next step, where generative AI can go from experiment to business engine, and
ensuring a strong return on the investment requires companies to tackle a broad array
of issues. Those include identifying the specific opportunities for generative AI in the
organization, what the governance and operating model should be, how to best manage third
parties (such as cloud and large language model providers), what is needed to manage the
wide range of risks, understanding the implications on people and the tech stack, and being
clear about how to find the balance between banking near-term gains and developing the
long-term foundations needed to scale. These are complex issues, but they are the key to
unlocking the really significant pools of value out there.
The state of AI in 2023: Generative AI’s breakout year 5
Responses show many organizations not yet addressing potential
risks from gen AI
According to the survey, few companies seem fully prepared for the widespread use of
gen AI—or the business risks these tools may bring. Just 21 percent of respondents reporting
AI adoption say their organizations have established policies governing employees’ use of
gen AI technologies in their work. And when we asked specifically about the risks of adopting
gen AI, few respondents say their companies are mitigating the most commonly cited risk
with gen AI: inaccuracy. Respondents cite inaccuracy more frequently than both cybersecurity
and regulatory compliance, which were the most common risks from AI overall in previous
surveys. Just 32 percent say they’re mitigating inaccuracy, a smaller percentage than the
38 percent who say they mitigate cybersecurity risks. Interestingly, this figure is significantly
lower than the percentage of respondents who reported mitigating AI-related cybersecurity
last year (51 percent). Overall, much as we’ve seen in previous years, most respondents say their
organizations are not addressing AI-related risks.
Web <2023>
<State of AI 2023>
Exhibit <3> of <11>
Inaccuracy, cybersecurity, and intellectual-property infringement are the
most-cited risks of generative AI adoption.
Generative AI–related risks that organizations consider relevant and are working to mitigate,
% of respondents1
Organization considers risk relevant Organization working to mitigate risk
Inaccuracy 56 32
Cybersecurity 53 38
Intellectual-property infringement 46 25
Regulatory compliance 45 28
Explainability 39 18
Personal/individual privacy 39 20
Workforce/labor displacement 34 13
Equity and fairness 31 16
Organizational reputation 29 16
National security 14 4
Physical safety 11 6
Environmental impact 11 5
Political stability 10 2
None of the above 1 8
1Asked only of respondents whose organizations have adopted Al in at least 1 function. For both risks considered relevant and risks mitigated, n = 913.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
6 The state of AI in 2023: Generative AI’s breakout year
McKinsey commentary
Alexander Sukharevsky
Senior partner and global leader of QuantumBlack, AI by McKinsey
There is broad awareness about the risks associated with generative AI. But at the same
time, the prevailing anxiety and fear is making it challenging for leaders to effectively address
the risks. As our latest survey shows, just a little over 20 percent of companies have risk
policies in place for generative AI. Those policies tend to focus on protecting a company’s
proprietary information, such as data, knowledge, and other intellectual property. Those are
critical, but we’ve found that many of these risks can be addressed by making changes in the
business’s technology architecture that reflect established policies.
The real trap, however, is that companies look at the risk too narrowly. There is a significant
range of risks—social, humanitarian, sustainability—that companies need to pay attention
to as well. In fact, the unintended consequences of generative AI are more likely to create
issues for the world than the doomsday scenarios that some people espouse. Companies that
are approaching generative AI most constructively are experimenting with and using it while
having a structured process in place to identify and address these broader risks. They are
putting in place beta users and specific teams that think about how generative AI applications
can go off the rails to better anticipate some of those consequences. They are also working
with the best and most creative people in the business to define the best outcomes for both
the organization and for society more generally. Being deliberate, structured, and holistic
about understanding the nature of the new risks—and opportunities—emerging is crucial to
the responsible and productive growth of generative AI.
The state of AI in 2023: Generative AI’s breakout year 7
Leading companies
are already ahead
with gen AI
The survey results show that AI high performers—that is, organizations where respondents
say at least 20 percent of EBIT in 2022 was attributable to AI use—are going all in on artificial
intelligence, both with gen AI and more traditional AI capabilities. These organizations that
achieve significant value from AI are already using gen AI in more business functions than other
organizations do, especially in product and service development and risk and supply chain
management. When looking at all AI capabilities—including more traditional machine learning
capabilities, robotic process automation, and chatbots—AI high performers also are much
more likely than others to use AI in product and service development, for uses such as product-
development-cycle optimization, adding new features to existing products, and creating new
AI-based products. These organizations also are using AI more often than other organizations in
risk modeling and for uses within HR such as performance management and organization design
and workforce deployment optimization.
Another difference from their peers: high performers’ gen AI efforts are less oriented toward cost
reduction, which is a top priority at other organizations. Respondents from AI high performers
are twice as likely as others to say their organizations’ top objective for gen AI is to create entirely
new businesses or sources of revenue—and they’re most likely to cite the increase in the value of
existing offerings through new AI-based features.
8 The state of AI in 2023: Generative AI’s breakout year
Web <2023>
<State of AI 2023>
Exhibit <4> of <11>
Smaller shares of AI high performers see cost reductions as their top
objective for generative AI efforts.
Top objective for organizations’ Respondents at All other
planned generative AI activities, AI high performers2 respondents
% of respondents1
Reduce costs in
19
core business
33
Create new businesses
and/or sources of revenue 23
12
100%
Increase revenue
27 21
from core business
Increase value of offerings
33
by integrating AI-based 30
features or insights
Note: Figures do not sum to 100%, because of rounding.
1Asked only of respondents whose organizations have adopted Al in at least 1 function.
2Respondents who said that at least 20 percent of their organizations’ EBIT in 2022 was attributable to their use of AI. For respondents at AI high performers,
n = 45; for all other respondents, n = 712.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
As we’ve seen in previous years, these high-performing organizations invest much more than
others in AI: respondents from AI high performers are more than five times more likely than
others to say they spend more than 20 percent of their digital budgets on AI. They also use AI
capabilities more broadly throughout the organization. Respondents from high performers
are much more likely than others to say that their organizations have adopted AI in four or
more business functions and that they have embedded a higher number of AI capabilities. For
example, respondents from high performers more often report embedding knowledge graphs
in at least one product or business function process, in addition to gen AI and related natural-
language capabilities.
While AI high performers are not immune to the challenges of capturing value from AI, the results
suggest that the difficulties they face reflect their relative AI maturity, while others struggle with
the more foundational, strategic elements of AI adoption. Respondents at AI high performers
most often point to models and tools, such as monitoring model performance in production and
retraining models as needed over time, as their top challenge. By comparison, other respondents
cite strategy issues, such as setting a clearly defined AI vision that is linked with business value
or finding sufficient resources.
The state of AI in 2023: Generative AI’s breakout year 9
Web <2023>
<State of AI 2023>
Exhibit <5> of <11>
Models and tools pose the biggest AI-related challenge for high
performers, while strategy is a common stumbling block for others.
Element that poses the biggest Respondents at All other
challenge in capturing value from AI, AI high performers2 respondents
% of respondents1 Other 1 2
Strategy 11
24
Data 11
Technology 13
18
Adoption and scaling 19
100%
13
Talent 20 15
21
Models and tools 24
6
Note: Figures do not sum to 100%, because of rounding.
1Asked only of respondents whose organizations have adopted Al in at least 1 function.
2Respondents who said that at least 20 percent of their organizations’ EBIT in 2022 was attributable to their use of AI. For respondents at AI high performers,
n = 49; for all other respondents, n = 792.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
The findings offer further evidence that even high performers haven’t mastered best practices
regarding AI adoption, such as machine-learning-operations (MLOps) approaches, though they
are much more likely than others to do so. For example, just 35 percent of respondents at AI high
performers report that where possible, their organizations assemble existing components, rather
than reinvent them, but that’s a much larger share than the 19 percent of respondents from other
organizations who report that practice.
Many specialized MLOps technologies and practices may be needed to adopt some of the more
transformative uses cases that gen AI applications can deliver—and do so as safely as possible.
Live-model operations is one such area, where monitoring systems and setting up instant alerts
to enable rapid issue resolution can keep gen AI systems in check. High performers stand out
in this respect but have room to grow: one-quarter of respondents from these organizations say
their entire system is monitored and equipped with instant alerts, compared with just 12 percent
of other respondents.
10 The state of AI in 2023: Generative AI’s breakout year
McKinsey commentary
Bryce Hall
Associate partner
Over the past six years as we’ve conducted our annual global AI research, one consistent
finding is that high performers take a broad view of what’s needed to be successful. They
are particularly strong in staying focused on value, and then rewiring their organization to
capture that value. This pattern is clear when looking at how high performers are working with
generative AI as well.
For example, on strategy, leaders from our analysis are mapping out where the high-value
opportunities are from AI across their business domains. Tellingly, they’re not doing this
for only generative AI. As excited as we all are about the dazzling new gen AI applications,
significantly more than half of the potential value for companies comes from AI applications
that don’t use gen AI. They are maintaining discipline in viewing the full range of AI
opportunities based on potential value.
That approach extends to all capability areas. In technology and data, for example, high
performers are laser focused on capabilities needed to capture the value they’ve identified.
This includes capabilities to enable large language models to train on company and
industry-specific data. They’re evaluating and testing the efficiencies and speed enabled
by consuming existing AI services (what we call the “taker” approach) and developing
capabilities to create competitive advantage—for example, by tuning models and training
them to use their own proprietary data (what we call the “shaper” approach).
The state of AI in 2023: Generative AI’s breakout year 11
AI-related talent
needs shift, and AI’s
workforce effects
are expected to
be substantial
Our latest survey results show changes in the roles that organizations are filling to support their
AI ambitions. In the past year, organizations using AI most often hired data engineers, machine
learning engineers, and Al data scientists—all roles that respondents commonly reported
hiring in the previous survey. But a much smaller share of respondents report hiring AI-related-
software engineers—the most-hired role last year—than in the previous survey (28 percent in
the latest survey, down from 39 percent). Roles in prompt engineering have recently emerged, as
the need for that skill set rises alongside gen AI adoption, with 7 percent of respondents whose
organizations have adopted AI reporting those hires in the past year.
12 The state of AI in 2023: Generative AI’s breakout year
The findings suggest that hiring for AI-related roles remains a challenge but has become
somewhat easier over the past year, which could reflect the spate of layoffs at technology
companies from late 2022 through the first half of 2023. Smaller shares of respondents than in
the previous survey report difficulty hiring for roles such as AI data scientists, data engineers,
and data-visualization specialists, though responses suggest that hiring machine learning
engineers and AI product owners remains as much of a challenge as in the previous year.
Web <2023>
<State of AI 2023>
Exhibit <6> of <11>
Hiring for AI-related roles remains a challenge, though reported difficulty
has decreased since 2022 for many roles.
Share of respondents reporting difficulty in organizations’ hiring of AI-related roles,1 % 2022 2023
LESS DIFFICULT MORE DIFFICULT
0 20 40 60 80 100
Machine learning engineers
AI data scientists
Translators
AI product owners/managers
Data architects
Prompt engineers2
Software engineers
Data engineers
Design specialists
Data-visualization specialists
1Asked only of respondents whose organizations have adopted Al in at least 1 function and who said their organization hired the given role in the past
12 months. Respondents who said “easy,” “neither difficult nor easy,” or “don’t know” are not shown.
2Not asked of respondents in 2022.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
The state of AI in 2023: Generative AI’s breakout year 13
Looking ahead to the next three years, respondents predict that the adoption of AI will reshape
many roles in the workforce. Generally, they expect more employees to be reskilled than to be
separated. Nearly four in ten respondents reporting AI adoption expect more than 20 percent of
their companies’ workforces will be reskilled, whereas 8 percent of respondents say the size of
their workforces will decrease by more than 20 percent.
Web <2023>
<State of AI 2023>
Exhibit <7> of <11>
Survey respondents expect AI to meaningfully change their
organizations’ workforces.
Expectations about the impact of AI adoption on organizations’ workforces, next 3 years,
% of respondents1
Change in number of employees Share of employees expected to be reskilled
Don’t know 8
Don’t know 12
Increase by >20% 3
Increase by 11–20% 4
Increase by 3–10% 8
>20% 38
Little or no change
(decrease or increase by ≤2%) 30
11–20% 18
Decrease by 3–10% 25
6–10% 17
Decrease by 11–20% 10
≤5% 20
Decrease by >20% 8
Note: Figures may not sum to 100%, because of rounding.
1Asked only of respondents whose organizations have adopted Al in at least 1 function; n = 913.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
14 The state of AI in 2023: Generative AI’s breakout year
Looking specifically at gen AI’s predicted impact, service operations is the only function in
which most respondents expect to see a decrease in workforce size at their organizations. This
finding generally aligns with what our recent research suggests: while the emergence of gen
AI increased our estimate of the percentage of worker activities that could be automated (60
to 70 percent, up from 50 percent), this doesn’t necessarily translate into the automation of an
entire role.
Web <2023>
<State of AI 2023>
Exhibit <8> of <11>
Service operations is the only function in which most respondents expect
to see a decrease in workforce size because of generative AI.
Effect of generative AI adoption on number of employees, by business function, next 3 years,
% of respondents1
Decrease Little or no change Increase Don’t know
Product and/or service development 30 35 20 15
Risk 31 37 20 12
Strategy and corporate finance 37 28 25 10
Marketing and sales 39 33 17 12
Manufacturing 40 33 12 15
HR 41 30 17 11
Supply chain management 45 32 14 9
Service operations 54 23 12 10
Note: Figures may not sum to 100%, because of rounding.
1Respondents were asked about only the business functions in which they said their organizations have adopted Al.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
The state of AI in 2023: Generative AI’s breakout year 15
AI high performers are expected to conduct much higher levels of reskilling than other
companies are. Respondents at these organizations are over three times more likely than
others to say their organizations will reskill more than 30 percent of their workforces over the
next three years as a result of AI adoption.
Web <2023>
<State of AI 2023>
Exhibit <9> of <11>
Respondents at AI high performers expect their organizations to reskill
larger portions of the workforce than other respondents do.
Share of employees at respondent’s Respondents at All other
organization expected to be AI high performers2 respondents
reskilled over the next 3 years
as a result of AI adoption, 9 Don’t
know
% of respondents1
21
>30% 73
14
18
21–30% 9
38
11–20% 10
≤10% 8
1Asked only of respondents whose organizations have adopted Al in at least 1 function.
2Respondents who said that at least 20 percent of their organizations’ EBIT in 2022 was attributable to their use of AI. For respondents at AI high performers,
n = 50; for all other respondents, n = 863.
Source: McKinsey Global Survey on AI, 1,684 participants at all levels of the organization, April 11–21, 2023
McKinsey & Company
16 The state of AI in 2023: Generative AI’s breakout year
McKinsey commentary
Lareina Yee
Senior partner, McKinsey; chair, McKinsey Technology Council
We are in the early innings of generative AI, and companies already anticipate a meaningful
impact on talent—from opening up new work opportunities and transforming how work
gets done to introducing whole new job categories such as prompt engineering. One of the
benefits of generative AI is that it can help nearly everyone with their jobs, and this is also its
greatest challenge.
This scale differs from traditional AI, which affected a fairly small—though no less important—
portion of the workforce who had deep skills in technical areas like machine learning, data
science, or robotics. Given the highly specialized capabilities required, AI talent always
seemed in short supply. Our survey highlights that hiring for these roles is still a challenge.
Generative AI, in contrast, will still need highly skilled people to build large language models
and train generative models, but users can be nearly anyone, and they won’t need data
science degrees or machine learning expertise to be effective. The analogy is similar to the
move from mainframe computers—large machines operated by highly technical experts—to
the personal computer, which anyone could use. It’s a revolutionary shift in terms of how
people can use technology as a power tool.
This view of generative AI as a tool is reflected in our survey. In most instances companies
see generative AI as a tool to augment human activities, not necessarily replace them. So
far, we’re mainly seeing companies that are leaning forward with generative AI, focusing on
pragmatic areas where the routes to improvements in top-line growth or productivity are
clearest. Examples include using generative AI tools to help modernize legacy code or speed
up research and discovery time in the sciences. We’re still just scratching the surface of these
augmentation capabilities, and we can anticipate that their use will accelerate.
The state of AI in 2023: Generative AI’s breakout year 17
With all eyes on
gen AI, AI adoption
and impact
remain steady
While the use of gen AI tools is spreading rapidly, the survey data doesn’t show that these newer
tools are propelling organizations’ overall AI adoption. The share of organizations that have
adopted AI overall remains steady, at least for the moment, with 55 percent of respondents
reporting that their organizations have adopted AI. Less than a third of respondents continue
to say that their organizations have adopted AI in more than one business function, suggesting
that AI use remains limited in scope. Product and service development and service operations
continue to be the two business functions in which respondents most often report AI adoption,
as was true in the previous four surveys. And overall, just 23 percent of respondents say at least
5 percent of their organizations’ EBIT last year was attributable to their use of AI—essentially flat
with the previous survey—suggesting there is much more room to capture value.
18 The state of AI |
76 | accenture | Accenture-The-Six-Pillars-effective-AI-Strategy-Video-Transcript.pdf | THE SIX PILLARS OF AN
EFFECTIVE AI
STRATEGY
VIDEO TRANSCRIPT
Javier Polit: able to execute that strategy across the
enterprise? And that means different teams and
I think there's maybe six pillars of an AI strategy, different responsibilities and different ways of
right? And I always say start with the business working and different behaviors in the
value. Define the trap business value and enterprise. And then the greatest investment is
recognize the leverage that you need to unlock the sixth piece of this is focus on your talent and
that growth for the business. And when you think the culture that you're building and how you're
about algorithms, which are the critical going to continue to retain, attract and engage
algorithms that are going to solve the business those resources that are helping you bring this
value that was defined by the business, and value to life and this distinctive capability that
when you think about algorithms today, it's a you're building in your enterprise.
complicated world, right? We need to make
certain that they're designed to scale and that
they're unbiased because we hear a lot of
algorithms are being defined with bias now. And
we have tobe very cautious about that. And then
you have tothink about data, right? Because you
understand the business now, you're built, you're
defining the algorithms are going to support that
business value that you're trying to capture.
And you’ve got to look at the data and have a
clear first, second, and third partydata strategy,
right? And make certain that you have a life
cycle around that data that to create signals of
value for the enterprise. The fourth area that I
would say is a platform strategy, making certain
that you have the right ecosystem, and we talked
about that earlier, making certain that you have
the right foundation of capabilities to create and Copyright © 2023 Accenture
be able to manage inside the enterprise. And All rights reserved.
then the ability to execute that strategy, right?
Accenture and its logo
How should our enterprises be organized to be
are registered trademarks
of Accenture. |
77 | accenture | Acceture-How-Mondelez-International-Data-AI-Transform-Enterprise.pdf | HOW MONDELĒZ
INTERNATIONAL USES
DATA AND AI TO
TRANSFORM THEIR
ENTERPRISE
VIDEO TRANSCRIPT
Venky Rao (00:30): of the winners in the spectrum of organizations
I am Venky Rao, Accenture’s, North America have brought themselves into that space
Consumer Goods and Services Industry lead. because of the AI capabilities that they have
We are here in Chicago today at the beautiful invested in. And we have seen that
new headquarters of Mondelēz International, organizations which have significantly invested
surrounded by some of their more delicious in AI have been able to deliver much better
brands. I'm joined by Javier Polit, Mondelēz results for their shareholders. Right, so in that
International’s, Chief Information and Digital context, knowing that you have led multiple
Officer. I have known Javier you for a long, long scale digital transformation initiatives and you
time now. You have been a big change agent have been successful at that and knowing and
throughout your career, not just here at understanding Mondelēz International's own
Mondelēz, but also through your stint at the digital journey and your own journey to
other big CPG companies. becoming an AI Achiever, we wanted to have
this conversation today to learn a bit more about
Javier Polit (00:59): your journey, to learn a bit more about how
Absolutely. Well, first of all, welcome, welcome Mondelēz is getting on its path, to becoming an
to our headquarters here, and we're glad to have AI achiever. What was the impetus for Mondelēz
you. And as always, it's good to be with you to becoming more of a data driven data led
Venky and looking forward to the dialogue, and company?
sharing as much as possible.
Javier Polit (02:22):
Venky Rao (01:08): I think it all starts with our goal at Mondelēz
Thank you. So let me dive right in. We are doing International is to be the leader of snacking. And,
this conversation in the context of the AI we need an even stronger growth strategy to
Achiever study that Accenture has put out there, keep up with the pace, and even influence, our
which really talks about AI and the capabilities consumer demand and our consumer behavior.
that AI brings into an organization, how that Sowe really started to focus on a relentless
creates the differentiation for companies. And consumer centricity in making certain that we
what we have learned through that study is 12% started to aggregate 360 degreeinsights of, of
our consumers. And the time was right because and it really wasn't about just filling one hole. It
we had been preparing from a business was really trying to understand the holistic
perspective and also from a technology opportunities that we had. And once we had that
perspective. We had the right foundation in defined, it was building that vision and that
place. The company was on a cloud strategy strategy and making certain that you got support
when I joined here, multi-cloud strategy, we of the strategy by the C-suite, which we did. And
brought in the Google Cloud platform. So we the executive team and the board were all
had that behind us and the team was doing behind us, and we started communicate that
some great work before I joined, and we finished strategy to the enterprise. And that required a lot
that work and, it gave us really time to pivot and of work for us to do and say we need to start
really start focusing on data and AI. investing in our people elevating capabilities,
looking at the strategic partners that we were
gonnause, right? Besides the Accenture’s and,
Venky Rao (03:13): and the Microsoft’s and the Googles of the world
Excellent. So now Mondelēz is on its way, to and other strategic partners. How we're gonna
establishing itself as an AI achiever. How do you firmly have the conversation that we had with
continue to get there on this path? you and all the other partners, bring your best to
us as we're continuing to try to be the best that
Javier Polit (03:22): we can and leverage partners as we're trying to
Well, there's a lot of levers to that. SoI could tell build capability inside the enterprise and, and
you that myself and my entire team we're really driving change in the enterprise as well. From a
invested in establishing Mondelēz as an AI behavioral and work perspective.
achiever being in that top 12%. We often talk
about being industry leaders, right? And we want Venky Rao (05:15):
to create an organization and a culture. We're 10 You know, there is this old saying, you know,
years young, we just recently celebrated our 10 what you track and what you measure actually
year anniversary. We have some incredible getsdone. So when you get on a transformation
brands that have been around for almost 200 journey like this, especially in this space of AI, AI
years, but we're transforming our culture. And, enabled, which is all new, how do you start
and it's, it's a young company. Sowe really have measuring success?
the ability tobecome a data driven in AI focused,
enterprise. And with that comes some Javier Polit (05:29):
challenges because, you know, we, you have to Yeah. Well, you know, you can't manage what
change the ways the company worked in the you don't measure. We've all heard that, that
past. You gottachange your behaviors. And nomenclature, I can tell you that we've had some
we're driving all those things, across the really, really goodmaturity here over the last 18
enterprise. And it's a journey. It's a continuous to 24 months in regards tohow we track, how we
journey. measure the ROI’son work that we're delivering
to the, to the business and the value based on
Venky Rao (04:08): the business case that we initially put together
I like the phrase, I mean, it is a journey, right? I for the business. And, and through that work,
mean, but then the question is how do you start what we're seeing now in all our business
a journey like that? Where do you start from? reviews that we have conversation around digital
comes up the work that's being driven around
Javier Polit (04:14): digital. And with that we talk about data science
The starting point is really spending time with the and we talk about the AI work that that's being
business, Venky, and really understanding, done, right? You know, you set a transformation
when I first joined, I was listening and learning. strategy and a vision and you say, okay, it's a
I'm still learning. I've only been with the company three year horizon. I always say that after the
two and a half years or so now, but really second year, you start figuring out what your
understanding what the pain points were. And, next three year horizon's gonnabe. So it's, it's
something that is just never done. Venky it’s just And then there is this aspiration that every part
continuous work. of your organization wants to have capabilities.
They all want to get those AI enabled
Venky Rao (06:17): capabilities and so on. Can you dig a little bit
Now, having said that, what are the most deeper and talk to us about how does the total
important factors in making a transformation enterprise reinvention happen practically in large
successful? organizations with all the complexities of, of a
large organization?
Javier Polit (06:23):
Well, I think when, when you think about a Javier Polit (08:08):
transformation in any large enterprise, and I've Yeah. It, it is a little sophisticated when you look
had the opportunity to do this a couple times, is at large enterprises and, and in my experience,
you need to have the right sponsorship. You having served Fortune 15 and Fortune 100
know, once you develop that strategy and that companies, it, it doesn't get easier wherever you
vision, making certain that the board, the sit. But, but I'm always a believer that there's a
executive team is behind it, and then you need trigger in every business that could be an
to communicate as much as possible and external trigger, like what we've lived through the
communicate that strategy and what you're last 24, 30 months, or it could be an internal
trying to do, and communicate the sponsorship trigger that, that drives a transformation for a
so that the whole enterprise feels good about the company or embarks in the beginning of a
work that you're trying to drive. And they transformation that'll then just forever be
understand that there's a sense of importance continual. And I think when, when you look at
and urgency to what you're doing. And, and those things[ that starts helping you define what
when I talk about communicating a lot of, I have the strategy is gonnabe and what the overall
about 30 touch points with my organization on company's mission and purpose is, as well as
an annual basis, and we talk about these things. you think about empowering people in the
And then the last thing is making certain that you organization to really drive some of these
have a core strategic central AI data science capabilities. Right?
team that's really helping the organization. You You know, some companies, as you know, are
can't have these silos in the enterprise where mandating digital fluency and there's a
they're going on and building their own data difference between digital fluency and digital
science and data strategies without literacy. We, we were talking about that recently.
understanding that there's a holistic data driven And, and here what we're trying to do is get
strategy that all that data needs to come beyond literacy and drive fluency, right? But,it
togetherand somebody needs to be the steward really happens with the organization. You gotta
of that. And monitoring is the data inside the bring the people along, understand the strategy,
enterprise is data outside the enterprise what and then have the right foundations to be able to
data needs to ingress or egress from different do that.
sources? And you just can't have that working in
a silo. SoI would say it's probably those three Venky Rao (09:08):
dimensions. It's very, very interesting that you say that
because our study, the AI Achiever study, it
Venky Rao (07:32): really looks and calls out that in the, among the
Getting through a massive enterprise leaders, we see the top leadership really
transformation. It's difficult, especially in large embedding AI as a strategic priority, right? I
enterprises. There are complexities, there is the mean, they're making it part of their corporate
corporate headquarters, there are the functions, strategy and they're embedding this as a key
there is the businesses. Then there are this part of their core transformation initiative. Can
whole notion of, hey, what's back office, what's you talk a little bit more around how that
front office? And so on and so forth. sponsorship actually happens and why that is so
important that it comes top down? how you're creating value with velocity. And
we've been able to stand up those models and
Javier Polit (09:39): we're still on the capability maturity curve, but it's
I think, the initial sponsorship, when I at least really moving along at a quick, quick pace force.
first joined Mondelēz a few years ago, you know, And it's working really well. We've seen some
I satand I listened to the business and I spoke to fantastic results. You guys may know a little bit
the business a lot about some of the things that about that cause we partnered with you on some
we were trying to do. And it wasn't that I was of the solutions. But,we're getting very, very
trying to just solve one particular problem. I was good results. And the organization's
trying to connect all the dots and see how I could understanding when you get business leaders
solve a holistic problem, and build a holistic talk, talking about data and the importance of
capability. And that sponsorship really starts data, you know, that you're making progress.
happening once you start creating awareness of
what's the possible and how you could really Venky Rao (11:56):
create that value for the business. And we did Oh, absolutely. So Javier, how do you see talent
that. We, talked a lot about that when I first and tech working together to achieve the
joined. And, you know, there was quick followers Mondelēz vision?
and there were some that weren't that quick.
And what I did with our team is we leaned Javier Polit (12:03):
forward with those quick followers and went, Yeah, there, there's a lot of dimensions to that.
worked in those parts of, of the world building And I will tell you that, you know, we win with our
capabilities, knowing that we create value with people. Our people are our greatest asset. And
the team and then others would follow. we invest in our people in many different ways
and our people are critical to anything we
Venky Rao (10:29): change or anything we make, you know, our
Soin my experience, some of the big challenges success is possible because it's 79,000
that I see is this whole notion of information incredible colleagues that we have around the
asymmetry, especially in large enterprises, world. And some of the things that we're doing
right? So where yes, the ambition is there, the right now is as we continue to drive the
intent is there, but it's not very often that you importance of being data driven enterprise and
have the whole organization on the same page. have an innovative culture, we're able to make
So how have you tackled, this challenge of those pivots and become a dynamic
bringing everybody on board with the right organization. We talk about being a dynamic
messaging and, you know, getting, making sure learning organization, right? Where we, we are
that everybody's on the same page? not a knowing culture, we're a learning culture
and we want to continue to innovate and take
Javier Polit (10:55): risk. And I think, you know, all that's done
Yeah. In, that challenge is continuous through sound leadership, but, but it's also
messaging. And the message is data matters having the right partners at the table, right? And,
and data's critical, and we're gonnawin with we firmly encourage our partners, whether it's
data. You know, that there was always this, this Accenture or whether it's Google or whether it's
nomenclature that we would talk about a race for Microsoft and many others, to bring the best that
talent. WellI say it's a race for data, it's a race you have. And we've had those conversations
for data that's contextual and that's relevant. too, bring the best to us and make certain that
That's enabled that the edges of the business we could really partner and do some really
with the right data governance models that the industry leading things, right? So, it's really not
business owns, the data and ingress is the data something that you could do on your own, but
into repository where they have the capability to you have tohave a pool of experts inside the
do that, combined with our data scientists and enterprise as well as the experts that your
then then build the AI capabilities. And that's partners bring as well.
Venky Rao (13:19): across the enterprise and, and you know, we
Absolutely. And there, I really want to emphasize look across the ecosystem and depend on our
that, you know, it has been a massively different partners to help us as well.
experience working with you and Mondelēz in
terms of your ability to see across the whole Venky Rao (15:27):
ecosystem, whether it's your partners like us or, Yeah. And then that's what I really appreciate
you know, the big cloud providers like Microsoft about the change that you're driving in Mondelēz
and Googles of the world. You collaborate in a is we do see that you guys measure the
way wherein the learnings flow seamlessly outcomes, consistently measure the outcomes,
between these organizations and then that's and you are evaluating how far you have gone
really a key for success on the business case that you started the
We have recently also seen in press that journey with. And you're also absolutely right
organizations are coming out and saying, ‘Hey, that sometimes you have totake these risks
we have made our investments in cloud, we are because you, for many organizations, these are
making our AI investments, we have made uncharted waters, uncharted territories, right? So
digital strategy as part of our core strategy and you have tomake those investments early on,
so on’. But they are still complaining that they're but you still have toensure that the ROI and
not able to see the ROI, they're not able to see then the business outcome mindset doesn't go
the growth, right? I mean, there is something away. Now if I…
missing here. How are you seeing Mondelēz get
the ROI that it planned for? Javier Polit (16:02):
And, and just to add something to that Venky, it's
Javier Polit (14:13): that business mindset, right? And also the
You know, you have tostart by taking a strategic contending business initiatives and
look at the work that you want to, to drive and understanding that if you start an initiative later
the value you want to create, right? And normally on, then was expected that ROI that you had
when you're doing those things, and you're, and identified suffers as well and it depends how you
leveraging AI, it's to replace the latent human look at things. You could look at it from a capital
ability to do some of these things right? And allocation perspective. Oh. Which you haven't
making certain that you have that ability in the spent the capital, but you haven't put the capital
enterprise. And once you're confident that you to work. Sodo you look at what's my internal
have a use case that's gonnadrive a business rate of return or versus my return on investment?
result, you start driving those and you start And sometimes companies take too long to
measuring that work, right? And seeing the make decisions, and we're breaking those
changes in behaviors and the changes in the barriers too here, we're making decisions a lot
ways that you work and the speed of the quicker now as an executive team to go ahead
outcomes that you're driving. And you measure and get these initiatives moving on time to make
those. And you know, as I mentioned earlier, sure that we capture those ROI’s, right? So
we've partnered in some on some work that we those are things, and we measure 'em. We,
were able to do those things and now we're measure on a quarterly basis. We know what our
using it as an example and it's proliferating strategic initiatives areand we come back and
across our regions and across our geography, measure how they're performing based on our
right? But there's a lot of expectations. You business plan.
know, it's about the investments and improving
the entire structure of the enterprise. It it's not Venky Rao (16:54):
just providing a band-aid, right? That you wanna Now how are you prioritizing long and short term
try to solve something very, very quickly. You investments?
gottathink about in certain, these cases I said
earlier, short term and long term strategic Javier Polit (16:58):
sustainable capabilities, right? We drive that Yeah. You know, short term it's about
understanding the broad needs of the business Yeah. Look, when, when we think about AI, we
and aligning with external partners that can help know that it's essential, it's essential to our
us deliver on that. And we think about long term growth, and it provides us competitive
Venky, it's about building the skill sets you need advantage. And, and we're really seeing, really
within your own talent to be able to do it understanding what data should look like and
internally. You know, today we have a lot of what the data strategy is. Because without good
partners helping us and, and how do we data and having accurate data, you can't build
continue to bring those capabilities and build ML that supports the AI. Right. So, we're making
those internally? Is our strategic longer term some good progress also in, in harmonizing
roadmap, right? But I think all these are data.
happening simultaneously in a very complex
environment as you're trying to deliver value to Venky Rao (19:22):
the enterprise and the true value proposition for SoJavier, how would you assess, CPG industry
this investment. It's gottabe sustainable, in terms of AI maturity compared to other
anything that you do has gottabe sustainable industries? I mean, especially, I know that you
and you gottaget to that destination of having look at the tech sector quite a bit, and, and you
the right skill sets and capabilities that have a take a lot of inspiration from how some of the big
sustainable business model. And the core technology companies operate. But how do you
doesn't have to be large either. You're always see that evolving in the CPG industry?
gonnahave a need to bring in partners to bring
in their expertise and their skill sets. I always say Javier Polit (19:42):
that, that our partners have broader apertures Yeah, you know, we're continuously doing
than we do because they're dealing with the top industry sensing in that space and see how we
50 companies and they can bring learnings to us match up to other CPG companies or fast
that help us even improve even more. So, it's moving consumer goods companies. But I think
never gonnabe, you have all the skill sets you it's fair to say that the tech sector is still far
need internally, just do it on your own. It's always ahead. But I would also say in the same breath
gottabe a strategic blend. that I think that the gap is narrowing and
especially I think what's, what's helped us
Venky Rao (18:06): narrow that gap that that gap is companies really
Ah, that's, that's really fair. And if I think about, advancing their digital roadmaps in the digital
you know, the whole talent spectrum, you are plans, right? SoI think, there's enormous room
not just training your employees, but you're also for growth in AI Adoption and AI Adoption across
giving those opportunities for them to participate all industries. Every company's a tech company.
in various events with the ecosystem partners We've heard that phrase. I always try to extend it
and partners like ourselves. I think that's a, that's and say, every company's a tech company and if
a big change for this industry is not just be you don't conduct yourself as such, you're just
inward looking when it comes to, you know, not gonnabe successful.
creating the talent asset, creating the AI core,
but be more participatory in a, in a larger Venky Rao (20:25):
ecosystem. And that is something that we have Absolutely. And that's such a spot onanswer
seen that, you know, under your leadership, you and, and a brilliant one at that. So Javier, where
guys are driving there at Mondelēz. Now how do you see the whole AI Adoption space
have you industrialized the tools, the tooling, evolving to? And if you have organizations who
and, you know, how have you created a strong want to become an AI achiever, what would be
AI core that people don't have to reinvent this your advice?
journey each time they come on an initiative?
Javier Polit (20:42):
When you think about the evolution of AI today,
Javier Polit (18:58): companies are using narrow AI, right? It's taking
the ability to have a human process be say is a platform strategy, making certain that
conducted through AI with greater efficiency. you have the right ecosystem, and we talked
And you have companies that are adopting that about that earlier, making certain that you have
well, that are the 12% AI achievers and those the right foundation of capabilities to create and
that are falling, following and, and a little bit be able to manage inside the enterprise. And
behind. And then the next level of AI is general then the ability to execute that strategy, right?
AI or human AI, where you have artificial How should our enterprises be organized to be
intelligence that can basically do what a human able to execute that strategy across the
thinks. And the more complicated AI that's enterprise? And that means different teams and
gonnabe happening in the future, and it's different responsibilities and different ways of
happening in different parts of the world today, is working and different behaviors in the enterprise.
super AI, where AI can now do things better and And then the greatest investment is, is the six
in a smarter way than humans can. So it's gonna piece of this is focus on your talent and the
be an evolving space. We'll have to see how culture that you're building and how you're
those technologies, when they come to be gonnacontinue to retain, attract and engage
commonplace are gonnabe leveraged in in those resources that are helping you bring this
different industries. And, and they're already value to life and this distinctive capability that
starting to be used in, in certain industries. you're building in your enterprise.
Venky Rao (21:34): Venky Rao (23:24):
Soin closing, any thoughts, Javier as we wrap Javier, that was an outstanding response and a
up. very, very good framework for everybody to
follow, right? Sothank you so much.
Javier Polit (21:37):
You know, there’s probably an abundance of Javier Polit (23:31):
thoughts and because I think we'd all agree that Venky that was a pleasure, thank you for the
it's a complicated space, but I think there's time. Thank you for the partnership.
maybe six pillars of an AI strategy, right? And I
always say start with the business value, right? END
Define the trap business value and recognize
the leverage that you need to unlock that growth
for the business. And when you think about
algorithms, which are the critical algorithms that
are gonnasolve the business value that was
defined by the business, and when you think
about algorithms today, it's a complicated world,
right? We need to make certain that they're
designed to scale and that they're unbiased
because we hear a lot of algorithms are being
defined with bias now. And we have tobe very
cautious about that. And then you have tothink
about data, right? Cuz you understand the
business now, you, you're built, you're defining
the algorithms are gonnasupport that business
value that you're trying to capture.
And you gottalook at the data and have a clear
first, second, and third partydata strategy, right?
Copyright © 2023 Accenture
And make certain that you have a life cycle
All rights reserved.
around that data that to create signals of value
Accenture and its logo
for the enterprise. The fourth area that I would
are registered trademarks
of Accenture. |
78 | accenture | Acccenture-Semi-GenAI-TL-Infographic.pdf | Breaking barriers,
building connections
Generative AI‘s role in the semiconductor industry
Discover how Gen AI is reshaping the value
chain from design to manufacturing and beyond
Supply chain
Market
Trends
Consumer
Manufacturing
Product Design Channel Partner
Semi Electronics
Product Development and Production Distribution & After Sales
According to our research, respondents
agreed with the following:
73 71 74
% % %
IP concerns are the biggest barrier It will take at least three years for New fabs coming online will focus
to generative AI deployment across the semiconductor industry to more on automation powered by
the semiconductor industry’s deploy generative AI at scale. generative AI.
value chain.
Industry leaders also agree on the opportunities,
challenges and urgency for successful Gen AI adoption:
Of semiconductor executives highlight
33
% design and manufacturing as the prime areas
for generative AI innovation.
85 Of companies have a strategy to deploy
%
generative AI projects or POCs.
Of executives agree that collaboration with
75
% industry partners will unlock greater value
from generative AI.
The following are 4 strategic priorities for companies and
executives to unlock Gen AI value:
Design your journey Leverage the ecosystem to
1 2
strategically scale generative AI
Lead and learn differently to
3 4
Continuously reinvent
reshape the workforce
Generative AI is not just a tool but
a transformative force for the
semiconductor industry.
Embrace the future with strategic
Read our report, learn more about how
investments and collaborative efforts
generative AI can revolutionize your
to unlock unprecedented value.
semiconductor business.
accenture.com/semi-value-chain-new-approach-gen-ai
Copyright © 2024 Accenture. All rights reserved. |
79 | accenture | Accenture-Generative-AI-Sourcing-and-Procurement.pdf | A new era of
generative AI
for everyone
Inspiring
smarter buying:
How generative AI will
reinvent sourcing and
procurement
Inspiring smarter buying: How generative AI will reinvent sourcing and procurement
For Chief Procurement Officers (CPOs), the
arrival of generative AI marks a major leap
forward in the value their teams can deliver
to the business—paving the way to faster,
more accurate decision-making, higher
resilience, increased sustainability and
lower operating costs.
Generative AIis outpacing any other technology innovation in its potential reach
and impact (Figure 1).
Executives around the world agree: according to Accenture’s 2023 Technology Vision,
95% of respondents said that advances in generative AI signify a new era of
enterprise intelligence.
The evolution in analytics, machine learning, and AI
Figure1:Accenture2023
This is why generative AI was identified as one of the four technology trends driving the
next phase of business transformation.
Companies that integrate this technology into a strong digital core can boost innovation
and accelerate progress to new performance frontiers. However, as humans working with
AI “virtual colleagues” become the norm, generative AI also raises many questions—not
least around responsible use of this technology and how best to adopt it at scale for
maximum value. Sowhat does this mean for procurement?
2
Inspiring smarter buying: How generative AI will reinvent sourcing and procurement
Generative AI: Procurement’s new co-pilot
Like most areas of the business, procurement stands to benefit hugely from generative AI.
That’s because one type, large language models (LLMs), don’t just analyze information and
answer questions, they can also provide insights and create content.
Once integrated into the rapidly evolving digital procurement landscape, generative AI
applications can transform a wide range of procurement capabilities (Figure 2). They’ll do
this by augmenting teams on routine tasks and, by acting as a co-pilot to category leaders,
providing strategic value-add through inspiration on-demand.
Instead of needing to undertake time-consuming research that risks falling rapidly out of
date, that could mean, for example, being able to get immediate answers to questions like
“what is my risk exposure buying raw materials in Indonesia?” or “which palm-oil suppliers
are net-zero and carry a less than 14-day lead-time?”
Figure2:Accenture2023
Delivering next-level sourcing and
procurement operations
To bring to life generative AI’s power, consider four use cases where procurement can
reap benefits in the near term:
1. Buying experiences – hyper-personalized and efficient
Procurement organizations have worked hard to improve the overall purchasing
experience, making it easier for business users to buy what they need to do their jobs –
and to do so responsibly. Generative AI takes all this to the next level—augmenting
category managers, facilitating decision-making and helping procurement to collect
business-wide insights.
• Generative AI can transform each purchase request into a conversation, using
internal and external data to guide business users to the right channels for their
specific needs (i.e., preferred suppliers, prices, terms and conditions)—all pre-vetted
for compliance and policy.
• By executing all tasks through conversational commands (rather than traditional
point-and-click interactions), generative AI can deliver huge efficiency gains across
complex buying requests that might previously have taken hours to complete.
• What’s more, by guiding users to preferred suppliers, the technology can
substantially enhance contract compliance by making responsible buying a
default behavior.
3
Inspiring smarter buying: How generative AI will reinvent sourcing and procurement
2. Supplier management – accelerated and simplified
Managing suppliers is often complex and time consuming. Generative AI can have a
significant impact across the entire supplier management lifecycle by accelerating
and simplifying processes.
• A generative AI chatbot could be used to centralize communications dealing with
supplier onboarding and provisioning access, as well as answering questions
around the engagement. This would reduce onboarding roadblocks and help
suppliers understand the company’s business needs so they can deliver
value faster.
• In supplier performance management, generative AI can identify supplier issues
and craft resolutions for subsequent supplier meetings.
• Generative AI can also help to identify areas of continuous improvement.
3. Category management and strategic sourcing – smarter
and enhanced
Generative AI can help procurement strengthen stakeholder and supplier relationships
and ultimately help procurement become a cross-functional leader for the business.
There are already plenty of AI tools that help define category plans and sourcing
strategies.
• The technology can “turbocharge” category insights dashboards by absorbing the
work category managers devote to market intelligence.
• Generative AI can collect, analyze, and contextualize data from multiple internal
procurement systems and platforms, as well as external insights.
• It can also provide real-or near-real-time market intelligence and innovation trends
for a category’s key scopes and identify opportunities for the category manager to
optimize value. Generative AI achieves this by helping teams tailor their analysis for
key stakeholders. For example, answering a request to generate a report of expiring
contracts for a specific business unit.
4. Risk management – transformed
Generative AI can proactively monitor for risks in real time and propose
mitigation plans.
• Say procurement wanted to purchase a commodity from a preferred supplier in a
specific region. Generative AI might identify rising tensions in that region and
recommend that upcoming supplies be secured in a different location where the
company is already working with suitable alternative vendors.
• LLMs also could be used to evaluate contract language across multiple suppliers
and identify key risks, as well as opportunities for efficiencies, renegotiation and
rationalization.
Getting started with generative AI
Generative AI is a revolutionary development. And because the technology is already here,
procurement leaders should start thinking now about how to use it as effectively as
possible. As they do so, they need to pay close attention to six essentials:
4
Inspiring smarter buying: How generative AI will reinvent sourcing and procurement
• Ensure a business-driven mindset toward adoption: identify, build and scale key
use-cases.
• Take a people-first approach: build talent pipelines of procurement specialists and data
scientists with the skills to take foundation models, adapt them and integrate them into
applications.
• Focus on data integrity: partner with leadership to review the data landscape and
privacy protections, determine how they align to enterprise priorities and make sure
procurement teams have access to the right data.
• Invest in a sustainable technologyfoundation that can support the high demands of
generative AI: make sure the right architecture and governance are in place and closely
monitor cost and energy consumption.
• Drive ecosystem innovation: partner with a strategic managed service provider that can
enable wider access to specialized talent, industry expertise and leading automation
platforms and identify eProcurement partners and other specialized solutions.
• Make sure there’s a robust Responsible AI foundation in place: implement relevant
security and governance policies to underpin rapid adoption of generative AI in
procurement, including controls for assessing potential risks from new use-cases at the
design stage.
And finally, remember procurement leaders don’t just need to scale generative AI
technologies. To realize maximum benefit, they should also invest in developing the
analytics skills and capabilities of their people. It’s time to get started.
Contacts:
Jaime R. Lagunas Robert Gimeno
Managing Director –Strategy & Managing Director –Strategy &
Consulting, Supply Chain & Operations Consulting, Supply Chain & Operations
Data & Artificial IntelligenceLead Generative AI Lead
[email protected] [email protected]
Robert P. Fuhrmann KeyraMorales
Senior Managing Director –Strategy Managing Director –Accenture
& Consulting, Global Practice Lead Operations -Offering Innovation-
Sourcing and Procurement Supply Chain and Procurement
[email protected] [email protected]
Neeraj Bajaj Lloyd Dufour
Senior Manager –Strategy & Senior Manager -Strategy &
Consulting, Sourcing & Procurement Consulting, Global Offering &
Generative AI Lead Innovation Lead Sourcing
[email protected] and Procurement
[email protected]
Andreu Bartoli Garcia
Senior Manager –Strategy &
Consulting, Supply Chain
& Operations
[email protected]
Read more:
Technology Vision 2023 | Tech Vision | Accenture
Generative AI Technology in Business | Accenture
Generative AI in Supply Chain I Accenture
6 |
80 | accenture | Accenture-Age-AI-Banking-New-Reality.pdf | The age of AI:
Banking’s new reality
2
Embracing generative AI
for a competitive edge
Generative AI has taken the world by storm. to be impacted by generative AI—39% by
The rates of adoption and enhancement automation and 34% by augmentation. Only
are more rapid than any major technology 27% of employees’ time currently has a low
innovation in the history of human potential to be transformed.1 Similar metrics
development, and few doubt its potential have been observed in banks worldwide.2
to have a transformative effect on business
and society. It’s no surprise, therefore, that within a year
of the launch of ChatGPT, almost every
Banks are at the sharp end. Our analysis bank had started to explore and evaluate
indicates that—due to the importance of early use cases. The leaders in this field
language throughout the value chain—the have gone further: they are already seeking
industry has a greater potential to benefit to maximize the value they have generated
from the technology than any other. In fact, by scaling their implementation across the
we concluded that 73% of the time spent organization.
by US bank employees has a high potential
3
Our latest financial projections indicate that the gains over
the next three years will be substantial for the early adopters:
From this it becomes apparent that while generative AI is likely to dramatically improve the efficiency of the banking operating model,
its potential to differentiate and drive growth by enhancing the customer experience is what excites bankers the most.
22% to 30% 600 bps 300 bps
productivity improvement rise in revenue growth increase in return on equity
Source: Accenture
Research analysis
4
The business of banking has barely services. By the time banks have executed
changed in hundreds of years. At its heart, their generative AI strategy, they will have
it’s about taking and safeguarding deposits reinvented and modernized most parts of By the time banks
and lending money. Generative AI—like the bank.
have executed
the internet and the smartphone that
transformed customer engagement—will Achieving these goals will be neither easy their generative AI
not change the fundamentals of banking. nor automatic. Consumers in their millions
strategy, they will
But no one doubts that its impact on may already be using ChatGPT, Microsoft’s
the industry will be seismic. Thanks to Copilot, Google’s Bard and other models
have reinvented and
its inherent ability to learn, advance and to good effect, but for organizations like
modernized most
create it will, over the next few decades, be banks to maximize the benefits a number
a driving force for continuous reinvention of obstacles need to be overcome. Given
parts of the bank.
across the enterprise. It will be widely the pace at which many are seeking to
deployed throughout the value chain, scale generative AI, it is important that
and will radically transform virtually every they plan their journey strategically and
facet of how banking gets done and how holistically.
customers experience their bank and its
5
Generative AI has a
role to play in every
part of banking
Our analysis of the potential impact of generative
AI on the banking industry3 concluded that every
role in every bank is likely to benefit in some way
from generative AI. Through this study and our
ongoing work with leading banks worldwide, we
have identified hundreds of promising use cases
that span the banking value chain.
From the back and middle offices through to
the tellers, advisors, relationship managers
and contact center agents in the front office,
the ability of generative AI to automate routine
manual tasks and augment workers’ capabilities
will make a profound difference (see Figure 1
on page 7).
6
Generative AI will transform banking roles in different ways and to different degrees,
depending on the specific nature of their tasks and the time that each takes.
Automation Augmentation All-round support
In our analysis of US banks, we discovered Employees whose work involves a high We determined that 25% of all employees
that occupations representing 41% of measure of judgment, such as credit will be similarly impacted by both
banking employees are engaged in tasks analysts, or who need to understand automation and augmentation. Customer
with higher potential for automation. Roles customers’ needs and circumstances service agents, who spend their time
such as tellers, whose jobs primarily involve and personalize their interactions, such explaining products and services to
collecting and processing data, would as relationship managers, could be customers, responding to inquiries,
benefit greatly from automation—60% of empowered by generative AI tools that preparing documentation and maintaining
their routine tasks could be supported by help them prepare for and run meetings sales and other records, are a good
generative AI. —34% of banking employees fall into this example. Of these tasks, 37% could be
category. automated while 28% could be augmented.
7
Figure 1: How the top 20 banking industry roles are like to benefit from generative AI.
Loan Interviewers and Clerks
noitatnemgua
rof
laitnetop
rehgiH
Industry
60% average = 39% Front office Middle & back offices
Personal Financial
Credit Analysts
Advisors
50% Securities, Commodities,
and Financial Services Sales Agents
Software Developers
Market Research Analysts
40% Financial Managers
and Marketing Specialists
Loan Officers Financial Examiners Industry
average = 34%
Tellers
30%
Customer Service Representatives
Financial and
Bookkeeping, Accounting,
Investment Analysts
First-Line Supervisors of and Auditing Clerks
20%
Non-Retail Sales Workers
New Accounts Clerks
Office Clerks and General
Accountants and Auditors
First-Line Supervisors of Office
10%
and Administrative Support Workers Bill and Account Collectors
Management Analysts
0%
15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75%
Higher potential for automation Bubble size: Relative
number of employees in US
Source: Accenture Research analysis and estimates on (Process work)
BLS and O*Net data as of December 2022.
8
In the back and middle offices, generative AI will be The same will happen in the front office, but here Productivity is the most obvious benefit of
used to transform the operating model. Many tasks employees will have access to intelligent tools that widescale adoption of generative AI. However, the
will be automated. This will improve speed and allow them to personalize customer experiences ability to better understand and meet customers’
accuracy, reduce costs and relieve employees of and sell more effectively. With both the time and needs, thereby increasing satisfaction, retention
the more tedious aspects of their jobs. By allowing the means to engage more meaningfully with and share of wallet, is likely to make a much bigger
them to take on more or other tasks that add value, customers, they will be able to restore the human contribution to banks’ bottom line.
they could have a bigger impact on the bank’s touch that was lost over the past two decades as
overall performance. banks digitalized their experiences.
59%
of banking employees
are already using AI
every day.
4
9
How generative AI
can be put to work
While the potential applications for generative AI
in banking are almost limitless, our experience
and analysis show there are mainly three ways
the technology is currently being employed: by
using tools in which generative AI is embedded
(e.g. email), by using the technology to transform
the operating model (e.g. call centers, code
development), and by using it to innovate and
differentiate the bank’s experiences and offerings.
10
Embed Transform Innovate and differentiate
Many software vendors whose platforms are used One of the most immediate ways banks could The greatest, most enduring impact of generative
by banks to run their business are incorporating put generative AI to work is to integrate it with AI will likely be in equipping banks to innovate and
generative AI into every aspect of what they do. middle- and back-office operations to drive differentiate their products, marketing and customer
For example, Microsoft began integrating large efficiency and effectiveness gains. Just one interactions. On the product side, banks are using
language models (LLMs) into its Microsoft 365 example is the transcription and summarization generative AI to produce thousands of scripts that
suite of apps back in March 2023 with the launch of customer call recordings. Generative AI could are tailored for individual customers. In marketing,
of Copilot.5 Adobe’s Firefly tool can generate also enable transformation that has been put off they are beginning to adopt the technology to
images from simple text prompts.6 Salesforce due to financial or talent constraints—such as achieve levels of personalization which, until now,
offers a CRM assistant called Einstein that gets core system modernization. It is still early days, have been economically impossible. They are
its intelligence from generative AI,7 and Workday but we are seeing some banks use generative AI combining internal and external customer data
recently started integrating the technology into its to dissect and reverse-engineer their legacy code, with behavioral economics to generate curated
tools.8 All of these are intended to both automate and rewrite it in a modern language. Westpac, for experiences similar to that of the latest vehicle
and augment banking tasks and roles. example, is pairing its engineers with a generative sat-nav systems. Customer intent has become
AI companion to help fast-track software more apparent, allowing banks to become more
development projects, resulting in a 20%+ empathetic, proactive and relevant. The ability to
increase in code written by its programmers.9 tailor customer interactions, recommendations and
pricing may very well be the most important benefit
banks gain by using generative AI.
Banks are understandably cautious about the reputational and other risks associated with this leap in innovation. However, given the opportunity
to reinvent their customer experiences and drive growth, most are working hard to ensure they take advantage in a responsible way.
11
How to lead
in the era of
generative AI
Accenture research10 shows that banks have
Many banks are asking how they can unlock identified a number of factors that are key to
the incredible potential of generative AI. the success of their adoption of generative AI.
The key is to develop a holistic strategy Their priorities are:
that identifies the most promising use
36% 46%
cases, but then commits to moving beyond
isolated proofs of concept to scaled,
responsible deployment in a way that is
aligned with the bank’s business goals and cloud infrastructure data strategy
reassures regulators.
34% 25%
talent acquisition overcoming worker
resistance to change
12
01
Our conversations with industry front-runners
Lead with value
reveal common themes.
02
Understand and develop a secure AI-enabled digital core
We see five key imperatives which C-suite
executives should address to reinvent in the
03
age of generative AI. We have also identified Reinvent talent and ways of working
the key steps for each that will help your bank
04
become a leader.
Close the gap on responsible AI
05
Drive continuous reinvention
Measuring the ROI
of generative AI
13
I M P E R AT I V E O N E
Lead with value
Since there are more potential use cases for
generative AI than any bank could possibly explore
1
at any one time (see Figure 2 next page), the big
question is not what to do but rather what not to
do—and therefore, how to prioritize adoption.
Measuring the ROI
of generative AI
14
Figure 2: Leaders are moving forward on use case development from front to back office.
Unsecured Secured Wealth
Deposits Commercial Banking
Lending Lending Management
Front-Back Book Offer Intent Transaction Banking Trade Finance Treasury Investment Mgmt.
Management
Optimization Optimization Identification
Commercial Commercial
Intelligent RM Advisor Mgmt.
Real Estate Credit Origination
Commercial Advisory Services
Products
Products
Product Development
Lead Generation & Optimization Account Servicing
& Pricing
Portfolio
Underwriting / Credit Assessment
Optimization
Application Processing & Fulfilment Trading
Lead Nurturing & New Offer Brand Brand Marketing Segmentation & Client & Sales Digital Content
Sales / Marketing Lead Origination
Qualification Management Management & Campaigns Targeting Insights Creation & Mgmt.
Client Engagement Customer Experience Loyalty Program Correspondence Branch & Advisor Call Center Client Tools & Portals Client Onboarding Channel Mgmt.
& Value Mgmt.
IT Planning & Application Doc. & Knowledge Data Sourcing Data Structuring BI Reporting &
Technology & Data IT Engineering Enterprise Testing Data Governance
Coordination Management Management Strategy & Processing Self-Serve
Deposit, Cash & Collections & Account & Investment Fund Services & Custody & Asset
Operations Cards Mgmt. Fraud Management
Payments Mgmt. Default Mgmt. Portfolio Mgmt. Management Administration Safekeeping
Risk, Compliance & Financial Crime &
Audit Compliance Risk Management KYC Finance Procurement HR Legal
Enterprise AML
Collaboration & Knowledge Mgmt. & Marketing Enterprise Resource Supply Chain Business Process
Enterprise Applications CMS CRM Project Management
Commun. Software Doc. Mgmt. System Automaton Planning Management Management
Estimated impact of generative Al Low impact Medium impact High impact
Source: Accenture analysis
Measuring the ROI
of generative AI
15
The key is to balance the need for rapid Banks can achieve the necessary balance by
diffusion throughout the organization with doing three things simultaneously:
the accompanying cost and with the relevant
• Lead with top-down support and funding for
regulatory requirements. Some use cases are
the prioritized initiatives;
simple and relatively inexpensive while others,
like building a digital twin of the bank’s mortgage
• Establish an operating and steerco model that
function, are complex and require a lot of
ensures adoption and is compliant with all
expertise, data and computation. With regard to
relevant regulations;
computation, the rapid decline in the cost of using
most generative AI models makes prioritization • Drive multi-speed implementation and
especially challenging. Many banks are starting adoption across business segments, functions
their generative AI journey with simple, no-regrets and enterprise applications.
applications while planning the timing of their
more complex initiatives by calculating where the
By broadening the scope beyond single
shifting cost and return curves are likely
applications, banks can integrate generative AI
to intersect.
more holistically into their value chains, leading
to transformative improvements across business
functions. However, this broader integration
requires strong C-level sponsorship and a broad
business strategy, all underpinned by a robust
governance mechanism.
Measuring the ROI
of generative AI
16
• Developing and enforcing standardized which projects to scale, and how to optimize their
Establishing a strong strategy and oversight approaches, assets, best practices and transformation journey. It will also help gain the
team is critical. This team should include leaders principles for the deployment of solutions. support of everyone in the bank for the holistic
from the business, risk and technology sides of adoption of generative AI.
• Establishing the frameworks and approaches for
the bank, and its mandate should encompass
model risk management, to ensure compliance Some banks may consider having separate
strategy, policy, talent, technology, regulatory
with not only the law but also corporate infrastructures for generative AI and traditional
compliance and data.
governance standards and requirements. AI / data functionalities. However, this could
One of its first priorities should be the cause strategic conflicts and make it more
• Supporting vendor assessments.
establishment of a generative AI center of difficult to capture efficiencies. A single
excellence (CoE). This dedicated group will focus structure will drive the initiative from a unified
• Assessing the talent impact and supporting
on generating business value by implementing the platform and facilitate synergy.
change management and upskilling efforts to
bank’s generative AI strategy and cross-pollinating
minimize disruption and encourage adoption.
Not all implementations are economically viable
the technology throughout the bank. It will
at this time. However, the overall trend in
prioritize use cases, clear the way for generative
A vital and ongoing role of the CoE would be
generative AI implementation and consumption
AI to be scaled up in a federated model, and
to accurately measure the ROI of the bank’s
is towards lower costs and greater feasibility.
catalyze innovation. The responsibilities of the
generative AI applications. This should not be
The challenge for banks is to position themselves
CoE could include:
limited to immediate cost and revenue gains
to capitalize on new use cases as they quickly
but should also consider long-term strategic
• Collaborating with the business units to become economically feasible. This will require a
benefits (see Measuring the ROI of generative AI).
develop proofs of concept and roll out the strategic approach to prioritization, focusing on
A clear and empirical view of these benefits will
successful ones throughout the organization. current objectives while keeping an eye on the
help banks decide where to allocate resources,
longer-term investment horizon.
Measuring the ROI
of generative AI
17
C A S E S T U D Y
European bank expands its CoE to scale AI benefits
A leading European bank started to build an AI they have skin in the game. A value assurance
CoE six years ago to ensure strategic alignment group, composed of planning, HR, legal and other
and facilitate allocation of resources for AI departments, assesses proposed use cases for
projects and programs. The CoE, with sponsorship their potential value.
from the CEO, CDO and CFO, is set to expand
from a small structure into a 300-strong team This approach has created a fertile environment
over the next three years. It has responsibility for for cross-unit collaboration. The C-suite has
scaling AI and generative AI use cases and setting enough confidence in the goals of the AI projects
technical standards. currently underway to have committed publicly
to increase the bank’s 2025 operating income by
Operating in a hub-and-spoke model, the CoE hundreds of millions of euros.
ensures economies of scale as well as the
consistency and quality of AI and generative
AI applications. Business units are responsible
for proposing use cases, securing funding and
quantifying the value derived from AI. They
retain ownership and accountability to ensure
Measuring the ROI
of generative AI
18
L e a d i n g w i t h v a l u e
ACTIONS
• Develop a comprehensive generative AI • Implement rigorous ROI measurement
integration strategy across all business protocols that include both quantitative
functions, moving from isolated use cases to a financial metrics and qualitative assessments of
more holistic and connected approach. strategic impacts such as customer satisfaction
and competitive differentiation.
• Establish a strong C-level governance
framework to ensure that generative AI • Monitor the market as the capabilities of
initiatives are aligned with the organization’s generative AI models evolve and the cost of
strategic goals and effectively integrated using them drops, changing the business case.
across departments.
• Foster cross-departmental collaboration to
break down silos, facilitating a unified approach
to generative AI implementation that leverages
diverse expertise and insights.
Measuring the ROI
of generative AI
19
I M P E R AT I V E T W O
Understand and develop a
secure AI-enabled digital core
2
Firms that showed early success in developing
Many banks’
a strong digital core and data foundation have
been leading in generative AI. A modern digital digital architecture,
core leverages the powers of cloud, data and AI
infrastructure and data
through an interoperable set of systems across the
bank—including enterprise platforms, automation, capabilities are likely to
integration and security—that allow for rapid
impede their successful
development of new capabilities. This core, with its
adoption of generative
architectures, infrastructure, capabilities and talent,
is essential to making the most of generative AI—
AI at scale.
whose capabilities are most often cloud-based.
Measuring the ROI
of generative AI
20
However, our analysis of the current banking This spread highlights the fact that many LLMs is their ability to consume and work with
landscape reveals significant variation in the banks’ digital architecture, infrastructure and data huge volumes of data in different formats (images,
caliber of banks’ digital cores. This observation capabilities are likely to impede their successful text files, video and audio recordings, etc.) and
emerges from our global study of 240 banks. It adoption of generative AI at scale. This is confirmed covering multiple topics (from prospectuses
ranges broadly from 0.2 to 0.8 on a scale of 0 to 1, by our survey finding that 47% of executives across and policy documents to relationship managers’
with 82% of banks having a score between 0.2 all industries list ‘getting their data strategy right’ meeting notes). The problem is that much
and 0.6. as one of their greatest challenges as they strive to of it today is not only unstructured but also
implement and use generative AI.11 unorganized, unlabelled and dispersed
throughout the enterprise.
82% of banks have a score Additionally, our research indicates that
between 0.2 and 0.6
approximately 35% of banks globally have For LLMs to work, all of this unstructured data
54%
migrated less than 5% of their workloads to the needs vectorized databases. These currently exist
cloud. This is a substantial constraint, because the alongside traditional data lakes and enable the
evolution of generative AI is increasingly geared parsing and extraction of key information so that
28%
towards cloud-native technologies. Banks with LLMs can leverage it at speed. A key consideration
limited cloud integration are likely to miss out on is whether these databases will converge, and
12% cloud-native AI functionalities. if so, how quickly and at what cost? Database
6%
convergence will have a significant impact
0%
The goal of scaling generative AI will impose new on banks’ ability to utilize the full potential of
0-0.2 0.2-0.4 0.4-0.6 0.6-0.8 0.8-1
requirements on the digital core, so it’s important generative AI to produce precise and personalized
Low High
for banks to understand the status of their core outputs.
Figure 3: Variation in the caliber of banks’ tech
today. For example, one of the advantages of
development (0-1 scale)
Measuring the ROI
of generative AI
21
Forward-thinking banks have an advantage The AI landscape is in a state of constant flux,
because they started migrating from data lakes marked by the continual emergence of new
to decentralized data meshes before generative models, enhanced capabilities and an expanding
AI was on the horizon. In such a structure, array of tools and providers. This dynamic
domains within a bank take ownership of their environment could make previously unviable use
data, including responsibility for data quality and cases feasible. This will require centralized but
accessibility. These domains manage and provide connected models management. This strategy
their data as products, making it easier for other will standardize critical capabilities, such as the
parts of the business to use it. selection and customization of foundational
models, allowing for their efficient and transparent
Regardless of the underlying LLM strategy integration across various business functions.
employed—be it licensing pre-built models,
adapting existing ones through retrieval-
augmented generation (RAG), fine-tuning or
developing models from the ground up—it
This dynamic environment
is crucial that the bank has a data strategy
and approach that allows it to be flexible and could make previously
future-ready. This approach will be crucial in
unviable use cases feasible.
gaining the best possible outputs.
Measuring the ROI
of generative AI
22
C A S E S T U D Y
Scaling an enterprise-wide LLM and generative AI capability
A leading global financial services firm is capabilities. The bank has implemented a secure
developing an enterprise-wide AI strategy, and compliant platform that can host ChatGPT and
supported by a strengthened IT infrastructure OpenAI services.
and a transformative approach to talent. The bank
built a team of thousands of AI and data experts. This platform will enable the bank to scale
This AI strategy has, to date, brought in tangible generative AI and future-ready, cloud-neutral
benefits totalling around 3% of its expected net functionality across its business. By modernizing
income. its digital core, the bank not only kept up with
existing tech trends, it also positioned itself to
In its move towards a modern digital core, the integrate advanced AI with its core banking
bank focused on building a scalable multi-cloud operations at scale and keep one step ahead of
environment that complies with banking regulations. new technologies as they emerge.
This infrastructure has enabled it to fast-track its
adoption of next-gen, cloud-neutral generative AI
Measuring the ROI
of generative AI
23
U n d e r s t a n d a n d d e v e l o p a s e c u r e A I - e n a b l e d d i g i t a l c o r e
ACTIONS
• Assess the complete inventory of unstructured • Start moving towards data-as-a-service models, • Test various architectures to find the best
data across the organization and analyze how it where employees and developers can access fit for each use case and plan the model’s
could help power generative AI. data from internal marketplaces to use in their lifecycle from experimentation to scaling and
own applications and tools. phase-out. This could be achieved through a
• Start to move this data into vector databases
‘model switchboard’ where banks can select a
and scale them with the precision required for • Elevate data governance standards to
combination of models based on the business
real-time analytics and the unique demands of effectively manage unstructured data in
context or on factors such as cost or accuracy.
generative AI. generative AI.
• Evolve security protocols to address the
complexities that come with diverse data
access.
Measuring the ROI
of generative AI
24
I M P E R AT I V E T H R E E
Reinvent talent and ways of working
Generative AI will be pervasive, affecting virtually As work and roles are transformed, waste is taken
every process, task and role in the bank. To out and banks have the choice of boosting the
3
maximize its transformative impact, banks will bottom line or investing to increase value. Those
need a culture that not only anticipates but that opt for investment are using the savings
champions change. for talent to transition to newly created roles
such as managing generative AI, or in strategic
Key to achieving this impact is the strategic areas like business development or relationship
integration of generative AI into the bank’s management. These new and transitioned roles
processes. This goes beyond the adoption of new are aligned with the desired strategic customer
technology; it’s about reimagining workflows to and business outcomes. In the mortgage sector,
increase efficiency and innovation and aligning for example, we envisage a workforce that will
them with the goals of the business. include several new roles and has the increased
capacity needed to unlock significant productivity
gains (see Figure 4 next page).
Measuring the ROI
of generative AI
25
Figure 4: An illustrative example of how work and roles in the mortgage business can be realigned with generative AI.
Today Tomorrow
Category Roles No. of People
Category Roles in the Role
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officers Fewer
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officers
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officer Fewer
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officer Assistants Assistants
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan and Credit Same
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan and Credit Managers
Managers
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Product More
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Loan Processors
Managers
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Underwriters (cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Sales Prompt More
Engineers
Today Tomorrow
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Loan Closers and Funders
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Ops Engineers More
Category Roles No. of People
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Category CustomReor lSeservice in the Role
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Loan Processors Fewer
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officers Fewer
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) (cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) CollectoLorsa n/ ODfefifcaeurslt
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Underwriters Fewer
Management (cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officer Fewer
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan Officer Assistants Assistants
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Loan Closers and Fewer
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan and Credit Same
(cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:448)(cid:349)(cid:400)(cid:381)(cid:396)(cid:455) Loan and Credit Managers Funders
Managers
What this chart shows: Loan o (cid:75)(cid:393)f (cid:286)fi (cid:396)(cid:258)c (cid:410)(cid:349)e (cid:381)(cid:374)r (cid:400) assistants Loan Processors (cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:75)(cid:448)(cid:349)(cid:393)(cid:400)(cid:381)(cid:286)(cid:396)(cid:396)(cid:455)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Loan ProducCt ustomerM Soerrevice Fewer
Managers
(second role in the left-hand table) will, following the
(cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Underwriters (cid:94)(cid:258)(cid:367)(cid:286)(cid:400)(cid:3)(cid:876)(cid:3)(cid:4)(cid:282)(cid:75)(cid:448)(cid:349)(cid:393)(cid:400)(cid:381)(cid:286)(cid:396)(cid:396)(cid:455)(cid:258)(cid:410)(cid:349)(cid:381)(cid:374)(cid:400) Sales PrompCt ollectorsM /o Dreefault Fewer
implementation of generative AI in the mortgages
Engineers Management
function, either retain their role(cid:75) w(cid:393)(cid:286)i(cid:396)t(cid:258)h(cid:410)(cid:349)(cid:381)i(cid:374)n(cid:400) a smaller groLuopan Closers and Funders (cid:75)(cid:393)(cid:286)(cid:396)(cid:258)(cid:410)(cid:349)(cid: |
81 | accenture | Accelerating-Irelands-Generative-AI-Reinvention.pdf | Contents
Executive summary 4
The generative AI opportunity 7
Ireland’s progress 17
The five imperatives to accelerate Ireland’s reinvention through generative AI 22
Imperative 1: Lead with value 25
Imperative 2: Understand and develop an AI-enabled, secure digital core 29
Imperative 3: Reinvent talent and ways of working 34
Imperative 4: Close the gap on responsible AI 38
Imperative 5: Drive continuous reinvention 42
The role of government 49
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 2
Preface
Generative AI (gen AI) is a game- At Accenture, we are seeing how gen AI can be a powerful of gen AI and drive sustainable growth. Achieving this
force for progress. We’ve been working with clients to navigate potential, will require action from the collective ecosystem
changer that’s reshaping work, life
this complex terrain—helping them harness the full potential of including government, business and academia to build an AI-
and industry. Its influence extends
AI to drive growth and innovation and reinvent processes and skilled workforce and foster responsible innovation.
customer experiences.
across every function and role, from
We believe this is a pivotal moment, with gen AI set to
the CEO to frontline workers. Given the remarkable pace at which gen AI is advancing, transform and redefine how businesses operate. Given the
leaders must move quickly to leverage the technology in rapid pace of change and the size of opportunity, it is essential
driving tangible business outcomes. Establishing a robust that we act, and act now.
digital core, preparing the workforce and fostering a culture
Whether you’re just starting out or already on your AI journey,
of continuous learning are all essential steps. These efforts
this report offers the formula to deploy gen AI successfully,
must be underscored by responsible principles to ensure
responsibly and with real impact.
data privacy, transparency, and fairness remain central in all
implementations.
For Ireland, gen AI offers a unique opportunity. Ireland’s Hilary O’Meara
successful track record of leading the digital wave, combined Country Managing Director,
Accenture in Ireland
with a young, skilled workforce and a globally-connected
business ecosystem, positions us well to harness the benefits
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 3
Executive
Fixing the triple fracture employees have access to gen AI tools, only 38% A formula for success
of employees at Irish organisations do. Moreover,
Ireland has been slow in building the foundations Nearly one in 10 (9%) organisations are using gen AI
summary workers at Irish organisations are nearly four times
for AI and the cracks are beginning to show. It must at scale, so we know it can be done.
more likely than their MNC counterparts to have
act now to capture the opportunity.
missed out on digital skills training in the past two What should public and private sector leaders do
A deployment gap is opening as organisations years. over the next 12 months to put their organisations—
struggle to move their use of gen AI beyond proofs and the Irish economy—at the forefront?
Gen AI promises to
of concept. Among those that have invested in the Make AI a multiplier
be transformative to Based on delivering more than 1,000 global gen
technology, 91% have yet to scale its use across
Closing these gaps requires a people-centric
AI projects, including with several of Ireland’s
their business. One in three organisations believe
Ireland’s economy. approach. Seventy percent of the nation’s
largest organisations, we see a formula for success
their cloud capabilities are insufficient to leverage
workforce could see at least a third of their working
emerging. In this report, we outline the five
gen AI, highlighting the need to accelerate the
hours enhanced by the current technology.
imperatives behind that formula and how it can
The technology could increase the long-term modernisation of their technological foundations.
Our economic modelling forecasts that when
accelerate Ireland’s AI-powered reinvention: lead
growth rate over the next 15 years (to 2038) by
employees are empowered to innovate and identify
Many workers still lack even basic digital skills and with value; understand and develop an AI-enabled,
more than 50% and generate productivity gains
new opportunities, financial gains are greatest.
access to the training needed to develop them, secure digital core; reinvent talent and ways of
of up to 30% in multiple sectors. However, three out of five executives would
signalling an inhibiting skills gap. Around 1.76 working; close the gap on responsible AI; and, drive
prioritise short-term cost-cutting investments in
million people —64% of today’s workforce—need continuous reinvention.
But there is no guarantee the full potential for
process automation over those that transform
reskilling. Executives report that less than half
productivity and growth will be realised. Today,
roles for the long term, missing the opportunity to The elements of the formula are mutually
(45%) of their workforce is confident in the digital
too few organisations use gen AI optimally and use cost savings to empower people with freed reinforcing, so shouldn’t be applied in isolation.
fundamentals required. A surge in digital skills
to amplify human abilities. But without a people- capacity. Strategic alignment between technology, talent,
training is needed, and urgently.
centric approach that empowers workers to governance and value roadmaps is essential. Our
There is a real optimism among Irish workers about
Finally, a trust gap is emerging between modelling estimates an organisation is four times
perform higher-value tasks—rather than simply
the impact of AI. Five times as many people think
employees and executives, impeding adoption. more likely to succeed in scaling the use of gen
automating existing processes—€96 billion
gen AI will accelerate, rather than decelerate, their
Only half (50%) of people expect business leaders AI if coordinated action is taken towards the five
in economic value could be left untapped by career progression. Many are moving ahead of
to be responsible and make the right decisions to imperatives simultaneously.
2038—an amount nearly equivalent to Ireland’s their organisations: half of the people using gen AI
ensure gen AI has a positive impact on Ireland, and
total public investment in 2024.1 at work are self-starters who are using tools they Over the past 18 months, gen AI has captured
even fewer (38%) trust the government to do so.
procured themselves. While this indicates that imaginations; now, with this formula, it can
Local Irish companies face greater deployment and more needs to be done to harness this enthusiasm, deliver results.
skills gaps compared to multinational corporations it also highlights the need for organisations to
(MNCs) operating in Ireland, putting them at a respond to employee interest by providing gen AI
competitive disadvantage. While half of MNC tools directly and ensuring they are used safely
and responsibly.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 4
Authors
This report was a
collaborative effort
between our Data
and AI team based in
Ireland, supported by
Denis Hannigan Noelle Doody Liam Connolly
our research team: Data & AI Lead—UK Data & AI Lead – Generative AI Lead –
and Ireland, Ireland Ireland
Accenture Accenture
Strategy & Consulting
Accenture
Audrey O’Mahony Austin Boyle Adrian O’Flaherty
Talent & Organisation Technology Lead – Senior Manager,
Lead – UK and Ireland, Ireland Data & AI –
Strategy & Consulting Accenture Ireland
Accenture Accenture
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 5
About the research
We took a multi-pronged approach to researching Ireland’s
gen AI-powered reinvention, building on insights from
research conducted in the UK. The report is based on:
Economic modelling to forecast the potential impact of gen AI on productivity and growth for the
economy, organisations and people. We mapped out the future growth trajectories under three different
AI deployment scenarios: aggressive, cautious and our proposed people-centric approach. This
modelling has been conducted for 23 countries globally.
Surveys conducted with 409 employees and 128 executives from public and private sector
organisations in Ireland. The surveys were also conducted in the UK with 3,752 employees and
1,085 executives. The samples covered 19 industries and included different demographic groups by
geography, company size and socioeconomic background. The employee survey looked at workers’
experiences with gen AI. The executive survey looked at leaders’ perceptions of the AI ecosystem, their
investments in gen AI and their AI strategy. The surveys were conducted in July and August 2024.
Interviews, client experience and case studies, drawing on insights with leaders from across the AI
ecosystem, including large technology providers, industry, government and civil society.
The authors and researchers of this report used gen AI in its design, analysis and prose in alignment with
Accenture’s responsible AI principles.
Further details on the research approach can be found at the end of the report.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 6
The generative AI
opportunity: For people,
organisations and the
economy
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 7
The gen AI state of play
Figure 1. Welcome to the age of generative AI
Analyse Simulate
Scenario Optimise
Segment Recommend
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 8
Strong foundations
Ireland has established itself as a technology hub for the digital age. It has
become one of the leading destinations for both tech multinationals and
startups. Eight of the global top 10 information technology companies have a
significant presence in Ireland,2 and the country ranks fourth in Europe in terms
of VC investment per capita.3 This has helped it become the second largest
exporter of ICT services in the world.4 The country has developed a deep
bench of technical skills. In Ireland, both the proportion of people with basic
digital skills and the percentage of ICT specialists exceed the EU average.5
Ireland’s skilled workforce and status as a tech hub have created strong
foundations for its AI ecosystem, which is described as advanced or world-
leading by most executives (63%) (see Figure 2).
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 9
Figure 2. Ireland’s AI ecosystem has strong foundations
State of Ireland’s Strengths of Ireland’s AI ecosystem Net Availability of AI skills in Ireland
AI ecosystem % respondents2 +/- # people reporting skills on LinkedIn3
% respondents1
13 World leading Talent pool 9 67 +58
Computing
10 67 +57
institutions
Research
12 68 +56
infrastructure
50 Advanced
Regulatory
17 51 +34
environment
32,988
Access to
20 54 +34 1.5x
funding 22,800
20 Somewhat developed
Cost of doing
28 50 +22
Underdeveloped business
6
Don’t know
11
Weakness Strength
2023 2024
(As of August) (As of October)
1. Respondents were asked: How would you describe Ireland’s AI ecosystem? AI ecosystem was defined as: the network of organizations, resources and stakeholders involved in the
development of AI technologies, including government entities, companies, research institutions and support structures such as funding infrastructure, regulatory frameworks and
talent pools that collectively contribute to the growth and development of AI. Accenture Ireland AI business leader survey, fielded July-August 2024.
2. Respondents were asked: Would you consider each of the following as either a strength or a weakness of Ireland’s AI ecosystem? Data for “neither strength nor weakness” is not
shown. Accenture Ireland AI business leader survey, fielded July-August 2024.
3. Accenture Ireland Tech Talent Tracker based on data from LinkedIn Professional Network.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 10
Impact from self
to society
Ireland’s strong foundations position it to
become a global leader in the gen AI era. Our
research brings into view the size of the prize:
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 11
Our research brings into
view the size of the prize:
For the economy For organisations
We model that gen AI could: A double-digit productivity uplift could be achieved across the private and public sectors, based on the
current state of the technology. The life sciences industry, with many of the world’s largest companies
• Add up to €148 billion to annual GDP in 2038—this amounts
operating in Ireland, could see productivity gains of nearly 20%.6 Other sectors that are poised to benefit
to a 22% increase to the baseline forecast for 2038.
the most from gen AI are financial services, high tech and software and platforms—all of which have a
• Shift average annual real GDP growth for 2023–2038 from a significant presence in Ireland (see Figure 3).
baseline forecast of 2.5% to 3.9%, representing a 55% boost
If the productivity benefits are translated into cost savings, the gains could be substantial. Across all
to Ireland’s long-term growth rate.
industries analysed, total annual savings could reach €22.2 billion if the full potential of today’s technology
to automate and augment work is realised.
Nowhere is this opportunity bigger than in the public sector. We estimate that 42% of working hours in the
We estimate that
Irish public sector (excluding healthcare) could be transformed by gen AI (either through automation or
augmentation). This translates into a potential productivity gain of 12-18% that, if realised, could result in
42
€2.9 billion in annual savings.
%
of working hours in the Irish public
sector (excluding healthcare) could be
transformed by gen AI (either through
automation or augmentation).
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 12
Figure 3. Potentialproductivitygainscouldbe30%+acrossthefinancialservicesandtechsectors
Productivity gains from gen AI exposure %
Modelled range*
Software & Platforms €1.6
Banking €0.8
Capital Markets €0.8
Insurance €0.3
High Tech €0.2
Communications & Media €1.4
Aerospace & Defence €0.1
Retail €2.6
Life Sciences €0.2
Travel €0.4
Utilities €0.5
Consumer Goods & Services €1.0
Public Service €2.9
Automotive €0.8
Industrial €2.5
Natural Resources €0.2
Health €1.8
Chemicals €0.2
Energy €0.1
5% 10% 15% 20% 25% 30% 35% Mid-point
cost savings (€bn)
Source: Accenture Research based on Central Statistics Office of Ireland and US O*net. Lower and upper bound based on potential hours saved by occupation valued at annual occupation headcount.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 13
But gen AI isn’t just a productivity play—it creates Over time, the effective use of gen AI will become
new avenues for growth. A significant proportion of an increasingly important source of competitive
the growth opportunity comes from the build out of advantage. We analysed earnings calls from 1,300
AI’s foundations. In the race for AI supremacy, leading global companies with revenues exceeding €900
technology companies are building infrastructure akin million to assess the extent to which they cited efforts
to the expansion of the electric grid in the early 20th to build competitive advantage using gen AI. Our
century. Data centres, of which there are already 82 analysis revealed that companies actively pursuing
in Ireland, form a key part of AI infrastructure.7 Just as this strategy delivered a 10.7 percentage point
electricity transformed industries and powered global total return to shareholder (TRS) premium in 2023
economies, gen AI is poised to drive the next wave of compared to those that did not, even after controlling
innovation. Analysts estimate over a trillion dollars will for company size, headquarters location and industry.9
be spent globally on AI infrastructure over the next
five years, as companies compete to ‘own the grid’ of
this new technological era.8
Just as electricity transformed
industries and powered global
economies, gen AI is poised to drive
the next wave of innovation.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 14
For people
By harnessing individual human potential, organisations will realise the most benefits. described how a gen AI tool streamlined onboarding for new carers, enabling them to reach
the top 20% of performers within six weeks. Workers recognise this potential—over five
No current technology has the potential to have a bigger impact on our working lives than AI.
times as many survey respondents expect gen AI to accelerate rather than slow their career
Seven in ten people in Ireland could have at least a third of their working hours enabled by the
progression.
technology, either through automation or augmentation.
As people spend more time doing work they enjoy and doing it well, gen AI could help in a
Automation will save people time, taking tedious tasks off human hands. Our modelling
more profound sense by improving the overall experience of work. In an experiment with our
suggests the average Irish worker could save 17% of their working hours spent on routine
own sales team, we found that gen AI didn’t just result in marked increases in productivity but
activities. A doctor, for example, could save five hours a week while a commercial sales rep
also grew peoples’ confidence (+34%) and their belief they were making a meaningful impact
could save twelve hours a week.
(+31%).12 Gen AI added to their job satisfaction rather than subtracted.
The time saved could be reinvested in the higher-value work people enjoy doing. Creativity
We see similar findings in our survey. Irish workers recognise gen AI will be important to their
is the most underutilised skill in Ireland: 27% of people we surveyed say they aren’t currently
productivity and problem-solving. But they also anticipate the technology will benefit their
applying their creativity at work. While many surveyed already in creative roles express
autonomy and sense of purpose (see Figure 4). Familiarity with the tools reduces anxiety,
concerns about the technology’s impact on their jobs, they are also among the first to
as employees recognise how the technology complements their existing skills and helps
leverage gen AI to support their work. They use it particularly for ideation, brainstorming and
them perform tasks more effectively. Daily ‘power users’ of the technology were more likely
accelerating the initial stages of the creative process.
to expect gen AI to be important to both their creativity and fulfilment from work, relative to
The benefit of augmentation will be accrued not just in time but in quality. AI-driven methods irregular users.
have accelerated the discovery of more than 50 drug candidates and could potentially result
in a 90% reduction in resource use.10
Gen AI could also help address talent gaps. In 2023, over half of organisations in Ireland (55%)
reported difficulties in hiring staff with the right skills.11 Gen AI can alleviate these shortages by
enhancing employees’ ability to absorb institutional knowledge more quickly. One interviewee
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 15
Figure 4. PeopleanticipatebroadbenefitsfromgenAI—theirexpectationsincreaseastheyusethetoolsmore
Workers’ level of gen AI use (of those with access to the tools), % respondents1
19 61 19
Irregular users Light users Power users
Share of workers that anticipate gen AI will be important to their work experience,
% respondents by level of gen AI use1
82
79
79 77
74
72 71 71
68
68
65
55
49 51
47
46 46 46
40 40
36
33
30
30
Productivity Problem-solving Learning Creativity Autonomy Well-being Fulfillment Purpose
1. Irregular users are respondents who never or rarely use the gen AI tools available to them. Light users use the tools often (at least once a week) or sometimes (once a month). Power users use the tools every day.
Source: Accenture Ireland AI employee survey, fielded July-August 2024.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 16
Ireland’s
progress
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 17
Mind the gap
Our survey of business leaders examined which Figure 5. B ased on the decisions being made today, Ireland is running closest to our
of the three economic growth scenarios we low-end economic scenario, potentially leaving €96bn in value on the table
modelled aligns most closely with Ireland’s
current trajectory.
Ireland economic growth simulation, 2023-38
GDP in € billions (constant prices)
In our most optimistic, ‘people-centric’ scenario,
Scenario GDP gain GDP CAGR GDP gain
organisations harness gen AI to automate routine
vs. baseline premium as a share
tasks, redirecting the time saved into higher-value 900 by 2038 vs. 2.51% of baseline
baseline
activities. With AI used to amplify human abilities,
People-centric €148bn +1.4pp +22.0%
employees are empowered to innovate and
800
identify new growth opportunities. In contrast,
€96bn
Cautious €112bn +1.1pp +16.6%
in our ‘aggressive’ scenario, companies prioritise
cost-cutting, with workers finding themselves in
700
Aggressive €52bn +0.5pp +7.8%
less dynamic roles (or unemployed) after being
displaced, which stifles growth and exacerbates
Baseline
inequality (see ‘Further details on the research’ for 600
more on these scenarios).
On current trends, Ireland is leaning toward the 500
lower end of the growth spectrum—closest to
our ‘aggressive’ scenario—potentially leaving €96
400
billion in economic value untapped (see Figure 5).
2023 2026 2029 2032 2035 2038
Source: Accenture Research, simulated GDP growth under three scenarios. Oxford Economics GDP forecast used as the baseline.
Exchange rate is based on the period average (USD per Euro), Oxford Economics
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 18
Triple fracture
What is contributing to the lost potential? These trends are mirrored among workers. While 43% of
employees in Ireland have access to gen AI tools to support
On average
We identified three points of tension where gen AI
their work, only 24% use them at least once a week. Only
deployment is strained:
one in ten are applying the tools to critical decision-making 56
or high-impact analysis. %
A deployment gap
In 2024, gen AI is expected to account for 12% of Irish There is a notable difference in gen AI deployment
businesses’ technology spend, rising to 15% in 2025. That between multinational corporations (MNCs) and local Irish of employees in MNCs
investment has yet to translate into scaled deployment. companies. Executives from MNCs in Ireland are more
have access to gen AI
While 85% of executives in Ireland report their organisations likely to report that their organisations have adopted gen AI
tools, compared to 38% in
have at least piloted gen AI in one or more parts of their compared to local Irish firms. On average, 56% of employees
business, only 9% have scaled the technology (with use in MNCs have access to gen AI tools, compared to 38% in organisations operating
cases in production in more than half of their business organisations operating solely within Ireland.
solely within Ireland.
functions). Many lack the foundations needed to scale.
A skills gap
Fewer than 21% of executives in Ireland, for example, feel
confident that their organisation’s technology capabilities A landmark shift in digital skills training is essential to
meet the requirements to successfully scale gen AI. unlock the benefits of gen AI. The executives we surveyed
estimate that 64% of their workforces will require reskilling—
Where gen AI is being implemented, the focus tends to
equivalent to roughly 1.76 million people (see Figure 6).13 For
be on the bottom line. Three out of five executives are
some, this will involve developing technical skills such as AI
prioritising investments in process automation that cut costs
engineering. For most, it will focus on training to collaborate
over initiatives that augment people’s roles and transform
with AI systems.
how they work.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 19
Yet, many workers still lack even basic digital The average share of the workforce confident
Figure6.Executivesestimatethat64%oftheirworkforces
skills or access to the training needed to in basic digital skills is 14 percentage points
willrequirereskillingduetogenAI
develop them. Irish executives estimate lower in local organisations compared to
Expectations for how gen AI will change roles at organisations in Ireland and the UK
that less than half (45%) of their workforce MNCs. Similarly, the share of workers who
% of current job roles1
is confident in the digital fundamentals report not having received any digital skills
Jobs to be transitioned: Requiring reskilling / upskilling for new roles
required for work. At the same time, 12% of training in the past 24 months is 17 percentage
Jobs with some enhancement: requiring some reskilling / upskilling
workers report not having received any digital points higher in local organisations.
Jobs with significant enhancement: requiring substantial reskilling/ upskilling
skills training in the last two years. Around
Jobs not impacted: No reskilling/ upskilling required
half (48%) say they are pushed to use new
technology they haven’t been trained on.
17
20
The skills gap is again more pressing among
64% 62% local, Irish organisations compared to MNCs.
22
21
23
23
12
%
of workers report not
having received any
36 38
digital skills training in
Ireland UK
the last two years.
4.78 33.09
Employment mn
1. ReRespondents were asked: How, if at all, do you expect generative AI to change job roles at your
organisation? (Please estimate what proportion of current job roles you expect to fall into the
following categories by distributing 100% points across the options listed.
Source: Accenture UK and Ireland AI business leader survey, fielded July-August 2024. CSO current
employment levels as of Q2 2024. ONS current employment levels. Apr-Jun 2024.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 20
A trust gap Figure7.Employeesandexecutivesarenotaligned
As we highlighted in our previous research Accenture’s global R&D and Innovation centre on the long-term societal impact of gen AI
report, Work, workforce, workers: Reinvented in Dublin, remarks: ‘Leaders should reflect
in the age of generative AI, transparency on whether AI is the only area where a trust
Expectations about the outcomes of the widespread
and trust are required for people to adopt gap exists, or if there are precedents in past
use of AI in Ireland
gen AI tools. That research revealed a workforce innovations. If a long history of trust
trust gap between workers and leaders. gaps exists, leaders shouldn’t be surprised if AI % of executive and employee respondents
Decrease Increase Net +ve Net -ve
follows suit.’
Nearly a year later, the trust gap persists.
Productivity
Trust and user acceptance remain the third Expectations around the value gen AI can
Executives 21% 56% +35
most common barrier to scaling gen AI deliver—whether in boosting economic growth, Employees 19% 37% +18
in organisations across Ireland, following equality or employment—differ significantly
Economic growth
implementation costs and technology between employees and leadership (see Executives 24% 52% +28
Employees 23% 25% +2
platforms not being ready for scale. Half (44%) Figure 7). This disparity highlights concerns
of workers have little or no confidence that about social inclusion and employee rights, Digital inclusion
Executives 27% 49% +22
business leaders will make the right decisions underscoring the trust gap. If not addressed,
Employees 24% 31% +7
to ensure gen AI positively impacts Ireland, these issues could undermine the potential
while a majority (62%) express similar doubts benefits of gen AI. Economic equality
Executives 28% 38% +10
about the government. Dr Kenneth McKenzie,
Employees 33% 20% -13
Head of Human Research at The Dock,
Social mobility
Executives 28% 41% +13
Employees 23% 22% -1
Local Employment
Executives 41% 30% -11
Employees 40% 14% -26
National Employment
Executives 39% 30% -9
Employees 41% 14% -27
Source: Accenture Ireland AI business leader survey, fielded July-August 2024.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 21
The five
imperatives
to accelerate
Ireland’s
reinvention
through
generative AI
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 22
A formula
for success
What can be done to
get Ireland’s gen AI-led
reinvention back on track?
Based on our experience of delivering over
1,000 gen AI projects globally, we see a
formula emerging for how organisations
can responsibly scale the use of gen AI:
‘Shifting from one-off efforts to real
innovation demands a more ambitious Imperative 1: Imperative 2: Imperative 3: Imperative 4: Imperative 5:
and integrated approach. While Lead with value Understand and Reinvent talent Close the gap on Drive continuous
many early adopters are focused on
develop an AI- and ways of responsible AI: reinvention:
Shift the focus from
building tech platforms and using
enabled, secure working:
the latest AI models, most have siloed use cases to Create governance Make the ability
overlooked the cultural, operational prioritising business digital core: Set and guide a vision structures and a culture to change a core
and business changes needed. Now capabilities across the Invest in technology for how to reinvent that operationalises competency and
is the time for organisations to entire value chain and that runs seamlessly work, reshape the AI responsibly, with part of company
address these areas to scale gen AI’ developing new, AI- and allows for workforce and prepare decision-making culture supported
enabled offerings. continuous creation of workers for a gen AI processes that by an ecosystem of
Denis Hannigan new capabilities. world. thoughtfully assess collaborators.
both the risks and
Data & AI Lead—UK and Ireland,
Strategy & Consulting rewards of the
Accenture
technology.
Generating growth: How generative AI can power Ireland’s reinvention Copyright © 2024 Accenture. All rights reserved. 23
The elements of the formula cannot be applied in isolation. AI’s multifaceted impact The constants of the formula
touches every part of the organisation, requiring all five imperatives to be addressed in a
mutually reinforcing way.
In applying the formula, organisations need to apply a consistent
Many early adopters of gen AI have focused primarily on building the technology. But set of principles:
the truth is, successful transformations are never just about tech. It’s essential to align
There should be clear alignment between business strategy and the extent of investment
technology, talent, governance and value roadmaps. Achieving this requires strong
needed across the five imperatives. Given the rapid evolution of gen AI and shifting
coordination across the entire business. Few organisations in Ireland are following this
business demands, adjustments must occur more frequently than in typical annual cycles.
formula—those that do will increase their chances of scaling gen AI.
Whether delivering a proof of concept for complaints handling or building a full gen AI
Based on our survey of business leaders in both the UK and Ireland, we segmented
program, the formula must be followed. This ensures no part of the transformation is
companies by their level of gen AI adoption.
overlooked, maintaining |
82 | accenture | Accenture-Nordic-AI-Maturity-Report.pdf | Nordic AI Maturity
Advancing from practice to performance
From insights to action, the path to extraordinary value starts here.
Contents
AI maturity: AI maturity: AI Achievers How AI Practice Key
Why it matters What it is advance from Achievers makes Capabilities
practice to master their progress
performance craft
07 11 17 21 34 40
The art of AI maturity—Advancing from practice to performance 2
Foreword by Per Österman
Since leaving the worst of the pandemic speed to insights, enabling clients to make
behind us, the European market has faster and better-informed decisions.
faced new challenges: ongoing war, an So, it is no surprise that 32% of Nordic
energy crisis and rising inflation. But we business leaders mentioned AI in their
have also seen technology and human earnings calls last year—and often saw
ingenuity help people persevere through their share prices increase, too.
difficult situations. One technology in
particular, artificial intelligence (AI), has It’s not a stretch to suggest that AI will
been applied in more ways than ever emerge as a crucial component of the EU
before—expediting immigration permits Commission’s digital future agenda. But
for refugees, advancing medical research we still have a long way to go. Though
and patient care, predictive maintenance, AI adoption has gained momentum, our
managing supply chain crises and research shows that only 6% of Nordic
innovating direct-to-consumer companies (compared to 12% of European
value chains. companies) can be categorized as AI
Achievers (companies leveraging AI’s
Pre-pandemic, AI adoption was full potential).
already in high gear in Europe, but the
transformational journey to maturity in The tenets that will help Nordic companies
AI is accelerating even more rapidly as progress in their AI transformation
investments in cloud grow. AI enables journeys and keep pace with the rest of
The art of AI maturity—Advancing from practice to performance 3
Europe include a strong cloud foundation Across Europe, AI is set to play a critical
to scale AI, alignment of strategy and role in alleviating sustainability concerns,
sponsorship, AI talent and culture, and the trade imbalances, supply chain issues
responsible deployment of AI. and regulation changes. AI, when used
strategically, can bring meaningful
The good news is that the groundwork change for people, the planet and profit
has already been laid—with 78% of centers—helping companies not only
organizations having reworked their survive economic downturns and related
strategy and cloud infrastructure plans in challenges, but also thrive despite them.
the last few years to achieve AI success. However, only those organizations that
With more companies in the Nordics invest in maturing their AI capabilities
experimenting with AI, the region is in now will be resilient enough to stamp
“pole position” to more than double their impact on our collective futures. As
the number of AI Achievers by 2025. In Winston Churchill once said, “Never let a
addition, upcoming EU AI regulations good crisis go to waste.”
will also formalize standards for AI
development, including generative AI 78%
technologies (like GPT-4 and DALL-E 2),
further building confidence and trust
in the sector’s potential and real-world
applications from AI practitioners and
of organizations
investors alike.
having reworked their
strategy and cloud
infrastructure plans
in the last few years
to achieve AI success.
The art of AI maturity—Advancing from practice to performance 4
Executive summary
Nordic companies are yet to take full advantage
of everything that AI can do
Artificial Intelligence is no longer hype— demand and win customers, Nordic still behind their European Achievers, who data that is AI relevant and increasing AI
we’re seeing practical implementations companies must work differently across aim to dedicate about one-third of their stakeholders within an organization, so
in the day-to-day business operations business and ecosystem partners. total IT budget towards data and AI by that they can reap the full benefit of AI
of Nordic companies. Specifically, AI 2024, creating more data- and AI-driven across the enterprise value chain.
is a key part of products and services Nordic countries rank high in the organizations in the process.
improving operational efficiencies vis-à-vis 2021 Government AI Readiness Index, Presently, the financial services, health
increasing productivity, enhancing worker according to “The Nordic AI and Data One way to catch up to continental & public services and communications
and customer experiences, and building Ecosystem, 2022.”i But executives competitors is enabling value chain & high-tech sectors are fast emerging
new synergies that were unimaginable a understand that without a significant optimization end-to-end. And our research as the front-runners increasing their AI
few years back. investment into AI from both the public shows that 48% of Nordic companies index in the next three years. But favorable
and private sectors, the Nordic AI are optimizing their use of data and economic and technology policies will
Each of those benefits has been shown landscape cannot be elevated on a global operating on enterprise-grade cloud help Nordic companies of all types make
to improve a business’s bottom line, too. AI map. Our research shows Nordic platforms. And 44% of Nordic companies significant leaps in their AI maturity.
According to Accenture’s AI Maturity companies are planning an increase of are actively addressing potential societal
– Nordic Survey, conducted between budget dedicated to developing and harms through techniques such as AI
September and October 2022, 15% of implementing AI products and services. design co-creation, stakeholder impact
participating companies said the return In 2019, Nordic companies devoted 10% assessments, consequence exercises,
on their AI initiatives exceeded their of their total technology budgets to AI, on human-AI interaction design guidelines
expectations, while only 1% of companies average, while in 2022 they devoted 19%. and environmental AI KPIs. But silos still
said the return did not meet expectations. That figure is expected to grow to 27% exist, so Nordic companies must continue
Still, it’s early days, and to further capture by 2025. However, Nordic companies are to encourage the sharing of experimental
The art of AI maturity—Advancing from practice to performance 5
What do AI Achievers do differently?
While there is clearly a science to AI, our findings demonstrate there is an art to AI
maturity. We discovered in our recent global AI research that AI Achievers are not
defined by the sophistication of any one capability, but by their ability to combine
strengths across strategy, processes and people.
Here are five ways AI Achievers master their craft:
1. Their top leaders champion AI as a strategic priority
for the entire organization.
2. They invest heavily in talent to get more from their
AI investments.
3. They industrialize AI tools and teams to create
a strong AI core.
4. They design AI responsibly, from the start.
5. They prioritize long- and short-term AI investments.
Further, our machine learning models suggest that the share of Nordic AI Achievers will
increase rapidly and significantly, more than doubling from the current 6% to 15%
by 2025.
In short, advancing AI maturity is no longer a choice. It is an opportunity for every
industry, every organization and every leader.
The art of AI maturity—Advancing from practice to performance 6
The art of AI maturity
AI maturity: Why it matters
AI maturity: Why it matters
From optimizing operations to freeing ownership of AI programs. Our survey
up workers to be more creative, AI of more than 100 C-suite executives and
offers businesses a range of benefits data science leaders from the Nordic
that are becoming essential elements region found that AI strategy is being
of competitive advantage. Intelligent, developed in the C-suite in new roles such
data-driven support systems can help as Chief Analytics Officers, Chief Data
businesses reimagine the way they build Officers and Chief Digital Officers, all of
new products, serve customers and whom are working in close collaboration
differentiate themselves in an increasingly with CEOs and board members.
competitive digital economy.
So, it’s no surprise that the percentage
As a result, we’re seeing close to half of of executives of the largest Nordic
Nordic companies shift their AI focus companies mentioning AI on their
from developing proofs of concept (PoCs) earnings calls is constantly growing
to launching AI-powered products and – up to 32% in 2022 from 21% in 2017.
services. And 78% of Nordic companies What’s more, in 2022, the largest Nordic
have adjusted their cloud strategy to companies were 6% more likely to see
align more closely with the progressing AI share prices increase when executives
strategy to achieve AI success discussed AI on earnings calls, up from
(compared to 73% of firms globally). just 1% in 2018. In 2021, this figure was a
staggering 36%, according to analysis by
This clearly reflects the way Nordic Accenture.ii
executives perceive AI: They’re taking
The art of AI maturity—Advancing from practice to performance 8
As always, execution is everything. And increasing operational efficiencies
based on our client experience, it is (43%), reimagining experience for Figure 1: Accenture projects that AI transformation will take less time than digital transformation
important that CEOs and senior leaders customers and workers (43%) and
focus on maturing their investment efforts seeking new growth opportunities
and strategies to drive value and achieve (40%) over the next three years.
desired AI outcomes. Timely and effective
action is key to realizing growth, seizing Companies in the Nordic countries •
market share and creating new value for are planning a significant increase of
all stakeholders. budget dedicated to developing and
implementing AI products and services
from 2022 to 2025: +43% (global
AI, accelerated
average: +37%).
With early successes building confidence Presently, only 11% of Nordic •
in AI as a value-driver, we estimate that AI companies dedicate more than 30%
transformation will happen much faster of their tech budgets to AI
than digital transformation—on average, development, but by 2025 33%
16 months faster (Figure 1). of companies intend to do so.
Our research suggests that Nordic
Source: Accenture Research
companies are making a significant and
Note: Our estimate is derived from a natural language processing analysis of investor calls of
timely push to strengthen their
the world’s 2,000 largest companies (by market cap), from 2010 to 2021, that referenced “AI”
AI capabilities:
and “Digital” in tandem with “business transformation,” respectively. Data was sourced from S&P
earnings transcripts.
Top priorities for Nordic companies
•
are developing AI products and
services (48%), improving ecosystem
partnerships for innovation (46%),
IA
gninoitnem
seinapmoc
egatnecreP
noitamrofsnart
ssenisub
rof
latigid
ro
Digital
transformation
90% AI
transformation
16 months
(13%)
9 years 8 years
11 months 7 months
10%
2010 2022 2030
The art of AI maturity—Advancing from practice to performance 9
There is incentive to move quickly. We Figure 2: Evolution of companies' AI-influenced revenue share – 2019, 2022, and 2025*
uncovered significant growth in Nordic
companies' AI-influenced revenue share
from 2019 to 2025. AI-influenced revenue
doubled between 2019-22 (8% in 2019
to 19% in 2022), and is predicted to triple
over the next three years (to 26% in 2025).
Note: Color indicates the achieved AI-influenced revenue threshold within each time period.
Source: Accenture AI Maturity Nordic Survey, September – October 2022
Note: *2025 = projected
*Definition of “AI-influenced” revenues:
a. a. Sales of existing products and services made possible through better AI-driven insights on customers, supply chain, channels; b. Sales of
new products and services made possible by human + AI, c. Higher prices through dynamic pricing ML algorithms. These sales include some
cannibalization and net new revenues. In contrast, this definition is excluding higher efficiencies in production operations thanks to AI.
)%(
erahs
eunever
decneuflni
-IA
8% 19% 26%
High
>30%
Medium
10%-30%
Low
<10%
2019 2022 2025
N=91
Legend:
High Medium Low
>30% 10%-30% <10%
The art of AI maturity—Advancing from practice to performance 10
The art of AI maturity
AI maturity: What it is
AI maturity: What it is
If most organizations are racing to embrace AI,
why are some seeing more value than others?
AI maturity measures the
To uncover strategies for AI success, not only in data and AI, but also in
Accenture designed a holistic AI-maturity organizational strategy, talent and
degree to which organizations
framework. Fittingly, our analysis itself was culture—to give companies a strong
conducted using AI. competitive advantage.
have mastered AI-related
We applied machine learning models This includes “foundational” AI
capabilities in the right
to unravel massive survey datasets and capabilities—like cloud platforms and
uncover drivers of AI maturity that would tools, data platforms, architecture, and combination to achieve high
have been impossible to detect using governance—that are required to keep
performance for customers,
more traditional analytical methods pace with competitors. It also includes
(more on the methodology in “differentiation” AI capabilities, like
shareholders and employees.
the Appendix). AI strategy and C-suite sponsorship,
combined with a culture of innovation that
Our research found that AI maturity can set companies apart.
comes down to mastering a set of key
capabilities in the right combinations—
The art of AI maturity—Advancing from practice to performance 12
The companies that scored best Figure 3: Only 6% of Nordic organizations are AI Achievers
in both categories are the AI Achievers.
AI Builders show strong foundational
capabilities and average differentiation
AI Innovators AI Achievers
capabilities, while AI Innovators show
12% 6%
strong differentiation capabilities and
Companies that have mature Companies that have differentiated
average foundational capabilities.
AI strategies but struggle AI strategies and the ability
to operationalize to operationalize for value
According to our research, only 6%
of the Nordic companies (vs. 12%
globally) have both the foundation and
differentiated strategy to fully capitalize
on the power of AI. These organizations
have advanced their AI maturity enough
to achieve superior growth and business
transformation. We call them AI Achievers.
AI Builders
1%
Achievers, Builders and Innovators
Companies that have mature
collectively represent just 19% (vs. 37%
foundational capabilities that
global) of the surveyed Nordic companies AI Experimenters exceed their AI strategies
81%
(Figure 3). These companies tend to have
Companies that lack mature AI strategies
more resources (such as technology,
and the capabilities to operationalize
talent and patents) to deliver on their AI
visions and transform their organizations.
AI FOUNDATION
Examples can be found across a wide
range of industries: Financial Services;
AI Foundational capabilities that are key drivers to achieving at least 10% AI influenced revenue
Source: Accenture Research analysis based on a sample of 91 Nordic companies. Thresholds are defined as top 25% of samples in both axes.
NOITAITNEREFFID
IA
gniveihca
fo
ledom
eht
morf
devired
seitilibapac
IA
eunever
decneuflni
IA
%03
tsael
ta
HIGH
HGIH
LOW
WOL
The art of AI maturity—Advancing from practice to performance 13
Health and Public Service (H&PS); According to our research, only in 1% of Figure 4: Levels of AI maturity by industry in Nordic ‘Now’ and ‘Future’ by median
Communications, Media and Technology Nordic companies do data and AI experts
(CMT); Resources (Energy, Natural work hand-in-hand with the business
The median AI Maturity Index in 2022 and 2025 by industry
Resources and Utilities); and Products leaders to drive the strategic agenda of
(Consumer Goods & Services, Retail, the organization. In those companies, data
Industrial Equipment, Automotive). science capabilities are fully integrated as 20 30 40 50 60 70
strategic capabilities. In addition, among
FS
A fourth group we are calling AI this 1%, a company’s strategic roadmap
Experimenters—those with average and budget are aligned with data science
H&PS
capabilities in both categories— initiatives at the C-Suite level.
make up the majority (81%) of those
Nordic 2022
CMT
surveyed. These numbers suggest that a
Nordic 2025
AI, applied
considerable number of companies may
struggle to make the foundational and Resources
cultural shifts needed to realize of the Currently, the Resources industry is ahead
promises of AI. of others sectors in its respective AI
Products
maturity.
In general, the Nordic region benefits
from a high degree of digital literacy and PiiA (Process Industrial IT and
a supportive tech infrastructure. But many Automation)iii and the Sustainable
Source: Accenture Research analysis based on a sample of 91 Nordic companies
Nordic companies see cultural challenges Process industry through Resource and
Note: *2025 = estimated scores. Industries’ AI maturity scores represent the arithmetic average
within organizations as a barrier in Energy Efficiency (SPIRE) have funded
of their respective Foundational and Differentiation index.
scaling AI (one of top 3 challenges for many European initiatives to develop
30% of respondents). Another barrier is AI in process industries, and continue
the inability to set up an organizational to support resource-based industries in
structure that supports continuous accelerating the development of AI.
innovation enabled through AI (25%).
The art of AI maturity—Advancing from practice to performance 14
Other sectors—FS, H&PS and CMT—have Public services in the Nordics are highly
so far been lagging because of legal and digitalized, and AI is seen to make
regulatory challenges, inadequate AI government more transparent, efficient
infrastructure and a shortage of AI-trained and accountable. It’s easy to point to
workers. However, these industries are examples of mature use cases, including
expected to make significant AI advances secure login solutions for government
and accelerate their AI maturity journey websites and banks across the region—
over the next three years. including NemID in Denmark, Bank ID in
Sweden and Norway, and the Platform
Fintech is a sector in which Nordic Altinn in Norway.
countries are considered AI pioneers
globally—but there is always room for As applications like this scale, the region
expansion and innovation. For instance, has the potential to quickly transform its
P27 is a new Nordic initiative to build the economy. And according to a 2020 report
world’s first real-time, intelligent cross- by DIGG, Sweden’s Digital Administration
border digital payment system in multiple Authority, AI is estimated to be able to
currencies. Here, AI will be used to create economic value in public activities
automate compliance and more quickly equivalent to SEK 140 billion annually (USD
detect fraud. $13 billion).v To support this growth, open
data initiatives in the public sector are
All Nordic countries place a high priority becoming more common—for example, in
on healthcare, and it is an important 2021, the Swedish government launched
sector for AI development within their an initiative to support municipalities
respective national AI strategies. Sweden to make better use of AI technologies,
and Denmark are particularly strong in backed by SEK 100 million in funding.vi
life sciences, while Finland has a strong
technology focus in the care delivery
sector—in hospitals, for example.iv
The art of AI maturity—Advancing from practice to performance 15
AI, applied across industries
A global home appliance manufacturer’s such as creating a consumer record to pilot, the company quickly realized a more
leadership had a clear agenda and enable and improve aftersales revenue, manageable, scalable and safer
vision for the future of the company— influencing supply chain improvements, inspection system.
they wanted to be data led. The CIO and improving forecasting and pricing
and CDO knew they needed to tackle through intelligent pricing.
Like its industry peers, a leading oil
the organizational complexity that was
and gas company had an ambition
impacting the company’s data pipeline. A major refining company has hundreds to achieve greater interoperability
To do this, the company launched a major of kilometers of oil and gas pipes in its
within its application landscapes
initiative to reshape the company’s data processing plants. Keeping this large and digital workflows. With a suite of
strategy, powered by AI and analytics. complex running smoothly means software from many different providers,
constantly monitoring the condition of the company began preparing to adopt
Working closely with the global CDO, the all pipes, tracking their maintenance Open Subsurface Data Universe (OSDU),
company and Accenture designed and and, most importantly, checking for a single unified platform that would
implemented the company’s three-year leaks—since leaks are not only costly, but enable the free exchange of data between
business and data strategy, enabling the also pose severe risks to safety and the applications. In just six weeks, OSDU was
company to capitalize on its potential environment. To ramp up inspections, established and populated with a variety
by using data to drive value through a extend the process to new pipelines, and of different data types—a critical first step
supply chain, sales and manufacturing reach its goals for efficiency, safety and that will allow the client to accelerate its
transformation. The manufacturer is environmental sustainability, the company OSDU journey.
now exploring ways to accelerate critical embarked on a proof of concept. And
data use cases throughout the business, with IoT, data and AI at the heart of its
The art of AI maturity—Advancing from practice to performance 16
The art of AI maturity
How do Nordic companies
compare with global peers
in their AI capabilities?
Nordic companies are like
Global AI Innovators Figure 5: Nordic Companies’ AI Capability Compared with Global Peers
Global
With strengths in digitalization, accessibility and
transparency, all Nordic countries are ready for the AI era, Achievers Builders Innovators Experimentrs Nordic average
as per research by the Oxford Insights on Government AI Strategy Senior Sponsorship
and
AI Strategy
Readiness Index. However, Nordic companies must further
Sponsorship
Proactive vs. Reactive
develop their data and AI capabilities before they can
Readily available AI And ML tools
compete with their global peers. Readily available developer networks
Data and Build vs. Buy
Currently, Nordic companies resemble global AI Innovators, AI Core Data management and governance - Change
Platform and technology
as they are defined by mature AI strategies but struggle
Data management and governance
to operationalize (i.e., they have strong differentiation Experimentation data - Change
capabilities and average foundational capabilities).
Talent & Mandatory training
Culture Employee competency in AI-related skills
Innovation culture embedded
Innovation culture encouraged
AI talent strategy
Responsible Responsible AI by design
AI
Responsible data & AI strategy
Out-perfocrming Under-performing
Source: Accenture AI Maturity Nordic Survey, September – October 2022
Note: Each square represents one of the 17 key capabilities. The square is filled in when the AI profile is outperforming against
peers (higher than the average across all companies in terms of % of companies reaching the mature level).
The art of AI maturity—Advancing from practice to performance 18
Our research shows that some Nordic Further, Nordic companies have low data
companies have a robust AI strategy in management and governance maturity,
place, developed and sponsored by senior which is critical to realizing the full value
leadership. These leaders are sensing of AI. Two-thirds (65%) of Nordic
the impact of AI on business and are companies are following the federated/
proactively helping their organizations disjoined data management, governance
leverage readily available AI and machine and integration systems. Companies
learning (ML) tools and developer are yet to take practical steps toward
networks that will help teams forming, documenting and implementing
innovate faster. data policies and procedures supporting
a data mesh. Considerable progress is
In addition, companies in the region are still required with respect to data quality,
embracing new training opportunities for model management and monitoring
all employees. And while leaders excel at scale.
at cultivating AI fluency and establishing
the innovation culture needed to drive Many Nordic companies are heavy
adoption, many organizations today lack users of cloud and realize the need to
the foundational capabilities required establish a robust centralized platform
to support AI at scale. More than 40% and technology foundation that forms
of Nordic companies have federated/ a backbone for enterprise-wide data
disjoined data processes, creating silos management capabilities. But few
across the enterprise value chain. Their have been through the complete cloud
workflows related to data and AI are still modernization journey. This is limiting the
scattered in nature, driven by function- full value companies get from their cloud
specific and project-specific requirements investment to support AI experimentation
rather than enterprise-wide processes. and innovation. Our research shows that
may soon change: eight out of 10
The art of AI maturity—Advancing from practice to performance 19
companies have to some extent reworked Transitioning from pilots to production Figure 6: Pilots across multiple business functions
their existing cloud strategies to be more is one of the key challenges for Nordic
in sync with their evolving AI strategy companies, according to the Nordic AI
Not started Early stage Full productization
and roadmap. and Data Ecosystem 2022 report.vii
Product Development
IT Security
But our research suggests that Nordic
Nordic organizations are organizations will move from pilots Production
to production at scale in the next few Procurement Global Achievers
pursuing pilots across
Global Experimenters
years, thanks to a robust private sector, Finance
Nordic Average
multiple functions
collaborative governments and a digitally Legal Risk
mature population with high trust in both Supply Chain
In the Nordic region, companies have a the private and public sectors.
Customer
clear vision to be data- and AI-driven but
HR
struggle to execute. They understand the Average of all functions 44 55 61
value of AI, but they do not know how to 0 25 50 75 100
Nordic n = 91
scale. Companies across industries are
conducting pilots in multiple functions,
Source: Accenture Research
but a large number of them are in
Note: Score 0-100, ranging from 0 = AI use case not started, 50 = AI use in early stage, 100 =
early stages.
having AI programs in place for full productization. The chart shows the difference in terms of
average score for AI use cases of different functions, between Achievers and other firms.
For Nordic companies, common barriers
Those differences can be statistically significant after controlling for industry, geography,
to scaling AI include cultural challenges
and company size.
within organizations, an inability to set up
an organizational structure that support
continuous AI-powered innovation and
the lack of viable cloud data solutions to
implement an AI strategy.
The art of AI maturity—Advancing from practice to performance 20
The art of AI maturity
How AI Achievers
master their craft
How AI Achievers
master their craft
It is worth noting that the potential for
AI-mature organizations will evolve
along with the technology itself. High
performance today will become business-
as-usual tomorrow.
Today’s AI Achievers have set the standard
and are poised to remain leaders. While
there is clearly a science to AI, they have
shown us there is also an art to AI maturity.
They have demonstrated that excellence
in areas like vision and culture are just
as critical as algorithmic integrity. Our
research uncovered five key success
factors for AI Achievers.
The art of AI maturity—Advancing from practice to performance 22
Success Factor 01
Champion AI as a strategic priority
for the entire organization, with full
sponsorship from leadership
Companies are realizing that AI is Over half of the Nordic companies in
increasingly becoming a must-have our survey say that they have created a
component to differentiate their platform through which all employees are
respective businesses, especially in a post- able to showcase failed and successful
pandemic economy. experiments, and seek constructive
feedback from leadership. In fact, 71%
Our research shows that, on average, 74% of the Nordic companies stated that
of Nordic companies have developed an innovation is integrated with their
AI strategy with strong sponsorship from organization’s vision, and that leaders hold
the CEO and/or the board members (vs. each other accountable.
78% of European Achievers and 56% of
European Experimenters). For the CEOs of AI Achievers, creating a
culture of innovation is itself a deliberate,
Our research also suggests that the best strategic move—one that is used as a
AI strategies tend to be bold, even when vehicle for experimentation and learning
they have modest beginnings. Bold AI across the organization. For them,
strategies, in turn, help spur innovation. innovation is a strategic discipline.
The art of AI maturity—Advancing from practice to performance 23
When one of the largest banks in the omni-channel experience for clients, and a
Nordic region was challenged with data-powered enterprise that is delivering
legacy technologies, siloed data, and no greater value to the company. The bank
single view of the customer, they knew has seen significant improvements in
they needed to act. For its data-powered ROI, and a 42% uplift through ML models
transformation, the team established and triggers. Significantly, the client's
a strategic roadmap, then worked to leadership can now focus on improving
architect and implement a data lake, the customer experience across the
advanced analytics powered by more user journey.
than 70 ML models, and a new campaign
management system. This included
42%
a distributed agile framework across
all geographies and time zones. The
company now benefits from an intelligent
marketing system that drives an
uplift through ML
models and triggers
The art of AI maturity—Advancing from practice to performance 24
Success Factor 02
Invest heavily in talent to get more
from AI investments
With a clear AI strategy and strong CEO companies are leveraging to a moderate
sponsorship, organizations are more likely or great extent the readily available data
to invest heavily in creating data and AI science talent and AI/ ML tools that will
fluency across their workforces. While AI help them innovate with data and AI.
proficiency must start at the top, it cannot
end there. Helsinki and Stockholm are among the
top 50 global AI hubs, even though the
We found that a whopping 87% of Nordic Nordics represent just 2% of global AI
companies say they have made AI talent, according to Silo Research and
trainings mandatory for most employees, OECD 2022 research. The private and
from product development engineers to public sectors have developed novel
C-suite executives (vs. 78% of European educational programs to develop digital
Achievers). Cleary, Nordic companies are and tech talent; for example, Finland’s
serious about developing AI talent and industry-specific ”AI for Built Environment”
upskilling their workforces—particularly certification course launched in November
around data engineering, AI/ML and 2021. Other examples include Sweden's
domain expertise. national “AI competence for Sweden”
curriculum, and “Elements of AI,” an online
As part of their current ecosystem course offered in all Nordic countries.viii
strategy, more than 80% of Nordic
The art of AI maturity—Advancing from practice to performance 25
Perhaps more than ever, it is important A global financial services firm, BBVA,
that companies address gaps in their enabled its digital journey with AI to create
AI talent and skills. Already, 75% of the intelligent data-driven banking operations
Nordic companies today have |
83 | accenture | Accenture-Going-for-Growth.pdf | Going
for growth
Navigating the great value
migration in the age of AI
Contents
The legacy of AI is already being written
Beyond the growing pains
Navigating the great value migration
Going for growth across all horizons
Sustainable growth is there for the taking
Going for growth: Navigating the great value migration in the age of AI 2
Authors
Jason Angelos Jon Edwards Nevine El-Warraky Chris Tomsovic
Senior Managing Director Managing Director Senior Managing Director Managing Director
Global lead, Corporate Corporate Strategy & Global lead, Industry & Global lead, Macro
Strategy & Growth Growth Customer Growth Foresight
Accenture Strategy Accenture Strategy Accenture Song Accenture Strategy
Contributor
Tomás Castagnino
Managing Director
Accenture Research
Going for growth: Navigating the great value migration in the age of AI 3
G2000 companies with the highest AI maturity see 4.7x higher
growth over a one-year period
115
110
105
100
95
90
2019 2020 2020 2020 2020 2021 2021 2021 2021 2022 2022 2022 2022 2023 2023 2023 2023
Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4
)001
=
4Q
9102
xedni(
seuneveR
Introduction
The buzz surrounding artificial intelligence (AI) and Figure 1: Companies with greater AI maturity outperform their peers over time2
generative AI is at an all-time high. The S&P 500
Information Technology Index, which includes tech
leaders in AI innovation, boasts a staggering 46%
year-over-year growth rate and year-to-date returns
Top AI Index companies Bottom AI Index companies
nearing 32%.1 This surge is disproportionately
driven by the early successes and future growth
expectations of a handful of companies.
4.7x
The growth potential for companies delivering AI-based
growth
solutions and services to corporate buyers is clear. But where
is the opportunity and return for the great majority of other
companies that make up the Forbes Global 2000?
The success to date of top-performing AI adopters serves as
an indicator of the potential growth opportunities available
from AI and gen AI for everyone else. Accenture analysis
Company average by group,
reveals that, since 2022, companies with the greatest AI 2019 Q4 = 100, cumulative last four
quarters, inflation adjusted
maturity have been growing 3 percentage points more (or
4.7x) year over year than companies with the least maturity. For
the average G2000 company with revenues of $6 billion USD,
this translates into a cumulative revenue differential of $260
Source: Accenture analysis
million, or $360 million since 2019 (See Figure 1).
Note: AI maturity evaluated using Accenture’s AI Index. The index incorporates more than 30 individual metrics sourced from more than 10 diverse data sets,
encompassing a broad spectrum of industries, and spanning more than 2000 large companies worldwide. See endnote for more information.
Going for growth: Navigating the great value migration in the age of AI 4
Despite these positive signals, most companies Companies that successfully And with good reason: Accenture estimates that
have yet to see the commercial impact. They are more than US$10.3 trillion in additional economic
pursue AI-fueled reinvention
understandably in search of where the AI growth value can be unlocked by 2038 just by companies
outperform their peers in
opportunity is for them and when they might adopting gen AI alone and at scale.
share in the AI wealth. Our answer: Soon. top-line performance by
Others should follow their example because the
15%—a gap that is expected
number of AI initiatives focused on driving business
Accenture found that companies successfully
to more than double by 2026. growth is expected to increase six-fold by 2025. And
pursuing AI-fueled reinvention have delivered top-
by 2029, growth and expansion will be the dominant
line performance that outperforms their peers by
goal of AI at 67% of companies.4
15%. By 2026, this revenue growth gap is expected
to more than double to 37%. Additional Accenture
Exponential growth opportunities are
analysis indicates that companies with differentiated
horizons that involve expanding the core,
AI strategies operationalized for value experienced around the corner.
activating growth in adjacent areas, and
a 3x increase in total return to shareholders over a
establishing new revenue lines. These forward-
5-year period.3
thinking leaders are embracing the paradigm
shift that AI represents. Rather than waiting
While cost optimization and efficiency have been AI’s
and monitoring the risk of disruption, they are
early business headliners, AI is proving its potential
taking proactive steps to find new growth and
to elevate competitiveness, expand markets, and
outmaneuver their competition.
deliver exponential growth for companies.
Companies that effectively adopt AI will find and
capture new growth opportunities across three
Going for growth: Navigating the great value migration in the age of AI 5
The legacy of
AI is already
being written
Going for growth: Navigating the great value migration in the age of AI 6
The persistent state of flux in which Business leaders and investors are also The excitement around AI is largely driven by
businesses now operate has become the expressing confidence in the enduring nature rapidly evolving consumer preferences and
of AI. Mentions of AI in corporate earnings calls behaviors (which often outpace businesses’
new normal. Recent Accenture research
have soared by 370% since late 2022.6 We ability to respond), and heightenend
found that the rate of change affecting
found that 75% of companies are prioritizing expectations for what AI will mean for them.
businesses has soared 183% in the past
investments in data and AI (up from 56% in early Consumers, already enjoying AI benefits
five years—and by 33% in just the past
2023).7 And evidence abounds in how venture through interactions with chatbots or receiving
year. Geopolitical tensions and trade
capitalists are placing their strategic bets, in the hyper-personalized offers from companies, now
skirmishes, inflation, and the speed of rapid rise of AI-related corporate technology expect their businesses to use AI to anticipate
technological advances are just a few of spending, and in the expanding talent market for their needs and help them make confident,
the factors with which CEOs need AI-related jobs: straightforward purchasing decisions—
something 75% of consumers now struggle
to contend.
• VC funding flowing into AI-related fields with.11 It’s no surprise that some business
tripled in the past decade and now leaders are rushing to use AI to deliver more
On top of all this is the uncertainty and debate
represents 14% of total corporate VC deals.8 engaging and relevant products, services, and
surrounding AI’s ultimate impact on business
experiences, reducing consumers’ decision-
performance. Many experts and economists
• 91% of executives believe their organizations making stress. They believe customer loyalty
are quite bullish on AI’s potential. They believe
will be ready to scale up generative AI will depend on it. And revenue growth will
AI is here to stay, representing a fundamental
technologies by the end of 2024.9 follow.
shift in how businesses operate, innovate and
compete. Some of these experts boldly predict,
• AI-related job postings have more than
for example, that AI will produce a 6.1% GDP uplift
doubled since 2019.10
in the United States by 2034.5
Going for growth: Navigating the great value migration in the age of AI 7
Beyond the
growing pains
Going for growth: Navigating the great value migration in the age of AI 8
For every industry expert, analyst and CEO of non-tech companies that have the greatest potential change, and find and deliver new value opportunities
that champions AI for growth, an equal to benefit from AI adoption have, in fact, under- that were previously hidden. For them, AI is more
performed the broader stock market.13 Given these than a response to current market conditions. It is a
number are skeptical. A recent headline
arguments, it’s understandable that some leaders are proactive strategy to gain the foresight needed to
from The Economist contributed to this
may question when AI will deliver the anticipated value navigate today’s uncertainties and activate entirely
sentiment by asking “What happened to
they seek. new growth models.
the artificial intelligence revolution?” as
its writers observed the limited economic
But it’s remarkable to observe, little more than a year
impact from the technology thus far.12 since the release of Chat GPT-4, the meteoric rise Savvy business leaders are turning
in investment in, consideration of and activity with
to AI to help them assess markets,
There are also observations that only 5% of generative AI and AI more broadly. The market activity
anticipate change, and find and
businesses consistently use AI and despite its suggests something far surpassing a gradual multi-
potential productivity per employee in developed year trend and companies would be wise to get off deliver new value opportunities
nations has remained flat. Additionally, share prices the sidelines. While AI’s overall value to businesses
that were previously hidden.
continues to be debated, savvy business leaders are
turning to AI to help them assess markets, anticipate
Going for growth: Navigating the great value migration in the age of AI 9
Navigating
the great
value migration
Going for growth: Navigating the great value migration in the age of AI 10
The historical value that came Nearly half (45%) of executives In fact, Accenture’s latest research reveals that
from refining business models nearly 45% of executives say they are using AI
are using AI extensively to explore
extensively for new product and service ideas, to
and optimizing ways of working
new product and service ideas,
identify new markets, to scale innovation across
pales in comparison to the value
identify new markets, scale multiple enterprise systems and for other strategy-
available to organizations that
related decision making. These leaders are giving
innovation and improve their
use AI wisely. In the age of AI,
reason for others to believe in the power of AI.
business growth is no longer solely a strategic decision making.
More importantly, they are providing a path to
function of how well companies can follow, beyond the hype, to deliver value and find
continually strengthen their core new growth.
business capabilities or operating
Companies that make strategic investments
models. While it is true that AI can
Early-movers can innovate to address unmet
in AI such as these are able to pursue growth
accelerate those critical activities, needs and expand into new and adjacent
opportunities in three critical ways: by amplifying
it does so much more. It adds more markets—and do so with increased organizational
and accelerating core business capabilities and
certainty to the bets that leaders velocity. Companies with the AI maturity to shape
assets; by expanding reach into adjacent growth
and activate their growth strategies can free
place. It lowers barriers to market
areas; and by activating new and entrepreneurial
themselves from endless offering development
entry. And it allows businesses to
revenue models.
and testing cycles. This means they can
extend traditional markets and
deliver business outcomes faster. For example,
unlock thousands of new revenue-
generative AI is accelerating the time to market
generating opportunities. In short, it
for early adopters in consumer goods by 25-50%.
is radically changing where value is
found. And how it is pursued.
Going for growth: Navigating the great value migration in the age of AI 11
All of these pursuits are under way today, often simultaneously within individual companies. Each is
underpinned by a strong digital core (see sidebar). Where these opportunity areas differ is in the scale of
Creating a digital core that
benefits they can deliver and the time horizon over which full value is realized. Each horizon promises to
unlock exponentially more top-line value than the one prior (see Figure 2). powers growth
As AI ushers in a new era of growth, companies
need to take three actions to ensure their digital
core is reinvention ready.
Figure 2: Companies using AI to pursue growth across three horizons are best positioned to reap the
exponential rewards AI and gen AI offer.
Build an industry-leading digital core. Companies
that achieve “industry-leading” levels of digital
prowess in platforms, cloud, data, AI and other
capabilities can expect to achieve a 20% acceleration
Growth Entrepreneurs
of revenue growth and a 30% boost in profitability.
AI initiatives focused on launching entirely
new offerings and revenue models,
reshaping industry value chains and Boost investments in innovation. Digital leaders
delivering disproportionate growth
continuously increase the proportion of their IT
budgets dedicated to strategic innovation (in
Growth Expanders areas such as generative AI). Shifting just 6% in
spending from maintenance to innovation is a
AI initiatives focused on the pursuit of
adjacencies and of finding new ways to recipe for success.
reach new customers
Balance tech debt with investments. AI has
Growth Amplifiers become a leading contributor to technical debt. To
AI initiatives focused on enhancing the manage this debt, leading companies allocate 15% of
core business and generating incremental
their IT budget toward debt remediation, which allows
revenue now from existing customers
them “pay down debt” without sacrificing
their strategic investments.
Source: Accenture analysis; estimates percentage range of companies in each horizon 1) in 2024 and 2) in 3-5 years.
Going for growth: Navigating the great value migration in the age of AI 12
Growth
Amplifiers
Opportunity to accelerate the core business with AI.
The most immediate and obvious growth horizon involves using AI to amplify and accelerate the core
business. Companies pursuing these opportunities are growing their top-line revenues by reaching
underserved market segments and better anticipating the needs of existing buyers. For companies that use
AI to strengthen consumer engagement, it is a vital part of the connected front-office team, putting formerly
hidden or ignored information to work with interactions that are more personalized, engaging, profitable and
ultimately more human.
Take the example of food service giant Sysco. The company is using generative AI to boost revenues by
not only optimizing its merchandising and product assortment capabilities, but also providing shopping
recommendations.14 Then there’s Best Buy, which is improving satisfaction and loyalty by using AI to transcribe
and summarize contact center calls, equip call center agents with all the resources they need to address
customers’ needs, and even automate personalized follow-ups.15
Going for growth: Navigating the great value migration in the age of AI 13
Where it’s working
Banking on happy customers
Global financial services group BBVA has made By combining first-party data with new data
wise and targeted investments in AI, cloud and sources to deliver a step-by-step view of the
data to create a data-driven, engaging and customer journey, BBVA’s new digital sales
differentiated customer experience. Its decision model helps the bank prioritize sales initiatives
to use digital technologies to reach people in for new customers and cross-sell to existing
new ways resulted in a staggering 117% growth customers. Their strategy and investments
in new customers in the last few years and a have had massive, positive impact including
profit of more than €8 billion ($8.6 billion) in acquiring more than 11 million new customers in
2023, the highest earnings in the bank’s history. 2023 and experiencing a 100% growth in digital
sales over the last four years.
These results would not have been possible had
the bank not consistently invested in its digital
“Providing a differentiated, better
core, harnessing the power of cloud, data and
experience was like discovering a
AI to facilitate the rapid development of new
capabilities and insights. For example, bank- pot of gold.”
wide data, predictive analytics and business
intelligence deliver a holistic view of the current — David Puente, Global Head of Client
and lifetime profitability—and likely behavior—of Solutions, BBVA
every customer.
Going for growth: Navigating the great value migration in the age of AI 14
Growth
Expanders
Opportunity to pursue adjacencies with AI.
The second growth horizon for AI offers businesses the opportunity to expand into new markets and/or pursue
industry-adjacent value. Here, AI helps companies activate, reposition and extend their existing intellectual
property, assets and services in more market-relevant ways or develop new, connected, service-rich and
outcome-based solutions.
Retailers, for example, have developed new, high-margin revenue streams with their retail media networks.
They are using AI to bring together first-party data, attribution models, digital and in-store media platforms, and
strong brand relationships to target and reach shoppers in new ways. Target has already turned such media
platforms into a billion-dollar business, with other retailers on track to quickly pass this milestone as well.16 And
infrastructure company Equinix has partnered with Nvidia to offer secure “Private AI” to allow for on-premise AI
compute as a managed service.17
Going for growth: Navigating the great value migration in the age of AI 15
Where it’s working
Tapping into new opportunities
Ecolab, a global leader in water, hygiene Integrating AI into customer outreach, advisory
and energy technologies, has shifted from and briefing processes enables Ecolab to
selling traditionally discrete products such as extend its reach with existing customers and
detergents and water-treatment chemicals accelerate growth.
to connected digital solutions in multiple
areas—from water management and predictive “AI has enabled the Field to
maintenance to remote monitoring of systems
make decisions and it ensures
and processes.
their on-the-ground insights are
AI has played a big role in supporting Ecolab’s not lost within the organization.
digital reinvention, as well as its efforts to
We’ve seen [that translate into]
extend its reach and accelerate growth.
hundreds of millions of dollars
AI-enabled market analysis tools have, for
example, helped the company create a new of value creation and value
market-relevant customer value proposition for
potential.”
digital services that is currently being rolled out
in the market. Equally important, AI is making — Kevin Doyle, Chief Digital Officer,
it possible for sales teams and engineers to
Ecolab
tap 100 years of expertise to better meet
and anticipate customer needs and to tailor
programs for distinct customers.18
Going for growth: Navigating the great value migration in the age of AI 16
Growth
Entrepreneurs
Opportunity to activate new revenue models with AI.
Horizon three encompasses the most profound growth opportunities for companies. Companies making their
moves in this space employ AI to activate new and entrepreneurial revenue models at unprecedented speed.
These are the opportunities that have the greatest potential to reshape industry value chains and deliver
disproportionate growth over time. As just one example, consider the potential for life sciences companies to
reinvent healthcare. Johnson & Johnson (J&J) MedTech is aggressively pursuing new AI capabilities in general
surgery. Working with Nvidia, the company is already scaling AI solutions that accelerate access to real-time
insights, enable open innovation, and improve decision-making, education and collaboration across the
connected operating room.19
The truth is that companies in virtually all industries are already starting to explore how they might use AI to
activate new revenue models and innovations. Long development cycles previously made such models and
innovations impractical. AI makes them not only practical, but also critical enablers and accelerators of new and
sustainable growth.
Going for growth: Navigating the great value migration in the age of AI 17
Where it’s working
Revolutionizing beauty, creativity and growth
L’Oréal, the world’s leading beauty company, age. And by leveraging science and technology,
is using advanced science, data, AI and it is developing new innovations and pursuing
generative AI to connect more personally with new opportunities that will enable growth and a
customers and deliver transformative beauty sustainable competitive edge.20, 21
innovations that answer its customers’ unmet
needs. By integrating advanced technologies “L’Oréal is no longer simply
into its products and services, the company has
a company selling cosmetics
activated a shift from “beauty for all” to “beauty
products, but products and
for each.”
services.”
This move has not only enabled ultra
— Béatrice Dautzenberg, Global Director
personalized customer experiences, but also
of Beauty Tech Services, L’Oréal22
allowed the company to develop and monetize
a host of augmented products, smart devices,
mobile apps, online platforms and digital
services. From new AI-powered assistants
and diagnostic tools to handheld devices that
enable people to enjoy salon-quality hair color
at home, L’Oréal is re-imagining beauty in the AI
Going for growth: Navigating the great value migration in the age of AI 18
Going for growth
across all horizons
Going for growth: Navigating the great value migration in the age of AI 19
Unprecedented business uncertainty, market
disruptions and technological advances are forcing
business leaders to rethink their legacy revenue
models and their approaches to strategic business
Hyper-personalized Rapid market
planning. AI and Gen AI, employed in the right
ways, offer a promising path forward. Leaders can products, services and assessments
anticipate market movements and quickly connect experiences for adjacencies
with stakeholders in new ways. They can identify
emerging growth opportunities, value pools and
even risks with greater certainty. And they can
quickly activate new programs to drive exponential
and sustainable growth.
To take advantage of AI’s growth
potential across all horizons, we
recommend leaders take action in
Dynamic Generative
four key opportunity areas today:
planning design
for perpetual for product
growth engine development and
innovation
Going for growth: Navigating the great value migration in the age of AI 20
01 Generate hyper-personalized experiences to expand
the core
One of the most effective ways to strengthen a
business’s core revenue-generating activities
involves developing hyper-personalized products,
Actions for leaders
services and experiences that cater to unique
preferences and needs. By maximizing the
• Build a strong data foundation that aggregates and analyzes data
relevance of their existing offerings, business
and enables generative AI to gain a deeper, real-time understanding of
leaders can increase customer satisfaction and stakeholder needs, preferences and value drivers.
lifetime value, achieve higher margins and enjoy
better market positioning. • Integrate generative AI into various touchpoints to help customers
throughout their journey, from early in their decision-making to follow-ups
that build lifetime loyalty.
Generative AI is a critical enabler for amplifying and
accelerating the core business. It provides the tools needed
• Continually monitor and optimize the performance of AI-driven
to analyze vast amounts of data, identify patterns, and create
personalization initiatives and use data-driven insights to refine them
personalized campaigns, recommendations and solutions
based on changing market dynamics.
that resonate with target audiences.
Going for growth: Navigating the great value migration in the age of AI 21
02 Generate rapid market assessments to find adjacencies
and extend reach
Leaders must also identify growth opportunities in
adjacent areas or among untapped market segments.
Using existing assets and new outcome-based
Actions for leaders
solutions are two important ways companies can
extend their reach beyond their core businesses.
• Use generative AI to aggregate and analyze data from diverse
sources to capture the voice of the market and uncover underserved or
Once again, generative AI can be invaluable to leaders looking
overlooked segments, trends and opportunities that may not be visible
to capitalize on such industry-adjacent growth opportunities. By
through traditional methods.
leveraging advanced AI capabilities, business leaders can generate
rapid market assessments to quickly analyze emerging trends,
• Apply generative AI to identify and evaluate adjacent markets that
determine market potential and discover new market
present opportunities for expansion and diversification. Generative AI is
segments, even in areas with limited data or insights. The
particularly well suited to simulate various market scenarios and assess
technology excels at processing vast amounts of data—from
the potential impact of different strategies.
market reports to social media trends to economic indicators—to
identify patterns and correlations that may not be immediately
• Establish ongoing AI-driven market assessments to keep track of
apparent. Such insights pave the way for leaders to set up and test
evolving trends and emerging opportunities. This proactive approach
new offerings, pricing structures or routes to market.
ensures that the business remains agile and can quickly capitalize on new
growth areas.
Going for growth: Navigating the great value migration in the age of AI 22
03 Leverage generative design to create new products
and services
Sixty percent of executives say it takes their company one
year or more to adapt to changing customer needs. In a world
in which expectations shift on a month-to-month basis, many
Actions for leaders
initiatives might become obsolete before they are even rolled
out. To meet continuously evolving demands, leaders need
• Examine all possible AI-fueled opportunities to create new revenue models, no
to develop new revenue models and launch new AI-driven
matter how ambitious or farfetched they may originally appear. Use AI to analyze
products, services and experiences at breakneck speed. market trends and human behaviors, identifying opportunities for new revenue
streams, with a clear view of ROI and an actionable plan to scale.
Generative AI, with its powerful generative design capabilities, makes it
possible for leaders to pioneer these new frontiers. For example, generative • Cultivate a portfolio of growth opportunities that balances potential returns,
AI can revolutionize the way companies approach product development feasibility and risk, and investments in talent and resources that will be needed to
and business model innovation. By leveraging advanced algorithms and bring each to fruition.
machine learning, AI can create countless design permutations, optimize
for specific parameters, and uncover novel solutions that humans might not • Leverage AI’s generative design capabilities to explore a wide range of design
easily envision. This capability allows companies to rapidly prototype and possibilities, accelerate the development process, rapidly prototype solutions, and
iterate new ideas, reduce time to market, and foster a culture of continuous refine and optimize products/services for performance, cost and sustainability,
innovation.
Beyond physical products, generative AI can help businesses activate
new revenue models—such as subscription services, pay-per-use
schemes, or all-digital offerings—tailored to evolving market dynamics and
technological advances.
Going for growth: Navigating the great value migration in the age of AI 23
04 Introduce dynamic planning to create a perpetual
growth engine
Regardless of the growth opportunities business leaders
pursue, they must utilize dynamic strategic planning
capabilities to navigate complexities and ensure a
Actions for leaders
perpetual growth engine is in place. Static and even
“rolling” strategic plans are no longer adequate. The
• Incorporate generative AI in the strategic planning process to help
pace of change companies face and the speed with
carry out continuous market assessments, scenario planning and
which they must react to (or anticipate) market forces forecasting—and to pressure test the most relevant opportunities.
demands an always-on approach. Continually adjust plans to align to shifting macro and market forces.
Enabled by a strong digital core, generative AI is fast becoming • Build a culture of adaptation in which people are willing to change and
indispensable in the creation of the adaptive strategic plans that embrace innovation. This involves communicating new insights and
are now needed. By harnessing vast amounts of historical data and strategic scenarios with key stakeholders to encourage leaders to seek
analogues, generative AI helps business leaders understand market new ways to create value.
forces and relationships in real time. It enables leaders to expand
their sphere of understanding to not only identify new value pools, • Establish a perpetual growth engine with a cross-functional value
but also model scenarios and launch growth initiatives at speed and navigation team that uses generative AI to actively monitor market
scale. Importantly, it also differentiates valuable market signals from dynamics, vet strategies, prioritize key initiatives and optimize results.
noise, helping to ensure that strategic decisions are based on high-
quality insights rather than extraneous data. The result? Informed
decisions that drive success.
Going for growth: Navigating the great value migration in the age of AI 24
Sustainable growth
is there for the taking
The unforgiving pace of change in the world today presents
a tremendous challenge for CEOs and other C-suite leaders.
But it also creates exciting opportunities for companies that
can proactively translate those challenges into sustained
competitive advantage and new growth. Until now, sustaining
value amid constant disruption has been difficult. But AI now
makes it possible.
Growth opportunities abound. Those that successfully pursue
them will think differently about the growth opportunities
before them—and how to find them and pursue them. They
will arm their organizations with new innovation capabilities.
And they will embrace AI as a key enabler of agility and
adaptability across the end-to-end growth lifecycle. Other
CEOs should follow their lead.
Going for growth: Navigating the great value migration in the age of AI 25
References
1 2024 S&P Dow Jones Indices, June 20, 2024. 12 “What happened to the artificial-intelligence revolution?” The Economist, July 6,
2 AI maturity was evaluated using Accenture’s AI Index. This index incorporates 2024.
more than 30 individual metrics sourced from more than 10 diverse data sets, 13 ibid
encompassing a broad spectrum of industries, and spanning more than 2000 14 Beth Stackpole, “Incorporating generative AI into your company’s technology
large companies worldwide. The index framework encompasses not only AI- strategy,” MIT Sloan School of Management, February 27, 2024.
related metrics but also the vital capabilities essential for companies to foster and 15 Best Buy, “How Best Buy is using generative AI to create better customer support
scale their AI endeavors: Strategic AI signaling, AI assets, Tech foundations, and experiences,” April 9, 2024.
Talent & Culture enablers. The 0-100 AI index reflects the company’s percentile 16 David Doty, “Walmart, Target and Other Mega-Retailers Leverage First-Party to
ranking position in its industry. The Top AI Index includes companies in the top Become new Media Giants,” Forbes, April 26, 2022.
quartile, and the Bottom AI Index includes companies in the bottom quartile. 17 Equinix, “Equinix Private AI with NVIDIA DGX—Turnkey, ready-to-run AI
Revenues have been adjusted by inflation to ensure comparability across time. development platform.”
3 Accenture Research analysis, 2024. Period 2017-2022. 18 Chris Stokel-Walker, “How one water-management company is using AI to unlock
4 Arielle Feger, “CEOs expect efficiency, cost savings from generative AI by 2025,” insights from its 100-year past,” Business Insider, June 18, 2024.
eMarketer, July 5, 2024. 19 Johnson & Johnson, “Johnson & Johnson MedTech working with NVIDIA to scale
5 Allison Nathan (ed.), “Gen AI: Too much spend, too little benefit?” Goldman Sachs AI for surgery,” March 18, 2024.
Global Investment Research (Issue 129), June 25, 2024. 20 L’Oréal, “L’Oréal accelerates Beauty Tech leadership with advanced bioprinted
6 Accent |
84 | accenture | Accenture-Going-for-Growth(1).pdf | Going
for growth
Navigating the great value
migration in the age of AI
Contents
The legacy of AI is already being written
Beyond the growing pains
Navigating the great value migration
Going for growth across all horizons
Sustainable growth is there for the taking
Going for growth: Navigating the great value migration in the age of AI 2
Authors
Jason Angelos Jon Edwards Nevine El-Warraky Chris Tomsovic
Senior Managing Director Managing Director Senior Managing Director Managing Director
Global lead, Corporate Corporate Strategy & Global lead, Industry & Global lead, Macro
Strategy & Growth Growth Customer Growth Foresight
Accenture Strategy Accenture Strategy Accenture Song Accenture Strategy
Contributor
Tomás Castagnino
Managing Director
Accenture Research
Going for growth: Navigating the great value migration in the age of AI 3
G2000 companies with the highest AI maturity see 4.7x higher
growth over a one-year period
115
110
105
100
95
90
2019 2020 2020 2020 2020 2021 2021 2021 2021 2022 2022 2022 2022 2023 2023 2023 2023
Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4 Q1 Q2 Q3 Q4
)001
=
4Q
9102
xedni(
seuneveR
Introduction
The buzz surrounding artificial intelligence (AI) and Figure 1: Companies with greater AI maturity outperform their peers over time2
generative AI is at an all-time high. The S&P 500
Information Technology Index, which includes tech
leaders in AI innovation, boasts a staggering 46%
year-over-year growth rate and year-to-date returns
Top AI Index companies Bottom AI Index companies
nearing 32%.1 This surge is disproportionately
driven by the early successes and future growth
expectations of a handful of companies.
4.7x
The growth potential for companies delivering AI-based
growth
solutions and services to corporate buyers is clear. But where
is the opportunity and return for the great majority of other
companies that make up the Forbes Global 2000?
The success to date of top-performing AI adopters serves as
an indicator of the potential growth opportunities available
from AI and gen AI for everyone else. Accenture analysis
Company average by group,
reveals that, since 2022, companies with the greatest AI 2019 Q4 = 100, cumulative last four
quarters, inflation adjusted
maturity have been growing 3 percentage points more (or
4.7x) year over year than companies with the least maturity. For
the average G2000 company with revenues of $6 billion USD,
this translates into a cumulative revenue differential of $260
Source: Accenture analysis
million, or $360 million since 2019 (See Figure 1).
Note: AI maturity evaluated using Accenture’s AI Index. The index incorporates more than 30 individual metrics sourced from more than 10 diverse data sets,
encompassing a broad spectrum of industries, and spanning more than 2000 large companies worldwide. See endnote for more information.
Going for growth: Navigating the great value migration in the age of AI 4
Despite these positive signals, most companies Companies that successfully And with good reason: Accenture estimates that
have yet to see the commercial impact. They are more than US$10.3 trillion in additional economic
pursue AI-fueled reinvention
understandably in search of where the AI growth value can be unlocked by 2038 just by companies
outperform their peers in
opportunity is for them and when they might adopting gen AI alone and at scale.
share in the AI wealth. Our answer: Soon. top-line performance by
Others should follow their example because the
15%—a gap that is expected
number of AI initiatives focused on driving business
Accenture found that companies successfully
to more than double by 2026. growth is expected to increase six-fold by 2025. And
pursuing AI-fueled reinvention have delivered top-
by 2029, growth and expansion will be the dominant
line performance that outperforms their peers by
goal of AI at 67% of companies.4
15%. By 2026, this revenue growth gap is expected
to more than double to 37%. Additional Accenture
Exponential growth opportunities are
analysis indicates that companies with differentiated
horizons that involve expanding the core,
AI strategies operationalized for value experienced around the corner.
activating growth in adjacent areas, and
a 3x increase in total return to shareholders over a
establishing new revenue lines. These forward-
5-year period.3
thinking leaders are embracing the paradigm
shift that AI represents. Rather than waiting
While cost optimization and efficiency have been AI’s
and monitoring the risk of disruption, they are
early business headliners, AI is proving its potential
taking proactive steps to find new growth and
to elevate competitiveness, expand markets, and
outmaneuver their competition.
deliver exponential growth for companies.
Companies that effectively adopt AI will find and
capture new growth opportunities across three
Going for growth: Navigating the great value migration in the age of AI 5
The legacy of
AI is already
being written
Going for growth: Navigating the great value migration in the age of AI 6
The persistent state of flux in which Business leaders and investors are also The excitement around AI is largely driven by
businesses now operate has become the expressing confidence in the enduring nature rapidly evolving consumer preferences and
of AI. Mentions of AI in corporate earnings calls behaviors (which often outpace businesses’
new normal. Recent Accenture research
have soared by 370% since late 2022.6 We ability to respond), and heightenend
found that the rate of change affecting
found that 75% of companies are prioritizing expectations for what AI will mean for them.
businesses has soared 183% in the past
investments in data and AI (up from 56% in early Consumers, already enjoying AI benefits
five years—and by 33% in just the past
2023).7 And evidence abounds in how venture through interactions with chatbots or receiving
year. Geopolitical tensions and trade
capitalists are placing their strategic bets, in the hyper-personalized offers from companies, now
skirmishes, inflation, and the speed of rapid rise of AI-related corporate technology expect their businesses to use AI to anticipate
technological advances are just a few of spending, and in the expanding talent market for their needs and help them make confident,
the factors with which CEOs need AI-related jobs: straightforward purchasing decisions—
something 75% of consumers now struggle
to contend.
• VC funding flowing into AI-related fields with.11 It’s no surprise that some business
tripled in the past decade and now leaders are rushing to use AI to deliver more
On top of all this is the uncertainty and debate
represents 14% of total corporate VC deals.8 engaging and relevant products, services, and
surrounding AI’s ultimate impact on business
experiences, reducing consumers’ decision-
performance. Many experts and economists
• 91% of executives believe their organizations making stress. They believe customer loyalty
are quite bullish on AI’s potential. They believe
will be ready to scale up generative AI will depend on it. And revenue growth will
AI is here to stay, representing a fundamental
technologies by the end of 2024.9 follow.
shift in how businesses operate, innovate and
compete. Some of these experts boldly predict,
• AI-related job postings have more than
for example, that AI will produce a 6.1% GDP uplift
doubled since 2019.10
in the United States by 2034.5
Going for growth: Navigating the great value migration in the age of AI 7
Beyond the
growing pains
Going for growth: Navigating the great value migration in the age of AI 8
For every industry expert, analyst and CEO of non-tech companies that have the greatest potential change, and find and deliver new value opportunities
that champions AI for growth, an equal to benefit from AI adoption have, in fact, under- that were previously hidden. For them, AI is more
performed the broader stock market.13 Given these than a response to current market conditions. It is a
number are skeptical. A recent headline
arguments, it’s understandable that some leaders are proactive strategy to gain the foresight needed to
from The Economist contributed to this
may question when AI will deliver the anticipated value navigate today’s uncertainties and activate entirely
sentiment by asking “What happened to
they seek. new growth models.
the artificial intelligence revolution?” as
its writers observed the limited economic
But it’s remarkable to observe, little more than a year
impact from the technology thus far.12 since the release of Chat GPT-4, the meteoric rise Savvy business leaders are turning
in investment in, consideration of and activity with
to AI to help them assess markets,
There are also observations that only 5% of generative AI and AI more broadly. The market activity
anticipate change, and find and
businesses consistently use AI and despite its suggests something far surpassing a gradual multi-
potential productivity per employee in developed year trend and companies would be wise to get off deliver new value opportunities
nations has remained flat. Additionally, share prices the sidelines. While AI’s overall value to businesses
that were previously hidden.
continues to be debated, savvy business leaders are
turning to AI to help them assess markets, anticipate
Going for growth: Navigating the great value migration in the age of AI 9
Navigating
the great
value migration
Going for growth: Navigating the great value migration in the age of AI 10
The historical value that came Nearly half (45%) of executives In fact, Accenture’s latest research reveals that
from refining business models nearly 45% of executives say they are using AI
are using AI extensively to explore
extensively for new product and service ideas, to
and optimizing ways of working
new product and service ideas,
identify new markets, to scale innovation across
pales in comparison to the value
identify new markets, scale multiple enterprise systems and for other strategy-
available to organizations that
related decision making. These leaders are giving
innovation and improve their
use AI wisely. In the age of AI,
reason for others to believe in the power of AI.
business growth is no longer solely a strategic decision making.
More importantly, they are providing a path to
function of how well companies can follow, beyond the hype, to deliver value and find
continually strengthen their core new growth.
business capabilities or operating
Companies that make strategic investments
models. While it is true that AI can
Early-movers can innovate to address unmet
in AI such as these are able to pursue growth
accelerate those critical activities, needs and expand into new and adjacent
opportunities in three critical ways: by amplifying
it does so much more. It adds more markets—and do so with increased organizational
and accelerating core business capabilities and
certainty to the bets that leaders velocity. Companies with the AI maturity to shape
assets; by expanding reach into adjacent growth
and activate their growth strategies can free
place. It lowers barriers to market
areas; and by activating new and entrepreneurial
themselves from endless offering development
entry. And it allows businesses to
revenue models.
and testing cycles. This means they can
extend traditional markets and
deliver business outcomes faster. For example,
unlock thousands of new revenue-
generative AI is accelerating the time to market
generating opportunities. In short, it
for early adopters in consumer goods by 25-50%.
is radically changing where value is
found. And how it is pursued.
Going for growth: Navigating the great value migration in the age of AI 11
All of these pursuits are under way today, often simultaneously within individual companies. Each is
underpinned by a strong digital core (see sidebar). Where these opportunity areas differ is in the scale of
Creating a digital core that
benefits they can deliver and the time horizon over which full value is realized. Each horizon promises to
unlock exponentially more top-line value than the one prior (see Figure 2). powers growth
As AI ushers in a new era of growth, companies
need to take three actions to ensure their digital
core is reinvention ready.
Figure 2: Companies using AI to pursue growth across three horizons are best positioned to reap the
exponential rewards AI and gen AI offer.
Build an industry-leading digital core. Companies
that achieve “industry-leading” levels of digital
prowess in platforms, cloud, data, AI and other
capabilities can expect to achieve a 20% acceleration
Growth Entrepreneurs
of revenue growth and a 30% boost in profitability.
AI initiatives focused on launching entirely
new offerings and revenue models,
reshaping industry value chains and Boost investments in innovation. Digital leaders
delivering disproportionate growth
continuously increase the proportion of their IT
budgets dedicated to strategic innovation (in
Growth Expanders areas such as generative AI). Shifting just 6% in
spending from maintenance to innovation is a
AI initiatives focused on the pursuit of
adjacencies and of finding new ways to recipe for success.
reach new customers
Balance tech debt with investments. AI has
Growth Amplifiers become a leading contributor to technical debt. To
AI initiatives focused on enhancing the manage this debt, leading companies allocate 15% of
core business and generating incremental
their IT budget toward debt remediation, which allows
revenue now from existing customers
them “pay down debt” without sacrificing
their strategic investments.
Source: Accenture analysis; estimates percentage range of companies in each horizon 1) in 2024 and 2) in 3-5 years.
Going for growth: Navigating the great value migration in the age of AI 12
Growth
Amplifiers
Opportunity to accelerate the core business with AI.
The most immediate and obvious growth horizon involves using AI to amplify and accelerate the core
business. Companies pursuing these opportunities are growing their top-line revenues by reaching
underserved market segments and better anticipating the needs of existing buyers. For companies that use
AI to strengthen consumer engagement, it is a vital part of the connected front-office team, putting formerly
hidden or ignored information to work with interactions that are more personalized, engaging, profitable and
ultimately more human.
Take the example of food service giant Sysco. The company is using generative AI to boost revenues by
not only optimizing its merchandising and product assortment capabilities, but also providing shopping
recommendations.14 Then there’s Best Buy, which is improving satisfaction and loyalty by using AI to transcribe
and summarize contact center calls, equip call center agents with all the resources they need to address
customers’ needs, and even automate personalized follow-ups.15
Going for growth: Navigating the great value migration in the age of AI 13
Where it’s working
Banking on happy customers
Global financial services group BBVA has made By combining first-party data with new data
wise and targeted investments in AI, cloud and sources to deliver a step-by-step view of the
data to create a data-driven, engaging and customer journey, BBVA’s new digital sales
differentiated customer experience. Its decision model helps the bank prioritize sales initiatives
to use digital technologies to reach people in for new customers and cross-sell to existing
new ways resulted in a staggering 117% growth customers. Their strategy and investments
in new customers in the last few years and a have had massive, positive impact including
profit of more than €8 billion ($8.6 billion) in acquiring more than 11 million new customers in
2023, the highest earnings in the bank’s history. 2023 and experiencing a 100% growth in digital
sales over the last four years.
These results would not have been possible had
the bank not consistently invested in its digital
“Providing a differentiated, better
core, harnessing the power of cloud, data and
experience was like discovering a
AI to facilitate the rapid development of new
capabilities and insights. For example, bank- pot of gold.”
wide data, predictive analytics and business
intelligence deliver a holistic view of the current — David Puente, Global Head of Client
and lifetime profitability—and likely behavior—of Solutions, BBVA
every customer.
Going for growth: Navigating the great value migration in the age of AI 14
Growth
Expanders
Opportunity to pursue adjacencies with AI.
The second growth horizon for AI offers businesses the opportunity to expand into new markets and/or pursue
industry-adjacent value. Here, AI helps companies activate, reposition and extend their existing intellectual
property, assets and services in more market-relevant ways or develop new, connected, service-rich and
outcome-based solutions.
Retailers, for example, have developed new, high-margin revenue streams with their retail media networks.
They are using AI to bring together first-party data, attribution models, digital and in-store media platforms, and
strong brand relationships to target and reach shoppers in new ways. Target has already turned such media
platforms into a billion-dollar business, with other retailers on track to quickly pass this milestone as well.16 And
infrastructure company Equinix has partnered with Nvidia to offer secure “Private AI” to allow for on-premise AI
compute as a managed service.17
Going for growth: Navigating the great value migration in the age of AI 15
Where it’s working
Tapping into new opportunities
Ecolab, a global leader in water, hygiene Integrating AI into customer outreach, advisory
and energy technologies, has shifted from and briefing processes enables Ecolab to
selling traditionally discrete products such as extend its reach with existing customers and
detergents and water-treatment chemicals accelerate growth.
to connected digital solutions in multiple
areas—from water management and predictive “AI has enabled the Field to
maintenance to remote monitoring of systems
make decisions and it ensures
and processes.
their on-the-ground insights are
AI has played a big role in supporting Ecolab’s not lost within the organization.
digital reinvention, as well as its efforts to
We’ve seen [that translate into]
extend its reach and accelerate growth.
hundreds of millions of dollars
AI-enabled market analysis tools have, for
example, helped the company create a new of value creation and value
market-relevant customer value proposition for
potential.”
digital services that is currently being rolled out
in the market. Equally important, AI is making — Kevin Doyle, Chief Digital Officer,
it possible for sales teams and engineers to
Ecolab
tap 100 years of expertise to better meet
and anticipate customer needs and to tailor
programs for distinct customers.18
Going for growth: Navigating the great value migration in the age of AI 16
Growth
Entrepreneurs
Opportunity to activate new revenue models with AI.
Horizon three encompasses the most profound growth opportunities for companies. Companies making their
moves in this space employ AI to activate new and entrepreneurial revenue models at unprecedented speed.
These are the opportunities that have the greatest potential to reshape industry value chains and deliver
disproportionate growth over time. As just one example, consider the potential for life sciences companies to
reinvent healthcare. Johnson & Johnson (J&J) MedTech is aggressively pursuing new AI capabilities in general
surgery. Working with Nvidia, the company is already scaling AI solutions that accelerate access to real-time
insights, enable open innovation, and improve decision-making, education and collaboration across the
connected operating room.19
The truth is that companies in virtually all industries are already starting to explore how they might use AI to
activate new revenue models and innovations. Long development cycles previously made such models and
innovations impractical. AI makes them not only practical, but also critical enablers and accelerators of new and
sustainable growth.
Going for growth: Navigating the great value migration in the age of AI 17
Where it’s working
Revolutionizing beauty, creativity and growth
L’Oréal, the world’s leading beauty company, age. And by leveraging science and technology,
is using advanced science, data, AI and it is developing new innovations and pursuing
generative AI to connect more personally with new opportunities that will enable growth and a
customers and deliver transformative beauty sustainable competitive edge.20, 21
innovations that answer its customers’ unmet
needs. By integrating advanced technologies “L’Oréal is no longer simply
into its products and services, the company has
a company selling cosmetics
activated a shift from “beauty for all” to “beauty
products, but products and
for each.”
services.”
This move has not only enabled ultra
— Béatrice Dautzenberg, Global Director
personalized customer experiences, but also
of Beauty Tech Services, L’Oréal22
allowed the company to develop and monetize
a host of augmented products, smart devices,
mobile apps, online platforms and digital
services. From new AI-powered assistants
and diagnostic tools to handheld devices that
enable people to enjoy salon-quality hair color
at home, L’Oréal is re-imagining beauty in the AI
Going for growth: Navigating the great value migration in the age of AI 18
Going for growth
across all horizons
Going for growth: Navigating the great value migration in the age of AI 19
Unprecedented business uncertainty, market
disruptions and technological advances are forcing
business leaders to rethink their legacy revenue
models and their approaches to strategic business
Hyper-personalized Rapid market
planning. AI and Gen AI, employed in the right
ways, offer a promising path forward. Leaders can products, services and assessments
anticipate market movements and quickly connect experiences for adjacencies
with stakeholders in new ways. They can identify
emerging growth opportunities, value pools and
even risks with greater certainty. And they can
quickly activate new programs to drive exponential
and sustainable growth.
To take advantage of AI’s growth
potential across all horizons, we
recommend leaders take action in
Dynamic Generative
four key opportunity areas today:
planning design
for perpetual for product
growth engine development and
innovation
Going for growth: Navigating the great value migration in the age of AI 20
01 Generate hyper-personalized experiences to expand
the core
One of the most effective ways to strengthen a
business’s core revenue-generating activities
involves developing hyper-personalized products,
Actions for leaders
services and experiences that cater to unique
preferences and needs. By maximizing the
• Build a strong data foundation that aggregates and analyzes data
relevance of their existing offerings, business
and enables generative AI to gain a deeper, real-time understanding of
leaders can increase customer satisfaction and stakeholder needs, preferences and value drivers.
lifetime value, achieve higher margins and enjoy
better market positioning. • Integrate generative AI into various touchpoints to help customers
throughout their journey, from early in their decision-making to follow-ups
that build lifetime loyalty.
Generative AI is a critical enabler for amplifying and
accelerating the core business. It provides the tools needed
• Continually monitor and optimize the performance of AI-driven
to analyze vast amounts of data, identify patterns, and create
personalization initiatives and use data-driven insights to refine them
personalized campaigns, recommendations and solutions
based on changing market dynamics.
that resonate with target audiences.
Going for growth: Navigating the great value migration in the age of AI 21
02 Generate rapid market assessments to find adjacencies
and extend reach
Leaders must also identify growth opportunities in
adjacent areas or among untapped market segments.
Using existing assets and new outcome-based
Actions for leaders
solutions are two important ways companies can
extend their reach beyond their core businesses.
• Use generative AI to aggregate and analyze data from diverse
sources to capture the voice of the market and uncover underserved or
Once again, generative AI can be invaluable to leaders looking
overlooked segments, trends and opportunities that may not be visible
to capitalize on such industry-adjacent growth opportunities. By
through traditional methods.
leveraging advanced AI capabilities, business leaders can generate
rapid market assessments to quickly analyze emerging trends,
• Apply generative AI to identify and evaluate adjacent markets that
determine market potential and discover new market
present opportunities for expansion and diversification. Generative AI is
segments, even in areas with limited data or insights. The
particularly well suited to simulate various market scenarios and assess
technology excels at processing vast amounts of data—from
the potential impact of different strategies.
market reports to social media trends to economic indicators—to
identify patterns and correlations that may not be immediately
• Establish ongoing AI-driven market assessments to keep track of
apparent. Such insights pave the way for leaders to set up and test
evolving trends and emerging opportunities. This proactive approach
new offerings, pricing structures or routes to market.
ensures that the business remains agile and can quickly capitalize on new
growth areas.
Going for growth: Navigating the great value migration in the age of AI 22
03 Leverage generative design to create new products
and services
Sixty percent of executives say it takes their company one
year or more to adapt to changing customer needs. In a world
in which expectations shift on a month-to-month basis, many
Actions for leaders
initiatives might become obsolete before they are even rolled
out. To meet continuously evolving demands, leaders need
• Examine all possible AI-fueled opportunities to create new revenue models, no
to develop new revenue models and launch new AI-driven
matter how ambitious or farfetched they may originally appear. Use AI to analyze
products, services and experiences at breakneck speed. market trends and human behaviors, identifying opportunities for new revenue
streams, with a clear view of ROI and an actionable plan to scale.
Generative AI, with its powerful generative design capabilities, makes it
possible for leaders to pioneer these new frontiers. For example, generative • Cultivate a portfolio of growth opportunities that balances potential returns,
AI can revolutionize the way companies approach product development feasibility and risk, and investments in talent and resources that will be needed to
and business model innovation. By leveraging advanced algorithms and bring each to fruition.
machine learning, AI can create countless design permutations, optimize
for specific parameters, and uncover novel solutions that humans might not • Leverage AI’s generative design capabilities to explore a wide range of design
easily envision. This capability allows companies to rapidly prototype and possibilities, accelerate the development process, rapidly prototype solutions, and
iterate new ideas, reduce time to market, and foster a culture of continuous refine and optimize products/services for performance, cost and sustainability,
innovation.
Beyond physical products, generative AI can help businesses activate
new revenue models—such as subscription services, pay-per-use
schemes, or all-digital offerings—tailored to evolving market dynamics and
technological advances.
Going for growth: Navigating the great value migration in the age of AI 23
04 Introduce dynamic planning to create a perpetual
growth engine
Regardless of the growth opportunities business leaders
pursue, they must utilize dynamic strategic planning
capabilities to navigate complexities and ensure a
Actions for leaders
perpetual growth engine is in place. Static and even
“rolling” strategic plans are no longer adequate. The
• Incorporate generative AI in the strategic planning process to help
pace of change companies face and the speed with
carry out continuous market assessments, scenario planning and
which they must react to (or anticipate) market forces forecasting—and to pressure test the most relevant opportunities.
demands an always-on approach. Continually adjust plans to align to shifting macro and market forces.
Enabled by a strong digital core, generative AI is fast becoming • Build a culture of adaptation in which people are willing to change and
indispensable in the creation of the adaptive strategic plans that embrace innovation. This involves communicating new insights and
are now needed. By harnessing vast amounts of historical data and strategic scenarios with key stakeholders to encourage leaders to seek
analogues, generative AI helps business leaders understand market new ways to create value.
forces and relationships in real time. It enables leaders to expand
their sphere of understanding to not only identify new value pools, • Establish a perpetual growth engine with a cross-functional value
but also model scenarios and launch growth initiatives at speed and navigation team that uses generative AI to actively monitor market
scale. Importantly, it also differentiates valuable market signals from dynamics, vet strategies, prioritize key initiatives and optimize results.
noise, helping to ensure that strategic decisions are based on high-
quality insights rather than extraneous data. The result? Informed
decisions that drive success.
Going for growth: Navigating the great value migration in the age of AI 24
Sustainable growth
is there for the taking
The unforgiving pace of change in the world today presents
a tremendous challenge for CEOs and other C-suite leaders.
But it also creates exciting opportunities for companies that
can proactively translate those challenges into sustained
competitive advantage and new growth. Until now, sustaining
value amid constant disruption has been difficult. But AI now
makes it possible.
Growth opportunities abound. Those that successfully pursue
them will think differently about the growth opportunities
before them—and how to find them and pursue them. They
will arm their organizations with new innovation capabilities.
And they will embrace AI as a key enabler of agility and
adaptability across the end-to-end growth lifecycle. Other
CEOs should follow their lead.
Going for growth: Navigating the great value migration in the age of AI 25
References
1 2024 S&P Dow Jones Indices, June 20, 2024. 12 “What happened to the artificial-intelligence revolution?” The Economist, July 6,
2 AI maturity was evaluated using Accenture’s AI Index. This index incorporates 2024.
more than 30 individual metrics sourced from more than 10 diverse data sets, 13 ibid
encompassing a broad spectrum of industries, and spanning more than 2000 14 Beth Stackpole, “Incorporating generative AI into your company’s technology
large companies worldwide. The index framework encompasses not only AI- strategy,” MIT Sloan School of Management, February 27, 2024.
related metrics but also the vital capabilities essential for companies to foster and 15 Best Buy, “How Best Buy is using generative AI to create better customer support
scale their AI endeavors: Strategic AI signaling, AI assets, Tech foundations, and experiences,” April 9, 2024.
Talent & Culture enablers. The 0-100 AI index reflects the company’s percentile 16 David Doty, “Walmart, Target and Other Mega-Retailers Leverage First-Party to
ranking position in its industry. The Top AI Index includes companies in the top Become new Media Giants,” Forbes, April 26, 2022.
quartile, and the Bottom AI Index includes companies in the bottom quartile. 17 Equinix, “Equinix Private AI with NVIDIA DGX—Turnkey, ready-to-run AI
Revenues have been adjusted by inflation to ensure comparability across time. development platform.”
3 Accenture Research analysis, 2024. Period 2017-2022. 18 Chris Stokel-Walker, “How one water-management company is using AI to unlock
4 Arielle Feger, “CEOs expect efficiency, cost savings from generative AI by 2025,” insights from its 100-year past,” Business Insider, June 18, 2024.
eMarketer, July 5, 2024. 19 Johnson & Johnson, “Johnson & Johnson MedTech working with NVIDIA to scale
5 Allison Nathan (ed.), “Gen AI: Too much spend, too little benefit?” Goldman Sachs AI for surgery,” March 18, 2024.
Global Investment Research (Issue 129), June 25, 2024. 20 L’Oréal, “L’Oréal accelerates Beauty Tech leadership with advanced bioprinted
6 Accent |
85 | accenture | Accenture-A-New-Era-of-Generative-AI-for-Everyone.pdf | A new era of
generative AI
for everyone
The technology underpinning
ChatGPT will transform work
and reinvent business
Table of 03
Welcome to AI’s new inflection point
Contents
04
How did we get here? | Milestones in the journey to generative AI
05
Consume or customize: Generative AI for everyone
08
A look ahead at the fast-paced evolution of technology, regulation and business
12
Embrace the generative AI era: Six adoption essentials
19
The future of AI is accelerating
21
Glossary and References
22
Authors
A new era of generative AI for everyone | 2
Introduction
Welcome to AI’s new inflection point
ChatGPT has woken up the world to A foundation model is a generic term for Business leaders recognize the significance
the transformative potential of artificial large models with billions of parameters. With of this moment. They can see how LLMs
intelligence (AI), capturing global attention recent advances, companies can now build and generative AI will fundamentally
and sparking a wave of creativity rarely seen specialized image- and language-generating transform everything from business, to
before. Its ability to mimic human dialogue models on top of these foundation models. science, to society itself—unlocking new
and decision-making has given us AI’s first Large language models (LLMs) are both performance frontiers. The positive impact
true inflection point in public adoption. a type of generative AI and a type of on human creativity and productivity will be
Finally, everyone, everywhere can see the foundation model. massive. Consider that, across all industries,
technology’s true disruptive potential for Accenture found 40% of all working hours
themselves. The LLMs behind ChatGPT mark a significant can be impacted by LLMs like GPT-4. This
turning point and milestone in artificial is because language tasks account for 62%
intelligence. Two things make LLMs game of the total time employees work, and 65%
ChatGPT reached 100 million monthly changing. First, they’ve cracked the code on of that time can be transformed into more
active users just two months after launch, language complexity. Now, for the first time, productive activity through augmentation
making it the fastest-growing consumer
machines can learn language, context and and automation (see Figure 3).
application in history.1
intent and be independently generative and
creative. Second, after being pre-trained
on vast quantities of data (text, images or
audio), these models can be adapted or fine-
tuned for a wide range of tasks. This allows
them to be reused or repurposed in many
different ways.
A new era of generative AI for everyone | 3
How did we
Machine learning: Analysis and prediction phase
The first decade of the 2000s marked the rapid advance viewed machine learning as an incredibly powerful field
get here?
of various machine learning techniques that could analyze of AI for analyzing data, finding patterns, generating
massive amounts of online data to draw conclusions – insights, making predictions and automating tasks at a
or “learn” – from the results. Since then, companies have pace and on a scale that was previously impossible.
Milestones in the journey
Deep learning: Vision and speech phase
to generative AI
The 2010s produced advances in AI’s that search engines and self-driving cars use
perception capabilities in the field of machine to classify and detect objects, as well as the
learning called deep learning. Breakthroughs voice recognition that allows popular AI speech
in deep learning enable the computer vision assistants to respond to users in a natural way.
Generative AI: Enter the language-mastery phase
Building on exponential increases in the size and phase in the abilities of language-based AI applications. Models
capabilities of deep learning models, the 2020s will be such as this will have far-reaching consequences for business,
about language mastery. The GPT-4 language model, since language permeates everything an organization does day to
developed by OpenAI, marks the beginning of a new day—its institutional knowledge, communication and processes.2
A new era of generative AI for everyone | 4
Consume or
customize:
Generative AI
for everyone
A new era of generative AI for everyone | 5
Consume or customize: Generative AI for everyone
Consume or customize: Generative AI for everyone
Easy-to-consume generative AI applications like We’re at a phase in the adoption cycle when
ChatGPT, DALL-E, Stable Diffusion and others are most organizations are starting to experiment
rapidly democratizing the technology in business by consuming foundation models “off the shelf.”
and society. The effect on organizations will be However, the biggest value for many will come
profound. The ability of LLMs to process massive when they customize or fine tune models using
data sets allows them to potentially “know” their own data to address their unique needs:
everything an organization has ever known—the
entire history, context, nuance and intent of a Consume
business, and its products, markets and customers. Generative AI and LLM applications are ready to
Anything conveyed through language (applications, consume and easy to access. Companies can
systems, documents, emails, chats, video and audio consume them through APIs and tailor them, to
recordings) can be harnessed to drive next-level a small degree, for their own use cases through
innovation, optimization and reinvention. prompt engineering techniques such as prompt
tuning and prefix learning.
97% of global executives agree AI Customize
foundation models will enable connections But most companies will need to customize
across data types, revolutionizing where models, by fine-tuning them with their own data,
and how AI is used.3 to make them widely usable and valuable. This will
allow the models to support specific downstream
tasks all the way across the business. The effect
will be to increase a company’s efficacy in using
AI to unlock new performance frontiers—elevating
employee capabilities, delighting customers,
introducing new business models and boosting
responsiveness to signals of change.
A new era of generative AI for everyone | 6
Consume or customize: Generative AI for everyone
Companies will use these models to reinvent the Creating. Generative AI will become an essential Automating. Generative AI’s sophisticated
way work is done. Every role in every enterprise creative partner for people, revealing new ways understanding of historical context, next
has the potential to be reinvented, as humans to reach and appeal to audiences and bringing best actions, summarization capabilities, and
working with AI co-pilots becomes the norm, unprecedented speed and innovation in areas like predictive intelligence will catalyze a new era
dramatically amplifying what people can achieve. In production design, design research, visual identity, of hyper-efficiency and hyper-personalization
any given job, some tasks will be automated, some naming, copy generation and testing, and real- in both the back and front office—taking
will be assisted, and some will be unaffected by the time personalization. Companies are turning to business process automation to a transformative
technology. There will also be a large number of state-of-the-art artificial intelligence systems like new level. One multinational bank is using
new tasks for humans to perform, such as ensuring DALL·E, Midjourney and Stable Diffusion for their generative AI and LLMs to transform how it
the accurate and responsible use of new social media visual content generation outreach. manages volumes of post-trade processing
AI-powered systems. DALL·E, for example, creates realistic images and emails—automatically drafting messages with
art based on text descriptions and can process up recommended actions and routing them to the
Consider the impact in these key functions: to 12 billion parameters when transforming words recipient. The result is less manual effort and
into pictures. Images created can then be shared smoother interactions with customers.
Advising. AI models will become an ever-present
on Instagram and Twitter.5
co-pilot for every worker, boosting productivity Protecting. In time, generative AI will support
by putting new kinds of hyper-personalized Coding. Software coders will use generative AI to enterprise governance and information security,
intelligence into human hands. Examples include significantly boost productivity — rapidly converting protecting against fraud, improving regulatory
customer support, sales enablement, human one programming language to another, mastering compliance, and proactively identifying
resources, medical and scientific research, programming tools and methods, automating code risk by drawing cross-domain connections
corporate strategy and competitive intelligence. writing, predicting and pre-empting problems, and inferences both within and outside the
Large language models could be useful in and managing system documentation. Accenture organization. In strategic cyber defense, LLMs
tackling the roughly 70% of customer service is piloting the use of OpenAI LLMs to enhance could offer useful capabilities, such as explaining
communication that is not straightforward and developer productivity by automatically generating malware and quickly classifying websites.6
can benefit from a conversational, powerful and documentation – for example, SAP configuration In the short term, however, organizations can
intelligent bot, understanding a customer’s intent, rationale and functional or technical specs. The expect criminals to capitalize on generative AI’s
formulate answers on its own and improve the solution enables users to submit requests through capabilities to generate malicious code or write
accuracy and quality of answers.4 a Microsoft Teams chat as they work. Correctly the perfect phishing email.7
packaged documents are then returned at speed —
a great example of how specific tasks, rather than
entire jobs, will be augmented and automated.
A new era of generative AI for everyone | 7
A look ahead at the
fast-paced evolution
of technology,
regulation and
business
A new era of generative AI for everyone | 8
A look ahead at the fast-paced evolution of technology, regulation and business
A look ahead at the fast-paced evolution of technology, regulation and business
Moments like this don’t come around often.
The coming years will see outsized investment
Figure 1: Each layer of the generative AI tech stack will rapidly evolve
in generative AI, LLMs and foundation models.
What’s unique about this evolution is that the
technology, regulation, and business adoption
Applications: Generative AI and LLMs will be increasingly
are all accelerating exponentially at the same
accessible to users in the cloud via APIs and by being embedded
time. In previous innovation curves, the
directly into other applications. Companies will consume them
technology typically outpaced both adoption
as they are or will customize and fine-tune them with proprietary
and regulation.
data.
The technology stack Fine-tuning: The importance of model fine-tuning will create
demand for a multidisciplinary set of skills spanning software
The complex technology underpinning engineering, psychology, linguistics, art history, literature and
generative AI is expected to evolve rapidly library science.
at each layer. This has broad business
Foundation models: The market will rapidly mature and diversify
implications. Consider that the amount of
as more pre-trained models emerge. New model designs will
compute needed to train the largest AI models
offer more choices for balancing size, transparency, versatility and
has grown exponentially – now doubling
performance.
between every 3.4 to 10 months, according to
various reports.8 Cost and carbon emissions Data: Improving the maturity of the enterprise data lifecycle
are therefore central considerations in will become a prerequisite for success – requiring mastery of
new data, new data types and immense volumes. Generative AI
adopting energy-intensive generative AI.
features within modern data platforms will emerge, enhancing
adoption at scale.
“The hottest new programming
Infrastructure: Cloud infrastructure will be essential for deploying
platform is the napkin.” generative AI while managing costs and carbon emissions. Data
Paul Daugherty, Accenture Group Chief Executive centers will need retrofitting. New chipset architectures, hardware
& Chief Technology Officer innovations, and efficient algorithms will also play a critical role.
Referring to the use of OpenAI to generate a working website
from a napkin drawing
A new era of generative AI for everyone | 9
A look ahead at the fast-paced evolution of technology, regulation and business
The risk and regulatory environment AI systems need to be “raised” with a diverse Figure 2: Key risk and regulatory questions for generative AI
and inclusive set of inputs so that they reflect
Companies will have thousands of ways to the broader business and societal norms of
apply generative AI and foundation models responsibility, fairness and transparency. When Intellectual property: How will the business protect its own
to maximize efficiency and drive competitive AI is designed and put into practice within an IP? And how will it prevent the inadvertent breach of third-party
advantage. Understandably, they’ll want to get ethical framework, it accelerates the potential copyright in using pre-trained foundation models?
started as soon as possible. But an enterprise- for responsible collaborative intelligence,
wide strategy needs to account for all the where human ingenuity converges with
Data privacy and security: How will upcoming laws like
variants of AI and associated technologies they intelligent technology.
the EU AI Act be incorporated in the way data is handled,
intend to use, not only generative AI and large
processed, protected, secured and used?
language models. This creates a foundation for trust with
consumers, the workforce, and society, and
ChatGPT raises important questions about the can boost business performance and unlock Discrimination: Is the company using or creating tools
responsible use of AI. The speed of technology new sources of growth. that need to factor in anti-discrimination or anti-bias
evolution and adoption requires companies considerations?
to pay close attention to any legal, ethical and
reputational risks they may be incurring.
Product liability: What health and safety mechanisms need
to be put in place before a generative AI-based product is
It’s critical that generative AI technologies,
taken to market?
including ChatGPT, are responsible and
compliant by design, and that models and
applications do not create unacceptable risk
Trust: What level of transparency should be provided to
for the business. Accenture was a pioneer in
consumers and employees? How can the business ensure the
the responsible use of technology including accuracy of generative AI outputs and maintain user confidence?
the responsible use of AI in its Code of
Business Ethics from 2017. Responsible AI is the
practice of designing, building and deploying Identity: When establishing proof-of-personhood depends on voice
AI in accordance with clear principles to or facial recognition, how will verification methods be enhanced and
improved? What will be the consequences of its misuse?
empower businesses, respect people, and
benefit society — allowing companies to
engender trust in AI and to scale AI with
confidence.
A new era of generative AI for everyone | 10
A look ahead at the fast-paced evolution of technology, regulation and business
The scale of adoption in business Figure 3: Generative AI will transform work across industries
Companies must reinvent work to find
Work time distribution by industry
a path to generative AI value. Business Banking 54% 12% 24% 10%
and potential AI impact
leaders must lead the change, starting
Insurance 48% 14% 26% 12%
now, in job redesign, task redesign and Based on their employment levels in the US in 2021
reskilling people. Ultimately, every role Software & Platforms 36% 21% 28% 15%
in an enterprise has the potential to Lower potential for
Capital markets 40% 14% 29% 18% Higher potential for Higher potential for augmentation or Non-language
be reinvented, once today’s jobs are automation augmentation automation tasks
decomposed into tasks that can be
Energy 43% 9% 14% 34%
automated or assisted and reimagined for
a new future of human + machine work. Communications & Media 33% 13% 21% 33%
Retail 34% 7% 12% 46%
Generative AI will disrupt work as
we know it today, introducing a new Industry Average 31% 9% 22% 38% 40% of working hours across
dimension of human and AI collaboration
industries can be impacted by
in which most workers will have a “co- Health 28% 11% 33% 27%
Large Language Models (LLMs)
pilot,” radically changing how work is
Public Service 30% 9% 35% 26%
done and what work is done. Nearly
every job will be impacted – some will Aerospace & Defense 26% 13% 20% 41%
Why is this the case? Language tasks account for 62% of total worked time
be eliminated, most will be transformed, in the US. Of the overall share of language tasks, 65% have high potential
and many new jobs will be created. Automotive 30% 6% 13% 50% to be automated or augmented by LLMs.
Organizations that take steps now to
High Tech 26% 8% 16% 50%
decompose jobs into tasks, and invest
in training people to work differently, Travel 28% 6% 15% 50%
alongside machines, will define new
Utilities 27% 6% 15% 52%
performance frontiers and have a big leg Source: Accenture Research based on analysis of Occupational
up on less imaginative competitors. Life Sciences 25% 8% 17% 50% Information Network (O*NET), US Dept. of Labor; US Bureau of
Labor Statistics.
Industrial 26% 6% 14% 54%
Nearly 6 in 10 organizations Notes: We manually identified 200 tasks related to language (out
Consumer Goods & Services 24% 6% 13% 57% of 332 included in BLS), which were linked to industries using their
plan to use ChatGPT for learning
share in each occupation and the occupations’ employment level
purposes and over half are Chemicals 24% 5% 14% 56% in each industry. Tasks with higher potential for automation can
planning pilot cases in 2023. be transformed by LLMs with reduced involvement from a human
Natural Resources 20% 5% 11% 64%
Over 4 in 10 want to make a worker. Tasks with higher potential for augmentation are those in
large investment.9 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% which LLMs would need more involvement from human workers.
A new era of generative AI for everyone | 11
Embrace the
generative AI era:
Six adoption
essentials
A new era of generative AI for everyone | 12
Embrace the generative AI era: Six adoption essentials
Dive in, with a Take a people- Get your Invest in a Accelerate Level-up your
business-driven first approach proprietary sustainable tech ecosystem responsible AI
mindset data ready foundation innovation
1 2 3 4 5 6
A new era of generative AI for everyone | 13
Embrace the generative AI era: Six adoption essentials
1
Dive in, with a business-driven mindset
Even when new innovations have obvious advantages,
diffusing them across an organization can be challenging,
especially if the innovation is disruptive to current ways of A bank uses enhanced search to equip
working. By experimenting with generative AI capabilities,
employees with the right information
companies will develop the early successes, change agents
and opinion leaders needed to boost acceptance and spread
the innovation further, kick-starting the transformation and
As part of its three-year innovation plan,
reskilling agenda.
a large European banking group saw an
Organizations must take a dual approach to experimentation.
opportunity to transform its knowledge
One, focused on low-hanging fruit opportunities using
consumable models and applications to realize quick returns. base, empower its people with access to
The other, focused on reinvention of business, customer
the right information, and advance its goal
engagement and products and services using models that
of becoming a data-driven bank. Using
are customized with the organization’s data. A business-
driven mindset is key to define, and successfully deliver on,
Microsoft’s Azure platform and a GPT-
the business case.
3 LLM to search electronic documents,
As they experiment and explore reinvention opportunities,
users can get quick answers to their
they’ll reap tangible value while learning more about which
types of AI are most suited to different use cases, since the questions — saving time while improving
level of investment and sophistication required will differ
accuracy and compliance. The project,
based on the use case. They’ll also be able to test and
which included employee upskilling, is
improve their approaches to data privacy, model accuracy,
bias and fairness with care, and learn when “human in the the first of four that will apply generative
loop” safeguards are necessary.
AI to the areas of contract management,
conversational reporting and ticket
98% of global executives agree AI foundation
classification.
models will play an important role in their
organizations’ strategies in the next 3 to 5 years.10
A new era of generative AI for everyone | 14
Embrace the generative AI era: Six adoption essentials
Figure 4: Generative AI will transform work across every job category
2
Take a people-first approach
Office and Administrative Support 57% 6% 14% 23% Work time distribution by major
Success with generative occupation and potential AI impact
Sales and Related 49% 13% 14% 24%
AI requires an equal attention on
Based on their employment levels in the US in 2021
people and training as it does on Computer and Mathematical 28% 32% 23% 17%
technology. Companies should
Business and Financial Operations 45% 14% 35% 6%
therefore dramatically ramp up Lower potential for
Higher potential for Higher potential for augmentation or Non-language
investment in talent to address Arts, Design, Entertainment, Sports, and Media 25% 26% 26% 22% automation augmentation automation tasks
two distinct challenges: creating
Life, Physical, and Social Science 27% 20% 25% 28%
AI and using AI. This means
both building talent in technical
Architecture and Engineering 21% 24% 25% 30%
competencies like AI engineering
and enterprise architecture Legal 33% 9% 58% 0%
and training people across the
Occcupation Average 31% 9% 22% 38% In 5 out of 22 occupation
organization to work effectively
groups, Generative AI can
with AI-infused processes. In our Management 30% 9% 44% 17%
analysis across 22 job categories, affect more than half of all
Personal Care and Service 29% 8% 31% 32%
for example, we found that hours worked
LLMs will impact every category, Healthcare Practitioners and Technical 22% 15% 40% 22%
ranging from 9% of a workday at
Community and Social Service 29% 7% 59% 6%
the low end to 63% at the high
end. More than half of working Healthcare Support 27% 8% 31% 34%
hours in 5 of the 22 occupations
Protective Service 29% 6% 23% 43%
can be transformed by LLMs.
Educational Instruction and Library 23% 8% 50% 19%
Food Preparation and Serving Related 25% 5% 9% 61% Source: Accenture Research based on analysis of Occupational
Information Network (O*NET), US Dept. of Labor; US Bureau of Labor
Transportation and Material Moving 23% 4% 7% 66%
Statistics.
Construction and Extraction 15% 4% 7% 75%
Notes: We manually identified 200 tasks related to language (out
Installation, Maintenance, and Repair 16% 1%9% 75% of 332 included in BLS), which were linked to industries using their
share in each occupation and the occupations’ employment level
Farming, Fishing, and Forestry 8% 8% 17% 66%
in each job category. Tasks with higher potential for automation can
be transformed by LLMs with reduced involvement from a human
Production 14% 2% 8% 76%
worker. Tasks with higher potential for augmentation are those in
Building and Grounds Cleaning and Maintenance 9% 0% 7% 84% which LLMs would need more involvement from human workers.
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
A new era of generative AI for everyone | 15
Embrace the generative AI era: Six adoption essentials
2
In fact, independent economic research indicates that
companies are significantly underinvesting in helping
workers keep up with advances in AI, which require Figure 5: Reinventing a customer service job, task by task
more cognitively complex and judgment-based tasks.11
Even domain experts who understand how to apply
To assess how specific jobs will be reinvented with AI, an Accenture analysis decomposed
data in the real world (a doctor interpreting health data,
one customer service job into 13 component tasks. We found:
for example) will need enough technical knowledge of
how these models work to have confidence in using
them as a “workmate.”
4
There will also be entirely new roles to recruit, including tasks would continue to be performed
linguistics experts, AI quality controllers, AI editors, primarily by humans, with low potential
and prompt engineers. In areas where generative for automation or augmentation.
AI shows most promise, companies should start by
decomposing existing jobs into underlying bundles of
tasks. Then assess the extent to which generative AI
might affect each task — fully automated, augmented, 4 tasks could be fully automated —
or unaffected. such as gathering, classifying, and
summarizing information on why a
customer is contacting the company.
5
tasks could be augmented to help
humans work more effectively — such
as using an AI summary to provide a
rapid solution with a human touch.
Importantly, new job tasks might also be needed to ensure the safe, accurate and responsible use of
AI in customer service settings, such as providing unbiased information on products and pricing.
A new era of generative AI for everyone | 16
Embrace the generative AI era: Six adoption essentials
3 4
Get your proprietary data ready Invest in a sustainable tech foundation
Customizing foundation models will require Companies need to consider whether they have the
access to domain-specific organizational data, right technical infrastructure, architecture, operating
semantics, knowledge, and methodologies. In the model and governance structure to meet the high
pre-generative AI era, companies could still get compute demands of LLMs and generative AI, while
value from AI without having modernized their keeping a close eye on cost and sustainable energy
data architecture and estate by taking a use-case consumption. They’ll need ways to assess the cost
centric approach to AI. That’s no longer the case. and benefit of using these technologies versus other
Foundation models need vast amounts of curated AI or analytical approaches that might be better
data to learn and that makes solving the data suited to particular use cases, while also being
challenge an urgent priority for every business. several times less expensive.
Companies need a strategic and disciplined As the use of AI increases, so will the carbon
approach to acquiring, growing, refining, emissions produced by the underlying infrastructure.
safeguarding and deploying data. Specifically, they Companies need a robust green software
need a modern enterprise data platform built on development framework that considers energy
cloud with a trusted, reusable set of data products. efficiency and material emissions at all stages of the
Because these platforms are cross-functional, with software development lifecycle. AI can also play a
enterprise-grade analytics and data housed in cloud- broader role in making business more sustainable
based warehouses or data lakes, data is able to break and achieving ESG goals. Of the companies we
free from organizational silos and democratized for surveyed that successfully reduced emissions in
use across an organization. All business data can production and operations, 70% used AI to do it.12
then be analyzed together in one place or through a
distributed computing strategy, such as a data mesh.
Read more on the practices data-mature
companies are using to maximize enterprise
data value: A new dawn for dormant data:
Unleash the intrinsic value of enterprise
data with a strong digital core on cloud.
A new era of generative AI for everyone | 17
Embrace the generative AI era: Six adoption essentials
5 6
Accelerate ecosystem innovation Level-up your responsible AI
Creating a foundation model can be a complex, The rapid adoption of generative AI brings fresh urgency
compute-intensive and costly exercise. And for to the need for every organization to have a robust
all but the very largest global companies, doing it responsible AI compliance regime in place. This includes
entirely on their own will be beyond their means controls for assessing the potential risk of generative AI
and capabilities. The good news is that there is a use cases at the design stage and a means to embed
burgeoning ecosystem to call on, with substantial responsible AI approaches throughout the business.
investments by cloud hyperscalers, big tech players, Accenture’s research suggests most companies still
and start-ups. Global investment in AI startups have a long way to go. Our 2022 survey of 850 senior
and scale-ups is estimated to exceed $50 billion in executives globally revealed widespread recognition
2023 alone.13 These partners bring best practices of the importance of responsible AI and AI regulation.
honed over many years, and can provide valuable But only 6 percent of organisations felt they had a fully
insights into using foundation models efficiently robust responsible AI foundation in place.
and effectively in specific use cases. Having the
right network of partners—including technology An organization’s responsible AI principles should be
companies, professional services firms and academic defined and led from the top and translated into an
institutions—will be key to navigating rapid change. effective governance structure for risk management
and compliance, both with organizational principles
and policies and applicable laws and regulations.
Responsible AI must be CEO-led, beginning with a focus
on training and awareness and then expanding to focus
on execution and compliance. Accenture was one of the
first to take this approach to Responsible AI years ago,
with a CEO-led agenda, and now a formal compliance
program. Our own experience shows that a principles-
driven compliance approach provides guardrails while
being flexible enough to evolve with the fast pace
of changing technology, ensuring companies aren’t
constantly playing “catch up.”
To be responsible by design, organizations need to move
from a reactive compliance strategy to the proactive
development of mature Responsible AI capabilities
through a framework that includes principles and
governance; risk, policy and control; technology and
enablers and culture and training.
A new era of generative AI for everyone | 18
The future of AI
is accelerating
A new era of generative AI for everyone | 19
The future of AI is accelerating
This is a pivotal moment. For several years, Businesses are right to be optimistic about the
generative AI and foundation models have been potential of generative AI to radically change how
quietly revolutionizing the way we think about work get done and what services and products
machine intelligence. Now, thanks to ChatGPT, they can create. They also need to be realistic
the whole world has woken up to the possibilities about the challenges that come with profoundly
this creates. rethinking how the organization works, with
implications for IT, organization, culture, and
While artificial general intelligence (AGI) remains responsibility by design.
a distant prospect, the speed of development
continues to be breathtaking. We’re at the start of Companies need to invest as much in evolving
an incredibly exciting era that will fundamentally operations and training people as they do in
transform the way information is accessed, technology. Radically rethinking how work gets
content is created, customer needs are served, done, and helping people keep up with technology-
and businesses are run. driven change, will be two of the most important
factors in realizing the full potential of this step-
Embedded into the enterprise digital core, change in AI technology.
generative AI, LLMs, and foundation models will
optimize tasks, augment human capabilities, and Now’s the time for companies to use
open up new avenues for growth. In the process, breakthrough advances in AI to set new
these technologies will create an entirely new performance frontiers—redefining themselves
language for enterprise reinvention. and the |
86 | accenture | Accenture-Art-AI-Maturity-GM.pdf | The art of AI maturity
Advancing from practice to performance
Growth Markets
Asia Pacific, Africa, the Middle East, and Latin America
From insights to action, the path to extraordinary value starts here.
Contents
Foreword Executive AI maturity: AI maturity: AI Achievers How AI Practice Appendix
summary Why it What it is advance Achievers makes
matters from master their progress
practice to craft
performance
03 04 06 09 14 17 29 35
The art of AI maturity—Growth Markets 2
The art of AI maturity – a Growth Markets perspective
Foreword
As artificial intelligence technologies is still evolving. Within the Growth Markets, They design AI responsibly, from the start. nearly double (to 32%) by 2024 in Growth
become more prevalent, some the AI maturity is picking up pace with 5. They prioritize long and short-term markets.
organizations will lead the change, and 17% of companies are what we call “AI AI investments. In the report, we delve
others will be fast followers. With growing Achievers”—that is, they leverage AI’s full deeper into each of these success factors. Because high-performance today will
confidence in AI as a value driver, we potential. become business-as-usual tomorrow,
see companies in Asia Pacific, Africa, the In most cases the right intentions are yet there’s an impetus to move quickly and
Middle East, and Latin America (Growth In this report, we look at what the AI to be converted into actions. While most move now.
Markets) evolving and maturing along with Achievers are doing right. Our findings companies have begun their Responsible
the technology itself. demonstrate that Achievers are not AI journey, the majority (94%) are yet to
defined by the sophistication of any operationalize across all key elements of
Also, governments in these markets, one capability, but by their ability to Responsible AI. To move from principles to
including China, Singapore, and India, combine strengths across strategy, practice, organizations need a structured
have announced ambitious national processes, and people by scaling AI. The approach to be responsible by design.
AI strategies. In the Middle East, AI is five ways in which AI Achievers master
at the center of all national economic their craft are — 1. Their top leaders We hope that the ‘Art of AI maturity’
development plans over the next few champion AI as a strategic priority for will serve as an inspiration for business
years. the entire organization. 2. They invest leaders to pave the way for a successful
Senthil Ramani
heavily in talent to get more from their AI AI maturity journey for their enterprises.
Senior Managing Director,
While AI continues to attract board level investments. 3. They industrialize AI tools With the strong industry momentum, we Growth Markets, Applied
attention and investment, the AI maturity and teams to create a strong AI core. 4. project the number of AI Achievers, to Intelligence
The art of AI maturity—Growth Markets 3
Executive summary
In fewer than 70 years, artificial intelligence (AI) has evolved
from a scientific concept to a societal constant.
17%
Today, so much of what we take for Another 30% of firms are somewhat In short, advancing AI maturity is no
granted in our daily lives, from travel to advanced in their level of AI maturity, longer a choice. It’s an imperative for
shopping, relies on machine learning (ML). while the remaining 53% (the majority) are every industry, every organization and
Companies across industries are investing merely testing the waters. every leader.
in AI to drive logistics, improve customer of firms have advanced
service, increase efficiency, empower This decades-long journey to AI maturity
their AI maturity enough
53%
employees and so much more. is now in high gear. Even pre-pandemic
to achieve superior
(2019), AI Achievers already enjoyed 56%
performance and growth.
Like their peers in developed economies, greater revenue growth, on average,
few organizations in Growth Markets compared with their peers. And in 2021,
(GMs) are capitalizing on AI’s full potential. executives who discussed AI on their of firms are still
earnings calls were 96.7% more likely to
testing the AI waters.
According to our analysis of approximately see their firms’ share prices increase—up
500 companies in GMs, only 17% of firms from 64.2% in 2018.
have advanced their AI maturity enough
to achieve superior growth and business
transformation. We call them the
“AI Achievers.”
The art of AI maturity—Growth Markets 4
What do AI Achievers do differently?
While there’s clearly a science to AI, our findings demonstrate there is also an art to
AI maturity. Achievers are not defined by the sophistication of any one capability,
but by their ability to combine strengths across strategy, processes and people.
Here are five ways AI Achievers master their craft:
1. Their top leaders champion AI as a strategic priority
for the entire organization.
2. They invest heavily in talent to get more from their
AI investments.
3. They industrialize AI tools and teams to create
a strong AI core.
4. They design AI responsibly, from the start.
5. They prioritize long- and short-term AI investments.
Our machine learning models suggest that the share of AI Achievers will increase
rapidly and significantly, more than doubling from the current 17% to 32% by 2024.
In short, advancing AI maturity is no longer a choice. It’s an opportunity facing every
industry, every organization and every leader.
The art of AI maturity—Growth Markets 5
The art of AI maturity
AI maturity: Why it matters
AI maturity: Why it matters
Figure 1: We project that AI transformation will take less time than digital transformation
There is a growing consensus that AI is
essential to competitive advantage.
In 2021, 46% of CEOs mentioned AI on • 38% of companies said the return
their earnings calls—when they did, their on their AI initiatives exceeded their
share prices were 96.7% more likely to expectations (compared to 42%
increase. globally). Only 2% said the ROI did not
meet expectations.
In Growth Markets specifically:
AI, accelerated
• 67% of companies have integrated
AI into their business strategies and
reworked their cloud plans to achieve AI is now widely considered a value
AI success. driver. We estimate AI transformation will
happen much more quickly than digital
transformation—on average, 16 months
faster (Figure 1). Source: Accenture Research
Note: Our estimate is derived from a natural language processing analysis of investor calls of
the world’s 2,000 largest companies (by market cap), from 2010 to 2021, that referenced “AI”
and “digital” in tandem with “business transformation,” respectively. Data was sourced from S&P
earnings transcripts.
The art of AI maturity—Growth Markets 7
There’s great incentive to move quickly. We found, Figure 2: Evolution of companies' AI-influenced revenue share from 2018 to 2024*
for example, that the share of company revenue that
33%
is “AI-influenced” more than doubled between 2018
and 2021 and is expected to roughly triple by 2024
(Figure 2). In response, companies plan to increase
and accelerate their AI investments. In 2021, 21%
of companies dedicated more than 30% of their
tech budgets to AI development. By 2024, 49% of
companies intend to do the same.
Note: Color indicates the achieved AI-influenced revenue threshold within each time period.
Source: Accenture Research
Note: *2024 = projected, N = 585
*Definition of “AI-influenced” revenues:
a. Sales of existing products and services made possible through better AI-driven insights on customers, supply chain, channels; b. Sales
of new products and services made possible by human + AI , c. Higher prices through dynamic pricing ML algorithms. These sales include
some cannibalization and net new revenues. In contrast, this definition is excluding higher efficiencies in production operations thanks to AI.
The art of AI maturity—Growth Markets 8
The art of AI maturity
AI maturity: What it is
AI maturity: What it is
We designed a holistic AI maturity framework to
uncover common strategies for AI success.
AI maturity measures the
Fittingly, our analysis itself was conducted not only in data and AI, but also in
using AI. We applied machine learning organizational strategy, talent and culture.
degree to which organizations
(ML) models to unravel massive survey (See pages 37 and 38 for key
datasets and uncover drivers of AI capabilities descriptions.)
have mastered AI-related
maturity that would have been impossible
to detect using more traditional analytical This includes foundational AI
capabilities in the right
methods. (More on the methodology in capabilities—like cloud platforms and
the Appendix.) tools, data platforms, architecture and combination to achieve high
governance—that are required to keep
performance for customers,
Our research found that AI maturity pace with competitors. It also includes
gives companies a strong competitive “differentiation” AI capabilities, like
shareholders and employees.
advantage. Unlocking this advantage AI strategy and C-suite sponsorship,
comes down to mastering a set of key combined with a culture of innovation that
capabilities in the right combinations— can set companies apart.
The art of AI maturity—Growth Markets 10
The companies that scored best in both Figure 3: Only 17% of organizations are AI Achievers
categories are what we call “AI Achievers.”
Meanwhile, “AI Builders” show strong
foundational capabilities and average
differentiation capabilities, while “AI Innovators”
show strong differentiation capabilities and
average foundational capabilities. Trailing these vs. 13% (Global) vs. 12% (Global)
cohorts are a fourth group we’re calling “AI
Companies struggling Companies that are capitalizing
to materialize their the power of AI by building
Experimenters”—those with average capabilities
AI strategy on strong foundation and
a differentiated strategy
in both categories.
In Growth Markets, Achievers accounted for
17% of all firms surveyed, Builders for 18% and
Innovators for 12%. Together, Achievers, Builders,
and Innovators represent 47% of surveyed
organizations—10% higher than their combined
global representation (37%). AI Experimenters
make up the majority (53%) (Figure 3).
vs. 63% (Global) vs. 12% (Global)
The marjority of companies Companies with strong AI
without strong AI foundations foundations but unclear
and clear AI strategy differentiation strategy
Source: Accenture Research analysis based on a sample of 1,200 global companies and 491 are from Growth Market
The art of AI maturity—Growth Markets 11
AI, applied
Figure 4: Levels of AI maturity by industry, 2021 and 2024*
While industries like tech are currently far In other industries, a range of factors
ahead of others in AI maturity, the gap may be contributing to relatively low AI
will likely narrow considerably by 2024. maturity. Financial Services institutions, for
In fact, there’s growing demand for AI example, still struggle to move projects
in the life sciences industry, due to the into production and scale AI across the
presence of top research institutions in organization. Meanwhile, healthcare
Growth Markets, rising investments in organizations have been slow to adapt to
the research studies of various diseases, the AI transformation. But many are either
and accelerated advancements in drug experimenting with or actively pursuing
discovery and delivery. In addition, various AI-enabled tools to bridge the huge gaps
airlines and airport authorities in Growth in resources and meet challenges created
Markets are increasingly investing in AI by rapidly aging societies (Figure 4).
for airport safety, predicting flight arrivals
more accurately, customer service
chatbots, operational efficiency, etc.
N = 516 | Source: Accenture Research analysis based on a sample of 1,200 global companies and 491
are from Growth Market
Note: *2024 = estimated scores. Industries’ AI maturity scores represent the arithmetic average of
their respective Foundational and Differentiation index.
The art of AI maturity—Growth Markets 12
AI, applied across industries
• A Middle East-based telecom • One coral conservatory used AI for • The third-largest bank in Thailand • A large holding company leveraged
operator uses an AI-driven reef restoration. Its cost-effective used AI to unlock the value of data to AI for workforce transformation. AI
bilingual virtual assistant to handle edge computing solution and enhance experiences for consumers, and ML models were used to match
approximately 1.5 million customer strategically placed underwater smart optimize operations and fuel future professional skillsets to specific
interactions—in both Arabic and cameras allowed for non-invasive growth. Their ongoing, multi-year company roles. Turns out 55% of
English—across multiple channels observations, from tracking the transformation journey combines recruits were matched with optimal
each month. migration of fish to colder climates advanced data and analytics positions, increasing performance
to monitoring illegal fishing in capabilities with people-focused and retention by 3X.
protected waters. processes and tools.
• A large chemicals and energy firm
is using drones and AI-powered • A leading Indonesian telecom
computer vision to monitor its • One of the world’s largest metals and • A leading Japanese cosmetic company deployed a best-in-class
equipment and remote locations. mining companies wanted to enable company used data and AI-driven AI-powered virtual agent for cost-
The upshot: More frequent intelligent, value-driven decision- insights to track marketing ROI, optimization and improving customer
inspections at lower cost to the making across its commercial gauge shifts in consumer behavior satisfaction scores.
company and fewer safety risks for ore value chain. The company’s in a post-pandemic world and drive
its maintenance workers. AI engagement resulted in better strategy for sales growth.
• A leading retail company leveraged
detection of possible disruptions
data and AI to create differentiated
in supply chains and a proactive
propositions for their brands.
approach to recovery planning.
Within nine months, they scaled
the business resulting in $10M from
new revenue streams. It’s aiming to
achieve a $25M incremental revenue
target by 2025.
The art of AI maturity—Growth Markets 13
The art of AI maturity
AI Achievers advance from
practice to performance
AI Achievers advance from
Figure 5: AI Achievers outperform in nearly all capabilities
practice to performance
Achievers Builders Innovators Experimenters
AI Achievers are going above and beyond, deploying AI
solutions to solve problems and identify new opportunities.
So it’s no surprise they thrive when it They are not defined by the sophistication
comes to traditional performance metrics. of any one capability, but by their ability
Pre-pandemic, they already enjoyed to combine strengths across strategy,
56% greater revenue growth on average, processes and people.
versus their peers. And today, they’re 3.7
times more likely than Experimenters to In comparison, Innovators typically excel
see their AI-influenced revenue exceed at securing senior sponsorship and
30% of their total revenues. embrace training for all employees, but
What sets the AI Achievers apart? they lack the foundational capabilities
required to support AI at scale.
Builders, on the other hand, excel at
Mastery of multitasking
creating data and AI platforms, but they
When compared with all other groups, AI tend to be weaker at cultivating AI fluency
Achievers demonstrate high performance and the innovation culture that is needed
across a combination of capabilities. to drive adoption. (Figure 5)
Source: Accenture Research
Note: Each cube represents one of the 17 key capabilities. The cube is highlighted when the AI profile is
outperforming against peers (higher than the average across all companies in terms of % of companies
reaching the mature level).
The art of AI maturity—Growth Markets 15
Turning pilots into production
Figure 6: Achievers excel at turning AI pilots into production
Achievers have largely moved beyond the AI investment
“tipping point,” going from experimenting with new AI in
isolation to applying AI at scale to solve critical business
problem (Figure 6). Achievers are 36% more likely to scale AI
pilots across the enterprise compared with Experimenters.
A multinational telecom company with a major market
in Japan was facing the challenge of unsubscribing users.
They wanted to drive data-led transformation for improving
efficiency and driving business growth. They also aimed at
strengthening their team of data scientists by upskilling their
existing workforce and hiring talent.
A joint venture company was established to help their
business challenges. The joint venture created end-to-end
data infrastructure across their business and enable them to
scale it with cloud migration. The company leveraged data-
led transformation to create hyper-personalized offers for
clients and drive business growth. Combining data scientist
training and analytics & BI environment we were also able to
upskill their team and create a future-ready workforce.
Source: Accenture Research
Note: Score 0-100, ranging from 0 = AI use case not started, 50 = AI use in early stage, 100 = having AI programs in place for
full productization. The chart shows the difference in terms of average score for AI use cases of different functions, between
Achievers and other firms. Those differences are statistically significant after controlling for industry, geography, and company
size; see Appendix for more details.
The art of AI maturity—Growth Markets 16
The art of AI maturity
How AI Achievers
master their craft
Five success factors
How AI Achievers
master their craft
It’s worth noting that the potential for
AI-mature organizations will evolve
along with the technology itself. High
performance today will ultimately become
business-as-usual tomorrow.
Today’s AI Achievers have set the standard
and are poised to remain leaders. While
science is at the center, they’ve shown us
there is also an art to AI maturity.
They have demonstrated that excellence
in areas like vision and culture are just
as critical as algorithmic integrity. Our
research uncovered five key success
factors for AI Achievers.
The art of AI maturity—Growth Markets 18
Success Factor 01
Champion AI as a strategic priority
for the entire organization, with full
sponsorship from leadership
Companies can create strong AI Our research also suggests that the
strategies, but unless those strategies best AI strategies tend to be bold, even
receive enthusiastic support from the when they have modest beginnings.
CEO and the rest of the C-suite, they’re Bold AI strategies help spur innovation.
likely to flounder. For CEOs of Achievers, creating a
culture of innovation is itself a deliberate,
Achievers are more likely to have formal strategic move—one that is used as a
senior sponsorship for their AI strategies. vehicle for experimentation and learning
We found that 86% of Achievers in across the organization. In fact, 59% of
Growth Markets have such sponsorship, Achievers embed innovation in their
while only 60% of Builders and just 56% organization’s strategies, while just 33%
of Experimenters have it. of Experimenters do.
The art of AI maturity—Growth Markets 19
For instance, Lendlease Digital (part of questions and share ideas with colleagues
multinational Lendlease Group) hopes across the company—compared to 6% of
to produce architectural blueprints for Experimenters. That number will only grow
buildings using generative design and AI, as these companies hire more AI talent.
then use those blueprints to manufacture
actual buildings in factories—fitting
together all the pieces like LEGO sets. The
86%
company’s bold vision starts at the top, led
by the CEO of Lendlease Digital,
William Ruh.
To encourage such end-to-end innovation,
Achievers implement systems and of Achievers have
structures that help employees showcase
CEO and senior
their innovation experiments and seek
sponsorship.
constructive feedback from leadership.
For instance, Achievers tend to be the
first to embrace new tools that encourage
their employees to experiment and
innovate. We found that 25% of Achievers
in Growth Markets are already using
platforms that allow workers to easily pose
The art of AI maturity—Growth Markets 20
Success Factor 02
Invest heavily in talent to get more
from AI investments
With a clear AI strategy and strong CEO We also found that 56% of Achievers in
sponsorship, organizations are more likely Growth Markets have employees with
to invest heavily in creating data and AI consistently high AI skills competencies,
fluency across their workforces. while Innovators (42%) and Experimenters
(35%) have significantly fewer such
We found that 76% of Achievers— employees, on average. Achievers also
compared with 66% of Builders and develop proactive AI talent strategies to
59% of Experimenters—have mandatory stay at the forefront of industry trends.
AI trainings for most employees, from In addition to hiring, this can mean
product development engineers to partnering with or acquiring specialist
C-suite executives. Because Achievers companies to fill critical roles (such
prioritize efforts to build AI literacy in their as data or behavioral scientists, social
workforces, their employees are also more scientists and ethicists). It also means
proficient in AI-related skills. This makes it having a plan to get these diverse,
easier to scale human-AI collaboration. multidisciplinary workers to collaborate,
create and sustain maximum value from
the company’s data-science capabilities.
The art of AI maturity—Growth Markets 21
What does this look like in practice?
Japanese e-commerce giant Rakuten digital fluency. It also created a cloud-
established an “AI Promotion Department” based performance reviewer that
54%
in 2016 to accelerate efforts to infuse scrutinized a decade’s worth of employee
AI into the company’s 70+ diverse data to recommend workers best suited
businesses. By 2018, the department for various digital roles. The innovation
helped turn more than 30 AI pilot projects saved the firm’s HR department significant
into successful offerings. time filling positions. It also reduced
scope for managerial bias in promotional of Achievers in Growth
And a leading Southeast Asian oil and decisions and helped workers assess and
Market have employees with
gas firm built an AI-powered, “gamified” close digital-skills gaps.
consistently high AI skills
learning platform to expand employees’
competencies, while Innovators
(42%) and Experimenters (35%)
have significantly fewer such
employees, on average.
The art of AI maturity—Growth Markets 22
Success Factor 03
Industrialize AI tools and
teams to create an AI core
Another priority for Achievers is building domain experts and systems engineers.
an AI core: An operational data and AI To build AI cores, Achievers harness
platform that taps into companies’ talent, the power of internal and external data,
technology and data ecosystems, allowing making that data trustworthy and storing
firms to balance experimentation and it in a single enterprise-grade cloud
execution. An AI core helps organizations platform—complete with appropriate
productize their AI applications and usage, monitoring and security policies.
integrate the technology into
other applications. To extract value from their data quickly
and effectively, Achievers in Growth
An AI core also works across the Markets are also 43% more likely, on
cloud continuum (from migration to average, than Experimenters to either
innovation), provides end-to-end data develop custom-built, machine-learning
capabilities (foundation, management applications or work with a partner that
and governance), manages the machine offers solutions-as-a-service. Achievers
learning lifecycle (workflow, model are also more likely than Innovators
training, model deployment) and to use AI for innovation, tapping into
provides self-service capabilities. AI readily available developer networks that
cores are, in turn, managed by dedicated can swiftly productionize and scale
interdisciplinary teams of machine successful pilots.
learning engineers, data scientists, data
The art of AI maturity—Growth Markets 23
To strengthen their AI cores, Achievers often
collaborate with external experts to stay
on top of breakthroughs in science and
engineering. In 2020, for example, American
Express partnered with the Indian Institute
of Technology Madras to create a Data
Analytics, Risk and Technology laboratory at
the prestigious university. Such innovation
ecosystems help Achievers develop AI apps
tailored specifically to their needs.
A leading Indian bank deployed AI at scale
to achieve higher growth and efficiencies
across multiple verticals, such as retail
and SMB, liquidity & risk management,
wealth management and more. It identified
priorities and devised a roadmap including
strategy, technology & infrastructure, and
talent. With an enterprise-wide data lake and
AI/ML platform, as well as a robust literacy
program, they were able to leverage the
value of data and AI across the organization.
The art of AI maturity—Growth Markets 24
Success Factor 04
Design AI responsibly, from the start
Adhering to laws, regulations and ethical compliance is a company-wide priority.
norms is critical to building a sound In fact, many organizations view AI
data and AI foundation. The potential for regulation as a boon rather than a
regulatory changes in many countries barrier to success.
makes the challenge even more daunting.
The ability to demonstrate high-quality,
In a separate Accenture study of 850 trustworthy AI systems that are “regulation
C-suite executives, we sought to gauge ready” will give first movers a significant
attitudes toward AI regulation and assess advantage in the short- and long-term,
organizations’ readiness to comply. enabling them to attract new customers,
Nearly all (99%) respondents believed retain existing ones and build
that regulation would impact them to investor confidence.
some extent, while 81% indicated that
The art of AI maturity—Growth Markets 25
Achievers are consciously applying Yet MAS was also wary of the threat posed
responsible AI with greater urgency than to firms and markets by the illegal and/or
their peers. In Growth Markets, they are unethical use of AI. It helped launch the
on average 36% more likely than Builders Veritas initiative, which aims to support
and 64% more likely than Innovators to the responsible use of AI in the finance
be responsible by design. This means industry. The effort has produced a
Even though only 8%
Achievers are designing, developing and practical methodology and first-of-its-
deploying AI that empowers employees kind toolkit that offers detailed guidance of the companies surveyed
and businesses, and impact customers on how to use AI leveraging the FEAT
and society fairly. principles—fair, ethical, accountable had already implemented
and transparent.
responsible AI practices, 42%
For instance, The Monetary Authority of
Singapore (MAS), the country’s central
of surveyed companies aspire
bank and financial regulator, recognized
the benefits that AI can provide to
to do so by the end of 2024.
financial firms.
The art of AI maturity—Growth Markets 26
Success Factor 05
Prioritize long- and short-term
AI investments
To avoid being left behind, most For example, the Saudi government’s
In 2018, Achievers
companies need to aggressively increase National Center for Artificial
their spending on data and AI. One reason Intelligence is on a mission to unlock
in Growth Markets
Achievers in Growth Markets get more out the value of data and AI as a national
devoted 15% of their of AI is simply because they invest more asset to fulfill the larger digital vision of
in it. We found that in 2018, Achievers the country. The center accelerated the
total technology budgets
devoted 15% of their total technology development of AI capabilities in priority
budgets to AI, while in 2021 they devoted sectors like energy, healthcare, agriculture
to AI. In 2021, that rose
29%. In 2024, they plan to devote 36%. and government—and it will play a pivotal
to 29%. By 2024, they role in the execution of the country’s
national AI strategy. Early returns have
Achievers also understand that their AI
expect to devote 36%.
been so successful that the Kingdom of
investment journey doesn’t have a finish
Saudi Arabia will allocate the strategy a
line. There is, they frequently note, no
budget of $20 billion by 2030.
“peak AI.” These companies know they
have only scratched the surface of their
AI transformations and that the quality of
their investments matters just as much
as the quantity. For Achievers, continued
investment largely involves expanding the
scope of AI to deliver maximum impact,
while “cross-pollinating” AI solutions and
redeploying resources in the process.
The art of AI maturity—Growth Markets 27
We project the share of
AI Achievers in Growth
Markets to nearly double
(from 17% to 32%) by 2024.
28
The art of AI maturity—Growth Markets
The art of AI maturity
Practice makes progress
Practice makes progress
The concept of using AI to solve business problems isn’t new.
The concept of using AI to solve business technology. As much about strategy as it subjected to it. Those who transform
problems isn’t new. By 2019, there was is about implementation. As much about will be the ones whose teams master
evidence that scaling AI beyond proofs responsibility as it is about agility. the art of AI maturity, using cloud as the
of concept had a significant impact enabler, data as the driver and AI as the
on ROI. Then the pandemic hit. For Every organization should be assessing differentiator.
many organizations, enterprise-wide its own AI maturity. To get started, Figure
transformation was a matter of survival. 7 has some sample questions for C-suite How can AI help you differentiate?
For others, it became a catalyst to thrive. leaders, according to Accenture’s AI
maturity assessment. There are also tools
AI Achievers in Growth Markets are available to help benchmark AI maturity
thriving. Across industries, they’ve moved and establish clear paths to progress and
past cloud migration to innovation. performance.
But the AI itself isn’t the secret to their
superior performance—it’s how they’re As AI technologies become more
approaching AI that makes them different. prevalent, the future of all businesses
They’ve established that AI maturity is going to look very different—some
is as much about people as it is about will lead the change, and some will be
The art of AI maturity—Growth Markets 30
Figure 7: AI maturity assessment: sample questions for C-suite leaders
Category Key questions
Does your C-suite have clear accountability for data and AI strategy and execution?
•
How do you identify potential value, and how are business cases prioritized—considering the potential risks and alignment
•
Strategy and Sponsorship with the overall strategy of the organization?
Are you allocating enough delivery resources to build AI products and services in-house, and are you able to get the most
•
out of your ecosystem partners?
To what extent do you have a cloud platform and technology strategy that supports your AI strategy?
•
Do you have an effective, enterprise-wide data platform, as well as strong data management and governance practices,
Data and AI Core •
to meet business needs?
Are you using data science and machine learning teams effectively across the lifecycle of AI development?
•
Is your data- and AI-literacy strategy aligned to your business objectives?
•
To what extent have you prioritized data and AI fluency for senior leaders, business stakeholders and employees across
•
your organization?
Talent and Culture
Do you have a holistic talent model to scale, differentiate, retain and develop AI talent (diverse, dedicated teams of
•
machine learning engineers, data scientists, data-domain experts and data engineers)?
How are you institutionalizing a data and AI culture within your organization?
•
Do you have an enterprise-wide framework to help you operationalize responsible data and AI from principles to practice?
•
Are you applying a consistent and industrialized responsible data and AI approach across the complete lifecycle of all
•
Responsible AI
your AI models?
Are you methodically tracking the evolution of AI-related laws and regulations across the different jurisdictions in which you
•
operate, while anticipating and preparing for future changes?
Source: Accenture Research
The art of AI maturity—Growth Markets 31
Meet the authors Resea |
87 | accenture | Accenture-Tech-Vision-2025.pdf | Technology Vision 2025
AI: A Declaration
of Autonomy
Is trust the limit of
AI’s limitless possibilities?
Technology Vision 2025 | AI: A Declaration of Autonomy Foreword 2
AI: A Declaration Welcome to our Technology Vision for 2025. This enabler to acting autonomously on behalf of We believe we can. We see this new age of
25th edition of our annual technology trends report people--equipping them with the capability to technology as an opportunity to inject trust in
of Autonomy
arrives at a watershed moment for technology and perform new tasks and perform others better than AI in a systematic manner so that businesses
humanity. As more and more leaders embrace the ever. Consider the possibilities and opportunities to and people can realize its incredible reinvention
Is trust the limit of AI's
need to continuously reinvent using tech, data reinvent as AI finds its way into new and unfamiliar potential. Together, we can prepare now for
limitless possibilities?
and AI, they, now more than ever, need a deep territories. To truly understand and take advantage a bold future when AI is autonomous and helps
understanding of AI. Why? Because the rate of AI’s of this potential, enterprises will be creating their us achieve more together.
technology diffusion is unprecedented and the own, unique AI cognitive digital brains that will
pace is only increasing—creating new opportunities completely reshape the role technology plays
for reinvention across the enterprise—including across their enterprise and with their people. This
new ways of achieving efficiencies, operating will dramatically upend how enterprise tech systems
the core of businesses, new business models are designed, used and operated; act as a brand
and new ways of engaging with customers. ambassador; and inhabit in the physical world by Julie Sweet Karthik Narain
powering robotic bodies. And when AI is spread Chair and CEO Group Chief Executive
of Technology and CTO
We view AI as the new digital because, like digital, across an organization, it enables people and AI to
it is both a technology and a new way of working. bring out the best in each other.
We believe it will be used in every part of the
enterprise and it will have a network effect on Leaders are aware of the challenges to creating
everything and everyone involved. Its impact this future, which include high up-front
is already real, and as companies continue to investments in their core technologies, data
scale AI—and use generative AI as a catalyst for centricity and quality, and talent and new skills.
reinvention—it will solve new problems, create And chief among these challenges is trust.
new inventions, change how we work and live,
and transform industries and governments. Our research finds that 77% of executives believe
unlocking the true benefits of AI will only be
Accenture research shows that only 36% of possible when it’s built on a foundation of trust.
executives say their organizations have scaled Leaders must build trust in digital systems and
gen AI solutions, and just 13% report achieving the AI models, with customers and the workforce
significant enterprise-level impact. We are by ensuring accuracy, predictability, consistency
actively equipping them to do it faster and more and traceability over and above the responsible
safely as we see 2025 as the year of scaled AI. use of AI. People’s trust in AI that it will perform as
expected and justly—beyond any technical aspect—
This year’s Technology Vision explores a future is an essential component that we must get right.
when AI transitions from being an automation
Technology Vision 2025 | AI: A Declaration of Autonomy Contents 3
Contents
Introduction
AI: A Declaration 01 The Binary Big Bang 02 Your Face, in the Future 03 W hen LLMs get 04 The New Learning Loop
of Autonomy their Bodies
Is trust the limit of AI's When AI expands exponentially, Differentiating when every interface How foundation models How people and AI are defining
limitless possibilities? systems are upended looks the same reinvent robotics a virtuous cycle of learning, leading,
and creating
Page 04-08 Page 09-21 Page 22-33 Page 34-46 Page 47-58
Technology Vision 2025 | AI: A Declaration of Autonomy Introduction 4
AI: A Declaration
on Artificial General Intelligence (AGI).2,3 And like
of Autonomy before, the race has captivated business leaders,
governments, and the world at large.
Is trust the limit of AI's
But it’s a red herring—a distraction most business
limitless possibilities?
leaders can’t afford. Someday, AGI will be hugely
consequential, but today it’s still far away with deep
technical and ethical challenges to address. Instead,
it’s vitally important that leaders see the far more
We are entering a new chapter
pressing matter already here: the generalization of
in technology—one shaped by
artificial intelligence, which will bring a new level of
a generalization of AI. Today’s autonomy and capability to enterprises’ systems,
workforces, and operations long before AGI comes
proliferation of accessible and
into play.
ever-present AI will drive new
levels of autonomy all throughout The Generalization of AI
the business, evolving the ability
To understand this generalization of AI, one simply
to reinvent with tech, data and
needs to look around and see how rooted AI is
AI. It will bring nearly limitless becoming in our lives. It’s been nearly 30 years
since Kasparov’s game, and now models that could
possibilities for innovation
make Deep Blue look like an average player are
and growth, but also challenge
sitting in everyone’s pockets. The Turing Test, once
enterprises’ confidence in systems considered the loftiest benchmark for machine
intelligence, is effectively broken every day by
and the way they think about trust.
conversations people have with Large Language
Model (LLM)-backed customer service bots and
The rush of an AI race is undeniable. sales agents. Today’s AI models have shrugged off
the deep but specific and linear approaches of the
We’ve seen it before. In 1997, Garry Kasparov past and are demonstrating more autonomy than
lost a six-game chess match against IBM’s Deep ever—in how they learn, approach tasks, and in
Blue.1 It was the first time a computer ever beat what they ultimately can do. And they’re bringing
a chess grandmaster, after decades of testing this autonomy to work, where 75% of knowledge
machine capability against humans using this workers report using generative AI; to how we
game. The victory set off a storm of excitement interact with technology, as a coding copilot and
and questions about AI and the future. Now, a by expanding voice assistant capabilities; and to
new race is underway. Many companies building nearly everything else, from robotics, to cars, to
today’s cutting-edge AI models have their sights set health care.4,5,6,7,8,9,10 Highly capable advanced AI
Technology Vision 2025 | AI: A Declaration of Autonomy Introduction 5
is diffusing across every dimension of our lives, What will the world look like as wide proliferation industries, it may look like the common framework society will uplift the world to the next level of
instantly accessible, and—effectively—always there. brings it to every dimension of our lives? It seems and communications protocol between companies capability, performance, and progress. It will spur
inevitable that as leaders start to combine their in an industry, or engines codifying the grand an evolution towards a world enhanced at all levels
This is the real disruption to focus on. Because right AI generalization efforts, they will soon enhance challenges that shape an industry—models that by AI cognition, and generate an unprecedented
now, even as executives race to implement this new and empower individuals, drive and help operate will help grow our understanding of things like wave of autonomy that will reshape technology and
generation of AI, few are looking past the separate enterprises, radically reshape industries and even physics, genetics, movement, and more. And for businesses as we know them.
pieces to truly understand the scope of what they uplift nation states. countries and governments, it brings together
are actually building: AI “cognitive digital brains” the unique knowledge, language, culture, laws, A first thought may be that this is exclusively a
that will completely reshape the role technology Take Insilico Medicine, a pharmaceutical company, and security to help industries, companies, and transition from automation using AI to autonomy
plays across the enterprise and people’s lives. which used generative AI to go from discovery citizens engage. Critically, these cognitive digital in digital systems. It’s not wrong, but it’s only part
to phase one trials of a drug in under 30 months, brains won’t operate in silos. When they begin to of the story—AI is powering autonomy in dozens
What leaders have to fully grasp is that the singularly around half the time it usually takes.11 They used interact at all levels, they will create a rising tide of of ways. It’s giving people access to skills they
most important feature of AI is its ability to learn. one model fine tuned on omics and clinical data intelligence that elevates the capabilities of every wouldn’t otherwise possess, letting them act
When AI becomes generalized, and as enterprises to identify potential targets for drug therapy. To party involved. with more initiative and less friction than before.
diffuse it across the business and people adopt it develop possible drug compositions, they used a It’s giving robots a new degree of context and
into their lives, it has the potential to become much generative chemistry engine that consisted of 500 This is why it is a “declaration of autonomy.” reasoning about the world, allowing them to take
more than just the new features and capabilities it predictive and pre-trained models. For Insilico, AI is We may call them different things, but across the on a wider and more complex range of tasks and,
provides. Enterprises aren’t merely empowering the at the very heart of what they do—shaping the very range the evolution is the same: the prolifieration most importantly, co-mingle with humans like never
workforce, creating a new channel for customer business and industry around it. of autonomous AI systems happening across before. And of course, agentic and multi-agent AI
service, or automating parts of their operations.
They are taking a technology that comes with broad A Cognitive Digital Brain at Every Level
general knowledge and is intrinsically defined by
What makes a Cognitive Digital Brain?
its ability to learn and they are teaching it about It can be difficult to see this trend; at every layer of
parts of the business. And when people use scale it manifests slightly differently. But across the
it, they’re further teaching it about their likes, board, this next stage for AI will infuse enhanced The cognitive digital brain will become the central nervous system for enterprise decision-making
preferences, and needs. capability and increased autonomy into everything it and continuous learning. Used to power enterprises' future ambitions, like intention-based
touches. For individuals, the cognitive digital brain architectures, it is comprised of four interconnected layers that together organize, process,
If built intentionally, enterprises can take all the will operate as a co-pilot or sidekick, something that and act on information.
distributed AI efforts they are pursuing and build will understand their job, learn their preferences,
a cognitive digital brain. They can hard-code and get to know them through its interactions, in Knowledge: Technologies like knowledge graphs and vector databases gather, organize, and
workflows, institutional knowledge, value chains, service of helping them be an enhanced version structure data from across the enterprise and beyond.
social interactions, and so much other crucial data of themselves. For businesses, it might seem
about businesses and the world into a system that more like a central nervous system—an evolution Models: Large-scale generative AI models as well as classical ML and deep learning models
can understand—and increasingly act—at a higher of the enterprise architecture into something perform critical thinking and reasoning functions to turn data into actionable outcomes.
level than ever before. that can capture the collective knowledge of the
business, its unique differentiators, and its culture Agents: Designed to be problem-solvers, tackle tasks with minimal human input, and learn
What can a person do with this power? What can and persona, and become a key orchestrator (and and grow over time, AI agents bring planning, reflection, and adaptability to the mix.
a business do deploying it across the workforce? even autonomous operator) for parts of it. For
Architecture: A comprehensive backbone is what turns AI experiments into enterprise-grade
solutions. It scales intelligence across the organization and into existing workflows and enables
repeatability, so solutions can be made once and reused.
Technology Vision 2025 | AI: A Declaration of Autonomy Introduction 6
systems are starting to take on entire workflows or AI lies in how enterprise leaders choose to harness Until now, technology systems have been broadly Because it is impacted. To start—enterprises need
customer interactions without the need for constant the new dimensions of autonomy it enables. But rules-based. Though these systems are less to realize that with growing autonomy in their
human intervention, while maintaining strategic succeeding in this new world and making the right intelligent, they are highly predictable and thus technology systems, they need to think differently
oversight. Tapping into this autonomy will stretch choices will be no small task. Intrinsically married to more trustable. As a result, their adoption and about how much they trust these systems and
the limits on what businesses thought possible. the idea of autonomy is an underpinning of trust— diffusion across enterprises is widespread. So now, what guardrails they may need to impose. Sakana
Accenture research has found that with its ability to and for enterprises, it’s trust that will be the biggest as we look ahead to a world that will be defined AI, an AI research firm, perfectly demonstrated
reimagine and augment complex tasks, generative backstop to tomorrow’s growth. by technology systems that both have and create why while testing their new system called “The AI
AI is expected to drive productivity gains of 20% in greater autonomy, we’re looking at a future where Scientist.”14 The system autonomously conducts
companies leading in AI adoption.12 The Only Limit is Trust trust is the most important differentiator and scientific research using LLMs, and in one run, was
the determining factor to AI diffusion within an given a problem it couldn’t complete within the
What we have today is the spark for unbounded Think about how trust defines the human organization. After all, we can only let systems be as experiment’s set time limit, so adjusted its own code
growth and innovation—as well as disruption. As experience—the relationship between a parent autonomous as we trust them. to give itself more time. Sakana AI has pointed to
ever-greater autonomy reduces friction within and child, for instance. We surround babies with this act as creative, but also demonstrative of the
and between organizations, letting us get more guardrails. From literal ones, like those in a crib, But the ramifications of this are not as obvious fact that an AI model with the ability to bypass a set
done faster, early movers will be able to secure to more figurative ones like cutting up food or as you might think. Of course, most leaders will constraint has major implications for AI safety.
advantages that last decades. Failing to act or covering sharp corners around the house. As they be well versed on how bad actors can spread
waiting too long will give ground for competitors, grow up, we learn to trust them more. They don’t misinformation more effectively through deepfakes And beyond an enterprise's trust in the AI models or
new and old, to disrupt industry norms just as need to hold your hand to cross the street, but we or conduct more convincing phishing attacks with systems it uses, growing autonomy is also disrupting
we saw in the digital era. And consider this: Less still walk next to them. They can play outside by better emails or spoofed voices of real people. the trust enterprises have built with people, in a lot
than 1% of today’s global internet market cap themselves, but only inside the fence. The more Or how biased decision-making can rear its head of different ways.
was founded in the first two years after Netscape our trust grows, the wider we paint the boundaries even with AI. To be clear, these are real issues, with
Navigator generalized the internet for the world.13 of the guardrails. Until, one day, they are fully ever-growing efforts for content watermarking Take the same synthetic content that bad actors
Now, it’s been a little over two years since formed adults. We’ll still check in—but they’re their or deepfake detection tools urgently seeking use; many enterprises are using the same core
ChatGPT’s release. Our foray into this generation of own person now, with the autonomy to make their resolutions to them. But this narrative pins the AI technology to great effect. AI-generated marketing
AI has only just begun, and with such large stakes, own decisions. trust conversation exclusively on bad actors and materials, chatbot conversations, product
it’s vital enterprises start now before they’re left exploitation. That’s simply not the whole story. To recommendations—the use cases are ever-growing.
irreparably behind. Critically, this example demonstrates how trust achieve true autonomy—in systems, throughout the But what happens when a customer finds out that
and autonomy are inextricably linked. But it also workforce, and with customers—leaders need to a product photo was AI-generated? Or if they
demonstrates the nuance of trust leaders now need think about trust more holistically. Like the analogy believed they were speaking to a customer service
To understand more about how digital to consider. The relationship between parents and of guiding a child into adulthood, trust is about representative, only to learn it was an AI agent all
platforms, data & AI, and digital foundations children hinges on both emotional and cognitive the confidence one develops in AI to perform as along? These interactions could leave customers
are empowering enterprises to grow through components of trust. Guardrails help foster a loving, intended from all dimensions—policies, morals, feeling duped by the business.
change and disruption, please see our work on nurturing, and safe environment, but also help ethics, and emotions—so that one can let it perform
Reinventing with the Digital Core parents build their own confidence in the child’s in a state of autonomy. Which means, trust isn’t just Or look at AI in the workforce. Every day more
decision making ability. We don’t really need to about when AI is taken advantage of, but the harder workers are finding value in using AI in their
differentiate between these two dimensions when question of how trust is being impacted even when jobs; in May 2024, over 40% of users had started
We are at the start of so many possible paths it comes to people, but with technology they we are using AI exactly as we intended. incorporating it just in the past six months.15 But
forward. The key to accessing the full potential of are different challenges with different solutions. they are hiding this from their employers: more than
Technology Vision 2025 | AI: A Declaration of Autonomy Introduction 7
half of workers using AI are reluctant to admit it and relevance that only AI agents can provide at scale. require dedicated teams of domain and decision Many companies are already familiar with ideas like
worry that using it for important tasks makes them But that autonomy needs to be facilitated by trust. scientists (or AI Ops teams) who will constantly explainability, transparency around data collection,
look replaceable. This isn’t a question of how much How much customers trust the enterprise, or test, evaluate and build the accuracy, predictability, debiasing, and other maturing techniques, but as
do workers trust the AI they’re using, rather it is enterprise leaders trust their systems, or workers consistency, and explainability necessary to leaders look to scale their use of AI, these efforts
proof that AI is shaking up the trusted relationship trust their employers, how much people trust AI, or maintain cognitive trust in the system. This is new will become a critical bridge between technical
between people and their employer. Employees dozens of other permutations across the ecosystem territory, with no one-size-fits-all solution. Every solutioning and the humans interested and invested
are used to having well-developed career paths, of relationships an enterprise has. enterprise has their own trust-building moments, in using the technology. Questions will swirl around
defined roles, skill expectations, and a shared technologies, AI strategies, and key relationships to how an AI is trained, who it is working for, and how
understanding of how work performance translates This is why trust is not simply one of many trends focus on. But broadly, any path forward will center it makes decisions—these are unavoidable. But what
into job stability. The infusion of AI is bringing in this year’s report. It is not a consideration for on addressing trust across systems and data, AI enterprises can do is be prepared with an answer,
uncertainty to this. businesses—it is the consideration. With every itself, and people. which is why they can’t sit back and wait, and need
company beginning to reinvent themselves with the to make responsible AI a key part of their strategy now.
For enterprises, trust is a crucial currency generalization of AI, the technology itself cannot be First, enterprises need to bolster the cybersecurity
underpinning their relationships with customers, the only focus. Reaping the benefits of AI will only and trust of their digital systems. The good news Lastly, the third and uncharted part of the roadmap
employees, regulators, and shareholders. Until now, be possible when it’s built on a foundation of trust, is that for systems and data, building this new is finding a new path to people-driven trust. We
this trust was built in small moments—moments and this needs to be every leader’s first priority. foundation doesn’t mean starting from scratch. know where we need to get to—new touchpoints
that AI is changing. Think of the micro-interactions Many previous technology and strategy investments and ways to establish and maintain trust with people
happening across businesses every day. A great Pathways to a Stronger Foundation can pay new dividends now. Cybersecurity as the generalization of AI disrupts traditional
sales rep saving customers money, or a support strategies like zero trust and entity behavior interactions. But how to get there will be different
rep going above and beyond to solve customers’ Trust isn’t gone in the world of AI—but it is analytics, for instance, will be critical. You can’t for every organization, so the place to start is with
problems. Quality service from a practitioner becoming far more dynamic and essential to control bad actors, but you can control how you self-directed questions: What will career paths look
or provider. Calling a customer for identity enterprise plans. With AI, enterprise leaders are protect systems and people from them—and with like when many entry-level jobs can be done by AI?
confirmation. On-time delivery of products. Every going to need to navigate both the emotional AI’s dependence on data, protecting everyone’s What will establish job security for employees who
one of these moments can, and will, be disrupted and cognitive dimensions of trust. The emotional data is increasingly important. Distributed ledger leverage AI to streamline their work? How will we
with AI. And many will be better for it—rich with dimensions—do people love AI, fear it, think it is technologies that foster ecosystem-scale trust maintain a personal touch with customers if our
more autonomy, less friction, and better outcomes. aligned with their interests, or feel taken advantage are also a great example of adapting traditional “frontline” support is AI agents? Enterprises should
But how far can you go before trust becomes an by it—are often considered publicly, but will need networks of trust toward new, technology-based seek to answer these questions in ways that will
issue? How will you reinvigorate the critical human real policy and governance as enterprises seek to ones. You don’t have to trust the entities using promote the potential of the symbiotic relationship
moments that build it? further diffuse the technology. And these efforts these technologies, because the system ensures between people and AI. Whether it is educators and
will only be successful with complementary action they comply with whatever agreements are put in students, mentors and proteges, or superheroes
These are the issues that leaders need to be taken to address the cognitive dimensions of trust: place. Ultimately, great cybersecurity overall will be and sidekicks, the world is filled with mutually-
tackling. Autonomy is the key to the next generation Does a system act reliably, competently, can it paramount to achieving AI trust and security at all. beneficial teaching and learning relationships that
of business growth and innovation. We want navigate challenges and still act as expected, within should inspire our future with AI.
employees to be able to work more autonomously, the guardrails laid out for it. This is a key aspect for The second dimension of the roadmap is thinking
with a fleet of agents at their command. We any system operating with autonomy, and especially about building trust in AI itself. By now the field
want customers to be able to freely interact with with AI where it is, by nature, one that will be relied of responsible AI is becoming an established
autonomous enterprise systems, purchasing on on to learn, grow, and act based on intent, not discipline, and one enterprises will increasingly rely
demand or enjoying a level of customization and necessarily explicit direction. Supporting this will on as they look to ethically steward their strategies.
Technology Vision 2025 | AI: A Declaration of Autonomy Introduction 8
The 2025 With a firm and clear approach towards building cognitive digital brains that will become an essential Finally, The New Learning Loop explores the
trust in AI systems, and by actively building the part of the enterprise DNA. The result will be a impact of cognitive digital brains through the
Technology Vision
cognitive digital brains that will create scaled dramatic increase in technology diffusion touching most valuable reinvention engine you have:
intelligence across the spectrum of society, every walk of business, consumer, and societal your people. Employees are starting to bring
Trends
businesses will be able to unlock the limitless interactions. It sets the stage for the emerging AI AI to work, and employers know the power it
potential of AI today. It seems prudent to mention era, where we will rapidly expand digital ecosystems can wield. But we need to change our mentality
that in 25 years of producing the Technology Vision, and increasingly trust autonomous systems to find from automation to equipping your people with
few technologies have had the widespread impact new ways to innovate with us. the power to automate—giving them the tools
on business, industry, and even technology itself to innovate, reimagine new ways to do things
that AI is poised to have now. We anticipate we are Your Face, in the Future pushes the thinking and drive progress from the ground up. We are
living in a time on par with the biggest moments in further, asking a simple yet critical question: if the building a virtuous cycle where people teach
technology, one which will be shaped and defined world is shaped by AI and increased autonomy, and learn from AI machines, and AI machines do
by AI-powered autonomy and the emergence of AI- and brings super-human consistency to everything the same with people. A cycle that will let both
based cognitive digital brains at all levels of society, it touches, where does that leave your brand and unleash new levels of performance and diffusion,
and we’ve only just begun. unique enterprise personality? Enterprises are at all underpinned by trust built through ownership.
the crossroads of an intermediation challenge. They
In the interest of preparing business leaders for the have the opportunity to radically transform the way What is the world going to look like in 30 years?
transformative journey ahead, the Technology Vision they engage customers and improve the relevance Around the time of Kasparov’s groundbreaking
this year is a deep investigation into this declaration of their customer journeys, but to do so, they must match, laptops were just starting to become
of autonomy. Our trends explore the business realize that their company’s AI personality is as popular among business workers, no one had ever
transformations—and trust revolution—that will critically important as its traditional brand built over heard of an iPhone, and economist Paul Krugman
happen as generative AI ripples across dimensions time by small, personal human interactions. infamously declared the internet would prove
of customer experience, technology development, to be of no more value than the fax machine.16
the physical world, and the workforce. When LLMs get their Bodies explores the Now, we see the beginnings of a future where
manifestation of AI autonomy in the real world, AI cognitive digital brains fuel every layer of
The Binary Big Bang tracks the emergence of and how a cognitive digital brain can transform an society, interact with each other, and bring new
language models coupled with agentic systems, and enterprise's physical presence. We are reaching a intelligence to everything and more autonomy to
how they challenge conventions around building watershed moment as the power of generative AI is everyone. And the question enterprises need to
software and crafting new digital ecosystems. This applied to physics and the field of robotics. Gone ask themselves is not whether this will pan out, but
is a redefining moment in the world of software are the days of narrow, task-specific robots that rather how they will invest in fostering the trust
engineering, where the role of programmers has require specialized training. A new generation of needed to make this future a reality, and what they
largely remained the same since Ada Lovelace wrote highly tuned robots with real world autonomy that will be able to do with this limitless capability.
the first algorithms for Charles Babbage’s Analytical can interact with anyone, take on a wide variety of
Engine. The trend dives into a generational tasks, and reason about the world around them will
transition, as leaders rethink how digital systems expand robotic use cases and domains dramatically.
are designed—building the foundation for the
TTeecchhnnoollooggyy VViissiioonn 22002255 || AAII:: AA DDeeccllaarraattiioonn ooff AAuuttoonnoommyy 9
01
The Binary
Big Bang
When AI expands
exponentially, systems
are upended
Organizations are entering a generation-defining
moment of transition: the Binary Big Bang. When
foundation models cracked the natural language
barrier, they kickstarted a shift in our technology
systems: how we design them, use them, and
how they operate. They are pushing the limits of
software and programming, multiplying companies’
digital output, and laying the foundation for
cognitive digital brains that infuse AI deeply into
enterprises’ DNA. We are now at the precipice of
more abundance, abstraction, and autonomy in
our technology systems than ever before, and the
decisions enterprises make today will profoundly
impact what they can achieve for the next decade.
TTeecchhnnoollooggyy VViissiioonn 22002255 || AAII:: AA DDeeccllaarraattiioonn ooff AAuuttoonnoommyy The Binary Big Bang 1100
1843 1946 1959 1973 1983 1995 2006
Ada Lovelace writes Researchers unveil COBOL, a major Alto, a computer with a Microsoft releases Sun Microsystems Amazon launches
“Note G,” widely ENIAC, the first programming language graphic |
88 | accenture | Technology-Vision-for-SAP-Solutions-2024.pdf | #TechVision2024 July 2024
Technology Vision for SAP Solutions 2024
SAP Solutions
in the Age of AI
Human-by-design
technology is reinventing
core business operations
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024
Foreword
We’re delighted to present this year’s Of course, applying a powerful general-
Accenture Technology Vision for SAP purpose technology like generative AI to a Caspar Borggreve Stephanie Guimbellot
solutions. In it, we explore how human-by- complex and business-critical domain like Global Lead Global Innovation Lead
design technology is reshaping interactions ERP comes with challenges. It’s why we also SAP Business Group SAP Business Group
between humans and machines, enabling explain some of the steps businesses will Accenture Accenture
new levels of business productivity and need to take to prepare their data, adopt LinkedIn LinkedIn
creativity—and what this means for composable architectures and build the
companies running SAP solutions. digital scaffolding for an increasingly AI-
In particular, we dive into the potential for driven future workplace. Not forgetting the
generative AI to enhance the way people need to ensure rigorous Responsible AI
access and work with SAP solutions and data, approaches are built in from the start.
as well as drive a pivotal shift towards It's an exciting time for enterprise
automated agent-based operations. We technology. Generative AI is opening up a
explain the numerous applications and use whole new world of possibilities for
cases that can be implemented now, as well augmenting and automating work. We look
Daniel Gonzalez Catherine Nguyen
as the likely evolution of the technology in forward to helping our clients capitalize on
the years to come. the many opportunities that await them. Americas Innovation Lead Europe Innovation Lead
SAP Business Group SAP Business Group
Accenture Accenture
LinkedIn LinkedIn
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024
Client and SAP Advisors
Johnny Rahme Sharmita Srivastava Dr. Philipp Herzig
Head of Innovation, Vice President, Head of Global Chief AI Officer,
APS, TotalEnergies ERP, Bristol Myers Squibb SAP
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024
Contents
The big picture 5-10
A match made in AI 11-17
Meet my agent 18-25
Going beyond 26-29
Conclusion 30-31
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision
The big
picture
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Human-by-design AI is transforming
next-level enterprise potential
The relationship between humans and An example? Look at the wave of advances
machines is changing. Enterprises are made by generative AI over the past 18
acquiring an array of increasingly powerful months. A whole range of models has
and intelligent tools and technologies, which emerged, accompanied by a technology
are allowing their employees to radically ecosystem to utilize them, with OpenAI’s
reshape the way they access, use and think GPT, Google’s Gemini, Anthropic’s Claude,
about enterprise data. They’re allowing Meta’s Llama and Mistral’s models among the
operational teams to develop new kinds of most significant. Solutions based on these
automation, including autonomous agents models have taken the world by storm,
that can act independently and interact with demonstrating remarkable abilities to
each other. And in the process, they’re converse in everyday language, summarize
fostering greater levels of business vast amounts of information into consumable
productivity, human creativity and insights, and produce useful and relevant
enterprise potential. responses to questions.
One of the most exciting aspects of these
new technologies is the fact they’re “human
by design”. That means they’re not only more
powerful, but also more intuitive to use, more
human-like in their responses, and easier to
integrate into the everyday patterns
of working life.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
For businesses, the impact will be far Look, for example, at the impact generative
reaching. The technology is allowing people AI is already having in activities like software
to access information, spark new ideas, bring development, exemplified by tools like 43%
data together and generate a variety of GitHub’s Copilot for coding. Then consider
content faster than ever before. It’s massively the massive potential in other industry-
expanding AI’s impact on day-to-day specific domains, including emerging
operations, widening the focus from routine applications like MIT’s experimental
automation and data analysis to task FrameDiff for accelerating drug discovery
augmentation and reinvention. and Google’s Vertex AI search tools for
of all working hours across end-to-
healthcare practitioners.
It's a profound shift in how we all work. And end supply chain activities could be
employees know it—in many cases
generative AI adoption is being driven impacted by generative AI.
organically from the shop floor, not the C-
suite. As this shift plays out, it will start to
reshape the way entire organizations, even
entire industries, operate.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Accenture has also developed a range of
What does this mean for companies
generative AI solutions that can be applied to
SAP systems. Take Ling.AI, our tool for
running SAP? expediting the translation of business
The good news? SAP Business AI helps documentation, including SAP-related
customers achieve real-world results with materials. Able to be hosted securely in any
embedded AI capabilities across their business. platform and customizable for individual
Companies have spent the past year business requirements, Ling.AI allows users
exploring these new AI capabilities. Now, Look, for instance, at Joule, SAP’s generative AI to instantly translate documents of any size
however, the focus is shifting to scalability copilot designed to accelerate work and while preserving formatting. We worked with
and ROI. How can business leaders turn all provide smarter insights. Then there’s the SAP multinational retailer Metro to implement
those interesting experiments into scalable AI Launchpad, a multi-tenant SaaS application Ling.AI, saving its teams significant time and
solutions that deliver real and sustainable on the SAP Business Technology Platform, and effort translating thousands of documents
value for the business? the SAP AI Core, which now includes a like SAP training materials into multiple
generative AI hub for experimenting with and languages. We’ve also worked with Metro to
To achieve that value, companies will need to managing the lifecycle of prompts given to identify and prioritize 35 other generative AI
start using their own data to optimize and generative AI models. use cases for its SAP transformation program,
customize generative AI, enabling it to
which we’re actively pursuing together.
deliver more accurate, more relevant, more In data management, too, SAP continues to
context-specific outputs. That means innovate. The company has enhanced its SAP
allowing generative AI to touch core ERP HANA Cloud database with a vector engine, an
systems and data—including the SAP important capability in allowing generative AI
ecosystem of mission-critical solutions used models to draw insights from enterprise
by so many of the world’s large organizations. data. While the SAP Datasphere continues to
enhance the way companies bring together
There’s no question this is a complex data across complex hybrid architectures and
undertaking, given the tightly integrated cloud environments.
nature of many mature ERP deployments.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
“Our ecosystem plays a critical role in helping our customers adopt SAP
Business AI to get immediate value from these exciting new
technologies and solutions.
We very much value our long-standing partnership with Accenture.
They are one of our most important partners in the industry for bringing
innovation to our joint customers, which includes activating SAP’s
embedded AI capabilities, such as Joule, and building customer use
cases in the SAP Business Technology Platform with SAP AI Core and the
generative AI hub.
I look forward to our continued collaboration and the outcomes that
generative AI will deliver in both business transformations and
operations for our customers.”
Dr. Philipp Herzig, Chief AI Officer at SAP
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
The trends to watch
Accenture’s Technology Vision 2024
sets out four of the key trends that
enterprises need to pay attention to in
the coming years. Of these, we see
two being particularly relevant for
companies running SAP solutions.
A match made in AI Meet my agent
People are asking generative AI chatbots for The journey to becoming an autonomous
information. This is reshaping our relationship enterprise is being accelerated by advances in
with data and transforming the business of AI, including generative AI and large language
search. It’s also redefining the software and models (LLMs). Soon this will include
data-driven enterprises of tomorrow. ecosystems of AI agents able to operate
more independently.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision
A match
made in AI
Reshaping relationships with data
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Employees’ access to business
insights is about to change forever
The “search engine” model of accessing An example? Look at the way electronic
information is now so embedded in everyday health record software company Epic has
life it’s become second nature. Almost 70 integrated GPT-4 into its products to allow
percent of all website traffic begins with clinicians to speedily generate summaries of
search. And it’s no different at work. Whether patient charts. Or the way Morgan Stanley is
we’re searching through emails, looking up applying generative AI to help its analysts
customer details in a CRM or finding a access relevant insights in its vast internal
particular document, we’re all completely knowledge library much faster. Accenture,
accustomed to the idea that accessing too, is enabling a centralized generative AI
information means asking a “digital librarian” search entry point called Amethyst for
for a list of potentially relevant documents or all its employees.
data points.
Generative AI completely flips that on its
head. Because rather than asking for a
curated list of search results, people can ask
a digital copilot real questions and get useful
answers in return. The original vision for
internet search engines is finally becoming
a reality. And it’s already changing the way
industries and enterprises think about
their data.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Intelligent assistance can deliver
ERP insights instantly
How is access to data changing within the functionality for a particular task, explain how It’s a simple and easy-to-use solution
SAP ecosystem? Just consider how many to perform certain activities within the ERP designed to help increase user adoption of
business activities involve combining and system, and retrieve operational insights, SAP Analytics Cloud for improved data-driven
connecting information across ERP systems, such as purchase order status. Users can even decision making.
and with data from other sources, in order to complete certain tasks end-to-end, such as
take a business decision—in finance, supply updating HR information, approving requests Similar capabilities can also help drive a
chain, manufacturing, or any other function. and giving feedback. Designed to integrate broader change management agenda.
All these activities stand to gain from the seamlessly into everyday work, SAP has Accenture, for example, is integrating a
ability of generative AI to bring disparate created Joule to help teams work faster, gain generative AI assistant into its
insights together instantly, in an easily smarter insights, and achieve better GenWizard offering.
consumable form. outcomes from SAP systems.
SAP has unveiled the SAP Joule Certified
These capabilities are already becoming Within SAP Analytics Cloud, SAP also offers a
Consultant solution. By drawing insights from
available within certain SAP applications. Just Ask feature, which allows users to query
a range of relevant documents, the assistant
Take Joule, SAP’s new generative AI copilot, analytics data models by asking questions in
can quickly answer user queries on specific
which is being rolled out across its cloud everyday language. Powered by generative
topics such as new functionalities in their
enterprise portfolio, initially embedded in AI, Just Ask interprets the query and returns
organization's ERP transformation.
SAP SuccessFactors and SAP S/4HANA the results as an intuitive data visualization.
Cloud. Using simple everyday language
within an intuitive interface, users can use
Joule to navigate to the correct SAP
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Powering the supply chain nerve center
With supply chain resilience at the top of the integral components of many of these unstructured information in analyst reports, to
agenda for manufacturing businesses, AI capabilities for years—including within SAP improve forecast accuracy. Another key use
capabilities are coming to the fore. Recent applications—the introduction of generative case is explaining the outcome of planning
disruptions have exposed significant AI is opening up new possibilities for supply runs, a task that is often too complex for
vulnerabilities across supply networks, while chain responsiveness. human analysts to complete quickly enough
supply chain resilience and responsiveness to be useful.
are becoming increasingly important revenue
Consider its practical uses in supply chain
drivers. Accenture’s Resiliency in the Making
planning. Generative AI-powered interfaces
research estimates supply chain vulnerability
with access to relevant data sources allow
is costing the world’s businesses a
planners to instantly query, summarize and
staggering $1.6 trillion in missed revenue Press Release: Accenture Expands Partnership
explain disruption alerts and data triggers as
growth every year. with SAP to Help Clients Establish
they come in—a task that could historically
Responsible and Resilient Supply Chains
take hours if not days of painstaking research.
To deliver the necessary resilience, leading
Generative AI can also suggest the most
companies are turning to intelligent supply Highlight Report: Accenture Builds on its SAP
effective corrective actions, such as suitable
chain management capabilities. By building Expertise and Launches the Supply Chain
alternative suppliers, for planners to consider.
supply chain nerve centers based on SAP Nerve Center
technologies, they’re enabling end-to-end
Its potential extends beyond chatbot
control towers, reconfigurable supply chain
interfaces. Accenture, for example, is building
networks, autonomous manufacturing,
a suite of generative AI tools into its Supply
improved demand foresight, predictive
Chain Nerve Center offering, including one
alerting and more. And while classical
that extracts insights from a range of different
machine learning techniques have been
market sources, such as complex
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Customer and sales experience are
getting smarter
Customer engagement and sales can also be Similarly, sales representatives can
transformed by this reinvention of human- revolutionize customer engagement and
machine interfaces. Take conversational increase conversion rates by leveraging
commerce, a concept gaining traction in generative AI applications during the sales
retail and consumer goods. By enabling journey. These applications allow them to
customers to articulate their needs to an AI better understand consumer preferences,
engine in the form of a natural conversation, recommend suitable products and enhance
brands can radically simplify the overall shopping experience. In industries
shopping experiences. like consumer packaged goods, these kinds
of solutions can not only improve customer
Imagine you want to redecorate your child’s engagement, but also deliver a significant
bedroom, but you’re stuck for ideas... and productivity boost to employees, freeing up
lack confidence in your painting abilities. By capacity in areas like field sales,
guiding you through a series of questions— administration and customer service.
the age of your child, their likes and interests, However, the success of such initiatives
the size and aspect of their room—an AI relies heavily on seamless integration with
chatbot can propose suitable paint brands, backend systems like SAP, for crucial data on
colors and equipment, as well as provide tips product availability and lead times.
on correct painting techniques.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Finance teams are gaining faster
access to insights
Companies are increasingly developing their Another valuable use case is compiling
own generative AI solutions for use within the finance narratives, such as those used in
SAP ecosystem. Look, for instance, at how preparing for earnings calls or external
Accenture has applied it within its own regulatory reporting. Historically, producing
finance function. It’s developed a financial these narratives requires a huge effort from
advisor tool powered by generative AI which finance teams who need to bring together a
proactively alerts finance teams of any cash wide range of data sources to produce
management variances, financial exposures, summaries of business performance that are
credit utilizations or other issues that need both accurate and cognizant of potential
immediate investigation. Because generative market reaction. Accenture has created a
AI provides the alerts in clear everyday generative AI tool to streamline this process.
language, employees can instantly It’s able to produce an accurate initial
understand the issue and quickly click narrative based on real financial data, which
through to see the relevant report in the SAP finance teams can then fine-tune. Likewise,
system. What’s more, by focusing generative the tool can auto-generate first drafts of
AI on a discrete task, and prompting it with certain regulatory submissions.
data generated through traditional
automation methods, the tool ensures
accurate insights are generated, minimizing
opportunities for “hallucinations” and other
inaccuracies that can creep into broader
LLM implementations.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
What to do now?
Prepare the data
As generative AI starts to be applied across The good news? Generative AI itself can Of course, managing data quality is an
the enterprise, business data has never been help. Accenture, for example, has been ongoing activity, not limited to the data
more important. Companies are under ever developing tools for expediting SAP data migration phase.
greater pressure to guarantee data quality migrations with generative AI by helping
and data accessibility. The ability to match design migration plans and generating Companies also therefore need the right
and combine data from different sources, migration code, as well as assisting business governance structure and tools to sustain data
including SAP solutions, across hybrid IT users as they validate migrations by quality after a system goes live. Again,
environments, is becoming critical for a comparing before/after outcomes. generative AI can help by making checks and
whole range of use cases, including offering recommendations to users during
generative AI. Similarly, generative AI can help streamline their data interactions. A US-based retailer, for
SAP data cleansing tasks like deduplication example, is implementing a chatbot that uses
Having a mature and efficient data and removing personal or sensitive generative AI to propose the right UNSPC code
foundation is therefore a prerequisite for information. It can be very effective at during procurement activities, helping ensure
reshaping the way companies access their producing context-specific manufactured the correct code is used. Efforts like these can
data with AI. But data management remains data for testing purposes. And it can also support a ‘virtuous loop,’ where company data
a perennial challenge in most organizations, support data reporting by taking on the is continuously checked and enhanced as part
and the scale of the work involved technical heavy lifting of putting together of an ongoing cycle.
is often underestimated. different reports and dashboards.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision
Meet
my agent
The road to the
autonomous enterprise
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
The first agent-based enterprises
are on the horizon
Companies have been embedding robotic natural language commands into subtasks for 96%
process automation and AI into business controlling physical robots. It’s true that
operations for many years. As generative AI is there’s a lot of work to be done to make this a
added to the mix, machines are acquiring the reality in most organizations. But the journey
power to operate increasingly independently. to the autonomous agent-driven enterprise
And AI is taking on new roles, evolving from has already begun. And innovative
being assistants that offer advice and insights companies are now building the digital of executives agree that leveraging
into something potentially more powerful— scaffolding that AI agents will operate within,
agents that are able to interact with each as well as upskilling their workforces for this AI agent ecosystems will be a
other, and take action on their own, in the increasingly automated future. Accenture
significant opportunity for their
real world. estimates that 40 percent of all working
hours could ultimately be augmented or organizations in the next three
Soon it will be commonplace to see entire automated by generative AI models such as
ecosystems of these agents operating across GPT-4. As the technology matures, this figure years
the enterprise, chaining together different will likely grow. Companies will need to
decisions and actions, driving automation to prepare for a future in which AI agents and
new levels. Already, cases are emerging, human employees work side by side to drive
where agents can automate activities across value for the business.
scientific research or break down
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
An ecosystem of AI automation
techniques
Companies already have numerous options Likewise, in transportation and logistics,
for building autonomous ecosystems. companies can build generative AI
Because the journey to the autonomous capabilities on top of their existing AI-
enterprise doesn’t begin and end with powered predictive alerts. For instance, when
generative AI, significant gains can be made a disruption alert is triggered in any SAP
by combining various kinds of automation, solution, instead of being passed
including classical machine learning and immediately to a human employee, that alert
robotic process automation (RPA) as well as can be supplied to a generative AI solution
generative AI, in a broad ecosystem of that can evaluate the various responses the
automation techniques. company could take and present them to the
employee in an easily consumable form,
This can be particularly valuable in situations saving time and effort. Similarly, generative
where accuracy is paramount, such as SAP AI can be combined with other cutting-edge
financial reporting. In financial close variance deep learning techniques in supply chain
reporting, for instance, Accenture’s finance optimization to make valuable insights
teams use classical AI to generate variance available to supply chain planners in an
insights from SAP S/4HANA Cloud as a first actionable way.
step. Then they layer generative AI on top to
summarize and explain those variances. This
combination ensures both high accuracy and
high usability.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
The evolution towards agent- whether an action is compliant or not. Longer
term, however, it opens the door for other AI
agents to access these policy determinations
based operations
autonomously before deciding whether or
not they should take a particular action.
As AI agents mature and their capabilities another updates planning and scheduling for
grow, companies will have even further production and warehousing. Such
opportunities to drive efficiency, productivity intelligent processes will not be entirely
and innovation. Generative AI will autonomous, of course. To ensure
increasingly be used to help orchestrate Responsible AI principles are rigorously
entire processes, breaking down decisions adhered to, it will be essential to retain a
into discrete steps and calling other tools, human in the loop to validate the actions
agents and physical robots to use its output agents are taking and maintain ultimate
and take the required action. control over operational decisions.
Take the transportation example described Another example is internal audit and policy
above. Ultimately, AI agents will enable compliance. For finance teams in particular,
almost completely autonomous responses to determining if a particular activity is
these kinds of inbound logistics disruption. permitted within the terms of the company’s
Having identified the initial disruption, one policies can be a difficult and time-
agent will assess various alternative consuming task. Increasingly, however,
responses by analyzing operational data organizations are looking to expose their
from the ERP, scheduling and manufacturing repositories of policy documentation to
execution systems. The next agent will then generative AI. In the short term, this will allow
trigger communication with alternative employees to ask an AI agent via a chatbot
suppliers and/or logistics providers, while interface for a reasoned explanation of
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
New human-machine interfaces
Generative AI is also fundamentally changing Increasingly, site operators and engineers Operations will become not only more
how people interact with physical machines. will use generative AI to interact with efficient but also safer by ensuring that
Look, for example, at the researchers who systems in a more intuitive and efficient workers receive the right information at the
put ChatGPT on board a Boston Dynamics way—without even having to use screens. right time, without the need to navigate
robot, allowing people to use natural They’ll be able to ask voice assistants simple through complex interfaces or perform
language to command the robot or ask it questions like “I'm stuck here, what should I multiple transactions.
about its previous tasks and receive a clear do next?” and the system, understanding the
response in plain English. It’s easy to see context, who the individual is, and where Workplaces themselves will become more
how this might be applied to robotics in an they are, could then allocate them the most adaptive and responsive. By leveraging the
industrial setting. suitable task. data model of a plant’s operations and
applying generative AI, it's possible to create
a dynamic and self-updating system that not
only guides the operators through their daily
tasks but also anticipates needs and adjusts
to changes in real time. Plants will be able to
operate increasingly autonomously, much
like modern airplanes, with minimal human
intervention, while machine learning
algorithms continuously learn, predict
and optimize based on the real-time
data generated.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Streamlined ERP and harnesses multi-agent capabilities, with “The vision is to have touchless
individual AI agents for specific types of
programming, data analysis, code reviewing testing…with AI writing the
implementations and more. This will allow developers to
simply upload a document containing scripts and documenting the
business requirements and functional
One area generative AI is already having a information—and have the ecosystem of results in a format that our IT
visible impact is custom code development. agents work collaboratively to translate it into
teams can instantly understand
This has significant implications for ERP a set of programming requirements and
implementation and maintenance. associated code. These capabilities will
and use.”
Accenture, for example, has been leveraging transform automation across the ERP
LLMs to optimize the customization process software development lifecycle, including
integral to large SAP ERP deployments. testing as well as coding. Sharmita Srivastava, Head of Global
By specifying their various technical
ERP at Bristol Myers Squibb
requirements through a chat interface, SAP itself is also now offering generative AI
developers can receive contextualized code development solutions. SAP Build Code, for
suggestions, whether that’s for custom example, is an environment enabling
reporting, a particular user interface or form, application development with Joule copilot.
a new workflow, or similar customizations. Optimized for Java and JavaScript, it’s been
designed to help developers with tasks such
Applicable to both greenfield and brownfield as coding, testing, integrations and
deployments, as well as application application lifecycle management through
maintenance scenarios, the solution aims to natural language prompts. SAP Build Code
accelerate the routine side of development includes Joule copilot, which allow
work and improve code consistency and developers to generate artifacts for the SAP
quality. It also adopts a multimodal approach Cloud Application Programming Model.
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match made in AI Meet my agent Going beyond Conclusion
Fine-tuning offers a foundation for
greater relevance
Some companies are thinking bigger than the resources and time involved mean this Such LLM models can be trained on the
simply using LLMs like GPT-4 and are option is only typically available to the largest company’s corpus of both human language
customizing pretrained models or even companies with the deepest pockets. and business data, including text and
building their own. Fine-tuning generative AI multimodal data as well as public sources.
on a company’s data allows generative AI to Global businesses, for instance, are looking to
develop the context-specific expertise that’s build their own LLM, leveraging its extensive
critical for supporting day-to-day operations. proprietary sources of biomedical data in
Whereas creating an LLM from scratch can order to improve generative AI’s performance
deliver even greater relevance and in specialized tasks.
competitive advantage,
Technology Vision 2024 | SAP Solutions in the Age of AI
#TechVision2024 Introduction The big picture A match mad |
89 | accenture | Reinventing_Enterprise_Operations.pdf | How reinvention-ready
companies are driving growth
and relevance with gen AI
Reinventing Enterprise Operations
Authors Preface
“We’re in a period of profound change.” These are Through our extensive experience in driving $39 billion
Arundhati Chakraborty
opening words from our 2023 report on how intelligent in P&L impact for over 2,000 clients, we have identified
Group Chief Executive,
operations are absolutely key to a reinvention strategy that a comprehensive operations strategy including
Accenture Operations
that sets a new performance frontier. Talent, Assets & Platforms, and Methods & Processes is
crucial. And our new research underscores that while
many companies have accelerated their shift to more
What’s changed since then? The now measurable
sophisticated operations, only the top performers are
impact of generative AI—for every business, in
effectively leveraging generative AI to drive significant
every industry.
value. These frontrunners are reinvention-ready,
Yusuf Tayob
moving faster by leveraging their digital core to put
Global Communications,
To thrive in today’s landscape, organizations must
Media & Technology hyper-automation and AI to work and amplify their
undergo transformative change, with gen AI playing a
Industry Practices Chair impact across the business.
pivotal role. And a gen AI-powered journey to Intelligent
2
Operations is absolutely essential to creating value
We anticipate that companies will take on even more
from these transformations.
meaningful reinventions to cultivate sustainable,
mature, Intelligent Operations with the support of
Intelligent Operations represent the pinnacle of
Bhavana Rao gen AI—and achieve remarkable gains in growth,
operations maturity, anchored by a digital core designed
Chief Growth & Strategy productivity, and profitability.
Officer, Accenture for perpetual adaptability. A purpose-built digital core
Operations
enables organizations to meet their evolving needs while
The time is now to become reinvention ready.
seamlessly integrating the latest emerging technologies.
snoitarepO
esirpretnE
gnitnevnieR
04 17
What’s at stake: The path to
Competitive Intelligent
relevance Operations
06 The business case for Intelligent Operations 19 Implement a domain-centric approach to
data modernization
12 Knowing the enablers of Intelligent Operations
22 Embrace a talent-first reinvention strategy
16 A modernized data foundation:
The gateway to gen AI 25 Link business and tech teams to co-own reinvention
29 Adopt leading processes to drive
business outcomes
3
31
In this report Looking ahead:
Organizing for
reinvention
snoitarepO
esirpretnE
gnitnevnieR
What’s at stake:
Competitive
relevance
New technologies, consumer expectations, climate change, hybrid work and other
factors are driving massive structural shifts in how organizations operate today. And the
changes are happening at lightspeed. More than ever, enterprises must reinvent, quickly
and continuously, to stay relevant and competitive in this evolving landscape.
That, in short, is the prize for reinvention:
Competitive relevance—and all that goes with it.
Growth. Profitability. Innovation. Market dominance.
A foundation for the future.
The stakes are that high, and most executives know it. Our research shows that
92% of C-suite leaders recognize the urgent need to reinvent and know that
generative AI is key to reinventing at scale and at speed.1 Eighty-one percent
of executives believe that rapid experimentation is key to scaling gen AI across 5
their enterprises over the next six to 12 months. And seven out of 10 (71%) say
they need to be less risk-averse when it comes to scaling gen AI use cases.2
Clearly, a majority of executives understand the urgency of reinventing with
gen AI. But are their enterprise operations ready to support such reinvention?
snoitarepO
esirpretnE
gnitnevnieR
The business case
for Intelligent Operations
6
Our 2024 survey was structured with that question in mind.
We spoke to 2,000 senior executives (57% C-level or equivalent)
across 15 industries and 12 countries (Figure 1). Our goal was to
assess the extent to which enterprise operations are prepared
to drive business outcomes with gen AI.
snoitarepO
esirpretnE
gnitnevnieR
Figure 1: Survey demographics
Share of survey respondents by country Share of survey respondents by industry
China 15% Automotive 5%
Japan 13% Banking 10%
India 10% Chemicals 7%
Australia 5% Communications 4%
Brazil 5% Consumer Goods and Services 10%
Healthcare 5%
High Tech 10%
United States 20%
Insurance 7%
Canada 5%
Life Sciences 8%
7
Media 5%
United Kingdom 7% Oil and Gas 5%
Germany 6% Retail 5%
Spain 5% Software and Platforms 5%
Italy 5% Travel 7%
France 5% Utilities 5%
n=2000
snoitarepO
esirpretnE
gnitnevnieR
Share of survey respondents by organizational function Share of survey respondents by role level
CEO 10% 21%
Finance 8%
HR 7%
Supply Chain 8%
Procurement 8% 43%
36%
Strategy 11%
Operations 8%
Technology 11%
Marketing 5%
8
Sales 5%
C-Level
Customer Service 5%
Director Level
Legal, Risk and Compliance 7%
Sustainability 4% VP Level
Other* 2%
n=2000
Note: (*) Other includes GBS Heads and Global Process Owners
snoitarepO
esirpretnE
gnitnevnieR
Organizations were evaluated across four criteria of operations readiness to
assess where they are on the Intelligent Operations continuum (Figure 2).
Organizations characterized as “Foundational” are in the earliest stages of their
journey while those assessed as “Reinvention-ready” have fully modernized,
AI-led processes.
01 Foundational 02 Automated
Foundational assets that Automation and
drive cost optimization adoption of descriptive,
and basic SLAs predictable AI 9
03 Insights-driven 04 Reinvention-ready
Fully modernized Hyper-automation and
data geared toward AI at scale to drive
customer experience business outcomes
snoitarepO
esirpretnE
gnitnevnieR
Figure 2: How we assess Intelligent Operations
While basic operations cost, and
Service-level agreements (SLAs) Decentralized data ownership
might be in place, automation of Deployment of low-code/ by domains with federated
tasks has not begun or is at very no-code automation for governance. Fully modernized data
early stages. exponential efficiency. foundation and end-to-end
Mature data products curated by platform integration, that
There is no AI strategy and Traditional AI deployed in domain experts and hosted on a supports hyper-automation
execution roadmap in place. nearly all processes, redefining self-service marketplace. across most processes.
performance benchmarks.
Data is stored in silos without On-demand, near real-time Application of traditional AI
much interconnectivity across Gen AI POCs being productized analytics, advanced modeling to augment tasks at scale
transaction systems; and is mainly across multiple functions and and data science, for data-driven and rapid scaling of gen AI
analyzed for historical reporting. business units. decision making. use cases.
lanoitadnuoF
detamotuA
nevird-sthgisnI
ydaer-noitnevnieR
8% 56% 20% 16%
2%
Reinventing
Reinvention-ready companies
that are already scaling
gen AI and driving exceptional
business outcomes.
Specialized talent fully prepared for AI-led enterprise reinvention. Strategic workforce planning, role reinvention and continual
Talent
upskilling, and flexible talent sourcing to meet talent needs.
10
Technology and business teams jointly own how assets, platforms and products are developed, with ecosystem partners
Assets & platform
to leverage descriptive, predictive and gen AI assets for business outcomes.
Rule-based and advanced processes have gone through end-to-end transformation to achieve high levels of standardization.
Methods & process
Process mining and benchmarking drive “best-in-class” performance.
Four criteria—and learnings from thousands of client assessments—are used to assess organizations across the Intelligent Operations journey.
snoitarepO
esirpretnE
gnitnevnieR
A lot has changed since we last assessed organizations on Intelligent
Operations back in 2023. Over the past year, the number of Reinvention-ready
companies has nearly doubled from 9% to 16%. These are organizations that
have modernized their data foundations to support strong business outcomes,
achieved end-to-end platform integration and are hyper-automating most of
their processes. They are also successfully applying traditional AI to augment
tasks at scale and are rapidly scaling gen AI use cases to drive new growth.
Compared to their Foundational counterparts, Reinvention-ready
organizations have:
2.5x 2.4x 3.3x
higher average greater higher likelihood to
revenue growth improvements in succeed at scaling
productivity high-value gen AI
use cases
11
Furthermore, a small but elite subset of Reinvention-ready companies—
just 2%—are already deploying gen AI at scale and are reporting
exceptional returns on their investments.
These organizations do not have a secret weapon or special superpower
that allows them to achieve these outcomes. They have modern, mature
operations that are held up by three critical enablers.
snoitarepO
esirpretnE
gnitnevnieR
The enablers of Figure 3a: The enablers of Intelligent Operations
Intelligent Operations
Talent is fully prepared for tech-led Methods and processes are applied
enterprise reinvention across all business functions
To achieve Intelligent Operations, organizations must Reinvention-ready 92% Reinvention-ready 87%
address how they transform Talent, Assets & Platforms,
and Methods & Processes. Our 2024 research shows that
Automated
19%
Automated
20%
organizations have begun to take a more holistic view of
reinventing enterprise operations and are paying equal
attention to the three enablers of Intelligent Operations. Foundational 1% Foundational 5%
They’re making all three a priority. This is a departure from
2023 when many organizations focused on just one or two
enablers at a time. Organizations now realize that the three
enablers are like the legs of a three-legged stool: each
Extensive collaboration to reinvent
plays a crucial role in supporting reinvention with gen AI.
assets and platforms
Reinvention-ready 87%
Reinvention-ready companies excel at developing
12
all three enablers in parallel and applying them in
unison (Figure 3a).
Automated
18%
Foundational 1%
snoitarepO
esirpretnE
gnitnevnieR
By comparison, organizations at the Foundational and Automated levels struggle to successfully While all three enablers are critical to reinvention, and all three
apply the three enablers (Figure 3b). should be pushed forward in unison, it’s important to note
that each phase of the Intelligent Operations continuum has a
primary enabler (Figure 4a).
Figure 3b: The enablers of Intelligent Operations
For example, Assets & Platforms is the primary enabler for
companies that are looking to transition from Foundational
Talent is relatively inflexible and Methods and processes are in to Automated operations. A key ingredient at this stage
unprepared for tech changes limited use or not applied at all is a governance model for key automation projects with
feedback loops for business needs. Companies that empower
Reinvention-ready 1% Reinvention-ready 1%
business and tech teams to jointly create assets and platform
development roadmaps are the ones that graduate successfully
Automated 31% Automated 30% to Automated operations.
Foundational 82% Foundational 78% Similarly, Methods & Processes is a primary enabler for
organizations at the Reinvention-ready stage. Compared to
organizations at the Insights-driven level, Reinvention-ready
companies are able to execute process mining as well as internal
13
and external benchmarking to drive best-in-class performance.
Collaboration to reinvent assets and
Their processes have been transformed end-to-end with a high
platforms is limited or non-existent
level of platform integration and hyper-automation. Almost
nine out of 10 (87%) of Reinvention-ready companies excel at
Reinvention-ready 2%
developing Methods & Processes compared to only 47% of those
at the Insights-driven stage (Figure 4b).
Automated
34%
Foundational 88%
snoitarepO
esirpretnE
gnitnevnieR
Figure 4a: Primary enablers in the journey to Intelligent Operations
Foundational Automated Insights-driven Reinvention-ready
Talent Employees are restricted to their respective Machines (automation, technology, analytics) Machines automate and augment human Machines augment human work in nearly
functions and processes. automate parts of human roles for some work for major business processes. all processes.
business processes.
Talent strategies are relatively inflexible, The organization uses an internal talent Organization is equipped with specialized
and teams continue to be measured on The organization is beginning to promote marketplace for on-demand collaboration talent to accelerate AI adoption.
traditional SLAs of productivity and output. talent movement across functions. where dynamic project teams can rotate on
and off projects as per strategic needs. Strategic workforce planning, role reinvention
and continual upskilling ensures a strong
talent pipeline aligned to strategic priorities.
Assets & Technology and domains/business Governance models for key projects have Technology and business functions Technology and business teams, partner to
platforms functions make siloed decisions on been established with feedback loops for collaborate across some functions to drive drive organization’s strategic roadmap and
transformation programs. business needs and technology priorities. focused investments and deployments. integrate ecosystem partners.
Governance over key projects is ad hoc, Joint products roadmaps developed for Joint governance models for key projects Technology and business experts, partner
with limited joint executive sponsorship select domains/functions. allow the organization to quickly adapt to to identify, create and scale AI + Automation
14
from technology and business functions. changing business needs. use cases.
Methods & Fragmented, non-standard processes that Leading practices and internal Advanced standardized processes Process mining as well as internal and
processes have gone through very few lean/process benchmarking data is used to measure with policies and practices that are external benchmarking is used to drive
improvement cycles. some processes. largely aligned. “best-in-class” performance.
Internal benchmarking data is Moderately rule-based processes that Process mining and internal End-to-end transformed processes with
unstructured and dated. have gone through basic improvements benchmarking data is used to drive high level of platform integration and
with point solutions. process improvements. hyper-automation.
snoitarepO
esirpretnE
gnitnevnieR
Figure 4b: Primary enablers in the journey to Intelligent Operations
2023 2024
Deploying class-leading methods & processes,
Reinvention-ready 9% 16%
including process mining and benchmarking,
separates Reinvention-ready operations from being
Insights-driven.
Insights-driven (47%) vs. Reinvention-ready (87%)
Insights-driven 25% 20%
Developing talent ready of AI-led reinvention is
a topmost enabler for companies moving from
Automated operations to Insights-driven outcomes.
Automated (19%) vs. Insights-driven (61%)
Automated 48% 56%
Bringing together business and tech teams to jointly
develop assets & platforms is the most important
enabler to move from Foundational operations to
Automation outcomes. 15
Foundational 18% 8%
Foundational (12%) vs. Automated (66%)
snoitarepO
esirpretnE
gnitnevnieR
A modernized data foundation: Figure 5: Momentum from modernized data
The gateway to gen AI
Data assets are modernized Organizations have clear
for gen AI use cases data governance roles
In addition to addressing all three enablers, Reinvention-ready Reinvention-ready 61% Reinvention-ready 62%
organizations also have much higher levels of data modernization
than their counterparts at other levels. They recognize the imperative
Automated
40%
Automated
37%
of having the right data strategies and core digital capabilities in
place to effectively leverage gen AI. Their data assets are designed
for gen AI use cases, they have clear roles defined for data Foundational 29% Foundational 29%
governance and they are able to trace all of their data throughout
the lifecycle, all the way back to the source. Our research shows
that a modern data foundation is yet another threshold separating
Reinvention-ready companies from their peers (Figure 5).
Organizations can trace data from
the source through the lifecycle
Reinvention-ready 60%
16
Automated
34%
Foundational 27%
snoitarepO
esirpretnE
gnitnevnieR
The path to
Intelligent Operations
Our 2024 research as well as anecdotal evidence from more than 1,000 completed gen AI
projects show a correlation between an organization’s investment in Intelligent Operations
and its ability to scale gen AI. We’re finding that companies with Intelligent Operations are
able to accelerate their use of gen AI, which then drives the evolution of their operations,
which then extends their use of gen AI and so on. It’s a virtuous but co-dependent cycle.
Our research indicates that the number of
organizations with Intelligent Operations
is increasing each year.
But charting out a well-defined roadmap continues to be one of the biggest
18
challenges they face. What’s the best path forward? What are the non-negotiable
elements that must be addressed at each stage of the journey? Here are four
actions organizations should take to chart a course, identify gaps and move
forward with Intelligent Operations.
snoitarepO
esirpretnE
gnitnevnieR
01
Implement a domain-centric
approach to data modernization
Reinvention-ready companies have centralized data governance and a
domain-centric view of data modernization. This creates a strong data
foundation that is ready for AI-led reinvention.
One way to evaluate a data foundation is to evaluate how the three 19
enablers—Talent, Assets & Platforms, and Methods & Processes—interact
with data on an everyday basis. Do people have a clear understanding
of how to create, handle and consume data? Are processes and tools
connected across functions so different teams—sales, supply chain,
service, HR, finance, R&D—all have access to the same data and analytics
using their favorite tools? Is data structured in a standardized way, with
security and accessibility baked in, using common data formats that allow
it to be accessed by AI tools across the business?
snoitarepO
esirpretnE
gnitnevnieR
These are the hallmarks of a modern data foundation. And it’s where most companies struggle. Modernizing
the data foundation takes a significant amount of time and resources. Our research shows that 71% of
Foundational organizations have a data foundation that isn’t modernized enough to get the full value of gen AI
across the organization.
Access to quality data is a key consideration. More than one in three Reinvention-ready organizations enable
high-speed access to quality data and metadata assets that are free of inconsistencies and redundancies.
This is made possible by placing equal responsibility on business teams and domain experts to modernize the
data foundation (Figure 6).
15%
19%
20
35%
26%
Reinvention-ready Automated
Insights-driven Foundational
snoitarepO
esirpretnE
gnitnevnieR
“
I think understanding the data
governance process is so critical.
Communicating that across the
organization requires a lot of education
which should not be underestimated
even though it may be obvious.”
Chief Data Officer, 20
Global Real Estate Services Provider
snoitarepO
esirpretnE
gnitnevnieR
Figure 6: Error-free data assets with supporting metadata
Client story
New data foundation drives $70M in new growth
This industrial giant that manufactures tools and New managed service centers based on the SAP
industrial equipment has grown rapidly by placing S/4 HANA platform are now used to deliver the
the right bets—not only on new products and ways of processes. The company also implemented a new
working but also on digital technologies to optimize data foundation—which involved a revamp of data
its finance operations. Digital transformation and strategy and governance—alongside a Center of
growth initiatives were crucial to the company’s Excellence to boost analytics capabilities. Using
ability to integrate acquisitions and support rapid Accenture’s AI-powered SynOps platform, this client
growth. Accenture collaborated with the company has streamlined its operations, centralized 80% of its
to develop an agile and resilient finance operating accounting processes, improved efficiency by 47%,
model, centralizing key processes like Procure to Pay achieved 50% touchless transactions and generated
(PTP), Order to Cash (OTC), Record to Report (RTR) up to $70 million in new business value.
and customer service.
21
snoitarepO
esirpretnE
gnitnevnieR
02
Embrace a talent-first
reinvention strategy
Leading organizations put people at the center of reinvention.
In the age of AI, that means reshaping the workforce so that new roles align to
business needs as the technology evolves. It means offering comprehensive
training to workers so they can thrive in their roles and take full advantage of
the power of gen AI. It means reinventing work and rethinking processes and
entire workflows to gain a clear view of where gen AI can have the most impact
in serving customers, supporting people and achieving business outcomes.
This deep dependency on people is often overlooked while planning for 22
gen AI-powered reinvention. Our research shows that 82% of Foundational
organizations do not have a talent reinvention strategy in place. They’re not
planning ahead to meet workforce needs, acquire new talent or train and
upskill workers to prepare them for gen AI-led workflows.
snoitarepO
esirpretnE
gnitnevnieR
By comparison, 92% of Reinvention-ready Change management programs should be
organizations have a well-defined talent designed to help teams adapt to new workflows
strategy to address workforce planning, role and embrace AI-driven process innovations.
reinvention and continual upskilling (Figure 7).
This ensures they have a strong talent pipeline
that is aligned to their strategic priorities.
Figure 7: Organizations investing in a three-pronged talent strategy
1%
Talent strategy must go beyond skills
development. Programs and policies must be
in place to ensure employees are physically,
emotionally and financially safe, that their work
is meaningful and their everyday goals motivate
19%
them. This has the added advantage of
attracting new hires with different backgrounds
and lived experiences who can bring cognitive
92%
diversity and informed perspectives to the
continuous journey of reinvention.
23
A strong talent strategy will also address
upskilling and learning. Training programs for
61%
non-technical teams should focus in three
areas: AI literacy programs should teach the
basics of gen AI including its capabilities,
limitations and risks. Practical applications
training should use workshop and sandbox
Reinvention-ready Automated
environments to demonstrate how AI can
enhance specific business functions like
Insights-driven Foundational
marketing, customer service and operations.
snoitarepO
esirpretnE
gnitnevnieR
“
A key measure of success is
productivity and reducing repetitive
tasks that give our people more time
to spend with our customers and
working on dealing with the more
interesting parts of their role. Project
specific measures include improving
code quality and simplifying processes
so that the bank can reduce servicing
times for customers.”
Les Matheson,
Group Executive Digital,
Data and Chief Operating Officer, NAB
Client story
Reinventing HR services and employee experience
HSBC, one of the world’s leading financial solutions from SAP, ServiceNow and MuleSoft
institutions, launched a global initiative to to streamline HR processes and improve
enhance employee experience and increase service accessibility. HSBC employees are
productivity with the goal of boosting now able to instantly access information to
shareholder returns and customer satisfaction. make informed decisions and can access HR
This transformation required HSBC to modernize services and support faster than ever before.
and digitize its HR function to address the The improvements encompass core services
challenges posed by manual, fragmented legacy such as payroll and workforce administration as
processes across different countries. well as new capabilities in talent management,
career development and performance
management. With faster access to data-led
Accenture helped HSBC implement technology
insights, HSBC leaders are better equipped to
and change management solutions including
make strategic decisions regarding their teams
experience design, global process configuration
and personnel. 24
and localization to comply with country-specific
regulations. The overhaul introduced digital HR
Intelligent Operations enables gen AI, which improves
Intelligent Operations, which further advances gen AI.
It’s a virtuous but co-dependent cycle.
snoitarepO
esirpretnE
gnitnevnieR
03
Link business and tech teams
to co-own reinvention
Gen AI is more than a technology. It’s the driver of a cultural shift that affects the
entire enterprise.
So it’s vital that tech and business teams co-own outcomes and work together
when making decisions around gen AI. That means reimagining how teams
collaborate and design solutions.
This is one of the starkest differences between Reinvention-ready and
Foundational operations. In our research, 87% of Reinvention-ready companies
stand out for “extensive collaboration” between their tech and business teams. 25
These organizations have created a culture of cross-function collaboration where
formerly siloed teams work together to identify and prioritize gen AI use cases
that align to the organization’s strategic goals. Collaboration between teams then
drives innovation as both teams jointly own how assets, platforms and products
are developed to leverage the full capabilities of gen AI across the enterprise.
By comparison, 88% of companies with Foundational operations say there is little
or no collaboration between their tech and business teams. This hinders their
ability to adopt modern data, automate processes and deploy AI.
snoitarepO
esirpretnE
gnitnevnieR
At the end of the day, gen AI is a technology, so internal resistance to change. CEO oversight also signals
tech teams play a vital role in merging it with the project’s importance to stakeholders, boosting
the organization’s digital infrastructure. Tech morale and commitment across the organization.
teams must assess and select from among Organizations that are Reinvention-ready understand
various AI technologies that can be integrated this and are driving large gen AI-powered transformation
into the existing tech stack. They need to programs directly from the CEO’s office (Figure 8).
manage the technical aspects of integration,
including software development, system
configuration and data integration and then
Figure 8: Tapping CEOs to lead adoption
maintain the overall performance of the tools.
They also must ensure that ecosystem partners
27%
and applications are seamlessly integrated and
help assess ongoing performance to make
sure gen AI solutions remain up to date and
effective. All of this should happen with direct
input from business teams. Together, business
36%
and tech teams create the gen AI roadmap,
share decision-making authority and define
53%
goals and outcomes.
26
An organization’s CEO should take a
leading role in fostering cross-departmental
47%
collaboration, prioritizing resources and
nurturing a culture of innovation. Under the
CEO’s leadership, tech and business teams
should be assigned equal responsibility
for identifying the path forward for gen AI
Reinvention-ready Automated
adoption. The CEO’s influence breaks down
silos, streamlines decision-making and reduces
Insights-driven Foundational
snoitarepO
esirpretnE
gnitnevnieR
“
As you start with a large
transformation program there is
always a capability gap. Take time to
select the right team from business
and technology, and let collaboration
bridge the capability gap.”
Chief of Revenue Growth,
Global Personal Care and Cosmetics Company
Accenture story
Accenture links business and tech teams to co-develop gen AI assets and platforms
Scalable gen AI use cases by function
Layer 3
Digital Platforms Finance Operations Supply Chain Marketing & Sales
HR Transformation
Domain-specific gen AI Transformation Transformation Transformation
use cases
Business Teams
Accenture SynOps
Technology Teams Common assets and services layer
Broad use cases with Multi-language search and extract Development Developer co-pilots
Layer 2 multi-department applications Multi-language document creation Enablers AI driven workflows
27
Data & AI Backbone
Common assets and services
for gen AI foundation Prompt Library, Knowledge base-as-a-service, Translation, etc.
gen AI digital foundation Cloud LLMs/ On Site LLMs with a custom wrappers
Trust & Safety, Quality, Accuracy, Ethics and Responsibility
Enterprise Digital Core
Layer 1
Digital Foundation Cloud-first Infrastructure Continuum Control Plane Security Composable Integration
Enterprise Digital Core
optimized for gen AI
snoitarepO
esirpretnE
gnitnevnieR
“We have set up a
transformation office under the
CEO. It tackles the multiple
mobilization challenges that
require a dedicated effort. It is
like a SWAT team handpicked
from Operations, HR, Finance,
and other enterprise functions.”
VP, Strategy & Business Transformation,
Tier-1 Automotive Supplier
Client story
Marrying tech innovation to human ingenuity
National Australia Bank (NAB), one of Australia’s four and protected is also at the forefront of minds at NAB,
major banks, is focused on developing products and and strict data and AI guardrails are applied to embed
solutions that meet the real needs of real people. safety from day one.
Led by NAB’s CEO and executive team, its people
are seizing on the new opportunities that allow them
The bank started with six use cases in mid-2023 to
to spend more time on complex matters and better
prove that each project could help cut the ‘drudgery’
support customers.
for its people. More than 20 use cases are now
being tested across the company and are showing
NAB has been assessing new ideas and opportunities compelling results. Legal document reviews have been
with gen AI through several lenses. Shortlisted ideas cut down from three days to one and higher-quality
are put into test-and-learn development cycles to code is being developed faster. Simplified, automated
guide their evolution for greatest value, return and processes are also improving customer outcomes –
impact for customers. How data would be governed a key measure of success.
28
“We want to ensure we are investing in the right place and not just building ‘cool
toys’ that do not meet our customers’ needs. That’s why the development of use cases
for gen AI is the responsibility of individual business units. They are best placed to
determine how investment will best support the needs of their customers.”
Les Matheson,
Group Executive Digital, Data and Chief Operating Officer, NAB
snoitarepO
esirpretnE
gnitnevnieR
04
Adopt leading processes to
drive business outcomes
According to our research, 87% of companies that are Reinvention-ready
say they have applied leading cloud-based practices to business processes
and process mining and have enabled internal and external benchmarking
to drive performance. By comparison, only a small minority of companies
in the Foundational and Automated tiers of Intelligent Operations— 5% and
20% respectively—have done the same.
Cloud-based process mining calibrates internal and external benchmarks
so it’s easier to visualize process gaps. This can speed gen AI adoption
by providing clear insights into operational inefficiencies while flagging
29
opportunities for improvement. Organizations get the data they need to
analyze their processes and identify areas where AI can add the most
value. With accurate benchmarks, organizations can set realistic targets
and simulate the impact of AI interventions using digital twins. This data-
driven approach ensures that AI initiatives are aligned with strategic goals to
improve decision-making and drive exceptional business outcomes at scale.
snoitarepO
esirpretnE
gnitnevnieR
None of this can happen without clean, readily available data. Figure 9: Speeding access to clean data
Companies that are Reinvention-ready stand out for their ability to
access that data at speed (Figure 9).
27%
Centralized data governance is |
90 | accenture | Accenture-Work-Can-Become-Era-Generative-AI.pdf | Work, workforce, workers
Reinvented in the age of generative AI
Contents
03 04-08 09-13 14-17 18-25 26-40 41-42
Preface Executive The gen AI Conflicting The trifecta of Gen AI GPS Prospects
summary state of play views erode opportunities: ahead
Charting the path
trust economy,
to realize gen AI’s
business,
full potential
people
Accelerator 1:
Lead and learn in
new ways
Accelerator 2:
Reinvent work
Accelerator 3:
Reshape the workforce
Accelerator 4:
Prepare workers
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 2
Authors Preface
Ellyn Shook Generative AI has burst onto the scene. It appeared fast and is evolving even faster. To date, our
Chief Leadership & Human teams have already worked on over 700 client projects. We’re seeing what success looks like—
Resources Officer and sharing it here.
Accenture
We know that achieving gen AI’s full potential hinges not just on a strong data foundation, but
also on leaders’ willingness to lead and learn differently. This makes it possible to navigate the
risks and seize the huge opportunity before us to reinvent work, reshape the workforce and
prepare people, responsibly. No other modern technology has impacted these areas to such a
degree—and we’re all about to experience it. However, similar to when digital came on the scene,
the rush for pilots and experimentation is too often leaving robust talent strategies behind.
Paul Daugherty
To spotlight the importance of focusing on talent early, our research brings data to the
Chief Technology &
groundbreaking reality that we’re seeing every day. As you dive into these insights, know that this
Innovation Officer
is the start of a journey like no other. We're exploring how gen AI is changing the game and how
Accenture
we can all come out ahead – as businesses, as leaders and as people.
Here's to exploring the age of generative AI together.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 3
Executive summary
Work reinvented, workforce reshaped, workers prepared
“Generative AI has the potential to If the paragraph on the left sounds like a robotic answer to the question,
“How will generative AI (gen AI) change work?” that’s because it is—it’s
significantly change the nature of work
a response generated by ChatGPT. While it’s correct to a degree, this
across various industries and fields. While answer overlooks how gen AI’s impact on value chains will fundamentally
transform the nature of work, reshaping how businesses deliver value
generative AI has the potential to bring about
and better experiences for employees and customers. Such details and
numerous benefits, it also raises ethical and insight are ones that only humans can bring to monumental questions
such as this. An even better answer is much shorter:
societal concerns, including issues related to
It depends on people and how they use it.
job displacement, data privacy, protection of
More specifically, it depends on leaders having the courage, knowledge
intellectual property, bias and the responsible
and understanding to shape the future. They will need to prioritize
use of AI. The impact of generative AI on
human-centered change efforts and learn in new ways to scale this
groundbreaking technology responsibly, to create value and to ensure
work will depend on how it is implemented,
that work improves for everyone. This means setting and guiding a vision
regulated and integrated into various
for how to reinvent work, reshape the workforce and prepare workers
for a generative AI world, while building a resilient culture to navigate
industries and organizations.”
continuous waves of change.
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 4
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Invest in people to
reinvent work
The impact and importance of what people
do with generative AI today and tomorrow
cannot be understated. In this age, gen AI
is influencing more than just productivity;
it’s impacting processes across the value
chain, changing the work itself.
Due to its ubiquity across job types and potential to
create exponential impact,1 gen AI is poised to provide
the most significant economic uplift and change to work
since the agricultural and industrial revolutions. The early
industrial revolution, for example, was marked by mass
production and standardized outputs. The age of gen AI
will be defined by not only productivity gains but also by
enhanced human creativity and potential to shape more
innovative employee and customer experiences.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 5
For the first time in history, we are embracing a generation In fact, our research shows that generative AI offers Most organizations view gen AI as a path to greater
of technology that is “human by design.” Gen AI’s a trifecta of opportunities: it can accelerate economic innovation, presenting more of a revenue-growth play
effectiveness hinges on human input to drive quality value and increase productivity that drives business than a cost-reduction play. And when it comes to the
outputs—whether they’re straightforward, like the draft of growth, while also fostering more creative and meaningful workforce, Reinventors (representing 9% of organizations)
an email, or complex, like a financial forecast. This shift work for people. are 2x more likely than other organizations to anticipate
will lead to a reinvention of work with more human-centric productivity gains of 20% or more in the next three years.
Comparative analysis of global gen AI adoption and
processes across the entire value chain. By synthesizing And two out of three strongly agree that, with gen AI,
innovation scenarios shows that more than $10.3 trillion
data, comprehending natural language and converting work will become more fulfilling and meaningful.4
in additional economic value can be unlocked by
unstructured data into actionable insights, gen AI is
2038 if organizations adopt gen AI responsibly and at
democratizing business process redesign, empowering
scale (industry by industry, value chain by value chain).2
everyone—from frontline workers to lab scientists to design
This potential is reflected in CxO optimism, with most
professionals—to reshape their own workflows.
believing gen AI will ultimately increase their company’s
Gen AI can also bring workers closer to their customers. market share, and 17% anticipating an increase in market
Imagine a banking scenario where gen AI transforms the share by 10% or more.3
customer experience: from using AI-powered analytics 95
to gain a comprehensive view of customer needs, to
customizing financial products and services based on %
of workers see value in working with gen AI—but their
those needs. This end-to-end change not only streamlines
top concern is that they don’t trust organizations to
operations; it also helps bankers know their customers
better, identify new products and improve experiences ensure positive outcomes for everyone.5
for both customers and employees. All these outcomes
positively impact the bottom-line.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 6
Our research explored the factors that contribute to this There’s a way, however, for leaders to close the trust gap Our research also highlighted the need to meet peoples’
trust gap. Currently, three-quarters of organizations globally and accelerate gen AI integration: Look at and emulate fundamental human needs, so they feel Net Better Off15 at
lack comprehensive strategies and initiatives to ensure how leading organizations are leveraging gen AI in ways work. Why? Because it is a clear pathway to strengthening
positive employee experiences and outcomes with gen AI.6 that are better for business and better for people. trust and getting people ready for, and comfortable with,
And two-thirds of CxOs we surveyed confess that they are gen AI. Indeed, by helping their people deepen their trust
Follow the Reinventors
ill-equipped to lead this change.7 Misaligned perceptions in the company and their colleagues, build market-relevant
between leaders and workers also erode trust. When it skills, work with purpose and strengthen their emotional,
Accenture’s research reveals that of the 9% of
comes to job security, 58% of workers are worried,8 yet less physical and financial health, an organization can unlock
organizations that have achieved the capability for
than one-third of CxOs feel job displacement is a concern two-thirds of an individual’s potential, which can lead to a
continuous reinvention (Reinventors), nearly half (47%) of
for people.9 There’s another disconnect when it comes to 5% revenue boost.16
them are already thinking bigger—recognizing that their
well-being, with 60% of workers concerned that gen AI may
processes will require significant change to fully leverage
In this age of gen AI, leaders should view their people
increase stress and burnout,10 compared to only 37% of
gen AI. And more than half (52%) are already taking
not as passengers on the journey, but as navigators.
leaders who see this as an issue.11 This lack of trust puts the
action to reshape the workforce by redesigning jobs and
Reinventors recognize this. And with a small percentage of
trifecta of opportunities at risk.
roles around gen AI. Key to all of this: three-quarters are
organizations currently leading the way, there’s substantial
actively involving their people in their enterprise change
opportunity to be among the front-runners. Success relies
Despite 94% of people saying they
efforts, while reskilling people. These organizations are
heavily on leaders who act with compassion and humility,
are ready to learn new skills to breaking down silos and making data accessible to all
and who create the conditions so that their people feel Net
employees, fostering transparency and building trust
work with gen AI,12 only 5% of Better Off at work.
among their people.14
organizations are actively reskilling
their workforce at scale.13
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 7
“Gen AI heralds the most significant
disruption to organizations—and, in my
case, to the newsroom—in the last 25
Prepare workers
Lead and learn years. Approached responsibly, it could
help the most important and respected
in new ways
Reinvent work
media companies provide an even
better and more accurate service and
Reshape the workforce
product going forward. It’s the people,
not technology, who understand the
purpose of the company and what it’s
trying to achieve.”
Our gen AI “GPS” later in this paper shows how Before diving into the gen AI GPS, we set the William Lewis, Chief Executive Officer and Publisher,
to navigate the journey ahead and is focused stage by examining the current state of gen AI, The Washington Post
on four accelerators. It emphasizes leaders as well as the conflicting views surrounding it. An
committed to continuous, deep learning and understanding of both is essential to fully realize
leading in new ways, along with human-centered the potential of gen AI for organizations, people
change management to reinvent work, reshape and society.
the workforce and prepare workers so they are
resilient for whatever tomorrow holds.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 8
Where we are today
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 9
The gen AI
AI’s evolution has been marked by three phases of significant advancements. The
Diagnostic Era was largely defined by the introduction of machine learning. The
Predictive Era gave us the ability to make increasingly accurate forecasts about
state of play
everything from operations to customer behavior. And late 2022 saw the dawn of the
Generative Era. Now, machines aren’t just predicting with high accuracy, they’re also
generating creative content and offering personalized suggestions (see Figure 1).
Figure 1. Welcome to the age of generative AI
Source: Accenture 2024
Diagnostic Predictive Generative
Why did this What might happen What should How can AI h e lp
happen? in the future? we do next? with the execution?
Analyze Pattern Simulate Advise Automate
Scenario Forecast Optimize Create Protect
SegmFeOntUNDATIONAL Model Recommend Code MATURE
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 10
These are very early days for generative AI, with most language-task-based21 workers relative to the full working
“If I have a concern
companies still in the planning and experimental stages. population, like in the UK (where 47% of all working hours
anywhere, it’s that people will
But looking across the landscape, several key trends will be impacted). There’s variation across sectors too
are emerging, reflecting gen AI’s influence on business (see Figure 2 on the next page). It’s also important to note underappreciate the need to
reinvention, workforce dynamics, regulatory environments, that people with lower levels of digital skills, less career
have human involvement in
executive perspectives and employee sentiment. These experience and less formal education could be more
the creation of these tools—
trends are important markers for understanding gen negatively impacted, which only highlights the risk of
AI’s current standing, as well as its future potential for exacerbating the digital divide.22 not only human involvement
transforming industries, work and employee experiences.
but the most diverse human
• Regulatory response: Some would argue that regulators
• Driving reinvention: Gen AI is seen as one of the main view gen AI as a proverbial horse having sprinted from involvement, or else we’re just
levers for enterprise reinvention at 81% of companies we the barn, citing for example the Biden administration’s
replicating the bias of human
surveyed,17 yet two-thirds of CxOs do not have the right late-October executive order requiring new safety
decision making.”
skills and capabilities needed to successfully reinvent assessments, equity and civil-rights guidance and
their organizations.18 Data strategy and technology research on the labor market.23 Mere weeks prior, China
Jacqueline Welch,
infrastructure emerge as top concerns for implementing introduced several regulations specifically targeting gen
Executive Vice President & Chief Human
gen AI, with nearly half of CxOs believing they’ll need AI.24 And in December 2023, the European Parliament
Resources Officer, The New York Times
to improve their data strategy to leverage gen AI passed the AI Act which, along with risk-based
effectively.19 regulations, sets transparency requirements for gen AI
usage.25 Increasingly, countries and regions recognize
• Magnitude of impact: Our modeling shows that 44%
the need to urgently establish regulatory frameworks,
of working hours in the US are in scope for automation
including robust IP protection and usage agreements, for
or augmentation.20 This percentage is even higher in
rapidly evolving AI technology.
countries with greater numbers of knowledge- and
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 11
Figure 2. A significant portion of working hours will be impacted (either automated or augmented) by generative AI
23%
23% 22% 22% 19% 22% 21% 22% 20% 21% 21% 21% 18% 20% 18%
19%
17% 18% 17% 16%
15% 15%
24%
Working hours in scope for
augmentation due to gen AI
Working hours in scope for
automation due to gen AI
Note: Estimates are based on
“Human+Machine” identification of
work tasks and exposure to impact
of generative AI.
Source: Accenture Research based
on National Statistical Institutes and
O*Net.
KU adanaC ynamreG ailartsuA napaJ ecnarF SU nedewS ylatI yawroN dnalniF kramneD anitnegrA niapS ocixeM elihC lizarB aibmoloC acirfA
htuoS
aibarA
iduaS
anihC aidnI
22 Countries:
47% 46% 46% 45% 44% 44% 44% 43% 42% 42% 42% 42% 42% 41% 41% 41% 39% 39% 38% 38% 33% 31%
23% 24% 23% 25% 22% 23% 21% 22% 21% 21% 21% 24% 21% 23% 22% 22% 21% 21% 22% 18% 16%
stekraM
latipaC
smroftalP
&
erawtfoS
gniknaB ecnarusnI aideM
&
.smmoC
liateR ecivreS
cilbuP
hceT
hgiH
secneicS
efiL
levarT ygrenE htlaeH evitomotuA ecnefeD
&
ecapsoreA
slacimehC seitilitU lairtsudnI secruoseR
larutaN
sdooG
remusnoC
19 industries:
72% 68% 67% 65% 51% 50% 42% 42% 41% 40% 39% 39% 39% 38% 31% 31% 30% 28% 24%
42%
35% 34%
36%
26% 22%
21% 19% 19% 17% 17% 23% 15% 16%
13% 13% 12%
11%
12%
30% 33% 33% 29% 25% 28% 21% 23% 22% 23% 22% 16% 24% 22% 18% 18% 18% 17% 12%
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 12
• CxO sentiment: Already, 86% of CxOs are using gen AI to some degree
“The uncertainty surrounding the emergence of new
in their work and nearly all believe gen AI will be transformative for their
technologies can often evoke fear. One of the best ways to company and industry. All CxOs surveyed—100%—anticipate changes to
their workforce, e.g., growing or reducing headcount and implementing
combat fear is to educate and get people involved, and the
plans to reskill.26 Yet only one in three leaders believe they have the
companies that do so will have a better chance at creating
technology expertise or feel they can tell a compelling transformation
narrative to lead the change that’s needed.27 This gap in knowledge
increased value for themselves and their customers.”
and confidence impacts both trust and transparency, which is critical to
Christy Pambianchi, Executive Vice President & Chief Human Resources Officer, Intel successfully navigate gen AI transformation efforts at scale.
• Employee sentiment: 95% of employees we surveyed see value in
working with gen AI, and 82% say they already have some understanding
“[Gen] AI can be useful, but at times it can also be
of the technology. However, their biggest concern is trusting their
overwhelming. Because you always get that feeling that organization to ensure positive outcomes for all. Further findings
highlight this concern: 60% of employees worry that gen AI may increase
if you are leveraging AI to work or get your work done,
stress and burnout, 58% feel insecure about their job and 57% need
there is a real possibility that AI can replace you.”
clarity on what this technology means for their careers.28
IT manager, Australian software & platform company Given the progress and trends already witnessed, and perhaps even as a
result, there are conflicting views about the risks, benefits and tradeoffs
involved with using gen AI at scale. We see this as an issue that must be
unpacked and understood to realize the full, positive potential of gen AI.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 13
The trust gap
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 14
Figure 3. Media coverage focused primarily on job displacement immediately
following the launch of ChatGPT, but now focuses more on privacy concerns
Conflicting
and job creation opportunities
Total mentions of gen AI topics
views erode
Q1 2023
trust
Privacy 1,991 317 Personalization
Generative AI's natural language interface increasingly
democratizes technology access to people across Job 5,721 3,226 Job creation
Displacement
industries and roles. Yet transparency and trust are
required for people to effectively adopt and embrace
these tools. Our research indicates that this includes—but Q4 2023
extends beyond—the need for trust in the tool itself: People
also need to trust that the organization will integrate gen
AI in ways that protect and prepare workers.
Privacy 4,489 414 Personalization
Messages in the media reflect where concerns lie.
Following the launch of ChatGPT, the potential for job
displacement dominated media attention; today, gen AI’s
potential for violating data privacy is being discussed more Job 5,480 5,492 Job creation
Displacement
frequently (see Figure 3).29
Source: Accenture Research NLP analysis on news articles (Dow Jones Factiva) across 329,314 articles; Jan 2022 – Dec 2023
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 15
Figure 4. Misaligned perceptions between workers and CxOs on key concerns related to gen AI’s
impact on work, the workforce and workers
Work
58%
Workers say:
Gen AI is increasing my job insecurity
But importantly, our research reveals the specific
trust gap between workers and leaders (see
CxOs say: 29%
Figure 4). To a greater extent than CxOs realize, Job displacement is a concern for our people
workers are asking whether their organization’s
Workforce
gen AI implementation will cost them their jobs
and whether those approaches will lead to stress,
Workers say: 82%
I feel I understand the technology
burnout and overload rather than to a better
employee experience. And they wonder whether
CxOs say: 36%
the tool itself will deliver quality outputs.30 Lack of understanding is a concern for our people
Our surveys also reveal that 32% of leaders see Workers say:
94%
I am confident I can learn the skills needed to leverage
talent scarcity, due to skill gaps or unawareness,
gen AI in my role
as a major barrier in utilizing gen AI. Additionally,
32%
CxOs say:
36% believe workers will not fully embrace gen Lack of worker skills is going to hold us back
AI due to a lack of technological understanding.31
Workers
Yet most workers (82%) believe they grasp the
Workers say:
technology, and 94% are confident they can 60%
I am concerned that gen AI may increase my stress
develop the needed skills.32 and burnout
CxOs say: 37%
Gen AI could contribute to peoples’ stress and burnout
Workers say: 53%
I am concerned about the quality of output
CxOs say: Sources: Accenture Pulse of Change survey, Wave
21%
Trusting the quality of output is a concern for our people 10 (Sept 2023): n=2,425 CxOs. Accenture Change
Workforce Survey (Oct-Nov 2023): n=5,000 employees.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 16
Further, while generative AI offers great potential to increase
efficiency and reduce human errors, there’s an inherent risk of
over-reliance on this technology at the expense of finding the
right blend of human intelligence and AI capability.
Understanding and closing the trust gaps—not merely
observing them—is crucial for business and societal leaders
working to deploy gen AI responsibly. By proactively resolving
these challenges, we don’t just acknowledge them; we turn
them into opportunities to get ahead in the Generative Era.
“I think gen AI’s greatest power is that it will help
us be more creative and advance our productivity as
human beings. However, there does need to be some
line there. We can’t have it set up to where it’s doing
everything for us.”
Purchasing & logistics manager, US consumer goods & services company
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 17
The trifecta of
opportunities
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 18
The trifecta of opportunities:
economy, business, people
Even with a year’s hindsight on generative AI's role in our
everyday lives, harnessing the trifecta of opportunities to
accelerate economic value, drive business growth and create
more meaningful work for people is an ongoing effort. For
each opportunity, the incentive only grows when people
are the navigators along the path to achieving gen AI’s full
potential. While previous transformations focused mainly on
workforce productivity, this age of gen AI will revolutionize work
and workflows across the entire value chain. Our research is
bringing into clearer view the big upside of integrating gen AI
responsibly.
Economic upside
Our modeling reveals insights from three economic growth
scenarios, each based on the pace of gen AI adoption and
innovation. Among them, the “people-centric” scenario—
where organizations adopt gen AI responsibly at scale, in ways
that place people and innovation at the heart—stands out,
potentially creating an additional $10.3 trillion in economic
value by 2038 (see Figure 5 on next page).33
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 19
Figure 5. Companies can unlock an additional $10.3 trillion in economic value by adopting responsible, people-centric approaches to gen AI
120,000
115,000 +$17.9 trillion USD against baseline
10.3
$
trillion USD +$13.5 trillion USD against baseline
110,000
additional value unlocked by 2038
105,000 +$7.6 trillion USD against baseline
100,000
95,000
90,000
People-centric scenario: Companies
adopt in ways that place people and
85,000
innovation at the center
Cautious scenario: Companies adopt
80,000
slowly, placing risk aversion at the center
Aggressive scenario: Companies adopt
75,000
quickly, placing cost-cutting at the center
Baseline expected growth
70,000
2023 2028 2033 2038
Source: Accenture Research. Simulated GDP growth under three scenarios. GDP forecasts from Oxford Economics across 22 countries.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 20
Business upside
Most CxOs believe gen AI will ultimately increase their Moreover, Reinventors (the 9% of organizations that
company’s market share, with 17% of them predicting lead in reinvention) are 2x more likely to anticipate a
that gen AI will increase their market share by 10% or productivity gain of 20% or more in the next three years.38
more.34 This confidence stems from gen AI’s ability to By intentionally involving their people in the change, such
help companies free up capacity and improve how they organizations are not only working to close the trust and
identify, reach, connect with and deliver to customers. transparency gap, they’re also increasing their chances to
Fittingly, more CxOs view gen AI as a tool for revenue reinvent at speed and scale by 1.7x and 1.6x, respectively.39
growth rather than for reducing headcount.35 In fact, our
modeling suggests that companies planning to reinvent
work—by integrating gen AI more deeply across functions
“At Mizuho, we’re focused on the future and thinking more broadly
and business processes at scale—expect to overtake the
revenue growth of even today’s leading companies in the about how our industry can transform by having gen AI in the
next five years.36
market and within our workforce. Managing this change effectively
Technology like gen AI is recognized by executives not is extremely important—especially communicating with employees.
just as a revenue driver, but also as a force of disruptive
People are wondering about the impacts and leaders need to take a
change. Importantly, so is talent. Our previous research
highly personalized approach. Talk with each individual about their
has shown that technology alone will not drive gen AI-
enabled growth; instead, prioritizing people alongside data
experiences, skills and potential expanded opportunities.”
and tech can lead to productivity gains of up to 11%, while
sidelining the human factor slashes that gain to just 4%.37
Makoto Umemiya, Deputy President & Senior Executive Officer and Group Chief Digital Officer,
Mizuho Financial Group
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 21
People upside
"Our goal is to really make AI helpful for everyone by improving Working with technology that is “human by design”—like
gen AI-powered agents and innovative digital spaces—
knowledge, learning, creativity and productivity, and enabling
enables people to enhance their productivity, creativity
others to grow through building and deploying AI responsibly.
and human potential. Moreover, among the Reinventors,
In the workplace, that means making the most of opportunities two-thirds strongly agree that, with gen AI, work will
become more meaningful, creative and impactful.40
to use AI to help people and teams work more effectively and
increase their impact. One thing that won’t change is that work Ultimately, gen AI presents a new, higher-stakes scenario
to reshape the workforce and prepare individuals to
is still centered around humans, so that people can bring their
transition from being focused on one or two areas of
creativity, which is such an important human trait.”
expertise (with supporting skills), to mastering multiple
interconnected capabilities at once.
Fiona Cicconi, Chief People Officer, Google
Such a shift presents an opportunity to create a more
agile and adaptive organization through, for example,
tailored learning pathways aligned to each worker’s
needs and aspirations. But this will only be achieved
if there is a culture of transparency and trust—and
executives have a significant role to play in exemplifying
these values.
IA
evitareneg
fo
ega
eht
ni
detnevnieR
:srekrow
,ecrofkrow
,kroW
Contents | Preface | Executive summary | The gen AI state of play | Conflicting views erode trust | The trifecta of opportunities | Gen AI GPS | Prospects ahead 22
Accenture’s research has shown that helping people
to become “Net Better Off” unlocks nearly two-thirds
If your people are Net Better Off
(64%) of a person’s potential at work. We showed that
when firing on all four dimensions, organizations can
01
unlock the potential of their people and ultimately
They're healthy and well—physically,
deliver 5% greater revenue growth.41 And our latest
emotionally and financially
research shows that leaving people Net Better Off is
a clear pathway to closing the trust gap and getting
02
people ready for, and comfortable with, generative They're connected, with a strong
AI. For instance, workers who are highly Net Better sense of trust and belonging
Off had a 19 percentage point greater incidence of
“strongly agree” responses regarding their comfort
03
with the technology—particularly in terms of how Their work has purpose
they can apply it to their work (see Figure 6 on the
next page).42
04
They ha |
91 | accenture | Reinvention-in-the-Age-of-Generative-AI-Report-Accenture-var3.pdf | Reinvention
in the age of
generative AI
South Africa’s formula for
success amid change
Contents
04-05 06-09 10-14 15-16 17-26
Executive Reinvention in Barriers to Generative AI Five key
summary the face of radical reinvention in enables and imperatives to
disruption South Africa accelerates drive reinvention
reinvention with generative AI
The widening value gap Legacy systems limit agility,
driving up technical debt
Imperative 1: Lead with value
Fragmented
Imperative 2: Understand
implementations, misaligned
and develop an AI-enabled,
goals hinder transformation
secure digital core
Skills gap limits digital core
Imperative 3: Reinvent talent
growth, development and
and ways of working
generative AI adoption
Imperative 4: Close the gap
on responsible AI
Imperative 5: Drive
continuous reinvention
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 2
Authors
Vukani Mngxati Yusof Seedat
CEO and Board Chairman Thought Leadership Director
Accenture Africa Accenture Research
Hina Patel Mayuri Naik
Data and AI Lead Africa Research Lead
Accenture Africa and UKIA Accenture Research
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 3
EXECUTIVE SUMMARY
South African businesses Imagine boosting productivity threefold, South Africa’s business environment In 2022, we predicted that companies
cutting product development timelines in is a mix of old challenges and new that embrace reinvention would dominate
stand at a defining point.
half or doubling revenue through hyper- opportunities. On the one hand, the coming decade. Today, we see that
Over the next 12 to 24
personalized customer experiences. industries—from mining and telecom to prediction coming to life. Globally,
These aren’t distant possibilities—they are financial services—have deeply ingrained forward-thinking organizations are pulling
months, generative AI will
within reach for companies that act now. legacy systems that resist transformation ahead, leaving competitors behind. Now
either unlock new pathways
Our estimates show that the responsible, and change. On the other hand, the in 2024, we have more recent evidence
to growth or widen the gap people-centric adoption of generative AI country’s young, tech-savvy population that reinvention, enabled by generative AI,
in South Africa has the potential to unlock presents a massive opportunity to create will become the default strategy for those
between those that adapt and
additional growth by up to $82 billion a skilled, future-ready workforce that can determined to shape the future.
those left behind. The stakes
over 15 years. By embracing generative AI, fuel AI-driven innovation.
Our research on reinvention reveals that a
South African businesses can revolutionize
are enormous.
But the window for action won’t be open digital core is essential for companies on
their operations, drive exponential growth,
for long. South African businesses must the path of continuous reinvention. Such
reduce costs and create entirely new
urgently decide whether they will take a digital core has three groups of distinct
revenue streams.
proactive steps to reinvent themselves but constantly interacting technologies:
However, the cost of inaction will be steep. or risk being left behind. Generative AI digital platforms, a data and AI backbone,
Companies that hesitate and remain on offers a rare chance to leapfrog global and the digital foundation, which includes
the sidelines will find themselves stuck, competitors by reimagining how work composable integration, cloud-first
saddled with legacy systems and buried gets done, how products and services are infrastructure, a continuum control plane
under technical debt. They will lose market delivered and how businesses connect and security.
share to nimbler competitors who have with their customers.
seized the AI advantage to innovate and
reshape market and industry standards.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 4
It enables organizations to accelerate
ahead of the competition and achieve their
1/ 2/ 3/
ambitions—using the right mix of tools and
practices for agility and innovation.
However, in South Africa, many businesses
Understand and
are still struggling to translate technology
develop an AI- Reinvent talent
investments into meaningful returns.
Technical debt is piling up, digital cores enabled, secure and ways of
are underdeveloped and there is a critical
Lead with value digital core working
misalignment between IT and business
objectives. The gap between investment
and outcomes is widening—and time is
running out for South African companies
to get it right.
4/ 5/
To seize the opportunity to reinvent with
generative AI, South African companies
must take immediate and decisive steps.
Our research identifies five key imperatives
for success.
Close the gap on Drive continuous
responsible AI reinvention
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 5
About the research
We took a multi-method This report is based on
approach again this year to
A multi-year survey of over 3,000 executives across The annual Pulse of Change Index, which quantifies the
research the topic of Total 19 industries and 10 countries. Respondents were level of change affecting businesses globally, caused by six
asked about their organization’s approach to business major factors: technology, talent, economic, geopolitical,
Enterprise Reinvention.
transformation and reinvention strategy, as well as about climate, and consumer and social. The index provides
their specific programs and success factors. The surveys context to the need for reinvention.
were conducted in November 2022 and from October
Economic modelling to forecast the potential impact of
to November 2023, and replicated for 100 South African
generative AI on productivity and growth for the economy,
companies from March to May 2024. In this report, we
organisations and people. We mapped out the future
provide comparisons between the two, focusing on new
growth trajectories under three different AI deployment
insights gained from the most recent fieldwork.
scenarios: aggressive, cautious and our proposed people-
Financial and non-financial analyses and econometric centric approach.
modeling to assess the performance impact of adopting
a reinvention strategy. The analysis combines data from
publicly available achieved results, analyst expectations
and survey data to create a robust view of both historic
and future performance.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 6
7
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
7
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Reinvention in the face
of radical disruption
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook
Figure 1
Has your organization adopted a deliberate strategy to reinvent
the way it operates across the enterprise in the past 3 years?
We are living through an era
of radical disruption, where
Yes, we’ve adopted an organization
56%
continuous reinvention— or enterprise-wide strategy to reinvent
all functions and business units
driven by rapid technological
advancements and
Yes, we’ve adopted a strategy
42%
to reinvent most functions and
accelerated by generative AI—
business units/departments
is the cornerstone of success.
Yes, we’ve adopted a strategy
1%
to reinvent some functions and
In South Africa, 99% of C-suite executives
business units/departments
we surveyed have, over the last three
years, adopted deliberate strategies
No, we have not adopted
to reinvent the way their organizations
a reivention strategy
operate (Figure 1).
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 8
Figure 2
Our research shows South African Which of the following best describe the role that you expect
leaders very well understand the crucial generative AI will play in driving each of the following in
role technology, especially generative
your organization over the next three years?
AI, plays in their reinvention journey—
and the urgency to act swiftly. In the
The #1 lever One of the main levers A minor lever (e.g., through experiments/pilots)
last year alone, 98% of executives have
fast-tracked their reinvention strategies
in response to external pressures like
47% 48% 5%
Reinvention strategy
inflation, evolving consumer expectations
and the relentless pace of technological
change. Furthermore, 95% acknowledge 43% 44% 13% 58
Incremental revenue growth
that technology is foundational to every %
current and future reinvention initiative.
Generative AI is emerging as a key driver Cost reduction/ 33% 51% 16%
P&L improvements
of reinvention, contributing to incremental of executives
revenue growth, cost reduction, new
40% 46% 14%
New ways of working anticipate that
ways of working and overall productivity
improvements (Figure 2). Fifty-eight
generative AI will
percent of executives expect it to boost Disruptive innovation 37% 46% 17%
(i.e. New revenue growth)
productivity by more than 20% within the boost productivity
next three years.
Employee productivity 47% 47% 6% by over 20% in the
(i.e. output per hour worked)
According to Accenture’s proprietary
next three years.
analysis, the responsible, people-centric
adoption of generative AI can elevate
South Africa’s overall economic growth by
up to $82 billion, adding an extra 17.5% to
the country’s forecasted GDP by 2038.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 9
Figure 3
The widening value gap
However, despite high expectations—and
sizable investments in technology and 170
AI, including generative AI—reinvention
efforts are falling short, and most
160
companies are not seeing the returns they
anticipated. There is a clear disconnect
between technology investments and
140
actual business outcomes (Figure 3). In
2023, our research indicated a 64% gap
between technology spend and business
120
growth.1 In 2024, this value gap has
widened to 98%, with aggregate business
revenue growth dropping to 2020 levels.2 100
The upshot: Spending alone will not drive
reinvention. Without strategic alignment
80
between technology investments
and business objectives, companies 2017 2018 2019 2020 2021 2022 2023
risk further disconnect between their
aspirations and results.
)001
ot
desaB(
htworG
+98%
IT spend
+64%
+32%
+46%
+19%
+16%
Aggregated
revenue
Source: IDC, S&P Capital IQ (Data shown for South Africa)
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 10
Barriers to
reinvention
in South
Africa
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
1111
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook
89
The reasons for these Legacy systems limit agility, Fragmented implementations,
%
diminishing returns on driving up technical debt misaligned goals hinder
reinvention efforts are clear: transformation
Legacy systems weigh heavily on many of South African
legacy systems; fragmented
South African companies, creating barriers
Our research shows that half of reinvention
C-suite executives
to progress by limiting agility and stifling
implementations with
programs in South Africa are confined to
innovation. This isn’t just a theoretical
specific departments or functions, missing acknowledge that
misalignment between
issue—industries like mining and telecom
the opportunity to drive enterprise-wide
business and IT objectives, are already facing the consequences in legacy infrastructure
impact. This lack of cohesion prevents
the form of job cuts and closures as they
leading to ineffective organizations from realizing the full
hinders their business
struggle to modernize quickly enough.
benefits of their investments. Moreover,
change management; and a
only 42% of leaders report a clear agility and contributes
In fact, 89% of South African C-suite
lack of necessary skills and
alignment between business and IT goals,
executives acknowledge that legacy
to accumulating
causing change management to falter and
capabilities to strengthen infrastructure hinders their business agility
diluting the effectiveness of transformation
and contributes to accumulating technical technical debt.
the digital core.
initiatives. Without this alignment, even
debt.3 Furthermore, 91% of organizations
the most ambitious programs struggle to
report that technical debt undermines
deliver lasting value.
their competitiveness, yet only 24% are
actively addressing the issue. This impact
is particularly pronounced in sectors like
banking and telecom, where outdated
systems continue to obstruct innovation
and growth.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 12
Figure 4
Skills gap limits digital core growth, Demystifying the digital core
development and generative AI adoption
A digital core fit for continuous reinvention includes three distinct
groups of technologies that constantly interact with each other.
In our Reinventing with a Digital Core report, we found that a
digital core is a prerequisite for companies to continuously
reinvent themselves as they navigate the radical disruption
fueled by generative AI.4 Accenture defines a digital core as the
critical technological capability that can create and empower
an organization's unique reinvention ambitions. Such a digital
Digital platforms
core has three groups of distinct but constantly interacting
technologies: digital platforms, a data and AI backbone and the
digital foundation—which includes composable integration,
cloud-first infrastructure, a continuum control plane and
Data & AI backbone
security (Figure 4). Together, these elements provide the agility
and innovation needed to accelerate ahead of the competition Data | AI
and achieve strategic objectives.
Digital foundation
Cloud-first infrastructure Security
Continuum control plane Composable integration
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 13
A considerable gap in foundational The talent challenge is compounded by Only
skills and capabilities—ranging from difficulties in sourcing new skills. Only 36%
36
data foundation and cloud to AI and of South African companies believe their
%
cybersecurity—is undermining companies’ talent strategy is flexible enough to support
ability to build and maintain a robust transformation programs. This shortage
digital core. It is the combined strength of digital capabilities is constraining
of South African
of these foundational capabilities that companies’ ability to scale operations and
enables businesses to unlock new maintain their competitive position.
companies believe
opportunities across the value chain.
their talent
Our research shows that more than
strategy is flexible
half of South African executives lack a
strong understanding of these crucial
enough to support
components, and only 35% have the
technological expertise to leverage them transformation
effectively. Moreover, only 38% of business
programs.
leaders feel confident that their workforce
has the necessary skills to achieve their
goals over the next three years.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 14
Generative AI enables and
accelerates reinvention
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
15
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
15
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 15
Figure 5
Reinventors expect to grow the value gap
across financial indicators
In 2022, we predicted that companies
Financial value gap
that embrace reinvention as a core
Revenue growth, indexed (2019 = 100)
strategy—using technology, data
Reinventors All others (Transformers + Optimizers) Profitability
and AI—would lead in the coming
(EBITDA/revenue)
decade. Our 2023 findings confirmed Expected
2.4x
this: Globally, a small group (9%) of
+5.6pp
increase
companies—we call them Reinventors—
200
Higher margins
is outpacing their peers by embedding
for Reinventors
compared to all
reinvention into their DNA. 180
others over 2019-22
+15pp Revenue
growth gap
+2.9pp
Accenture’s analysis (Figure 5) shows that, globally,
160
Revenue growth
Reinventors are outperforming their peers by a wide
gap to all others
Uplift in margins each
margin. Between 2019 and 2022, these leading companies
by 2022
year following adoption
140
saw revenue growth that was 15 percentage points higher
of a reinvention strategy
than the rest. We expect this gap to grow by 2.4 times to 37 vs. those not pursuing
reinvention
percentage points by 2026.
120
+37pp
Revenue growth
Reinventors are also more profitable. Their average gap to all others
by 2026
profit margin (EBITDA/revenue) between 2019 and 2022
100
was 5.6 percentage points higher than the rest. Our
2019 2020 2021 2022 2023 2024 2025 2026
modeling indicates that for every year a company adopts a
reinvention strategy, it sees a 2.9 percentage point uplift in
margin compared to those that don’t.
2019-22 = CAGR based on actuals. 2023-26 = self-reported expectations stress-tested vs. analyst expectations. Average EBITDA margin based on actuals
for 2019-22. Panel data model tests the relationship between # of years of reinvention (from year respondents report adopting reinvention strategy) and
EBITDA margin, controlling for industry, geo and company size. Financial services companies are excluded. Source: Accenture reinvention survey, Oct-
Nov 2023. Sample size: Total, 1,500; Reinventors, 136; Transformers, 1,210; Optimizers, 154.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 16
In South Africa, 7% of businesses have reached this With its ability to impact the entire value chain and
high bar of reinvention. The vast majority—around drive productivity and growth to unprecedented
85%, whom we refer to as Transformers—are levels, generative AI can transform every facet
making strides but still have room to accelerate of business. It is already revolutionizing the way
their progress. They are not yet building the we work, fostering a new kind of collaboration
long-term capabilities necessary for sustained between people and machines. Our modeling
reinvention. The remaining 8%—whom we refer to shows that 38% of working hours in South Africa
as Optimizers—are holding back on reinvention have scope for automation or augmentation
altogether, missing critical growth opportunities through generative AI.5
and exposing themselves to risk in a rapidly
Beyond automation, generative AI can empower
shifting market.
leaders to make smarter, faster and more accurate
Reinventors are fully committed to continuous choices by converting vast amounts of data into
transformation. They’re not settling for incremental insights. For both customers and employees,
changes but using generative AI and other generative AI delivers tailored experiences,
technologies to reshape their business from the deepening engagement and driving better
ground up. These organizations are setting new outcomes. Crucially, generative AI can help
performance standards, driving innovation across build “connective tissue” across an organization
the board and intensifying their use of generative by unlocking data and breaking down people
AI as a core enabler of their strategy. siloes through its ability to seamlessly process
structured, unstructured and even synthetic data.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 17
The Reinventor's playbook
Five key imperatives to drive reinvention with generative AI
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
18
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 18
Using generative AI to reinvent is no
longer optional—it’s a prerequisite 1/ 2/ 3/
for success. Companies will compete
on how fast they are able to harness
Understand and
and deploy generative AI to create
develop an AI- Reinvent talent
material value. This is a reality that
enabled, secure and ways of
not everyone has yet absorbed.
Lead with value digital core working
Success will require every CEO and their
team to assess where they are today in their
competitive set, and then systematically execute
a reinvention strategy with five imperatives that 4/ 5/
can be broadly applied. Here, we describe these
imperatives in the context of generative AI and
illustrate with client examples.
Close the gap on Drive continuous
responsible AI reinvention
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 19
1/ Lead with value
In the era of generative AI, Begin by targeting strategic bets—areas It’s also important to ensure that
where generative AI can create unique every AI initiative you pursue is value-
it’s crucial to prioritize value
sources of value that competitors led. Too many organizations are still
across the business.
can’t easily replicate. Evaluate whether experimenting with AI without a C-suite-
your organization is truly ready to approved mechanism to measure
execute your AI strategy, or if you risk success. To bridge the gap between hype
being outpaced by competitors with and material results, rapid interventions
stronger digital cores or more agile and decisive choices are needed.
talent. This critical self-assessment will
Finally, reorient your organization. Move
help you prioritize the most impactful
away from siloed functions and enable
opportunities.
end-to-end decision-making through
Next, shift from fragmented pilots a unified data architecture and cross-
to building end-to-end business functional teams. This approach will
capabilities, powered by AI—including unlock new opportunities across your
generative AI. Be intentional in executing value chain and help you tap previously
a roadmap that connects AI to your hidden value pools.
broader operational goals. Rather than
getting bogged in proof-of-concept
projects, focus on transforming entire
workflows to unlock real value.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 20
2/ Understand and develop an AI-enabled, secure digital core
Building an AI-enabled Start by assessing your digital core: How It’s equally important to ensure that your Lastly, rigorously measure your progress
does your technology stack up to industry Chief Information Officer embeds strong with an eye on the future. Direct a
digital core goes
standards, and is it ready for generative AI? cybersecurity practices early in the substantial share of your technology
far beyond writing
Align your strategy with the areas where technology lifecycle to protect both digital investments toward building new
reinvention offers the greatest value. and physical systems. Only 41% of South capabilities, not just maintaining legacy
checks for technology
African companies believe they lead in systems. Innovation today sets the
upgrades. It needs Next, develop the core capabilities needed
enterprise systems security, so a strong foundation for competitiveness tomorrow.
to build a robust data and AI backbone,
meticulous development security culture is essential for long-term
such as handling unstructured and
resiliency.
of an infrastructure that
synthetic data and creating an architecture
can support rapid and that integrates multiple AI models. Our With robust cybersecurity practices
research shows that 96% of South African bolstering your defenses, it’s time to take
continuous reinvention.
companies foresee significant shifts a hard look at your current technology
in their data strategy to fully leverage and advisory ecosystems in order to
generative AI, and almost half continuously radically compress the reinvention cycle.
monitor all aspects of their digital core for Reconsider risk-reward relationships,
AI readiness. and whether co-creating with partners
or industry leaders will fast-track your
transformation efforts.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 21
A Southeast Asian national oil
company exemplifies this approach.
Like many others in the oil and gas industry, this On the front end, a new search engine simplifies
Southeast Asian national oil company has huge and accelerates the way people find important
volumes of data in different formats, and generates information, allowing them to “chat” with the
more daily. company’s data to find what they need in a quick
and conversational way, speeding up decision-
With no efficient way to access and search its data,
making and giving people confidence to act.
decision-making was only getting slower, while the
risk of accidents due to missing data points kept The speed at which the right information can
growing. Staying on top of pipeline maintenance now be accessed is also helping avoid equipment
and repairs was time-consuming, as technicians downtime as historical data can be accessed
and engineers had to comb through pages and almost instantly, like finding out how long it’s been
pages of historical documents to predict where since a piece of equipment was serviced or had a
issues may come up. fault.
After taking a holistic look at the issues, the It’s also speeding up onboarding by replacing
company deployed generative AI and cognitive dense logbooks with a simple search engine to
search, and can now realize the true value of its teach complex knowledge. Ultimately, the new,
data and drive new growth. Its new knowledge integrated setup makes information discoverable
base incorporates more than 250,000 documents with minimal effort, automates the knowledge-
with structured and unstructured information, gathering process for different roles across the
surfaces whatever information the user is looking organization and helps reduce accidents.
for and converts it into the desired format.
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 22
3/ Reinvent talent and ways of working
For a digital core to reach Leaders need to look beyond tactical A transformation of this magnitude also A forward-thinking talent strategy also
questions like which tasks to automate requires people-centric change capabilities calls for a review of human resource
its full potential, it has to
and consider how AI, including generative across functions to fully grasp generative (HR) capabilities. HR should not be
be backed by a workforce
AI, can free up human potential—and AI’s impact on the workforce—not just an afterthought but a core part of the
how to reskill employees to maximize operationally, but in the experience of reinvention vision. Invest in the right
that’s equally prepared to
this potential. employees themselves. Manage change HR technologies needed to support
evolve. The next challenge
in a way that actively involves employees, AI-driven transformation. Revisit your
Create a talent strategy that maps out
is rethinking how talent giving them a voice in how AI—including employee value proposition to ensure
how work will change, documents the
generative AI—is adopted and integrated it reflects an environment where AI
is managed, reskilled
impact to roles and identifies the skills
into their daily tasks. empowers employees, making them feel
and aligned with the needed for every generative AI use case.
“Net-Better-Off”.
Leaders must make transparent decisions At the heart of this reinvention is the need
demands of a generative
on how to reallocate freed-up talent, so for continuous learning capabilities, either
AI-driven world. that employees fully understand how their organically or with partners. Employees
roles will change. As it stands, only 38% must be equipped with market-relevant
of South African businesses have a clear skills to thrive in a South Africa where 38%
understanding of the workforce skills of working hours are likely to be automated
they’ll need in three years. or augmented by generative AI.5
IA
evitareneg
fo
ega
eht
ni
noitnevnieR
Contents Executive summary Reinvention in the face of radical disruption Barriers to reinvention in South Africa Generative AI enables and accelerates reinvention The Reinventor's playbook 23
4/ Close the gap on responsible AI
As AI adoption grows, so The first step toward responsible AI However, responsible AI is more than
use is to establish clear AI governance a technology issue—it requires cross-
does the responsibility
frameworks that outline principles for the functional collaboration across the
to ensure that it is used
ethical design, deployment and use of organization. Leaders from compliance,
AI systems. Without a solid governance HR, sustainability, privacy and security
ethically and responsibly.
structure, companies risk deploying AI should work together to ensure that AI
Pressure is mounting for
in ways that could harm their reputation, systems are designed and managed
organizations to establish their employees and even their customers. responsibly. This holistic approach will
address the wide-ranging impact of AI,
governance frameworks that
Conduct regular AI risk assessments—both
from workforce implications to regulatory
mitigate the risks associated qualitative and quantitative—evaluating
compliance and data privacy.
AI use cases, applications and systems
with AI while building trust
against a reference architecture to identify Despite the urgency, only 31% of South
with customers, employees risks. Responsible AI cannot be achieved African executives have established
without system enablement for testing and responsible data and AI principles, and
and regulators.
a dedicated AI monitoring and compliance even fewer—just 3%—are either drafting
function to evaluate for fairness, or have completed drafting responsible
explainability, transparency, accuracy data and AI principles with C-su |
92 | accenture | Accenture-Supply-Chain-Networks-In-The-Age-Of-Generative-AI.pdf | Supply chain networks
in the age of generative AI:
Turning promise into performance
The annual Accenture Pulse of Change Index found that technology rose to the
top of the list of business disruptors in 2023, catapulted by advances in generative
AI. The technology is unique in its ability to impact the entire value chain,
reinventing every part of an organization and resetting the performance frontier.
Based on our Technology Vision 2024,95 percent of executives agree that
generative AI will compel their organization to modernize its technology
architecture.The good news for supply chain leaders is this exciting revolution in
machine learning is creating an array of possibilities for reinventing work in their
domain too.
In this paper, we present a comprehensive and forward-thinking exploration
of the opportunities across the end-to-end supply chain. We see applications
in everything from sourcing and planning, through manufacturing and fulfillment,
to aftersales and service. We also see significant value in cross-functional
outcomes like supply chain sustainability, resilience, talent management, and
customer-centricity.
Can organizations realize this value today? We believe they can. But it means
approaching generative AI not merely as ‘just another’ technology implementation.
It’s an enterprise transformation, with implications for the way an organization
thinks about its data, talent, and ways of working. Not to mention the critical
importance of implementing generative AI responsibly and securely.
By embracing this broader change, supply chain leaders can fully capitalize on the
age of generative AI. And drive innovation across supply chain networks that
deliver better outcomes for business, for people, and for the planet.
Kris Timmermans
It’s an exciting journey. And it’s one I look forward to supporting our clients on in
the months and years ahead. Global Lead – Supply Chain & Operations
2
Generative AI is booming. Since ChatGPT launched in late 2022 the
technology has taken the world by storm. Across industries and
business functions, companies are looking to explore the possibilities
and capitalize on the transformative potential of the creative side of AI.
The sheer number of possible applications has captured the attention
of business leaders. Our research found that 97 percent of senior
executives agree that generative AI foundation models (also known as
Large Language Models or LLMs) will be transformative for their
Accenture analysis suggests 43 percent of all working
company. And 100 percent anticipate changes to the workforce.2
hours across the entire supply chain function will be
impacted — with generative AI either automating Why is this good news for supply chain leaders? LLM capabilities are
activities (29 percent) or significantly augmenting the not limited to coding, content creation or marketing. They also hold
immense promise across the end-to-end supply chain network. There’s
work of human employees (14 percent).1 Given the sheer
value to be gained in everything from new product development,
scale of the global supply chain workforce, the potential procurement and planning, manufacturing and logistics, to after sales
cumulative value for businesses is massive. and services.
3
There’s broad consensus about generative AI’s potential,
and many organizations are actively experimenting. But Success with generative AI means getting
our Pulse of Change Quarterly survey suggests only one
the data ready, getting people ready, and
in three has so far made a significant investment.
getting the enterprise ready
Why?
All C-suite leaders are grappling with fundamental questions. How much
of the hype around generative AI is real? Can its promise be turned into
Generative AI excels in language-related activities, as we’ll explore in
scalable solutions? Which use cases can deliver real value today? And how
the following sections of this paper. However, supply chain leaders must
do leaders get the data and the organization ready to capitalize on the
also recognize that, while it’s incredibly powerful at what it does well, it’s
opportunity?
not suited to every task. In particular, supply chain activities that are
more focused on numerical processing or require greater levels of
Our view? complex reasoning will see less direct impact. It’s why we also
recommend viewing generative AI in its broader context — as part of a
There’s real value on the table across the end-to-end supply chain. But continuum of automation capabilities that include traditional process
reaping the benefits requires a profound shift in the way an organization automation and classical machine learning models, as well as LLMs.
thinks about creating value and getting work done. It means approaching
generative AI not merely as the latest in a long line of software
implementations, but rather as an enterprise transformation, with a clear
focus on end-to-end business capabilities and implications for areas like
data, people, ways of working, processes and responsible adoption.
4
Generative AI-powered reinvention helps bridge the
gap from the linear supply chains of the past to the
truly interconnected, intelligent supply chain networks
of the future. Building on previous advances in supply
chain management artificial intelligence, generative AI
offers a range of new capabilities.
5
Contextual understanding. Supply chain Conversational capabilities. Supply chain Content generation. Generative AI offers
managers can use generative AI to make workers can use generative AI to gain the promise of creating relevant, context-
better decisions based on contextualized access to tailored insights and automations specific text, code, images or insights on
insights from unstructured data sources that based on chatbot interactions in everyday demand and on an industrial scale. Today,
were previously inaccessible. Examples language. That might include asking a applications in sourcing and procurement
include improving forecasting by scanning chatbot to help find a specific spare part are the most robust, such as auto-generated
huge numbers of public online sources to and create a call-off or spot buy to a vendor-specific insights (KPIs, market
identify the root causes of future demand. preferred supplier if it’s not available. Other trends, demand forecasts) to support
Or embedding generative AI into a Supply applications include auto-generating contract renewal negotiations with
Chain Control Tower to enhance the way users documents like purchase orders, training suppliers, as well as contextualized business
interact with data, improving explainability and and upskilling manufacturing workers and operational performance metrics.
trust. Generative AI can also be combined with maintenance troubleshooting.
existing process automation to significantly
streamline supply chain activities.
Together with existing AI, machine learning models and workplace platforms, these capabilities will allow companies to optimize and elevate supply
chain operations, solve pressing supply chain challenges, and, ultimately, ensure supply chain networks have a more positive impact on business,
people and the planet.
6
For Chief Supply Chain Officers (CSCOs), generative AI’s promise
extends all the way across supply chain network operations,
from designing and planning through to aftersales and service.
Accenture’s analysis indicates that, in total, a massive 58 percent of
the 122 supply chain processes analyzed, can be reimagined.3
7
Design and engineer
In domains like model-based systems engineering, LLMs will increasingly augment and
accelerate the work of designers. By tapping into historical data, generative AI solutions will
quickly generate new designs and models, saving time and reducing repetitive effort,
especially during design iterations.
Packaging design is a good example. The need to consider multiple factors — sustainability,
ease of transport, durability, regulations, branding, and more — eats into time and limited
resources. At the same time, documenting and retrieving packaging information becomes
increasingly difficult with large product portfolios. Generative AI can serve up multiple design
concepts (in 2D or 3D) as well as proposing suitable packaging copy and marketing based on
summarized design information. Human co-workers can then review these concepts to
ensure compliance with product and regulatory requirements.
The applications for biopharmaceutical companies are particularly powerful. Terray
Therapeutics is using generative AI to revolutionize small-molecule drug discovery.
Its COATI foundation model for chemistry translates chemical structures into numerical
representations, allowing generative AI to design novel optimized molecules.4
8
Plan
Many CSCOs have already implemented advanced analytics
solutions to augment and optimize supply chain planning
activities. However, the complexity of the insights these tools
produce, and the need for specialist expertise in making them
actionable, means they can often be challenging to use in practice.
Generative AI promises to revolutionize access to insights, not
only in supply chain planning but also in areas like network design
optimization. Through simple-to-use interfaces, employees can
query optimization recommendations in everyday language and
receive explanations they can easily understand and action. This
opens up critical insights to a much larger number of supply chain
workers, while also improving trust in data and accelerating speed to
action for domain experts.
At the same time, generative AI can be used to bring a broader set of
unstructured data sources (such as market reports, news results and
social media) into forecasting calculations. It also supports more
collaborative and streamlined ways of working across sales and
operations planning — instantly summarizing meeting action points,
comparing plans with actual outcomes, building dashboards of key
metrics, even generating draft plans themselves. This will free up
planners’ valuable time for more strategic tasks.
9
Source
Today, sourcing and procurement teams grapple with
challenges stemming from inefficient, manual processes,
diverse categories, and system integration issues. While
teams often spend significant time on strategy alignment,
sourcing, and data reconciliation, generative AI presents an
opportunity to streamline operations, bridge information
gaps, and improve access to a broader array of data
sources, enabling faster insights and simplified processes.
It also opens up the possibility of hyper-automation, where
different forms of automation — including existing machine
learning algorithms and process automations as well as
generative AI — are linked together as part of an increasingly
autonomous system at scale. This promises to free teams for
more valuable work and enhance overall efficiency.
Consider how retail giant Carrefour is using generative AI to
enhance its internal purchasing processes. The company is
developing a solution that will help employees complete
everyday tasks more quickly, including drafting invitations to
tender and analyzing quotes.5
10
Imagine if every business user had an assistant buyer powered by What about RFP drafting? Fine-tuned on historical RFI, RFP and RFQ
generative AI. When they needed to buy something, the assistant could information, generative AI can not only draft RFx documentation, but
guide them to the right buying channel, support any call off or spot buy, also review and compare the responses that are returned by suppliers.
and, if needed, connect with a professional buyer to handle the Upstream procurement activities like supplier discovery and category
purchase. management also stand to gain from generative AI’s ability to rapidly
summarize a wide array of market intelligence insights.
Text-heavy activities like contract generation also stand to gain
significantly. A generative AI solution can be applied to large volumes of Accenture has built a smart sourcing and contracting tool using
unstructured procurement information, such as historical contracts, generative AI. It helps sourcing managers with supplier negotiations by
procurement policies and product specifications, to identify common analyzing business requirements, historical contracts, and bidding
patterns and requirements. This allows it to instantly produce a first draft patterns to suggest suitable sourcing strategies. The tool also suggests
of a new contract, which teams can then review and enhance using their terms and conditions to help ensure best-in-class contracts result from
procurement expertise. negotiations.
11
Make
As data availability and trust improves, generative AI will also be increasingly
If companies can bring their IT data together with their operating and
applied to the wealth of insights in operational digital twins, expediting
engineering data, generative AI will help them achieve a consistent level of
diagnoses and root cause analyses. And the combination of classical and
quality and operational excellence in their manufacturing operations,
generative AI offers the promise of significantly streamlining access to
particularly in areas such as asset maintenance and empowering the
predictive maintenance insights, real-time data analysis and failure
workforce with actionable predictive insights. It can also offer new insights
diagnostics by making the information more consumable through easy-to-
into product design and quality control.
use Q&A interfaces.
In plant management, for example, asset maintenance teams often
Quality control and compliance, too, stand to gain. Even companies in
grapple with complex processes and large volumes of asset-specific
heavily regulated industries like pharmaceuticals are exploring how
documentation. Generative AI can be used to digest all this information and
generative AI can be applied to multiple data sources to identify
summarize it into a series of logical steps as part of a work order. It means
irregularities in cold chain management and auto-populate compliance
expert know-how is unlocked and democratized across the workforce —
documentation for review by human experts. Generative AI can also draft
improving not only operational performance but also job satisfaction.
technical publications with accurate content, significantly reducing
authoring efforts. In aerospace, for instance, it can accelerate the
What about maintenance planning? Many companies in heavy industries production of legally mandated technical documentation such as
are moving towards risk-based inspections (RBI) to unlock value. But work/assembly/repair instructions, user manuals, warranty information and
planning for these inspections, plus preventive maintenance and operator instructions for use (IFUs).
care routines, is still a manual, human-intensive and repetitive process. It
needs highly skilled field engineers to create planning documents, as well as
subject matter experts to review them. However, generative AI can write
precision maintenance job plans for equipment classes or specific
equipment with high accuracy and completeness. That significantly
reduces the time needed to create and review key planning documents.
12
Fulfill
Today, supply chain disruption is everywhere. It’s forcing companies to transform supply chain operations for
greater resiliency, relevancy, and responsibility. Leaders are focused on improving forecasting while
implementing Transportation Management Systems (TMS), Warehouse Management Systems (WMS)
andWarehouse Automation/Robotics to drive up agility and efficiency.
By layering generative AI onto the broader data maturity and automation agenda, companies can achieve
significant gains in fulfillment. That includes enhancing hyper-personalized customer experiences and
extracting new revenue opportunities from insights based on large volumes of omnichannel data. Fulfillment
operators can also use generative AI to suggest ways to optimize transportation management and
improve forecasting by considering a broader range of factors from unstructured information (such as
weather forecasts and competitor activity).
Consider how an LLM-powered import/export document generator could transform shipping and export
processes. Generative AI can be applied to a comprehensive collection of multi-modal unstructured
information, including historical internal records and governmental regulations, across various formats,
including PDFs and tablets. Shipping and export documents can then be automatically populated for human
experts to review and verify, reducing opportunities for error while saving time and manual effort.
13
Service
The goal of providing services rather than just products is
becoming a reality for many companies. However, the service
space is typically still highly fragmented, with assets and
resources distributed regionally and globally. It’s also heavily
reliant on coordination with other parts of the supply network. Not
only that but executing a service-oriented strategy requires a far
more proactive approach to forecasting and responding to
individual customer needs.
It's why generative AI can have a game-changing impact. Its ability
to scan vast amounts of information across a broader range of
data sources — including unstructured data that was previously
difficult to process — offers the promise of deeper insights. From
geographic locations to weather conditions and from customer
lifestyles to individual usage patterns, these can be combined with
classical AI techniques to enable truly one-to-one service
experiences on a global scale.
An example? Look at how Accenture helped one major
automotive company use generative AI to enhance customer
support. By creating an intelligent incident resolution copilot to
summarize incidents, detect known issues, recommend
resolutions and compose customer responses, we’re helping
customer support agents access contextualized information and
resolve incidents faster.
14
Cross-functional
value on the table
For CSCOs, the generative AI era promises a wealth
of additional benefits that cut across individual
supply chain functions.
Sustainability
Companies are under pressure to increase their supply chain sustainability and
report on their corporate responsibility commitments more accurately.
However, with information dispersed across a multitude of sources and
sustainability categories, teams are faced with an almost insurmountable
challenge collecting and analyzing the data. The work is slow and requires
intense manual effort from subject matter experts.
It’s no surprise, then, that 63 percent of CEOs say the lack of ESG data
measurement across the value chain is a key challenge.6 But generative AI
offers solutions. For example, we worked with one global pharmaceutical
company to accelerate supply chain decarbonization efforts. The company’s
teams had spent years painstakingly compiling data on how many suppliers
had science-based targets (SBTs). We built a generative AI solution capable of
delivering near-instant insights by trawling through thousands of supplier
websites. After one hour, the company had reliable intelligence confirming it
had already exceeded its supplier SBT target.
Generative AI has many other use cases in sustainability, including generating
prioritized decarbonization roadmaps for individual companies and
enhancing Scope 3 emissions reporting. Today, for example, accurately
matching company spending to emissions is time-consuming and laborious
work. Accenture developed a generative AI solution able to sift through millions
of lines of spend data, across multiple languages, and automatically map each
line item to relevant emissions factors, which procurement teams can then
review. A process that once took days can now be completed in minutes.
16
Intelligent ways of working
One of generative AI’s most revolutionary aspects is the way it lets
people interact with unstructured data more easily and
comprehensively.One way to think of it is as a “superpowered
navigation system” for language-based activities, providing near-
instant access to consumable data insights that help people
accomplish tasks faster and more effectively.
This will empower supply chain leaders and their teams to
reinvent the way work gets done. For instance, generative AI’s
ability to shift unstructured data on a superhuman scale helps
demand planning and supply chain resilience teams unlock
insights into market trends and developments. Examples include
the rapid analysis of market data to understand and predict
pricing changes of raw materials, understand consumer reaction
to promotional activity, and connect the dots between global
disruption events and supplier lead times.
Accenture created a generative AI powered market watcher
tool for commodities. It’s designed to help business analysts at oil
and gas companies as they make purchasing decisions. The tool
ingests a broad range of both structured and unstructured data
and outputs key metrics in numerical formats for further analysis,
saving time and effort while also enriching model outputs with
expanded data sources.
17
Resilience
When it comes to managing disruption in supply chains — which
has cost businesses $1.6 trillion in missed revenue opportunities
over the last 2 years, according to recent research — one of the
key challenges for CSCOs is knowing who their n-tier suppliers are
and assessing if they’re a potential source of risk and vulnerability.
Understanding the full configuration of these supplier networks is
a critical prerequisite for increasing supply chain resilience.
Generative AI can support these efforts by augmenting existing
AI-powered solutions that analyze structured data (such as trading
reports) with the analysis of much larger volumes of unstructured
data (such as news sources, videos, chatting traffic, etc) to
produce deeper insights into the supplier network.
Procurement teams can also use generative AI chatbot interfaces to make those
insights more accessible, helping them collaborate with suppliers to understand where
priority risks exist and make more effective sourcing decisions.
An example? Accenture built an N-tier Supply Chain Navigator powered by OpenAI
GPT. It helps procurement managers analyze supplier network data by providing real-
time insights, answering specific queries, and facilitating data-driven decision-making.
Employees can quickly and easily query the tool to identify supply network
vulnerabilities — such as suppliers with geographic ties to conflict areas or locations
experiencing natural disasters.
18
Customer-centricity
Companies can use LLMs in conjunction with classical AI to
Generative AI’s ability to provide accurate, easy-to-use chatbot interfaces has
transform service-related call center experiences. Examples
many applications in building a more customer-centric supply chain
include predicting customer intent and creating a tailored tone of
network. Take product design, for example. Generative AI can analyze a broad
voice — especially important when handling complaints. LLMs can
range of unstructured customer feedback, such as online product reviews and
also be used to summarize calls, generate action points, and draft
social media sentiment, much faster. This can then be channeled back into
customer responses, freeing up employees to focus on bringing
product design workflows, allowing for rapid feedback loops between
human creativity and empathy to customer actions where they
customer demand and product development.
can add most value. What’s more, each new customer interaction
serves as additional context for AI models, improving the
relevance and quality of outputs and thus customer retention.
Generative AI chatbots can also allow customers and employees
to explore complex technical product documentation faster
and more easily. For example, Accenture developed a generative
AI solution for managing technical documentation, such as
product manuals and guides. It not only allows companies to draft
these documents faster, but also then query and summarize them
in plain language, meaning readers can find and consume the
information they need almost instantly.
19
Unlocking talent
For the first time in history, we’re embracing a generation of technology that
is “human by design”. Generative AI’s effectiveness hinges on human input to
drive quality outputs— whether that’s something straightforward, like drafting
an email, or complex, like a financial forecast. These more human-centered
processes will reinvent work across the entire value chain.
CSCOs also see key challenges in sourcing and retaining skilled
By synthesizing data, comprehending natural language, and converting talent. For example, 32 percent see talent scarcity, due to skill gaps
or unawareness, as a major barrier in utilizing generative AI. And 36
unstructured data into actionable insights, generative AI is democratizing
business process redesign, empowering everyone — from frontline workers to percent believe workers will not fully embrace generative AI due to
lab scientists to design professionals — to reshape their own workflows and a lack of technological understanding.8 However, most workers (82
make language-based work faster and easier. Generative AI is also being percent) believe they do grasp the technology. And 94 percent are
used to produce tailored learning materials, to help onboard and upskill new confident they can develop the needed skills.9
team members.
However, nearly half of organizations that are leaders in reinvention recognize
that processes across the value chain will require significant changes in order
to realize the opportunity for generative AI to accelerate economic value,
increase productivity and drive business growth, while also fostering more
creative and meaningful work for people.7
20
How to get started
As CSCOs embark on their generative AI
transformations, there are several key success
factors to bear in mind.
The good news? Generative AI can itself be applied to an organization’s data
pipelines to accelerate digital maturity. Companies can use it to automatically
synthesize and extract knowledge from their supply chain data, including
dramatically simplifying and maximizing the use of unstructured data. This
creates a circular pathway that uses LLMs to mine and process supply chain
Given the large amounts of data needed to customize and optimize LLMs, a data, which can then be supplied to supply chain use cases, including those
mature enterprise data strategy is a critical prerequisite for a generative AI supported by generative AI itself.
transformation. Those with strong supply chain data capabilities have an
important head start over their peers.
Companies are understandably cautious about supplying external generative
AI solutions with business-critical manufacturing, purchasing and other supply
However, many companies are still wrestling with the challenge of increasing chain information. Strict data retention and privacy policies and trustworthy
their data and digital maturity across their supply chain networks. Now, they’ll security guardrails are therefore vital. CSCOs will need to weigh up the relative
need to take this further by extending their data lifecycle management to risks and rewards of using their proprietary data to enhance LLM outputs in
include large volumes of unstructured mixed-modality data (meeting each use case. Working with partners who can guarantee data security and
transcripts, technical documents, video, audio, images, and more), as well as provide sandboxed generative AI solutions is one way of safeguarding data in
prompt engineering pipelines and new “ModelOps” ways of working. supply chain implementations.
22
From potentially biased and harmful outcomes, to question marks over accuracy, “supply
chain cannot hallucinate” and user trust, to security and data vulnerabilities, generative AI
represents a unique shift in the business risk landscape. That’s why it’s essential to take a
responsible approach to supply chain implementations from the very start. Employees,
customers and supply chain partners all need to trust that any AI implementation is fair,
secure and reliable.
Accenture believes strongly in leading by example when it comes to responsibility. It’s why
we’ve been pioneering our responsible AI framework for the best part of a decade.
Updated for generative AI and built on four key pillars — principles and governance; risk,
policy and control; technology; and people, culture and training — our framework has been
scaled to over 700,000 people in our organization worldwide.
23
While generative AI is not about replacing people or jobs, it will have an increasingly central role in
day-to-day work. Accenture analysis indicates that, in seven of 15 supply chain network occupations
— including purchasing managers and buyers, production, planning and expediting clerks, industrial
production managers, logisticians, and others — more than half of all working hours will be
impacted by the technology through varying degrees of automation and augmentation.
It's incumbent on both supply chain leaders and their workforces to understand and plan for this
reinvention of work on two dimensions: which tasks can be automated or augmented, and which
people need to be upskilled to make use of generative AI. By analyzing these factors, companies can
map out the different levels of impact on their people and develop the right upskilling programs.
24
Work time distribution by occupation and potential LLMs impact
Ordered by their employment levels in the US in 2022
Higher potential for automation
Higher potential of augmentation
Lower potential for automation or augmentation
Non-language tasks
Heavy and Tractor-Trailer Truck Drivers 26% 14% 8% 51%
Shipping, Receiving, and Inventory Clerks 35% 19% 8% 39%
First-Line Supervisors of Production and… 25% 10% 35% 29%
First-Line Supervisors of Transportation and… 29% 9% 25% 37%
Inspectors, Testers, Sorters, Samplers, and… 9% 7%6% 78%
Our analysis finds that the roles for production, planning and
Driver/Sales Workers 37% 6% 9% 48%
expediting clerk and procurement clerk have the highest
Buyers and Purchasing Agents 32% 21% 47%
potential impact from generative AI — 72 percent and 75
percent of their time respectively. This significant potential for Production, Planning, and Expediting Clerks 57% 15% 18% 10%
transformation, however, does not necessarily equate to job Industrial Production Managers 30% 19% 29% 22%
losses. Rather, it indicates that a considerable portion of their
Transportation, Storage, and Distribution Managers 36% 10% 38% 17%
work could be augmented by generative AI technologies. For
Logisticians 32% 24% 32% 12%
instance, 34 percent of procurement clerks tasks could be
augmented by generative AI — this includes tasks such as Cargo and Freight Agents 30% 24% 26% 20%
evaluating the quality and accuracy of data and determining Procurement Clerks 41% 34% 13% 12%
the value or price of goods and services. Embracing generative Purchasing Managers 31% 22% 47%
AI would allow these professionals to reallocate their time to
Weighers, Measurers, Checkers, and Samplers,… 19% 18% 5% 58%
more value-added activities, enhancing overall efficiency and
0% 20% 40% 60% 80% 100%
productivity in their role.
Note: Estimates are based on Human+Machine identification of work tasks exposure to impact
of generative AI. Source: Accenture Research based on US BLS May 2023 and O*Net.
25
To reinvent work in a way that drives innovation and enriches the employee
experience, companies will not only need to upskill their people in core
generative AI skills, but also develop other dimensions such as working with
purpose, strengthening trust and supporting emotional, physical and financial
health. Accenture research has found that companies that lead in driving
reinvention are also around twice as likely to be prioritizing the soft skills that
are increasingly important to ensuring generative AI adoption and value.11
Generative AI can itself be used to identify reinvention priorities for both
people and processes. For example, applied to a range of unstructured
internal and external information, it can help supply chain planners suggest
trends, summarize requirements, understand cross-functional dependencies,
capture the employee voice, and identify people’s pain points, sentiment and
workplace challenges.
Generative AI will help us ideate new ways of operating
that are truly innovative — and don’t simply recreate
what we’ve done in the past
26
More than ever, generative AI requires companies to build partnerships with the broader
technology ecosystem. With every cloud hyperscaler and numerous supply chain platfo |
93 | accenture | Accenture-Unlocking-The-Power-of-Data-and-AI.pdf | Unlocking the power
of Data
and AI
Are you making the most of your data?
June 2023
Copyright © 2023 Accenture. All rights reserved.
Data and AI are It’s time to take the next step on the Data and AI AI, leaving many businesses unable to realize
journey and extract the real value from the data
the full value of data.
available to organizations.
foundational
Data and AI is now a foundational capability and
The typical obstacles that companies
critical for the survival and success of any
encounter when trying to mature their Data and
capabilities business. For this capability to mature, data
AI capabilities center around three main issues:
transparency and trust in the data is key—and
1) Lack of trust in data accuracy and this demands examining the flaws of current
for the digital
completeness data platforms and remediating them at speed.
When the data platform is trusted, secure, easy
2) Lack of a clearly defined and industry-
business to use, and reliable, business focus can shift
relevant data model that makes it easy to
from merely solving data issues to using data to
understand and use the data to innovate
innovate and create value.
With the fall of data silos and an accelerated move 3) Lack of a channel to integrate AI insights in a
to cloud platforms, data and AI have become a timely way into business flows and interactions
critical capability for fueling the future of
Most data architectures arose organically, with
businesses.
different areas of the business pushing various
The move to cloud platforms facilitated a massively data sources to the cloud. Taking such a siloed
accelerated improvement in data availability and approach has created multiple “versions” of the
data access. data with different levels of fidelity and
accuracy. In addition, this siloed approach has
Although cloud is now a mainstream technology and
limited the ability of businesses to create a well-
data is seemingly widely available, only 12% of firms https://www.forbes.com/sites/gilpress/2019/06/09/9-
defined and catalogued data model that is indicators-of-the-state-of-artificial-intelligence-ai-may-
report that they’ve advanced their AI maturity 2019/?sh=3ff55cdd577f
required for AI at speed. Finally, integrating AI
https://www.accenture.com/us-en/insights/artificial-
enough to achieve superior growth and business
into other applications that improve employee intelligence/ai-maturity-
transformation. andtransformationc=acn_glb_aimaturityfrompgoogle_13131656
and customer interactions has lagged. These &n=psgs_0622&gclid=Cj0KCQiA8aOeBhCWARIsANRFrQEzb0-
IUnISnIlfCalVtuBiaQpp8SJJ-FNS2Hl4kS-
three issues have severely limited the scaling of dZuLH4LC1GMsaAumgEALw_wcB&gclsrc=aw.ds
Copyright © 2023 Accenture. All rights reserved. 2
Data and AI have become a critical driver
of Total Enterprise Reinvention
Insights at speed Good for Reduced risk Improved experiences
the bottom line
AI can improve the outcomes of Al has helped companies Embedding AI into engineering,
multiple business processes. Incorporating AI into operations become more compliant and has operations, and business
New ways to incorporate Data reduces costs and increases enhanced their audit and risk workflows can reinvent and
and AI into daily operations arise revenue. Companies who invest initiatives. Incorporating Data improve customer interactions,
constantly, and it’s critical to be in AI are 40% more likely to see and AI into compliance product development, employee
able to respond and embed share price increases1. processes has reduced risk and experience, and sustainability.
insights at speed. improved compliance across the
enterprise.
Source: 1 The Art of AI Maturity| Accenture
Copyright © 2023 Accenture. All rights reserved. 3
With the exponential growth of ChatGPT and
Generative AI, businesses are more than
ever looking into AI and eager to experiment
with the new technology to understand how
it can augment their operations. Accenture’s
research suggests that up to 40% of business
operations tasks will be impacted by
Generative AI.
Source: Accenture Technology Vision 2023: Generative AI to Usher in a Bold New Future for Business, Merging Physical and Digital
Worlds | Accenture
Copyright © 2023 Accenture. All rights reserved. 4
Why the chasm between data aspiration and
realization remains wide
1 Data is bigger The enterprise data landscape is expanding at a speed
and scale that is hard to fathom.
2
Data is more complex
30% of corporations' data will be synthetic data.
These silos hamper their ability to capture, process, and
3
Data remains siloed
extract value from today’s variety of data types and
deliver insights with high agility.
4 For AI and ML applications, faster access to operational
Data velocity is faster
data is required.
As companies increasingly seek operational and
5 competitive advantage beyond the limits of their first-
Data sharing is now critical
party data, there is a growing need to share data quickly,
safely, and in multiple forms.
Copyright © 2023 Accenture. All rights reserved. 5
While most companies invest in Data and AI,
only 12% have a mature AI capability that
drives value for the business by using the
wealth of available data.
The remaining 88% of companies struggle on
their journey to translate data into
innovation and value for the business.
Copyright © 2023 Accenture. All rights reserved. 6
The differentiator is
the ability to quickly
use changing data
The leaders in extracting value from data
have more mature data capabilities. They
quickly add data to analytics models by
using catalogued structured,
unstructured, and external data. The
winners in the Data and AI race are
focused on getting their data ready for AI.
Source: The state of AI in 2022—and a half decade in review| McKinsey
Copyright © 2023 Accenture. All rights reserved. 7
Storm clouds ahead
While most companies appreciate the value of data
and plan to better use it, the journey to a mature
Data and AI capability is not an easy one.
Reevaluate investments to date. While significant investments have
been made in data platforms, very few platforms are mature enough to
handle a spectrum of business needs, and companies often have
multiple different solutions that operate in silos. Typical challenges such
as siloed data, insufficient error handling, delayed or slow data
ingestion, and limited data validation need to be resolved. Data
platforms need to be consolidated to improve the reliability of data and
reduce the cost to operate.
Clean up and catalog available data to get it ready for AI. Most existing
data platforms have abundant data, but the quality and documentation
of the data is typically insufficient to support AI and generate insights at
speed and scale. Significant effort is required to clean up and catalog
the existing data and set up automated processes to label and catalog
future data sources so data can be added rapidly to new AI models.
Copyright © 2023 Accenture. All rights reserved. 8
Why
Harness AI with Accenture and Oracle
Accenture Why Oracle when it comes to
Success of AI relies on (a) the ability to use all types of data to solve broad
and Oracle
speDctraumt oaf b uasinnesds c hAalleIn?ges, (b) easy-to-use data technologies for
labeling, data quality check, and synthetic data generation, and (c) delivering
when it
AI insights in business workflows for maximum usage with minimum friction.
comes to
Data and
AI?
Use all types of data Apply AI at scale Deliver AI in workflows
Using structured and Oracle offers scalable data At times, the last step of integrating
unstructured data for AI can technologies for data labeling AI into business processes can be
mean more accurate results. and integration as well as a the most challenging part. But with
Oracle is the only end-to-end data science platform where AI and ML services on the same
data platform for integration, raw data can be prepared for cloud along with Oracle business
transaction processing, data specific AI delivery. applications, it becomes easier to
warehousing, data lake, and augment existing application
more, backed by unlimited workflows with AI—bringing AI
deployment options. closer to day-to-day activities for
real business insights.
Copyright © 2023 Accenture. All rights reserved. 9
Use all types
Oracle uniquely offers a unified When you add Oracle Autonomous Data
strategy and set of tools for making Warehouse to the mix, it provides an added
of data with
the most of data, advanced analytics, edge: improving performance even more
and AI. while streamlining database activity and
Oracle increasing database analyst (DBA) efficiency.
Nearly half the world’s data runs on Oracle
In addition, Oracle offers competitive Object
databases. As more organizations move that
Storage for collecting and analyzing all types
data—and the workloads that rely on it—to
of data including text, images, audio, and
the cloud, it’s vital to ensure that the data is
video recording.
used, managed, and secured in the best way.
That’s where Oracle Data Platform provides Oracle Data Platform meets you where you
an all-important advantage. are. Use as many or as few of the services as
you need for your structured and
Oracle Data Platform is a comprehensive
unstructured data needs and integrate those
suite of tools, services, and applications that
services with your own trusted tools.
help businesses manage their data effectively
Sources:
throughout its life cycle. It covers the whole
9 Indicators Of The State Of Artificial Intelligence (AI)| Forbes
data stack from Oracle, including Oracle The art of AI maturity| Accenture
transactional databases, data lake, data
warehouse, AI/ML services, and more, while
leveraging Oracle Cloud Infrastructure (OCI)
and Oracle Cloud Applications (Fusion ERP,
CRM and HCM) to provide a comprehensive
solution for data management.
Copyright © 2023 Accenture. All rights reserved. 10
Apply AI With the fall of data silos and an use by decision makers. For example, supply
accelerated move to cloud platforms, chain leaders can consume AI insights such as
at scale Data and AI have become a critical demand forecasts, predicted ETA, and outliers in
capability for fueling the future of the SCM planning, transportation, and inventory
businesses. workflows for seamless decisions. Furthermore,
with its deep business knowledge in ERP, SCM,
On applying AI at scale, Oracle offers OCI Data
CX, and HCM segments, Oracle helps deliver AI
Labeling and OCI Data Science to enrich
insights into the diverse SaaS landscape through
business data with annotations, generate
powerful data connector technologies including
synthetic data, develop scalable AI models, and
Oracle Integration Cloud, Data Integration, and
automate data and ML pipelines. Large-scale
Oracle GoldenGate.
customers use OCI Data Labeling monthly to
The combination of these services ensures that
annotate and enrich thousands of data objects to
AI can be delivered at scale in a more
build custom AI models using OCI Vision,
streamlined manner.
Language, and Document Understanding. OCI
Data Science serves over 200 million inference
Sources:
calls for over 2,000 customers using over 1,000 9 Indicators Of The State Of Artificial Intelligence (AI)| Forbes
The art of AI maturity| Accenture
ML models.
More than 10,000 customers run their
businesses on Oracle’s SaaS applications, so
Oracle enables delivering AI insights in
conjunction with business processes for ease of
Copyright © 2023 Accenture. All rights reserved. 11
Deliver AI in Data science services and business with AI to automatically assign new account
combinations and help match transactions with more
applications need to work together
than 99% accuracy.
workflows seamlessly for real business impact.
AI can be powerful in consuming and organizing all
In the absence of such integrated
forms of business data. Document Understanding AI
delivery, AI will be narrow and available automates invoices and other documents uploaded
to Oracle NetSuite to help automate business
only to few, limiting its value.
transactions.
Oracle, with its leading business applications
Businesses run on executive dashboards because
portfolio and more than 40 years of experience in
they help organizations monitor and proactively
helping its customers to run a broad spectrum of
address disruptions. AI deliveries such as anomaly
businesses, delivers AI in business workflows for
detection, forecasting, sentiment analysis, and image
maximum impact withminimum friction.
detection in Oracle Analytics Cloud help business
Furthermore, Oracle pioneers in bringing the best-of-
users consume AI insights where they make their
breed AI with partnerships including NVIDIA and
business-critical decisions.
Anaconda.
Data quality is fundamental to AI’s success, and
Companies seek more forecasting capabilities to
Oracle’s SaaS applications collect a broad spectrum
gain an edge over the competition. With AI,
of business data. Anomaly Detection, classification,
businesses can generate forecasts by using historical
and outlier detectionAI help in organizing data and
sales, promotions, product attributes, holidays, and
identifying data quality issues to help route them to
other extraneous factors to achieve improved
the right personnel for remediation.
accuracy and reliability. Oracle delivers AI-based
finance and sales forecasts to Enterprise OCI Data Science helps several healthcare ISVs,
Performance Management (EPM) customers. including Ronin, whichempowers clinicians with an
oncology solution by delivering health record
Automating back-office tasks with AI improves
summation, comparative insights, and decision
business efficiency and customer experiences.
support to treat patients individually instead of by a
Oracle automates general ledger account
set of averages.
management in EPM Account Reconciliation Cloud
Copyright © 2023 Accenture. All rights reserved. 12
Data is a strategic asset
Enterprises must treat data as a form of capital and invest in
its acquisition, growth, refinement, safeguarding, and
Data and AI have
deployment.
become a critical
driver of Total
Extricate data from functional silos
Data must be analyzed together in one place to unlock its
Enterprise Reinvention value. This can be done through cloud computing or a
distributed computing strategy like data mesh
Foundational models can create exponential impact
Foundational models can be fine-tuned to solve specific
industry problems and embed data intelligence into business
flows and across the enterprise to enable the Total Enterprise
Reinvention.
Copyright © 2023 Accenture. All rights reserved. 13
Accenture offers a
full spectrum of
services to help
companies unlock
the value of dormant
data
We work with you to help your business capture the full
value of data, using our experience of over 100 Data and
AI projects in nearly every industry with an unparalleled
ecosystem of alliance partners.
Accenture can help put cloud to work for your business
with solutions from one of our leading providers, Oracle.
Copyright © 2023 Accenture. All rights reserved. 14
About Accenture
Snejina Alexieva
Accenture Oracle, Business
Accenture is a leading global professional services company that helps the world’s leading Group, Data and AI Lead
businesses, governments and other organizations build their digital core, optimize their operations, [email protected]
accelerate revenue growth and enhance citizen services—creating tangible value at speed and
scale. We are a talent and innovation led company with 738,000 people serving clients in more
than 120 countries. Technology is at the core of change today, and we are one of the world’s Andrea Cesarini
leaders in helping drive that change, with strong ecosystem relationships. We combine our
strength in technology with unmatched industry experience, functional expertise and global delivery Accenture Oracle, Business Group,
Europe Lead and Global CTO
capability. We are uniquely able to deliver tangible outcomes because of our broad range of
services, solutions and assets across Strategy & Consulting, Technology, Operations, Industry X [email protected]
and Accenture Song. These capabilities, together with our culture of shared success and
commitment to creating 360°value, enable us to help our clients succeed and build trusted, lasting
relationships. We measure our success by the 360°value we create for our clients, each other, our Viji Krishnamurthy, Ph.D.
shareholders, partners and communities. Visit us at www.accenture.com.
Sr. Director, Product Management,
OCI AI and Data Science
[email protected]
About Oracle
Oracle is a global provider of enterprise cloud computing, empowering businesses on their journey of
DISCLAIMER: This document is intended for general informational purposes
digital transformation. Oracle Cloud provides leading-edge capabilities in software as a service, only and does not take into accountthe reader’s specific circumstances, and
platform as a service, infrastructure as a service, and data as a service. Oracle helps customers may not reflect the most current developments. Accenture disclaims, to the
fullest extent permitted by applicable law, any and allliability for the
develop strategic roadmaps and advance their journey to the cloud from any point: new cloud
accuracy and completeness of the information in this presentation and for
deployments, legacy environments, and hybrid implementations. Oracle’s complete, integrated
any acts or omissions made based on such information.
approach makes it easy for companies to get started in the cloud and to expand as business grows.
Copyright © 2023 Accenture. All rights reserved. Accenture and its logo are
430,000 customers in 175 countries use Oracle technologies to seize opportunities and solve real
registeredtrademarksofAccenture.Thisdocumentreferstomarksownedbythird
challenges. parties. All suchthird-party marks arethe property oftheir respective owners. No
sponsorship,endorsement,orapprovalofthiscontentbytheownersofsuchmarks
isintended,expressed,orimplied.Thiscontentisprovidedforgeneralinformation
purposes and is not intended to be used in place of consultation with our
professionaladvisors.
Copyright © 2023 Accenture. All rights reserved. 15 |
94 | accenture | Accenture-POV-Getting-your-workforce-ready-for-AI-and-Spatial-Computing.pdf | Innovation at scale:
Getting your workforce ready
for AI and Spatial Computing
Content
Executive summary
Introduction
Thought leadership
Use cases
Key takeaways
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Executive summary
Generative AI and Spatial Computing will not only reinvent how we work but also reshape our workforce as a
whole.To be ready for what’s next, enterprises will need to upskill their workforce and ensure their technology
is ready to meet the computational demand of these new technologies.
New realities
Technology disruption became the #1 cause of business change in 2023 catapulted by advances in Generative
AI. Only 27% of Accenture surveyed companies claim their organizations are ready to scale up Gen AI.* As a
result, companies are accelerating the executions of their transformation programs across talent and
technology.
In addition to AI, Spatial Computing technology is already becoming an integral part of our enterprise fabric
and could grow to be as groundbreaking as desktop and mobile, ushering in a new era of technology
innovation.
Accenture research has found that companies that take a people-centric approach to AI could create $10.3
trillion in economic value.*
The successful adoption of these technologies will require significant change management, reinvention and a
prepared workforce.
*Work Reinvented, Workforce Reshaped, Workers Prepared Accenture 2024
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Gen AI is the #1 driver of reinvention today
Company transformation programs need to shift from siloed use cases to a holistic approach that looks across the
organization’s whole value chain. Those looking to stay ahead will need to embrace Gen AI not only as multi-year
change agenda but as a continuous reinvention. This means companies need more people who can work with Gen AI,
not less. There is no AI-ready workforce companies can hire now. Companies will need to prepare workers, reshape
their workforce and reinvent work for the Gen AI era. This requires investing in people and in the technology that will
scale with them – and their AI toolsets.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
86%
Our future with AI
In the coming years, businesses will have an increasingly powerful array of technologies at of CxOs are already using Gen AI to
their disposal that will open new pathways to unleash greater human potential, productivity, some degree in their work and nearly
and creativity.
all believe Gen AI will be
Enterprises will need to develop investment strategies that enable employees to realize the transformative for their company and
value of these new tools. industry*
Our relationship with data is changing – and with it, how we think, work, and interact with
technology. The entire basis of the digital enterprise is being disrupted.
70%
The announcement of Gen AI changed the “librarian” model of search to a new “advisor” model
seemingly overnight. And now every company is working to implement LLMs. With this change
comes the need to rethink our computing structures and efficiency.
of client ISVs are integrating AI in apps
*Source: Accenture Pulse of Change Wave 10 Survey (Sept 2023)
**Source: Intel survey –PC AI ISV adoption (n=48)
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Spatial computing:
How we will experience AI
Immersive experiences will create seamless interactions with AI.
Today most of our interactions with Gen AI are through text-based or application-based user interfaces, but as
enterprises scale their capabilities, those interactions will become more integrated throughout our lives and our ever-
evolving mixed realities. Spatial Computing will provide an interactive layer for more immersive AI interactions. Scaling
the hardware to power these experiences will be key to their success.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
92%
Immersion through Spatial Computing
Immersive experiences, empowered by spatial computing, will blend our digital and physical
of executives agree their organization
realities while reinventing business models to create new human connections.
plans to create a competitive
Over the next decade, immersive experiences will revolutionize various aspects of life and business,
advantage by leveraging Spatial
facilitating learning, collaboration and sales in both virtual and augmented spaces, 2D and 3D,
Computing.
blurring the lines and changing how we interact.
These changes will create new business models and markets while also changing how we learn and This revolution will generate new lines
work. This change will be more gradual than Gen AI, will often be powered by Gen AI and will also of business and transform interactions
force significant changes across our enterprise data and computing structures.
between customers, employees and
companies.
Source: Accenture Technology Vision 2024
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Reinvention with Gen AI
The shift to Gen AI will require a multi-year change agenda and continuous reinvention powered by a modernized data
foundation with flexible architecture and an efficient and secure digital core. As companies scale this technology, they
will need faster computing power and an empowered workforce with a desire to facilitate change.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
The reinvention of work
AI is unleashing new levels of productivity and creativity while forging a path to the future that is different and
faster than any previous technology wave.Synthesizing data, comprehending natural language and converting
unstructured data into actionable insights takes significant computational power along with new human
interfaces and skills.
Gen AI will force a reinvention of work. These skills are not readily available in the workforce; companies need to
focus on enabling an AI-ready workforce. Enabling employees will require upskilling, change management,
and AI-ready technology.
Creating a Gen AI ready workforce
▪ Overall enterprise readiness for Gen AI must include focus on sustainability, cost efficiency, security and
upskilling employees.
▪ Comparative analysis of global Gen AI adoption and innovation scenarios shows that more than $10.3 trillion in
additional economic value can be unlocked by 2038 if organizations adopt Gen AI responsibly and at scale.
▪ Intel® Core Ultra Processors prepare your workforce to leverage Immersive meetings and the rapid
proliferation of AI across tools and apps.
▪ Intel is leading performance and reliability, executing a wide range of AI software through its global AI PC
Acceleration Program.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Beyond the headset and through the laptop
Many immersive experience platforms are available on both laptop and headset. By leveraging gamification techniques
to enhance employee and customer engagement, companies can utilize behavioral user data for better analytics, help
employees tap into the right expertise across the globe and build highly customized and engaging customer
experiences to attract and retain loyal customers.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Powering the experiences beyond headsets
Traditionally, immersive experiences required headsets to deliver the highest fidelity. However, in an
enterprise setting, headsets can be inconvenient and costly.
Many immersive platforms are now overcoming this challenge by offering accessibility through both
headsets and laptop devices.
This accessibility ensures that all enterprise employees with laptops can participate, maintaining the
benefits of Active Directory integration and enterprise level security.
The case for PC immersion:
▪ Empower employees to learn through simulation while retaining the benefits of immersive learning and
collaboration.
▪ Leverage gamification techniques, utilize behavioral user data, and help employees tap into the right
experience and expertise across the globe.
▪ Reduce enterprise operational costs, enhance engagement, and improve analytics.
▪ Create opportunities to leverage Spatial Computing using familiar and comfortable interfaces that have
an easier bar for entry.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Examples:
Collaboration
Virtual team breakouts and watercooler
discussions to connect working groups and
people across the organization
AI + Immersive
Experiences are
Onboarding
Memorable onboarding experiences to get
creating new realities
new hires excited, engaged and job-ready
powered by AI agents
Gen AI workforce empowerment and enterprise class immersive
experience use cases provide significant value in the workplace, Learning
Educational spaces to learn about specific,
each with its own unique benefits and situations:
hard to replicate scenarios at work
Brand Loyalty
Gamified experiences attract new customer
demographics and build loyalty
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
The AI Accelerant: Generative AI propels Spatial Computing
opportunities
Generative AI will be a driver for cost reduction as it reduces or eliminates the need for human-led work on content creation, but it also is an unlock to a previously
impossible level of scaled personalized service. Together with the metaverse, Gen AI is the powerful, personalized content engine that provides the ‘front-end’ interface of
spatial computing platforms.
ACCELERATED ACCELERATED PERSONALIZED PERSONALIZED
Digital twin / Environment Learning content development Synthetic human Synthetic human
creation and evaluation approaches agents for employees agents for patients/ Customers
AI is accelerating our ability to make digital Learning content platforms are speeding up Synthetic human agents provide a visual Synthetic human agents, powered by LLMs, also
twins of physical places like labs and their content production workflows with AI by interface for large language models (LLMs). enable more personalized, on-demand advice and
manufacturing facilities. Faster scanning incorporating co-pilot capabilities, making They can serve as a mentor, coach, and guide guidance for patients and customers through
techniques, prompt-to-environment, and learning development, engagement, and across various needs within the talent cycle. complex information as part of digital therapeutics
image-to-3D tools, and advanced analytics evaluation faster and more personalized. What They can help onboard, lead immersive learning efforts. They can be deployed on websites,
accelerate the creation of simulations, has previously taken months to create now sessions, keep track of performance metrics, integrated with apps, or appear in virtual immersive
collaborative spaces, and digital learning takes mere weeks or even days, enabling and provide a personalized, on-demand guide spaces. This enables more on-demand care and
areas. learning to be more flexible and adaptive. across various enterprise systems. guidance to supplement human capabilities.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Immersive Experiences: Scaling for adoption
As hybrid workplaces emerge, global teams collaborate more naturally using immersive spaces. Outdated hardware may hinder the compute demands of those processor-
intensive environments, so ensuring that the right hardware is in place will be key for scaling. The future of virtual collaboration and immersive experiences will start off with
familiar technologies and interfaces, namely laptop/desktop experiences, before making a jump to more mixed reality platforms.
RAPID ADOPTION FOR GROWTH
COLLABORATION & PEOPLE SCALING FOR SUCCESS
Case study: Accenture
Bridging physical space in the virtual Powering AI & immersion with the right
hardware Accenture serves as a notable case study for
Enterprises will build custom immersive spaces for virtual team
Mesh adoption, having successfully onboarded
meetings, collaboration, breakouts & fun, enabling a more Guaranteeing an optimal experience necessitates over 300,000 new employees in AltSpace and
connected work experience. hardware that can handle the demanding CPU and GPU Microsoft Mesh. These immersive experiences
Digital twins of offices, warehouses and manufacturing floors allow loads of programs like Microsoft Mesh. allowed Accenture to create both a consistent
teams to interact in what feels like the real environment, to safely Intel's Core i9 processors are well-suited to deliver a basic and unique global onboarding experience.
experiment with process improvements & layouts prior to experience and enable employees to leverage use cases. Their adoption of Mesh features has been rapid;
implementations.
Accenture enabled Avatars for 827,000
Moreover, the latest Intel® Core Ultra Series processors
The benefits of this approach includes reduced travel costs, real push the limits ofmultitasking performance to deliver real- employees in May 2023, with over 100,000
estate savings, increased collaboration & innovation for hybrid world business computing, making a compelling case for unique self-installed users, within one month of
work, employee engagement and retention. upgrading to the latest hardware. the Avatars’ launch in Teams.
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Up to
65% faster
image creation
Our future is digital
Up to
50% faster
To support what’s NEXT in innovation, we will need technology that’s designed to support the
demands of these new realities.
photo editing
The new Intel® Core Ultra Processors, including Intel® AI Boost, support a new generation of
personal computer able to span the physical-digital divide.
Up to
These chips will empower the transformation of individuals’ and organizations’ interactions with
40% power savings
each other and with the world, striking the right balance of power and performance.
while streaming
This includes personalizing and automating much of our daily lives through artificial intelligence.
Up to
38% power savings
while video conferencing
*Source: Intel AI Software Enabling November 2023
Executive summary | Introduction | Thought leadership | Use cases | Key takeaways
Key takeaways
The Enterprise technology revolution will be powered by next generation chips, designed for AI
& Spatial.
AI will be endemic – Every industry will be impacted by adoption of AI to support our workforces.
As the demand for more computational power grows, companies will need the workforce and
hardware to meet that demand.
Spatial is already here – Video conferencing spatial experiences are already available; the
capabilities will continue to expand.
Empower employees – Employee empowerment will accelerate adoption; hardware designed for
these new technologies will enable employees to design our future AI and spatial processes and
work environments.
Hardware matters – The new Intel® Core Ultra Processors, including Intel® AI Boost, support a new
generation of personal computer able to span the physical-digital divide and touch all aspects of our
lives – personal & professional.
Nathaniel Meyer
Digital Workplace Lead for the
Accenture and Intel Partnership
[email protected] |
95 | accenture | The-Travel-Industrys-New-Trip-Final.pdf | The travel industry’s new trip
How generative AI can redefine customer experiences and unlock new value for organizations
Content
03
Introduction
The traveler experience today 04
How gen AI can reinvent travel 13
Where travel providers stand 17
Building the data foundations to take
23
gen AI to scale
Key principles for executives seeking to
26
unlock the power of gen AI
Let’s move people 29
The Travel Industry’s New Trip 2
Introduction
The number of people traveling around the world itself, accommodation, car hire, excursions One particularly surprising finding from the traveler
is expected to reach an all-time high in 2024, as and more. And at each step, they face a myriad survey? Travelers’ views are remarkably consistent
global leisure and business travel volumes finally of options, which can be helpful, but can also regardless of age or income. And 60% of travel
surpass pre-pandemic levels. Overall, more than lead quickly to overload and dissatisfaction. industry CXOs see potential for gen AI in product
a billion people1 will make an international trip As recent global Accenture research2 found, application development and management. The
in 2024, with just as many traveling within their 74% of consumers have walked away from an implication? Effective solutions may not be as
country. And while some trips are for business, intended purchase because the complexity and difficult to tailor as they may seem.
others for leisure or personal reasons and others an overabundance of options were overwhelming.
a mix of both or all three, each trip requires an Nearly the same number (71%) say that they see
In this report, we’ll explore the current travel
extensive and careful planning process. From either no improvement or an increase in the time
landscape, and then delve into the potential to
the industry standpoint, that process opens the and effort required to make a purchase decision.
transform it for travelers and industry players
door to a host of opportunities for companies to
alike. We’ll focus on how advanced technologies,
differentiate and win consumers, from the moment
What if there were an easier way? That’s the particularly generative AI (gen AI), can remove the
someone is inspired to travel through post-trip
question that compelled our most recent research. friction that travelers currently experience. And
follow-up services after their trip is over.
We surveyed 8,079 travelers and 313 C-suite we will demonstrate the ways in which advanced
industry executives and complemented those AI tools can offer travelers a smarter, far more
The problem is, from the traveler’s point of view, surveys with a crowdsourcing exercise involving personalized and fully integrated way to identify
today’s travel-planning process is too often time- 200 travelers from across four countries, and an and explore options and design, build and book the
consuming and frustrating. AI-based cluster analysis of their views.3 We looked perfect trip.
closely at the whole traveler experience—from
inspiration to post trip—to identify travelers’ chief
Consider: While every traveler has unique needs, The stakes are high: According to Skift, gen AI
sources of friction and frustration, and what they
preparing for a trip typically involves using multiple presents a $28 billion opportunity for the travel
want to see most in the way of improvements.
websites and apps. They need to book the travel industry.4
The traveler
experience today
The traveler experience today
To begin with the basics, most travelers still prefer using their desktops or laptops to
explore destinations and to book trips. Our survey revealed, for example, that 48% of
travelers prefer using a desktop or a laptop, while 33% use their smartphones.
They also tend to start early and plan carefully. For those traveling domestically,
preparation typically starts one to three months before departure and for international
travel it’s likely to be six months to a year. Overall, our survey finds almost half of travelers
(45%) start planning one to two months in advance. More than a quarter (26%) start three
to six months before their trip.
We start planning our international and
“domestic travel well in advance. We watch
for deals, airfare fluctuations, and hotel
options, focusing on getting the best value.
– Traveler, US, 41–50 age group, traveling 2–5 times a year for leisure
The Travel Industry’s New Trip 5
The traveler experience today
At a more granular level, they break travel in to three distinct stages:
Seeking inspiration, planning (balancing cost with other considerations) and booking:
What inspires today’s traveler?
Travelers draw from a wide variety of sources that are not mutually exclusive to find
inspiration for destinations, activities, and types of trips.
Travel reviews are the most popular and influential. 90% of people say they use them,
and 96% think they are very important. Social media and travel influencers (on sites
such as TikTok, Instagram and Facebook) are also leading guides. And a strong majority
(71%) of travelers consult social media and influencers for inspiration about where to go.
In fact, 63% say these social media platforms/sites directly influence their final choice.
The appeal? These sites offer multi-modal content, offering insights into all facets of
an experience from activities to accommodations. And if a consumer follows someone
because they share interests, then the insights can be particularly relevant.
I rely on YouTube, Instagram, TripAdvisor,
“Yelp, and ChatGPT as dependable sources
for discovering new destinations. As a visual
person, I prefer video recommendations over
text whenever possible”
– Traveler, US, 41–50 age group, traveling 6–10 times in a year for leisure
The Travel Industry’s New Trip 6
The traveler experience today
Personal contacts hold considerable sway as well, with 61% of travelers saying they rely
on conversations with family, friends and peers to help them make up their minds.
Other sources of inspiration include books, magazines and the arts (music and
entertainment). Unsurprisingly, 55% of travelers report that industry conferences and
networking events influence their destination decisions.
Most notable in recent years (post-pandemic) has been the rise of “bleisure” trips,
Rich, immersive media to plan and inspire
where business travelers combine leisure options with work travel. These trips now
account for over a quarter of all travel (27% versus 38% for business trips and 36% for
pure leisure trips). Travelers (96%) use interactive maps or virtual reality tools such as Google Street
View to explore destinations before they book. Giving them rich media options
will help them make better-informed choices. Visual appeal is also crucial at the
inspiration stage. Over half of travelers (55%) say photos and videos influence
their decision-making. For 13%, they can be a dealmaker or breaker.
Online travel reviews provide accurate
“information about destinations, and YouTube
offers videos, making them my go-to sources
for trip research and planning.”
– Traveler, India, 21–30 age group, traveling 2–5 times in a year for leisure
The Travel Industry’s New Trip 7
The traveler experience today
Getting down to planning
Today, 28% of travelers turn to an offline travel agent or specialist for help planning their Is it any wonder the overall planning experience can be time-consuming, stressful
journey. They like the full-service nature of agents and specialists, as well as the sense and disjointed for so many? A full 68% say they use up to 10 sites to plan their trip,
of security they get from working directly with someone. They also appreciate the and 25% visit between 11–20 different sources for information during this planning
ability to ask for clarifications, and an agent’s ability to understand and accommodate stage. To manage the details, they often rely on multi-tabbed browsing sessions,
special requirements. bookmarking websites, offline spreadsheets and detailed notetaking. The most-used
planning activity across all travelers? A map, to scope their destination, locating hotels
and activities in advance of booking.
But for the rest, this is where the hard work begins. Knowing that good planning is
crucial for making the best of their investment, and seeking the right balance of price,
time and number of activities, travelers often visit multiple sites to pull together the
information they need. For the 44% of travelers with a fixed budget, always looking for
7%
the best deal is the greatest challenge. Those with more flexible budgets (43%) still
have many decisions to make, ranging from how long they want to stay in one place to
the transit links they’ll use between the airport and their destination.
From planning
25%
to booking,
how many
sources does
a traveler refer?
68%
1-10 sources 11-20 sources >20 sources
The Travel Industry’s New Trip 8
The traveler experience today
The travel planning process can be lengthy
and challenging, as many websites redirect
“
you to others, making it hard to compare Who’s doing the planning and booking?
and find the best deals”
Just 32% of travelers plan their travel themselves. Of the rest, 31%
depend on executive assistants, while 29% take help from spouses,
family or friends.
– Traveler, Greater China, 61 and older age group, traveling more
than 10 times in a year for Bleisure
What are their biggest planning headaches?
Respondents to our survey cited the following key challenges
I start by bookmarking travel blogs and
• Complexity of managing all the variables, especially accommodation
“sites, then create manual lists to sort my
• Managing their itinerary, including the need to compare options
preferences and compile price lists-the most • Tight scheduling and lack of support
• Travel unknowns or unfamiliarity with local conditions and transportation
challenging part. Maps are helpful too, but
• Decision fatigue
all this is quite time-consuming” • Risk of getting lost during the trip
– Traveler, India, 41–50 age group, traveling 2–5 times a year for leisure
The Travel Industry’s New Trip 9
The traveler experience today
Interestingly, 27% cited safety was their most important criteria when initially
planning a trip, followed by trip experience, flexibility (to change, cancel, etc.)
and accommodation.
Safety 27%
Destination/ trip
22%
experience
Flexibility (to change,
13%
cancel, etc.)
Accommodation 11%
Budget 10%
Transportation 8%
Activities and
5%
attractions
Reviews and
3%
recommendations
Cuisine 1%
Figure 1: Key considerations for travelers
Once they decide on a destination, travelers start to consider more specific
criteria. The most commonly cited of these is quality of service, including
cleanliness and friendliness (28%), followed by food and dining options (26%).
Other things they search for: extra reassurance on safety and security, proximity
to local transport and attractions and whether they’ll have access to personalized
services such as pick-up/drop-off options for transfers, or concierge services.
The Travel Industry’s New Trip 10
The traveler experience today
The great disconnect:
Travelers’ expectations versus reality
A significant majority (66%) of our survey challenge. Many are looking for convenience
respondents said they’re dissatisfied with the and simplicity: 69% say they prefer booking
planning options available to them today. travel packages and additional services
along with their hotel or airline tickets from
the same website.
Most travelers use hotels, airline or online
travel agents’ (OTA) websites or apps for
• A one-click process
Interestingly, most people (89%) also said
exploring their options, planning and
• Intuitive search
they have at least some interest (with 38%
booking. More than half (57%) say that they
• Intelligent live support for booking and other inquiries
very interested) in a subscription-based travel
trust those providers to look after their travel
platform. For a monthly fee, that approach • Automatic, personalized suggestions (schedule, itinerary) – mimicking a local
and booking data.
would give them access to benefits such travel guide
as customized trip planning, best deals and • Simplified view of offers (with points, miles, redemption)
But 61% of travelers also say that they find
curated itineraries.
navigating apps and websites complex. • High-definition photos for reference
And 56% say that the lack of options for • Clear cancellation/modification process and procedures and safety advisory
The most-cited feature travelers wish for from
customization or filtering content adds to
• Automatic prompts to the best spots and hidden places
provider websites? Personalization. More
the time required to make a decision and,
• Journey assistant for live reminders
than a third ranked this as their top desire for
in some cases, prevents them from making
their travel planning experience. After that,
a decision at all. Many also complain of
they seek natural language search (25%),
unwanted notifications and promotions,
Figure 2: The Travelers’ Wish List
connected trip recommendations (15%) and
and 52% say that they have concerns about
automatic itineraries (11%), as well as being
general data privacy and security.
able to ask open-ended questions (7%).
One of the problems many travelers face is a
Ultimately, when we asked travelers to create
lack of joined-up experiences in the planning
and prioritize a wish list for what tomorrow’s
and booking phase. Almost two-thirds (64%)
travel experience should look like, here’s
say that lack of bundling options to create
what they told us. (See Figure 2)
a seamlessly connected trip is their biggest
The Travel Industry’s New Trip 11
The traveler experience today
And when we analyzed our findings more deeply across each stage of travel, we identified the sub-categories shown in Figure 3:
Inspiration, planning Compare and During the journey Post-journey These are all capabilities at which gen AI
and search purchase excels. It’s clear that the travel sector has
much to gain from putting the power of gen
AI into its customers’ hands.
• Natural language • Product cross-sell • Real-time itinerary • Personalized travel
search. recommendations. management. summary for memories
or travel journals.
• AI-generated hotel/ • Sort order optimization • AI-powered customer
A I Saudia’s Travel Companion
airline description, on app. assistant for support, • Expense reporting.
content and imagery. scheduling and
• Upsell and offer • Automated photo
Saudia Airlines has launched Travel Companion,
reminders.
• Content recommendations. sorting and album
an AI-powered virtual assistant designed to
personalization by • Real-time language/ creation.
• Real-time pricing and
enhance customer experiences. This platform,
individual—including content translation.
offers. • Feedback collection
a key component of Saudia’s broader strategy
recommendations.
• Contextual and analysis to improve
• Sort order optimization to innovate travel experience, simplifies the
• Automatic trip creation recommendations future experiences.
on payment methods.
booking process including various travel
based on website/ (e.g., dining,
• AI-driven content
services—such as accommodations, transport,
chatbot interaction. attractions).
creation for blogs or
dining, and activities—into a single interface.
• Automation loyalty • Real-time safety social media posts.
Future updates will include additional features
member recognition. regulatory alerts and
• Suggest new like voice commands and multiple digital
guidance.
destinations for next
payment options.
• Proactive disruption trip, based on past
management. preferences—inspiring
them to begin planning
• Support remote
all over again.
destination travel
planning.
• Adapt to users’
emotions based on
interactions.
Figure 3: Zooming in on the wish-list
The Travel Industry’s New Trip 12
How gen AI can
reinvent travel
How gen AI can reinvent travel
Our research confirms that travelers are willing to use dedicated travel apps to 48%
50
help them improve their experience from search to booking. In fact, 55% say that
they already use dedicated travel planning apps such as TripIt, Routeperfect
40
and Google Trips, with 37% saying that they sometimes use them. These apps
offer features such as automatic itinerary generation, conversational assistance 29%
30
(including recommendations and offers) tailored to user/traveler’s profiles
22%
and behaviors.
20
But an overwhelming majority (97%) of travelers want a travel “superapp.” They
10
want something that will offer one-stop, integrated access to a whole range of
travel-related services, including personalized, inspirational destination ideas,
0
flights, dining and everything in between. And a related Accenture study,
Book (purchase) Inspiration (finding Planning (search,
The Empowered Consumer, found that over half of consumers are open to using
relevant content) compare and customize)
conversational AI solutions.
Figure 4: Travel Planning: Stages Ranked by Complexity
Enter gen AI
During the inspiration stage, for example, gen AI tools can prevent overload.
Our respondents ranked inspiration as the second-most complicated stage of
Using voice commands to tell an AI travel app
travel, after booking. With an overabundance of choices available, it’s easy to
become overwhelmed with information and possibilities. Gen AI can take each “about my destination and desired activities, and
traveler’s unique needs and motivations to filter out the noise and focus on the
having it suggest detailed itineraries—including
rich signal of what will be most relevant, appealing and ultimately rewarding
for every individual. Moreover, they can do this in the course of a natural-
transport and exact timings—would allow me
language interaction, while offering multi-modal responses (photos, videos,
charts as desired).
to choose the best options easily”
– Leisure traveler, US, 41–50 age group, traveling 6–10 times in a year
The Travel Industry’s New Trip 14
How gen AI can reinvent travel
At the planning stage, gen AI tools can stand out with their ability to personalize
a trip. While travelers say that planning is less complicated than other stages
(inspiration and booking), there is still plenty of scope for gen AI to simplify the
ways travelers plan, manage and track their travel details. For example, few tools
Use your words!
today can handle collaborative planning, and it’s still not easy to compare prices
and track them across multiple trip options and/or timetables.
Being able to use natural language instructions – including voice – to ask questions
And although today’s chatbots provide some tailored recommendations, there’s
and make commands is one of gen AI’s major appeals to users. Today, travelers
significant room for improvement. For example, with the responsible use of
are largely reluctant to make their bookings via voice search, with only 28% saying
customer data, gen AI could analyze each traveler’s unique preferences and
they’re comfortable booking this way. Barriers to voice search include:
travel history to shape an individualized, highly relevant itinerary that goes well
beyond standard attractions and activities.
• Difficulty in specifying preferences (e.g., room type or airline seat) due to
interface complexity (56%)
• Misunderstanding or incorrect assumptions made by the voice assistant (50%)
• Difficulty in finding specific dates, flights, or hotels due to limited options (47%)
• Difficulty in accurately recognizing spoken commands with lack of confidence
in the end-result (44%)
The Travel Industry’s New Trip 15
How gen AI can reinvent travel
Booking is by far the most complicated stage of a journey. Today, it still tends to be a
highly siloed process, as arranging each part of an overall trip—hotels, flights, activities,
restaurants and car rentals—requires separate payment and reservation processes.
Here, gen AI tools—particularly teams of gen AI tools operating through a single
interface — could offer a simpler, more centralized view of options such as payment,
offers, rewards and itinerary. While online travel agents (OTAs) have improved at
bundling various options into a single view, again, there is great room for improvement.
Ultimately, the transformative power of gen AI offers travel businesses the ability
to analyze vast amounts of data in real time and gain unprecedented insights into
travelers’ needs and preferences. It can automate research and planning by providing
real-time, data-driven recommendations—based on current and past preferences—
saving travelers time and personalizing their experience. And the travel industry can
maximize revenues by seeing booking patterns in a new light and embracing both
traditional and digital channels in real-time. In essence, gen AI will not merely be an
analysis tool. It will also usher in a new era of innovation and competitiveness.
The Travel Industry’s New Trip 16
Where travel
providers stand
Where travel providers stand
Are travel players ready to grasp this opportunity? Most are embracing gen AI tools in theory but are finding considerable challenges when it comes to scaling initiatives. Consider:
Executives’ gen AI priorities
Travel executives are increasingly recognizing the value that gen AI can bring to their consumer-facing and internal operations. Our survey finds that, globally, almost three-quarters
(73%) of travel leaders are focused on adopting gen AI for cost savings and greater efficiency. Significant numbers are also looking to use it to improve top-line growth (63%) and
enhance brand perception (61%). These findings are generally similar across all segments of the travel ecosystem, suggesting a broad recognition of the value on offer. (See Figure 5)
Airlines Airports OTAs Hotels and resorts Cruise Car rental
Cost savings/ Improved brand Cost savings/ Cost savings/
Top-line growth Top-line growth
improved efficiencies perception improved efficiencies improved efficiencies
Cost savings/ Cost savings/ Improved brand Improved customer Cost savings/
Top-line growth
improved efficiencies improved efficiencies perception experience improved efficiencies
Improved brand Improved employee Improved customer Improved brand Improved brand
Top-line growth
perception experience and retention experience perception perception
Improved employee
experience and retention
Figure 5: Business leaders’ priority gen AI outcomes
Priorities ranked in order of preference
The Travel Industry’s New Trip 18
Where travel providers stand
At the same time, travel leaders acknowledge that to fully realize these benefits, Chatbots, Virtual Device
65%
they’ll need to implement gen AI at scale—across the enterprise and value chain. Assistant and customer service
They will also need to measure its impact. Currently, companies are developing
Market and competitor
62%
and implementing gen AI use cases in areas such as customer service, market and
forecasting and predictions
competitor forecasting and product/application development. Almost half (49%) of
leaders are working toward executing these use cases, while a smaller proportion, Product and applications
60%
development/management
17%, say they’ve identified multiple use cases, and are exploring value chain
synergies to implement them at enterprise scale.5 (See Figure 6)
Sales and marketing 56%
Content translation 48%
Optimizing
48%
internal operations
Content creation 41%
Personalized travel planning
38%
and recommendations
Workforce training
37%
and skilling
Booking
30%
recommendations
Creating an
18%
end-to-end superapp
Figure 6: Use cases underway
Percentage of business leaders who see the most potential for gen AI applications across the enterprise.
The Travel Industry’s New Trip 19
Where travel providers stand
Prioritizing the workforce
Whichever specific use cases businesses focus on, one element is crucial: Continuous training by using resources such as
the people who make up the travel industry’s workforce. Yet two-thirds of the massive open online courses (MOOCs), digital 56%
learning platforms, boot camps.
executives we surveyed believe that workforce readiness and lack of training are
major barriers to progress with gen AI.
Training using experiential and immersive
56%
methods such as gamification and Metaverse
To address those barriers, companies are increasingly recruiting talent with
relevant expertise, as well as encouraging greater collaboration between their
Joining or actively participating in
data scientists, travel domain experts and IT professionals. But with gen AI talent digital training programs (e.g., the World 49%
such a scarce and keenly contested resource, travel companies are also investing Economic Forum’s SkillSET)
in training their people, with initiatives including boot camps, immersive methods
such as gamification and participation in third-party digital training programs. Instructor-led training workshops in a
48%
physical or virtual classroom
(See Figure 7)
Establishing ‘Data and AI institute’
48%
within the organization
Focused apprenticeship or
42%
certification programs
Figure 7: Training and upskilling initiatives in place across the industry
Percentage represents executives reporting anyone initiative being used at their organization.
The Travel Industry’s New Trip 20
Where travel providers stand
Tech readiness
AI broadly Generative AI
Companies recognize the importance of responsible adoption,
citing transparency, AI ethics policy and governance processes as Hardware infrastructure (e.g., specialized hardware
Strategy Assess
important levers to ensure data security and customer privacy. They for training and predictions, operational workloads).
are also starting to create the foundational elements for implementing
AI-specific applications by developing an AI-enabled digital core—
Cloud computing (e.g., computer hardware exposed
including AI-ready data and applications, a gen AI backbone, security, Assess Assess
to developers in a cloud operating model).
ecosystem, partnerships and responsible AI.
But most are still developing strategies and assessing potential Understand and develop an AI-enabled digital core—
deployments, especially in areas like cloud computing, data platforms AI-ready data and applications, a GenAI backbone, Transform Transform
security and the right ecosystem of partners.
and talent reinvention.
Figure 8 shows broadly where travel companies are in their gen AI
Availability of a modern data platform with mature
journeys, from the strategic stage (planning), through assessment
data management and governance practices — to Transform Assess
(partnering with other organizations and evaluating potential
help leverage unstructured data and synthetic data.
deployment methods), to transformation (implementing AI/gen AI in
some functions of the organization and for specific purposes). Fewer
than 20% of respondents say they’re engaged in AI implementation at Reinvent talent and ways of working—includes
leadership, learning, new ways of working, new roles Assess Assess
scale (across the operation, continuously improving) for any processes
and skills and continuous learning.
in the travel value chain.
Practicing responsible AI—an intentional method
of designing and deploying AI to drive value while Transform Transform
protecting from the risks.
Figure 8: Where are travel companies on their gen AI journeys6
The Travel Industry’s New Trip 21
Where travel providers stand
Some travel 01 Expedia has unveiled Romie, a travel planning, 04 Booking.com introduced AI Trip Planner,
shopping, and booking assistant. It adapts to an AI-powered bot enabling travellers to ask general
companies have
unexpected changes like weather disruptions, or specific travel-related questions, across any stage
suggests indoor alternatives, updates itineraries of the trip planning. It also recommends customized
already started
in real-time, integrates information from emails, itineraries and inspirational content, based on each
recommends activities and joins SMS chats to offer traveller’s preferences.
using gen AI
advice and summarize discussions.
to provide new
05 Despegar, a travel tech company, launched SOFIA -
02 IHG hotels is partnering with Google Cloud to a gen AI travel assistant that provides
services and
launch a gen AI-powered travel planning capability, recommendations on inspiration, planning,
experiences for to be launched in H2 2024. Customers using the coordination, and journey logistics.
IHG One Rewards mobile app can use gen AI for an
travelers.
easier and interactive planning experience.
03 KAYAK launched a suite of AI products using gen
AI to make travel planning faster, easier and more
intuitive. It launched PriceCheck, a price comparison
tool, and Ask KAYAK, to personalize travelers’
search experiences.
The Travel Industry’s New Trip 22
Building the data
foundations to take
generative AI to scale
Building the data foundations to take gen AI to scale
Ultimately, creating the transformed experiences that travelers crave will require We have access to
60%
nothing short of enterprise reinvention. This means building a digital core—the 1st party data
critical technological capability that enables the organization to use the most
relevant advanced technologies to their potential now and adopt the next wave
We have access to
50%
of technologies with ease. 2nd party data
It also means developing the ability to operate in a trusted ecosystem of partners We have access to Zero
party data about our clients 44%
to offer and integrate all relevant services, but also, crucially, to share vital data
and ecosystem partners
and applications. The industry still has some way to go in taking this next vital
step. Just 21% of respondents say they have a readily available ecosystem of
We have access to
industry data partnerships. And only 15% of respondents claim to have access to 34%
3rd party data
readily available developer networks to a great extent.
We have access to
Collectively, the travel industry has huge amounts of data available, including 12%
synthetic data
traveler preferences, booking patterns and local insights. Anonymizing this data,
and then using gen AI to analyze it, creates a very valuable asset. Yet, as the
Figure 9: Who’s data? From where?
industry continues to struggle to update its aging data systems and capabilities,
only a small percentage of companies are currently monetizing their data
through methods like anonymized data sales (less than one-sixth) or partnerships
Travel companies’ projected investments in gen AI confirm that they’re committed to
(about one-third). This is a major missed opportunity that forward-thinking travel
making the leap from pilots to scaled implementation. Organizations are prioritizing
organizations should address urgently. Moreover, the availability of high-quality,
gen AI in their technology investments and will continue to do so—currently 34% of
contextualized travel industry data is vital to pivoting to a gen AI architecture.
travel organizations are dedicating more than half of their technology budget toward
AI (including gen AI). This number is expected to reach 69% (from 34%) in the next 18
Figure 9 shows the range of travel company abilities to access data types7 months. Making this move will require travel companies to address the barriers they
required to realize the potential of gen AI. face today.
The Travel Industry’s New Trip 24
Building the data foundations to take gen AI to scale
Barriers to adoption
Travel leaders identified a number of challenges that they’ll need to overcome as they progress
to full-scale gen AI adoption. Among the biggest challenges: lack of technology capability
in-house, inability to manage rising volumes of data and complexity, workforce readiness and
inability to integrate gen AI systems with legacy systems with no clear ROI.
At the same time, however, leaders are also taking positive steps to address these barriers,
including:
• A majority (63%) prioritize high-quality data availability, security and privacy through
investment in data management tools, and governance policies.
• Six out of 10 are prioritizing talent acquisition and retention through investment in
training programs.
• Two out of three leaders are looking to invest toward the integration of new gen AI systems
with legacy systems.
• Three out of four C-suite leaders are setting policies and guidelines to mitigate operational
and strategic risks associated with the use of gen AI.
• A strong majority (70%) prioritize change management by developing a clear vision,
communicating the benefits of initiatives and involving employees in the planning process.
The Travel Industry’s New Trip 25
Key principles for
executives seeking to
unlock the p |
96 | Autres | AIQRATE-Global-AI-Adoption-Report-2022-CPG-and-Retail.pdf | CPG & Retail
GLOBAL AI
ADOPTION
REPORT 2022
ACCELERATE | ACCENTUATE | AUGMENT
The AI in the CPG & Retail Market is
expected to reach USD 30.90 billion by 2025,
at a CAGR of 35% over the forecast period
2020 – 2025.
CONTENTS
1.Overview - Page 2
2.Business Value chain: AI Adoption Areas - Page 4
3.Spending on AI - Page 11
4.AI Adoption across Regions - Page 14
5.Impact on Revenue and Costs - Page 19
6.Challenges - Page 21
7.The Way Forward - Page 23
1
Global AI Adoption Report 2022
CPG & Retail
Overview
Consumer products organizations (CPG) and Retail are entering a new phase of innovation with
AI at its core. The results are profound, offering a host of previously unimaginable capabilities –
from automatically rerouting shipments to bypass bad weather, to personalizing in-store
services based on analysis of a customer’s facial expressions.
The adoption of AI in Retail and CPG industries is expected to leap from 40% of companies
currently to more than 80% by 2025. Investments in AI-powered predictive and prescriptive
analytics would more than double between 2020-2025.
CPG and Retail organizations with AI investments report current benefits in five key areas:
creating better consumer experiences, revenue growth, employee upskilling, improved decision-
making and reducing risks.
Last five years have been highly challenging and disruptive amidst a changing competitive
landscape marked by new consumer behaviors. ‘Business as usual’ is not enough anymore—and
the organizations recognize that innovation must accelerate. The adoption of digital and
analytics offers CPG and Retail companies the opportunity to drive growth, deliver productivity
and stay ahead of the competition. The effort needed to take advantage of this value potential
will be worth it. The companies that adopt digital technologies early and at scale outperform
traditional incumbents.
In the 1990s, the eCommerce revolution initiated a fundamental change in consumer shopping
behaviour, which has continued to gain momentum in the mobile and social media era. In the
process, customer demands have reshaped the retail and consumer products industries. To
meet these changes, retailers and brands have leveraged technologies over the past decade that
enable them to stay close to local market trends, understand consumer preferences and
shopping behaviours, design products, provide value-added services and engage consumers in a
contextual way.
2
GGlloobbaall AAII AAddooppttiioonn RReeppoorrtt 22002212
CCPPGG && RReettaaiill
The changing customer preference and growing competition among retailers to hold significant
market share have increased the deployment of AI in the Retail industry. The growing
digitalization coupled with rising internet penetration and proliferation of smart devices across
the globe is rapidly increasing the use of AI by retailers.
The competitive landscape is shifting and it’s no longer about just pursuing AI—it’s about being
among the first to adopt AI at scale to reach unprecedented levels of personalization, precision
and profitability. The good news is CPG & Retail organiztions now have access to the necessary
innovation, compute power, skill sets and solutions required to fully embrace AI responsibly
across the enterprise to create value and fuel profitability.
Rapid growth in consumer spending, presence of young population, government initiatives
towards digitization, enhanced internet and connectivity infrastructure, and growing adoption of
AI-based solutions and services are helping Asia Pacific region to register the fastest growth in
the global artificial intelligence in CPG & Retail market.
3
Global AI Adoption Report 2022
CCPPGG && RReettaaiill
Business Value Chain: AI Adoption Areas
1. Product categorization 2. Customer Support
3. Product Search 4. In-store Assistance
5. Digitally Enabled Virtual Experience 6. Tracking Customer Satisfaction
7. Predicting & Influencing customer 8. Cashier-free Stores
behavior 9. Trade Promotion Optimization (TPO)
10. Adjusting prices 11. Supply chain management and
12. Product Recommendations logistics
13. Consumer Goods Manufacturing
1. Product categorization
Artificial intelligence is a smart way to classify products. It is used nowadays for product
categorization through optimization of sales and promotions, increasing understanding of in-
store customer behaviour and better management of inventory levels.
LovetheSales.com employs machine learning to categorize more than a million commodities
from numerous retailers.
Lalafo has made a step forward by sorting merchandise and services via AI-powered image
recognition. When sellers want to market goods on Lalafo, they can just upload an image of
these goods with no need to add a description. Artificial intelligence has helped Lalafo
increase content relevance and improve sales.
2. Customer Support
Chatbots are one more popular application of AI in the CPG & Retail industry. Chatbots help
retailers to provide great customer service, help customers find items on the site, notify them
about new collections, and offer them apparel similar to things they’ve already chosen. Other
customer support tools include Guided Search, conversational support using customer data
insights and emotional response, Demand Forecasting, Optimized development and more
expenditure in research and development.
Burberry and Tommy Hilfiger have already launched AI-driven bots on Facebook Messenger
that guide customers through their latest collections and answer their inquiries.
1-800 Flowers has also launched an AI-powered concierge named Gwyn (Gifts When You
Need). Gwyn emulates messaging platforms like WhatsApp and can successfully reply to
customer questions, help customers find the best gifts, and assist them through the entire
shopping experience.
4
Global AI Adoption Report 2022
CPG & Retail
3. Product Search
Voice Product Search
Artificial intelligence has made possible voice search for products. Many prominent brands
such as Costco, Kohl’s, Target, Tesco, and Walmart use either Google or Amazon AI
technology and smart devices to serve customers with easy and fast search. Customers
don’t need to type in queries on small devices anymore; they can just ask Alexa to add
carrots or new glitter shadows by MAC to their shopping bag.
Visual product search
Artificial intelligence has opened visual search to retailers as well, allowing customers to
upload images and find identical or similar products. AI-powered technology scrutinizes an
image and analyzes colors, shapes, and patterns to identify an item. John Lewis has added
this technology to their iPad app. The Find Similar feature has gotten 90 percent positive
feedback from customers. American Eagle Outfitters also offers visual search in its mobile
app. American Eagle image recognition technology lets customers not only find the exact or
similar clothing but also get recommendations on what goes well with it.
Virtual Fitting Rooms
A great way for customers to save time and shop from the comfort of their house. A virtual
fitting kiosk from Me-Ality can scan you in 20 seconds and measure 200,000 points of your
body in this period. Companies like Levi’s, Gap, Brooks Brothers, Old Navy, and others
installed these scanners in their stores and received massive sales increases.
4. In-store assistance
Many retailers invest in AI-driven technologies that can both assist customers while shopping in
their physical stores and help their staff handle customer inquiries. Using AI, the stores can
become cash-free, chatbots for customers, automatic price adjustments on goods.
Using image recognition data for Shelf Intelligence compliance monitoring stores are optimizing
in-store presentation, display and shelf space use. Survey finds the global image recognition in
retail market size to grow from USD 1.4 billion in 2020 to USD 3.7 billion by 2025. Increasing on-
shelf availability, enhancing customer experience, and maximizing ROI are expected to majorly
drive this market.
John Lewis spent £4 million in 2017 on a shop floor app for its personnel. This app equips
employees with information about products and stock availability so they can answer
shoppers’ questions right on the spot.
·Kroger Edge technology eliminates paper price tags in their stores; smart shelf tags are
now used. This technology also provides video ads, nutritional info, and promotions on the
displays.
5
Global AI Adoption Report 2022
CPG & Retail
·Lowebot, an autonomous in-store robot from Lowe’s, helps customers find what they need
in the store in different languages. At the same time, it helps with inventory management
thanks to real-time monitoring capabilities
·Trax’s XRetail Watch real-time shelf-monitoring and analytics platform reveals what’s
happening in the aisles so you can optimize operations. Poorly managed shelves result in
unhappy shoppers and missed sales, but retailers don’t have the manpower to spot every
error as it happens. Trax automatically scans shelves, analyzes conditions, and prioritizes
fixes to unlock each aisle’s full potential. Inn-store cameras capture real-time shelf
conditions. Images are sent to cloud servers, where deep-learning algorithms analyze with
pixel-perfect accuracy to identify each SKU. Platform analyzes real-time shelf conditions and
communicates insightful data through mobile- and web-based alerts and dashboards.
5. Virtual fitting rooms and mirros
The virtual fitting room is a great helper for busy shoppers as they can try out manifold apparel,
find the right outfit and an accessory that perfectly matches it, and do all this in a matter of
minutes. The virtual fitting room works as follows:
1.The input video is split into frames and processed with a deep learning model which
estimates the position of a set of specific leg and feet keypoints.
2.A 3D model of footwear is placed according to the detected keypoints to display the
orientation to a user naturally.
3.A 3D footwear model is rendered so that each frame displays realistic textures and lighting.
Moda Polso lets its clients create their own avatars. These virtual avatars let Moda Polso
shoppers try on an unlimited number of outfit options and make a purchasing decision
quickly and easily.
Me-Ality, a Canada-based tech startup, has developed a virtual fitting kiosk that can scan a
shopper’s whole body. A scan takes about 20 seconds and measures 200,000 different
points on the body. Gap, Levi’s, J.Crew, Old Navy, American Eagle, and Brooks Brothers set
these scanners in their stores and saw a dramatic increase in sales.
Specsavers was one of the first retailers to offer a Virtual Try On feature. With Specsavers, a
customer can scan their face with the camera on their desktop, tablet, or mobile and virtually
try on glasses in one click.
6
Global AI Adoption Report 2022
CPG & Retail
6. Tracking Customer Satisfaction
Apart from scrolling through social media and gathering feedback left by customers, artificial
intelligence can detectthe actual mood of your customers in the store. Customer satisfaction can
be increased by improving response time, having more personalized interactions, issue
prioritization, proactive service and round-the-clock availability.
Walmart is rolling out facial recognition cameras that can define a customer’s level of
satisfaction at the checkout. If a customer is frustrated, a company representative will talk
to them to soften the annoyance and revive their relationship with the store.
Multi-brand online retailer Shop Direct is working with IBM to develop an AI-driven chatbot
that can determine customers’ moods as well. The chatbot goes through the words and tone
that customers use in their text messages. Once the chatbot has detected an annoyed or
disappointed customer, it directs them to a representative for help via chat or a telephone
customer service line.
7. Predicting and Influencing Customer Behaviour
Artificial intelligence platforms like Personali allow retailers to leverage behavioural economics
and reach customers with an individual approach. Personali’s Intelligent Incentive platform
analyzes customer psychology and emotions to encourage purchases.
Businesses are leveraging using AI in customer behavior and predicting their needs. The
prediction of trends in customer behavior helps in devising market campaigns, content
marketing, enhanced communication, assisting in customer sentiment analysis and increases
customer turnover.
AI also influences customer behavior by increasing their spending, increasing their loyalty
towards the brand, improving expectations of the people in regards to the company and overall
market dominating influence.
Artificial intelligence platforms like Personali allow retailers to leverage behavioural economics
and reach customers with an individual approach. Personali’s Intelligent Incentive platform
analyzes customer psychology and emotions to encourage purchases.
Reckit Benckiser is bringing together multiple data sources to enable consumer segmentation
and marketing campaign measurement. They will use machine learning capabilities to evaluate
ROI and plan future campaigns more effectively. RB will also run its own ML and auto-ML
models, generating insights to optimise media spend, and creating more natural digital journeys
as consumers go from awareness, to purchase, to advocacy, whilst always respecting data
privacy.
7
Global AI Adoption Report 2022
CPG & Retail
8. Cashier-free Stores
Cashless shops are the new concept over-taking the pre-exisiting concept of maintaining small
amounts as change. It reduces waiting time for customers and saves money for the retailers by
saving money on hiring employees. A cashier-less checkout may work like this:
Before a customer enters a store, they need to download a smartphone app. Once inside the
store, the app is authenticated by a QR code. If the retail store has introduced a smart shopping
cart—such as the AI-powered, weight sensitive cart produced by Caper, which identifies exactly
what a shopper has placed in their cart—the customer can then log into the cart, before said
cart automatically scans each item with a barcode.
When the customer has finished shopping, they then need to enter a sensor-enabled lane which
automatically charges their card. The process doesn’t end there, however. Using big data
analytics, the smartphone app is able to record, store and use data about each individual
shopper so that it can
a) identify customer behaviour and
b) personalize future recommendations.
Amazon has already instigated the cashierless checkout revolution with its Amazon Go
cashierless stores. Other chains, including Walmart, Kroger and Sam’s Club had announced that
they will soon follow suit.
The robotization of stores helps diminish lines, reduce the number of employees needed, and
dramatically save operational costsfor a company.
Amazon artificial intelligence has enabled checkout-free stores. The Amazon Go app along with
Just Walk Out Shopping technology automatically react to a customer’s taking from and
returning products to the shelf.
9. Trade Promotion Optimization (TPO)
Trade promotion optimization is a really important aspect and has the second highest
expenditure after COGS for stores. AI is used in this segment to improve the efficiency and
optimize the process. Artificial Intelligence improves market campaign quality, discovers which
promotion provides better return on investment and forecasts a model-based predictive
analysis for better adjustment to market prices.
Genpact offers a software called Contract Assistant, which is a sub-product of Genpact Cora.
Genpact claims Contract Assistant can help CPG companies stop overpaying retailers for
carrying out promotions such as sales or in-store displays. The software uses natural
language processing to match trade promotion contracts to invoices.
Wipro offers Promax Optimize, which it claims can help CPG companies optimize future
trade promotions using predictive analytics.
8
Global AI Adoption Report 2022
CPG & Retail
10. Adjusting prices
Artificial Intelligence is important as it can show retailers likely outcomes of different pricing
strategies so they can come up with the best promotional offers, acquire more customers, and
increase sales.It also improves customer relations. 4 benefits of adjusting prices through AI are
raising of prices without affecting sales, factoring consumer behavior in pricing strategy,
predicting impact of different prices on sales and combining data and experience to maximum
effect.
eBay uses AI-powered pricing and inventory algorithms to define the most appropriate
prices for goods and notify sellers.
Kroger applies artificial intelligence for price optimization as well. Analytics data helps the
company stay flexible and change prices and promotions instantly based on shopper
insights.
11. Supply chain management and logistics
An excess or short supply of products can affect a company’s profitability and costs retailers
worldwide $1.1 trillion each year. Leftover stock is often marked down and leads to low sales
turnover. Out-of-stock situations, on the other hand, make for lost sales and dissatisfied
customers who can easily switch to your competitors. AI helps retailers replenish supplies by
identifying demand for a particular product based on sales history, location, weather,
promotions, trends and so on. This way companies can prevent underperforming products from
building up, stock what customers are likely to buy, achieve faster deliveries, reduce returns, and
save lots of money.
H&M uses AI to analyze store returns, receipts, and loyalty cards to predict future demand
for apparel and accessories and manage inventory.
Morrisons has partnered with BlueYonder, a leading AI solutions provider for retailers, to
optimize stock forecasting and replenishment across its 491 stores. Use of artificial
intelligence has helped the company to reduce shelf gaps in-store by up to 30 percent.
12. Product recommendations
Hanes Australasia, with the help of With Google Cloud and Recommendations AI, is delivering
personalized product recommendations to customers, improving engagement and experience.
This is enhancing transaction conversion rates and improving revenue. The business is now well
positioned to use additional Google Cloud machine learning products to further enhance
customer experiences and grow across new and existing markets.
9
Global AI Adoption Report 2022
CPG & Retail
13. Consumer goods manufacturing
Shop floors are leveraging real-time equipment performance monitoring and analytics to
measure the productivity vs planned allowing the constant tracking of productivity and
performance of all equipment and assets during production.
In Kewpie’s plant, the Tensorflow based AI system could detect potatoes that aren’t fit for use in
baby food, even as they were running at high speeds on a conveyer belt. The system was
“educated" to identify the clean and healthy ingredients, by making it recognize almost 20,000
photos of potatoes, which included acceptable and useable, as well as defective and unusable
potatoes.
10
Global AI Adoption Report 2022
CPG & Retail
Spending on AI
Global spending on AI by retailers is estimated to reach $12 billion by 2023, all because AI offers
new ways to improve the customer experience and to optimise operational efficiency and
productivity.
Digital and analytics can unlock at least $490 billion in value for CPG by 2023.
A few examples of spending & application of AI by Retail & CPG companies on AI are given as
follows: -
LIVEPERSON- Teaching bots to help human agents
LivePerson’s Conversational AI lets organizations automate straightforward customer service
tasks via online chat and text messaging, so trained agents can focus on the queries that require
a human touch. In 2021, the company introduced the ability to integrate Conversational AI into
commerce systems, broadening its original focus on after-purchase support.
Dunkin’, for example, has added QR codes to food packaging at 9,000 stores, letting customers
sign up for its loyalty program by chatting with a bot. Commerce isn’t Conversational AI’s only
new territory: Bella Health, a COVID-19 screening bot in use at 500 locations, is helping to detect
infections before employees unwittingly spread them to coworkers. A new feature called AI
Annotator has allowed support reps to improve a company’s bots on the fly, no deep knowledge
of data science required; overall, there’s been a 40% year-over-year increase in automated
conversations performed on LivePerson’s platform.
ADOBE- Photoshop wizardry within reach
Adobe’s new neural filters use AI to bring point-and-click simplicity to visual effects that would
formerly have required hours of labor and years of image-editing expertise. Using them, you can
quickly change a photo subject’s expression from deadpan to cheerful. Or adjust the direction
that someone is looking. Or colorize a black-and-white photo with surprising subtlety. Part of
Adobe’s portfolio of “Sensei” AI technologies, the filters use an advanced form of machine
learning known as generative adversarial networks.
That lets them perform feats such as rendering parts of a face that weren’t initially available as
you edit a portrait. Like all new Sensei features, the neural filters were approved by an Adobe
ethics committee and review board that assess AI products for problems stemming from issues
such as biased data. In the case of these filters, this process identified an issue with how certain
hairstyles were rendered and fixed it before the filters were released to the public.
11
Global AI Adoption Report 2022
CPG & Retail
McDonald’s Drive - Through Smart Voice Assistant
One of the world’s favourite restaurants moved quickly to transition into the AI era. The top folks
at McDonald’s have done impressively well to stay on top of the latest trends over the last few
decades and their recent move indicates they are not relenting any time soon. McDonalds
installed a voice-based platform for complex, multilingual, multi-accent and multi-item
conversational ordering. It also acquired an artificial intelligence company called Apprente, which
has built this platform for them. This has made the process of ordering faster and it is cost-
efficient as well.
H&M’s Assortment Planning using Artificial Intelligence
Big brands like H&M have realized the importance of using AI in their assortment planning. H&M
aims to forecast trends months in advance. The retail giant is employing over 200 data
scientists, analysts and engineers to use AI to review purchasing patterns of every item in each
store. The data incorporates all the information from over five billion footfalls from last year to
its stores and traction on its websites. It also considers data from external sources.
Pepper Robot – Nestlé’s Solution to sell coffee Machines
Nestlé Japan is using a humanoid robot to sell its coffee machines built by SoftBank Robotics. It’s
one of the first robots in the world that can sense and respond by feeling human emotions. It is
equipped with the latest voice and emotion recognition technology. And the best part is that it
can respond by understanding human facial expressions.
Boch Automotive’s Artificial Intelligence – Powered Sales Assistant
Boch Automotive, an England based car dealership company, has adopted a unique AI software
that streamlines its sales funnel and establishes an automated sales assistant to increase
service revenue via engagements.
Mango and Vodafone’s Smart Digital Dressing Room
The concept of a digital fitting room involves using an Internet of Things (IoT) digital mirror that
was designed by Mango and developed by Vodafone in collaboration with Jogotech. These new
fitting rooms are another step in the digital transformation of retail stores to create a whole new
experience for the customers.
53 Degrees North – Automated AI for Customer Segmentation
Data science and AI have transformed this landscape as well. Using techniques like market
basket analysis, association rules, clustering and so on, businesses are able to create granular
segments to enhance their marketing efforts. 53 Degrees North (53DN), an Irish lifestyle retail
chain, partnered with Brandyfloss for using their automated customer segmentation software.
This solution will solve the segmentation problem and propel its marketing campaigns to the
corrected targeted population.
12
Global AI Adoption Report 2022
CCPPGG && RReettaaiill
Domino’s Pizza – Delivery by a Robot
Domino’s launched its Domino’s Robotic Unit (DRU). They have built an artificial intelligence-
based robot that will deliver hot piping pizza at your doorstep. This innovation marvel is like a
self-driving car with a mini oven and a fridge on wheels. The vehicle itself is a collaboration
between Domino’s Pizza and a Sydney-based robotic company Marathon Targets.
Walmart Deploys Robots to Scan Shelves
Walmart in Tampa Bay (Florida) has introduced a robot on wheels that is doing this task very
effectively. The robot travels along the aisle, stretches its arm till the top of the shelves and
automatically captures the required data. It takes in prices and the number of items available.
That’s quite a lot of time and effort saved and the company will also cut down on operational
costs with this adoption. The company aims to increase its customer interaction rather than
spending its customer’s time on shelf alignment.
Olay – Using AI to Personalize Skincare
Olay’s AI-powered skin advisor, an online service that relies on artificial intelligence and
proprietary deep learning, is analyzing a user’s skincare needs at a very granular level.
CPG & Retail has one of the leading global spend on AI systems, with the category projected
to invest on solutions like automated customer service agents, shopping advisers and
product recommendation platforms. More than 325,000 retailers are expected to adopt AI
technology by 2023.
13
Global AI Adoption Report 2022
CPG & Retail
AI Adoption across Regions
Source: Mordor Intelligence
Geographically, the global artificial intelligence in the CPG & Retail market is segmented into
five major regions, namely, North America, Europe, Asia Pacific, Latin America, and the
Middle East and Africa.
At present, North America holds a dominating position in the global AI in retail market. The
region has high technology adoption rate, presence of key players & start-ups, and high
penetration of internet.
The APAC region is expected to grow at the highest CAGR owing to the growing adoption of
AI-based solutions and services among retailers.
Analysis of AI Adoption in CPG & Retail market for major countries across the regions of US,
Europe & Asia Pacific (APAC) is given as follows: -
Challenges in adopting AI in CPG and Retail industries
Source: IDC
14
Global AI Adoption Report 2022
CPG & Retail
AI Adoption across US
1. Warby Parker
In April 2019, Warby Parker, a US-based company started practicing innovative ways. By the use
of artificial intelligence, it is providing its customer to try the virtual Try-On that allows them to
try on virtual frames through augmented reality, a technology that overlays computer-generated
images onto real-world images (your face).
2. Anki
Founded in 2010, this robotics and AI start-up made a huge impact by outdoing their own
overdrive racetrack to release Cozmo.
Cozmo is an adorable robot toy that makes a healthy profit for Anki in sales.
3. Blue Yonder
Blue Yonder is focused on using AI to automate the process of tech industry retail. They aid
retailers and pinpoint the keys to higher revenues, increased margins and fast and efficient
reactions to a constantly changing market. Blue Yonder has taken a pretty scientific approach to
be the leading provider of cloud-based predictive applications for retailers.
3. Infinite Analytics
Another company focused on the optimisation and growth of other companies through the
power of AI, Infinite Analytics is set on maximising sales and engagement by discovering rich
insights, identifying the right customers and expanding their clients’ exposure across all
channels.
4. Signifyd
Signifyd is the most well-funded AI start-up in the fraud detection industry for retail and
eCommerce, having raised $180 million. They specialize in fraud detection for retail and
eCommerce companies. Their most prominent offering is called “guaranteed fraud detection,”
and it likely uses anomaly detection technology to recognize fraudulent transactions and prevent
chargebacks.
5. Lowe’s
Lowebot, an autonomous in-store robot from Lowe’s, helps customers find what they need in
the store in different languages. At the same time, it helps with inventory management thanks
to real-time monitoring capabilities.
15
Global AI Adoption Report 2022
CPG & Retail
AI Adoption across Europe
1. Panther Solutions
As a prominent retail AI solution provider in Europe, this company brings to the table the price
optimisation silver bullet, Panther Pricing, made by retailers for retailers. Panther Solutions
leverages the prowess of AI and the cloud to generate automated price recommendations that
enable retailers to reduce price markdowns significantly.
2. MySales Labs
MySales Labs empowers retailers with insights that boost business growth, increase both
profitability and revenue, optimise inventories without sales losses, and give a head start in
tightening competition on the global markets. The company utilises data analytics, machine
learning (ML), and artificial intelligence (AI), to offer retail management solutions for demand
forecasting, price optimisation, stock replenishment, and promotion modelling.
3. PricingHUB
PricingHUB leverages data at scale and machine learning to help retailers implement multiple
pricing strategies and action their daily trading. As one of the top retail AI companies in Europe,
PricingHUB offers a dynamic pricing SaaS platform to manage P&L by utilizing solid pricing
algorithms and a transparent performance measurement methodology. Governed by the
mission to bring dynamic pricing to physical retail stores by leveraging a blend of real-time
customer data and machine learning algorithms, PricingHUB helps retailers understand price
elasticity and drive better pricing decisions.
4. Nextail
Nextail is a Spanish company that offers an automated inventory management tool, which the
company claims can help retail fashion businesses balance inventory among its stores to
optimize sales using predictive analytics and machine learning. Nextail claims that the
application is accessible throughout the retail organization to digitize most aspects of the
physical retail business.
16
Global AI Adoption Report 2022
CPG & Retail
5. Cortexica
Cortexica is a UK-based company that offers AI-driven image and video applications, which the
company claims can help retail businesses offer online shoppers visual search tools of products
they want to purchase using computer vision. Cortexica claims that shoppers, from their device,
can upload a photo of the item they are looking for to the application. The algorithms compare
the pixels in the uploaded image to images in the eCommerce database. It will then identify
images that are similar or a match to the uploaded image. Once it recognizes similar items, the
system returns with the recommended results in the form of curated photos of the items.
2. Metail
Metail is a UK-based company that offers MeModel, an application for eCommerce sites and
smartphones, which the company claims can help retail shoppers try on clothes virtually using
machine learning.
The company claims that the application could increase sales, enhance customer experience and
loyalty, reduce product returns, and deepen the retailer’s knowledge about shoppers, among
other benefits.
AI Adoption across Asia
1. ViSenze
ViSenze is a Singapore-based company that offers a namesake software that the company
claims is capable of allowing customers to search by image. Once the software is integrated into
a retailer’s website, customers could upload a photo to the website’s search bar. The search
software would then return a visually-similar item for the customer.
2. Trax
Trax is a Singapore-based company that offers a software called Trax Technology Stack, which it
claims can give consumer packaged goods businesses a view of how their products compete
with other brands on the retail shelf using computer vision. The company claims that this can
help businesses develop strategies for where to display their products on shelves and inventory
management.
17
Global AI Adoption Report 2022
CPG & Retail
3. Zenatrix
Zenatrix is an Indian company that offers software called Wattman and Wattman Lite, which the
company claims can help retail cha |
97 | Autres | 1113-Article Text-1110-1-10-20080129.pdf | AI Magazine Volume 15 Number 4 (1994) (© AAAI)
Workshop Report
AI in Business-Process collection and indexing of customer
support hotline cases. Amy Rice and
Robert Friedenberg (both of Inference
Reengineering
Corporation) presented the partici-
pants of the Workshop on AI in
Business-Process Reengineering (held
during the 1994 national conference
on AI) with examples of successful
Walter Hamscher reengineering efforts that are based
on an analysis of the flow of knowl-
edge in the organization and use AI
technology to capture and deploy
the knowledge.
n Business-process reengineering (BPR) is Fortune 500 company annual reports
A second, less common but poten-
a generic term covering a variety of per- explicitly discussed reengineering
tially important role for AI is in tools
spectives on how to change organiza- efforts that were currently under way.
to support the change process itself.
tions. There are at least two distinct One analyst recently estimated the
roles for AI in BPR. One role is as an A current example is in the use of
annual market for BPR services in
enabling technology for reengineered knowledge-based simulation to sup-
U.S.-based companies at $1.8 billion;
processes. A second, less common but port the analysis of an existing busi-
another predicts a growth of 20 per-
potentially important role is in tools to ness process and to model the
cent each year from 1994 to 1996
support the change process itself. The performance of a proposed process.
Workshop on AI in Business-Process (Caldwell 1994). To measure the For example, the G2/SPARKS system
Engineering, held during the national long-term impact of this work, one
(Yu 1991) provides a knowledge base
AI conference, allowed participants to must consider a multiple of this fig-
of typical business processes and
learn about projects that are aimed at ure as the cost reductions and rev-
work products in service industries
exploiting insights from AI. enue enhancements brought about
and makes it possible to rapidly
by today’s reengineering begin to be
Virtually any business can be realized over the next few years. assemble a stochastic simulation
viewed as a collection of pro- There is hype, to be sure, but the model. Such a simulation model
cesses that, taken together, phenomenon is real. serves the obvious role of estimating
respond to customer demands by There are at least two distinct roles cost savings, order-processing times,
inventing, producing, delivering, and for AI in BPR. One role is as an backlogs, and the like. Because of the
billing for goods and services. These enabling technology for reengineered complexity of business organizations,
processes vary from business to busi- all the familiar issues of acquisition,
ness, but in the overwhelming reusability, scalability, and compre-
majority of cases, these processes and hensibility turn up for such models.
the organizations that execute them AI as a field has a great deal of accu-
have not been engineered in any A report on the mulated experience and insight to
meaningful sense; they have evolved 1994 AAAI offer in dealing with these problems
over time in response to their busi- as well as developing a framework for
workshop held in
ness environments. Changing envi- further research.
ronments frequently destroy such Seattle, Washington One project aimed at exploiting
companies unless they make a con- insights from AI in the area of mod-
scious and periodic, if not continu- eling business processes is the TOVE
ous, effort to reengineer these pro- (Toronto virtual enterprise) Project at
cesses to exploit changes in suppliers, the University of Toronto, presented
customer needs, and technological at the workshop by Mark Fox and
processes. A typical success story of
innovation. Viewing a business as a Michael Gruninger. TOVE encompass-
this type places an expert system in
collection of customer-driven pro- es a generic ontology for modeling
the hands of a single worker who is
cesses is the essence of business- business processes; a specific instanti-
then able to perform many steps of a
process reengineering (BPR), a generic ation of the ontology describing a
process for a single customer or order
term covering a variety of perspec- hypothetical enterprise in detail; and
tives, none of which is particularly rather than has several workers in a test bed with tools for browsing,
rigorous, on how to change organiza- different departments handle the visualization, simulation, and deduc-
tions. It is easy to dismiss BPR as same case, dramatically cutting over- tive queries. As in any modeling
hype, a management consultant’s all order-processing time. Some effort, formulating the model
marketing slogan, but the phe- examples of this general story requires committing to the particular
nomenon is real and extremely appearing at IAAI-94 were in the pro- reasoning tasks it is expected to sup-
important. In 1993, 60 percent of the cessing of insurance claims, identifi- port. TOVE uses the notion of advis-
management letters appearing with cation of mental health needs, and ers—each with a particular perspec-
Copyright © 1994, AAAI. 0738-4602-1994 / $2.00 WINTER 1994 71
Workshop Report
tive on the enterprise—to inform and failure—Michael Hammer predicts resentations of agents’ beliefs and
constrain the modeling effort. Exam- that two thirds of all BPR efforts now intentions (for example, the frame-
ples are advisers for cost, quality, effi- under way will fail (Caldwell 1994)— work of Cohen and Levesque [1990])
ciency, incentives, and agility: The in large part because stakeholders in or a case library of past behavior (for
cost adviser requires that the model the organization resist changes that example, the VOTE system [Slade
represent information about material might diminish their power or other- 1991]) opens up interesting possibili-
and process costs, the incentive wise disrupt their career and other ties for sophisticated modeling and
adviser is likely to require informa- plans. An intriguing question raised fine-grained predictions about agents’
tion about organizational structures, repeatedly in the course of the work- reactions to different proposed orga-
others will require the representation
shop was whether modeling tools nizational designs.
of time and state, and so on. As dis-
could raise the likelihood of success- The workshop ended positively
cussed at the workshop by Bob Young
with the final discussion session. In
and Elaine Kant (both of Schlumberg-
the area of modeling and analysis of
er Laboratory for Computer Science),
processes to support design, partici-
many of the issues appearing in mul-
pants agreed with Mark Fox’s posi-
tiperspective modeling of engineered
The nature of designing a tion that enough is already generally
artifacts apply directly to large-scale
modeling efforts such as TOVE. business process known about knowledge representa-
tion to have significant impact on
Modeling and analysis of business
is quite different
processes is part of the broader task of actual practice, provided, of course,
designing a new business process, from that of that the nascent AI in BPR communi-
that is, tools for evaluating designs ty in fact focuses its efforts outside
designing a
formulated by humans. An interest- the AI community and in communi-
ing and challenging next step is to mechanical device. ties where organizational modeling is
use AI techniques to automatically … already the focus of attention. In the
produce new designs. Pramod Jain, area of supporting process change,
Sheet metal doesn’t
Jie Liu, and Steve Wagner (all of participants seemed to agree that
Andersen Consulting) reported on a care how it is used modeling stakeholders and their reac-
prototype system that proposes new tions to change and incorporating
or even whether
process designs by using heuristic the knowledge upstream in tools for
transformations of existing models. it is used or not; supporting business process design
For example, the system would pro-
employees do. was an exciting possibility worthy of
pose to delete processes or invert the
further research.
order of pairs of processes. Although
the prototype falls short of providing
assistance to the analyst in actually References
evaluating the impact of the changes
ful change, for example, by helping Cohen, P., and Levesque, H. 1990. Inten-
it proposes, it is an intriguing system
to anticipate the reactions of process tion Is Choice with Commitment. Artifi-
for stimulating the creative process of
participants to proposed changes. cial Intelligence42(3): 213–262.
producing a new design.
Eric Yu and John Mylopoulos (Uni- Caldwell, Bruce. 1994. Missteps, Miscues.
However, analysis of existing and
versity of Toronto) presented work Information Week 480 (20 June): 50–60.
proposed processes is only a small
on modeling organizations using a Slade, S. 1991. Goal-Based Decision Strate-
part of actually effecting change in
multilevel framework in which one gies. In Proceedings of the Thirteenth
an organization, and the scope for AI
level, the actor dependency model, Annual Conference of the Cognitive Sci-
tools in this area is correspondingly
makes the relationships between ence Society. Chicago, Ill.: Cognitive Sci-
large. As pointed out by David
actors explicit in terms of their ence Society.
Bridgeland (Coopers and Lybrand) in
dependence on other actors to Yu, D. 1991. Achieving Excellence in the
his workshop position paper:
achieve their goals. In a somewhat Global Marketplace Using Knowledge-
The nature of designing a busi- different vein, Gary Klein (MITRE Based Simulation. In Proceedings of the
ness process is quite different Center for Advanced Aviation System First International Conference on AI
from that of designing a Development) presented work that Applications on Wall Street, 103–108.
mechanical device because the explicitly models the complex Washington, D.C.: IEEE Computer Society
components are fundamentally behavior of individual actors within Press.
different. Sheet metal doesn’t a changing business process; in par-
care how it is used or even ticular, the tendency for individuals
whether it is used or not; to adapt over time to changes in the
employees do. sources and quality of information
Walter Hamscher is affiliated with the
Implementing changes in an orga- that they use to make their deci- Price Waterhouse Technology Centre in
nization is an effort that is prone to sions. More generally, using rich rep- Menlo Park, California.
72 AI MAGAZINE |
98 | Autres | 608-Article Text-1985-1-10-20231125.pdf | Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
OPEN ACCESS
Co mputer Science & IT Research Journal
P-I SSN: 2709-0043, E-ISSN: 2709-0051
Vo lume 4, Issue 2, P.85-110, November 2023
DO I: 10.51594/csitrj.v4i2.608
Fa ir East Publishers
Jou rnal Ho mepage : www.f epbl.com/index.php/csitrj
INNOVATIVE BUSINESS MODELS DRIVEN BY AI
TECHNOLOGIES: A REVIEW
Oluwatoyin Ajoke Farayola1, Adekunle Abiola Abdul2, Blessing Otohan Irabor3,
& Evelyn Chinedu Okeleke4
1Independent Researcher, Dallas, Texas, USA
2Independent Researcher, Maryland, USA
3Independent Researcher, Lagos, Nigeria
4Ericsson LM Lagos, Nigeria
_______________________________________________________________________________
*Corresponding Author: Oluwatoyin Ajoke Farayola
Corresponding Author Email: [email protected]
Article Received: 10-10-23 Accepted: 19-11-23 Published: 26-11-23
Licensing Details: Author retains the right of this article. The article is distributed under the terms of the
Creative Commons Attribution-NonCommercial 4.0 License
(http://www.creativecommons.org/licences/by-nc/4.0/) which permits non-commercial use, reproduction
and distribution of the work without further permission provided the original work is attributed as specified
on the Journal open access page
_______________________________________________________________________________
ABSTRACT
In an era where artificial intelligence (AI) is revolutionizing business paradigms, this study delves
into the intricacies of AI-driven business models, offering a nuanced understanding of their
emergence, evolution, and impact on traditional business strategies. This scholarly inquiry aims to
dissect the role of AI in reshaping business models, highlighting the interplay between
technological innovation and business strategy. The study meticulously examines the integration of
AI into various business facets by employing a systematic and thematic analysis of a diverse range
of literature, including academic journals, industry reports, and case studies. This methodological
approach facilitates a comprehensive understanding of AI's role in business innovation, addressing
both the opportunities and challenges it presents. The findings reveal that AI-driven business
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 85
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
models are characterized by enhanced operational efficiency, data-driven decision-making, and
customer-centric approaches. These models signify a transformative shift from conventional
business strategies, demanding a reevaluation of leadership roles and ethical considerations in the
digital age. The study identifies key challenges in AI implementation, such as technical
complexities and ethical dilemmas, while uncovering AI's vast opportunities for business growth
and competitive advantage. Conclusively, the study recommends a balanced approach to AI
integration, emphasizing the need for ethical AI practices, continuous adaptation, and a synergy
between AI capabilities and human insights. It advocates for business leaders to embrace AI not
just as a technological tool, but as a catalyst for sustainable and innovative business growth. This
scholarly work contributes significantly to the discourse on AI in business, providing a
foundational framework for future research and practical application in AI-driven business
innovation.
Keywords: Artificial Intelligence, Business Models, Digital Transformation, AI Integration,
Leadership in AI, Ethical AI Practices.
_______________________________________________________________________________
INTRODUCTION
The Emergence of AI in Modern Business: An Overview
The emergence of artificial intelligence (AI) in modern business has been a transformative force,
reshaping industries and creating new paradigms for how companies operate and compete. The
integration of AI into business models has become a pivotal aspect of contemporary business
strategy, offering unprecedented opportunities for innovation, efficiency, and competitive
advantage.
AI-driven business models, as conceptualized by Hahn et al. (2020), are characterized by the use
of AI technologies to enhance or create at least one component of the business model. This
integration of AI has led to the creation of new businesses and has significantly altered existing
ones. Unlike traditional data-driven models, AI-driven models are based on a set of techniques that
learn and improve autonomously, reducing the need for explicit human programming. This
autonomy in learning and adaptation is a key characteristic that sets AI-driven business models
apart, enabling businesses to respond more dynamically to market changes and customer needs.
The impact of AI on small businesses, particularly during challenging times such as the COVID-19
pandemic, has been profound. Coltey et al. (2022) highlight the role of AI in enabling small
businesses to navigate rapidly changing market conditions. By leveraging AI-driven tools, such as
natural language processing (NLP), businesses can automate market research, adapt to changing
conditions, and maintain operational efficiency even in times of crisis. This adaptability is crucial
for small businesses that often lack the resources of larger corporations.
In the insurance sector, the influence of AI is equally significant. Zarifis, Holland, and Milne.
(2019) identify four emerging business models in the insurance industry driven by AI and data.
These models range from insurers taking a smaller part of the value chain and allowing AI and
data-centric companies to dominate, to technology-focused companies using their AI prowess to
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 86
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
enter the insurance market. This model diversity illustrates AI's versatility in reshaping traditional
industries and creating new opportunities for innovation and growth.
The integration of AI into business models is not without its challenges. The need for significant
investment in technology, the requirement for specialized skills, and the management of ethical
and privacy concerns are some of the hurdles businesses face. However, the potential benefits,
including enhanced decision-making capabilities, improved customer experiences, and new
avenues for growth, make the integration of AI a strategic imperative for businesses looking to
thrive in the modern economy.
The emergence of AI in modern business is a defining feature of the current economic landscape.
AI-driven business models offer a new paradigm for businesses operating, competing, and
innovating. From small businesses to large corporations, the integration of AI is creating new
opportunities and challenges, reshaping industries, and redefining the future of business.
Defining AI-Driven Business Models
The integration of artificial intelligence (AI) into business models represents a significant
evolution in the way companies operate and strategize. AI-driven business models are
characterized by the incorporation of AI technologies to enhance, innovate, or create new aspects
of a business's operations, products, or services. This section delves into the key characteristics,
evolution, and the intersection of AI with traditional business strategies, drawing on recent
scholarly literature.
AI-driven business models are distinguished by their ability to leverage data and machine learning
(ML) technologies to create more efficient, responsive, and intelligent business processes. Ahmed
and Miskon (2020) discuss the role of AI and ML in digital transformation, particularly in the
manufacturing sector. They emphasize how AI-driven models utilize large datasets generated by
the integration of devices in the Internet of Things (IoT) environment to gain rapid insights and
enhance decision-making processes. This approach is pivotal in achieving resiliency and
efficiency, especially in sectors like manufacturing where integrating intelligent and integrated
systems is crucial (Ahmed & Miskon, 2020).
In the realm of customized manufacturing, AI-driven models are reshaping traditional production
paradigms. Wan et al. (2020) explore the implementation of AI in customized manufacturing
factories, highlighting how AI technologies enable manufacturing systems to adapt to external
needs and extract process knowledge. This includes the development of intelligent production
models, networked collaboration, and extended service models. The AI-driven customized
manufacturing factory is characterized by its self-perception, operations optimization, dynamic
reconfiguration, and intelligent decision-making capabilities. These characteristics underscore the
transformative impact of AI on manufacturing, moving towards more flexible and efficient
production methods (Wan et al., 2020).
The integration of AI in customer service, especially in the e-commerce sector, provides another
perspective on AI-driven business models. Ping (2019) focus on the constructs of AI customer
service in e-commerce, illustrating how AI can assist human agents, enhancing service quality and
productivity. The integration of AI in customer service is a response to the limitations of
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 87
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
traditional models, such as limited availability and inefficiency. AI-driven customer service
models in e-commerce are characterized by their ability to provide personalized and efficient
service, leveraging technologies like chatbots and automated response systems (Ping, 2019).
The evolution of business models in the AI era is marked by a shift from traditional, often rigid,
business processes to more dynamic, data-driven, and customer-centric approaches. AI-driven
business models merge the capabilities of AI, ML, and IoT to create systems that are not only
efficient and resilient but also capable of continuous learning and adaptation. This evolution
signifies a move towards more personalized, responsive, and intelligent business operations,
catering to the specific needs of customers and the market.
The intersection of AI with traditional business strategies involves rethinking conventional
business practices. AI-driven models do not merely supplement traditional strategies but often
redefine them, creating new value propositions and competitive advantages. This intersection is
evident in various sectors, from manufacturing to customer service, where AI technologies are
used to enhance operational efficiency, customer engagement, and innovation.
AI-driven business models represent a significant shift in the business landscape, characterized by
their use of AI and ML to innovate and improve various aspects of business operations. From
manufacturing to customer service, the integration of AI is transforming traditional business
models, leading to more efficient, adaptable, and intelligent business processes.
Key Characteristics of AI-Driven Business Models
AI-driven business models are reshaping the landscape of various industries by integrating
advanced artificial intelligence (AI) technologies into their core operations and strategies. These
models are characterized by several key features that distinguish them from traditional business
models. This section explores these characteristics, drawing insights from recent scholarly
literature.
One of the primary characteristics of AI-driven business models is their focus on leveraging AI for
enhanced decision-making and operational efficiency. Metelskaia et al. (2018) present a business
model canvas specifically designed for AI solutions, which outlines the critical elements of AI-
driven business models. This canvas includes components such as value propositions that AI, the
use of multi-sided platforms for customer segments, automated services for customer relationships,
and the integration of social networks in marketing channels, uniquely tailors. The canvas also
highlights the importance of investors as key partners and emphasizes research and development
(R&D) and human resources as essential resources. This framework demonstrates how AI-driven
business models are constructed differently from traditional models, focusing on AI's unique
capabilities to create value (Metelskaia et al., 2018).
In the healthcare industry, AI-driven business models are particularly transformative. Kulkov
(2023) examines the next-generation business models for AI start-ups in healthcare, identifying
three unique design elements: value creation, delivery to customers, and market communication.
These elements are framed within 16 unique models and three unifying design themes, illustrating
the diverse ways AI can be integrated into healthcare business models. This study underscores the
role of AI in creating new value propositions in healthcare, such as personalized medicine and
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 88
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
efficient patient care, and highlights the importance of AI in communicating and delivering these
values to the market (Kulkov, 2023).
Another key characteristic of AI-driven business models is their application in customized
manufacturing. Wan et al. (2020) discuss the implementation of AI in customized manufacturing
factories, focusing on intelligent production, networked collaboration, and extended service
models. These factories are characterized by their self-perception, operations optimization,
dynamic reconfiguration, and intelligent decision-making capabilities. Integrating AI technologies
allows these manufacturing systems to adapt to external needs and extract process knowledge,
leading to higher production flexibility and efficiency. This study demonstrates how AI-driven
models can transform traditional manufacturing processes into more agile and responsive systems
(Wan et al., 2020).
AI-driven business models are marked by their innovative use of AI to create new value
propositions, enhance operational efficiency, and transform traditional business processes. These
models leverage AI's unique capabilities to analyze data, learn autonomously, and make intelligent
decisions, leading to more dynamic and responsive business operations. The integration of AI in
various sectors, from healthcare to manufacturing, illustrates the transformative potential of these
models, offering new opportunities for growth and innovation.
The key characteristics of AI-driven business models include their focus on leveraging AI for
enhanced decision-making, operational efficiency, and the creation of new value propositions.
These models are reshaping industries by introducing innovative ways to integrate AI into business
operations, demonstrating the transformative impact of AI on the modern business landscape.
Evolution of Business Models in the AI Era
The advent of artificial intelligence (AI) has ushered in a new era in business, fundamentally
altering traditional business models and introducing innovative paradigms. This evolution is
characterized by a shift towards more technologically advanced, data-driven, and customer-centric
approaches. This section explores the transformation of business models in the AI era, drawing on
insights from recent scholarly literature.
A significant aspect of this evolution is the changing nature of human-machine interaction and its
impact on competitive business strategies. Delbufalo, Di Bernardo and Risso, (2022) delve into the
dynamics of human-machine interaction in the digital era, emphasizing the need for businesses to
strike a balance between artificial and human intelligence. They argue that the competitiveness of
companies in the AI era hinges on sustainable strategies that effectively integrate both human
creativity and AI's mechanical thinking. This integration is crucial in decision-making processes,
where AI can provide data-driven insights while humans contribute with creative and strategic
thinking. The study highlights the importance of redefining business models to accommodate AI
and human intelligence roles, ensuring that businesses remain innovative and competitive
(Delbufalo, Di Bernardo & Risso, 2022).
The role of AI in brand engagement and social interaction represents another facet of the evolving
business models. Marrone and Testa (2022) explore the impact of brand algorithms and social
engagement in the digital era, focusing on how AI and related technologies transform marketing
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 89
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
strategies and customer relationships. They discuss how AI, big data, and the Internet of Things
(IoT) are key drivers in revolutionizing communication and relationships between individuals,
products, and brands. The study underscores the influence of AI-mediated algorithms on value
creation and customer engagement, highlighting the shift towards more personalized and
interactive marketing approaches. This evolution reflects a broader trend in business models where
digital transformation and AI are central to creating and maintaining customer relationships
(Marrone & Testa, 2022).
The integration of Artificial Intelligence (AI) with the advancements of 5G technology is
revolutionizing business models and driving digital transformation across various sectors (Banda,
Mzyece, & Mekuria, 2022). This synergy is fostering the development of new, innovative services
and applications, such as enhanced image recognition and sophisticated natural dialogue AI
systems. These technological advancements are not only streamlining operational processes but are
also opening new channels for customer interaction and service provision. The convergence of AI
and 5G is indicative of a shift towards more interconnected, intelligent, and agile business models,
leveraging the high-speed and extensive capabilities of 5G networks to maximize AI's potential
(Banda, Mzyece, & Mekuria, 2022).
In summary, the evolution of business models in the AI era is marked by a greater integration of
AI and technology in various aspects of business operations. A shift towards more data-driven
decision-making characterizes this transformation, enhanced human-machine interaction, and
innovative customer engagement and marketing approaches. Integrating AI with other advanced
technologies like 5G further accelerates this evolution, leading to more agile, efficient, and
customer-centric business models.
The Intersection of AI and Traditional Business Strategies
The integration of Artificial Intelligence (AI) into traditional business strategies marks a pivotal
shift in the business landscape, blending the strengths of AI with established business practices.
This intersection is creating new paradigms for innovation, strategy development, and competitive
advantage. This section explores how AI is being integrated into traditional business strategies,
drawing on insights from recent scholarly literature.
In the education technology (EdTech) sector, the integration of AI and learning analytics is
revolutionizing traditional business models and strategies. Alam and Mohanty (2022) discuss the
transformation in EdTech companies, where AI and learning analytics are being used to create
personalized educational experiences. This integration reflects a shift from traditional educational
models to more data-driven, customized approaches. The study highlights the challenges and
motivations influencing this transition, emphasizing the need for a deeper understanding of data
and its potential to enhance learning experiences. This example illustrates how AI can be
integrated into traditional sectors like education, transforming them with innovative, data-driven
strategies (Alam & Mohanty, 2022).
Wisniewski (2020) addresses the broader implications of AI in business, focusing on the need for
future decision-makers and leaders to understand and leverage AI in their strategies. The paper
discusses the integration of AI into business curricula, emphasizing the importance of preparing
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 90
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
leaders who can navigate the complexities of AI and its impact on business. This approach reflects
a growing recognition of AI's strategic importance and the need for a new generation of business
leaders who are adept at integrating AI into traditional business models and strategies. The study
underscores the transformative potential of AI in reshaping business education and, by extension,
business practices (Wisniewski, 2020).
Fenwick, Vermeulen, and Corrales (2018) work explores the business and regulatory responses to
AI, particularly in the context of dynamic regulation and innovation ecosystems. They discuss how
businesses and regulators are adapting to the challenges posed by disruptive AI technologies. The
paper highlights the importance of dynamic regulation and the creation of innovation ecosystems
that foster partnerships between established corporations and AI-focused startups. This approach to
managing AI's impact suggests a strategic alignment between traditional business practices and the
innovative potential of AI. The study provides insights into how businesses can strategically
manage AI's disruptive nature while leveraging it for competitive advantage (Fenwick, Vermeulen,
& Corrales, 2018).
The intersection of AI and traditional business strategies is characterized by a synergistic blend of
innovation and established practices. This integration is leading to the transformation of various
sectors, from education to broader business practices. The key lies in understanding and leveraging
AI's potential within the context of traditional business models, preparing future leaders for this
new landscape, and adapting regulatory and strategic frameworks to accommodate AI's disruptive
potential.
Significance and Scope of AI in Business Innovation
The integration of Artificial Intelligence (AI) into traditional business strategies represents a
significant paradigm shift, offering new opportunities for innovation and competitive advantage.
This intersection is reshaping how businesses operate, strategize, and interact with their
stakeholders. This section examines the convergence of AI with traditional business strategies,
drawing insights from recent scholarly literature.
Alam and Mohanty (2022) delve into the intersection of AI with learning analytics in the context
of educational technology (EdTech) companies. They discuss how these companies are integrating
AI into their business models and strategies to provide personalized educational experiences. This
integration reflects a broader trend where traditional industries like education are being
transformed by AI, leading to more data-driven and customized approaches. The study highlights
the challenges and motivations influencing this transition, emphasizing the need for a deeper
understanding of data and its potential to enhance learning experiences. This example illustrates
how AI can be integrated into traditional sectors, transforming them with innovative, data-driven
strategies.
Fenwick, Vermeulen, and Corrales (2018) address the business and regulatory responses to AI,
particularly focusing on dynamic regulation and innovation ecosystems. They discuss how
businesses and regulators are adapting to the challenges posed by disruptive AI technologies. The
paper highlights the importance of dynamic regulation and the creation of innovation ecosystems
that foster partnerships between established corporations and AI-focused startups. This approach to
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 91
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
managing AI's impact suggests a strategic alignment between traditional business practices and the
innovative potential of AI. The study provides insights into how businesses can strategically
manage AI's disruptive nature while leveraging it for competitive advantage.
The intersection of AI and traditional business strategies is characterized by a synergistic blend of
innovation and established practices. This integration is leading to the transformation of various
sectors, from education to broader business practices. The key lies in understanding and leveraging
AI's potential within the context of traditional business models, preparing future leaders for this
new landscape, and adapting regulatory and strategic frameworks to accommodate AI's disruptive
potential.
Objectives and Structure of the Review
The aim of this study is to explore and understand the transformative impact of Artificial
Intelligence (AI) on business models, focusing on how AI technologies are reshaping business
strategies and operations in the contemporary business landscape.
The objectives of the study are:
1. To identify the key characteristics of AI-driven business models, examining the unique
features and components that distinguish these models from traditional business
approaches.
2. To analyze the evolution of business models in the AI era, understanding how the
integration of AI technologies has transformed business practices across various industries
and sectors.
3. To explore the intersection of AI and traditional business strategies, investigating how AI is
being combined with conventional business approaches and the resulting synergies and
challenges.
4. To assess the significance and scope of AI in business innovation, evaluating the overall
impact of AI on business practices, including the opportunities and challenges it presents
for businesses in different contexts.
Limitations of the Literature Review
This literature review on the impact of Artificial Intelligence (AI) in business models
acknowledges several inherent limitations. Firstly, the rapid evolution of AI technology means that
some reviewed literature may not reflect the most current developments and trends. Secondly,
there is a potential bias in the sources, primarily academic journals and industry reports, which
might emphasize certain aspects of AI in business while overlooking others. Thirdly, the vast and
diverse applications of AI across various industries imply that not every sector or innovative use of
AI is comprehensively covered. Finally, the interdisciplinary nature of AI in business leads to
varying definitions and interpretations of AI-driven business models, posing challenges in drawing
generalized conclusions. These limitations highlight the need for a cautious interpretation of the
findings, recognizing that the review provides a snapshot of a rapidly evolving field.
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 92
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
METHODOLOGY
Approach to Literature Review: Systematic and Thematic Analysis
The methodology for this literature review on AI-driven business models is anchored in a
systematic and thematic analysis approach. This method involves a structured process of
searching, selecting, and synthesizing relevant literature to ensure a comprehensive understanding
of the topic. Predefined criteria guide the systematic review process and aims to minimize bias,
providing a transparent and replicable framework for analysis (Bulatnikov & Constantin, 2021).
The thematic analysis component of the methodology involves identifying, analyzing, and
reporting patterns (themes) within the data. This approach allows for the integration of diverse
perspectives and insights on AI in business models, facilitating a nuanced understanding of the
subject. The thematic analysis is particularly useful in synthesizing complex and multifaceted
topics, such as the integration of AI in business strategies and operations (Sureeyatanapas et al.,
2020).
Criteria for Selecting Relevant Literature on AI and Business Models
The criteria for selecting literature in this review are centered around relevance, quality, and
recency. Relevance is determined by the extent to which the literature addresses AI in the context
of business models. This includes studies focusing on the integration of AI technologies in
business strategies, the evolution of business models in the AI era, and the impact of AI on
business innovation and operations.
Quality is assessed based on the credibility of the source and the rigor of the research
methodology. Peer-reviewed academic journals, reputable industry reports, and in-depth case
studies are prioritized to ensure the reliability of the information. The research methodology of the
selected literature is also scrutinized for its robustness and appropriateness in addressing the
research questions.
Recency is another crucial criterion, given the rapid development of AI technologies and their
applications in business. Literature published within the last five years is primarily considered to
capture the most current trends, practices, and insights in the field. However, seminal works that
have significantly contributed to understanding AI in business models are also included, regardless
of their publication date.
The approach to this literature review combines systematic and thematic analysis to ensure a
comprehensive and nuanced understanding of AI-driven business models. The selection criteria
focus on relevance, quality, and recency, ensuring that the review is grounded in credible and
current literature that accurately reflects the evolving landscape of AI in business.
Sources of Information: Academic Journals, Industry Reports, and Case Studies
In the exploration of AI-driven business models, the sources of information are pivotal in shaping
the understanding and insights derived. Academic journals stand as a cornerstone in this regard,
offering peer-reviewed, scholarly articles that provide a robust theoretical foundation and
empirical evidence. Wiener, Saunders, and Marabelli (2020) work exemplifies this, offering a
critical literature review and a multiperspective research framework that is invaluable for
Farayola, Abdul, Irabor, & Okeleke, P. 85-110 Page 93
Computer Science & IT Research Journal, Volume 4, Issue 2, November 2023
understanding big-data business models. These academic insights are crucial for grounding the
review in a solid theoretical base.
Industry reports complement academic journals by providing practical, real-world insights into the
application of AI in business. Enholm et al. (2022) demonstrate this through their systematic
literature review, which elucidates how organizations leverage AI technologies for added business
value. These reports offer a glimpse into the industry's current state, trends, and future directions,
making them an essential component of the literature review.
Case studies from academic and industry sources provide detailed, context-specific insights.
Gomes et al. (2022) contribute to this by presenting a systematic literature review on AI-based
methods for business processes. These case studies are instrumental in understanding AI's practical
application, challenges, and successes in business, offering a nuanced view that complements the
broader perspectives provided by academic journals and industry reports.
Framework for Analyzing and Synthesizing Collected Data
The framework for analyzing and synthesizing the collected data in this literature review is a
meticulous process that involves several stages. Initially, the literature is categorized based on its
relevance to AI in business models. This categorization is crucial for maintaining focus and
ensuring that the review addresses the study's core themes.
The next stage involves a thematic analysis, where common patterns, trends, and divergences
within the literature are identified and examined. This approach is critical for synthesizing a
coherent narrative around AI-driven business models. The thematic analysis also allows for the
integration of diverse perspectives, as seen in the works of Wiener, Saunders, and Marabelli
(2020), and Enholm et al. (2022), ensuring a comprehensive understanding of the subject.
Finally, the review critically evaluates the findings in light of the study's objectives and the broader
context of AI in business. This evaluation considers the strengths, limitations, and implications of
the literature, as highlighted in the systematic reviews by Gomes et al. (2022) and others. This
critical evaluation is essential for providing a comprehensive understanding of the current state of
AI-driven business models and identifying areas for future research.
RESULTS
Summary of AI-Driven Business Models Identified in th |
99 | Autres | FINAL_REPORT_AI_MSMEs_Ministerial_10_Oct_2024.pdf | G7 REPORT ON DRIVING FACTORS AND
CHALLENGES OF AI ADOPTION AND
DEVELOPMENT AMONG COMPANIES,
ESPECIALLY MICRO AND SMALL
ENTERPRISES
Authored by:
Raffaele Spallone – Ministry of Enterprises and Made in Italy
Matteo Bandiera – Competence Industry Manufacturing 4.0
The following report is the result of joint efforts among G7 countries and does not
represent author’s opinion.
INDEX
1. Introduction ..................................................................................................................... 5
1. 1 - Framing the report and identifying objectives ............................................................. 5
1.2 - Defining AI and its potential for industry ........................................................................ 6
1.3 - The transforming potential of Artificial Intelligence .................................................... 7
1.4 - AI in the context of MSMEs ................................................................................................ 8
2. Data, Facts & Trends..................................................................................................... 10
2.1 - Significant Trends ............................................................................................................... 10
2.1.1 - Workforce ...................................................................................................................... 11
2.1.2 - Funding and Investment ............................................................................................ 15
2.2 - Trends Specific to MSMEs ................................................................................................ 18
2.2.1 - Difference in adoption rates ..................................................................................... 18
2.2.2 - Businesses purchasing cloud computing services and performing big data
analytics ..................................................................................................................................... 21
2.2.3 - Barriers to entry ........................................................................................................... 22
2.2.4 - Training in MSMEs ...................................................................................................... 23
3. The potential impact of AI on the production process ............................................... 25
3.1 - From 4.0 to 5.0 ..................................................................................................................... 25
3.2 - AI adoption by business functions and tasks ............................................................. 26
3.3 - AI applications in Manufacturing .................................................................................... 29
3.3.1 - Processes ...................................................................................................................... 30
3.3.2 - Product ........................................................................................................................... 32
3.3.3 - Customers relations.................................................................................................... 33
3.4 - AI adoption and MSMEs .................................................................................................... 33
4. Limits challenges and risks ......................................................................................... 35
4.1 - Computational capacity for AI development ............................................................... 35
4.2 - Diffusion and accessibility ............................................................................................... 39
4.3 - Safe and trustworthy AI ..................................................................................................... 41
4.4 - Impact of AI adoption on the workforce........................................................................ 42
5. Public Policies ............................................................................................................... 46
5.1 - Policies for a shared infrastructure ............................................................................... 46
5.2 - Policies concerning financial leverages ....................................................................... 47
5.3 - Governance .......................................................................................................................... 49
5.4 – Acceleration of the Digital Capacities of Companies ............................................... 51
6. Recommendations to Enable AI adoption and development among Micro, Small,
and Medium-sized Enterprises (MSMEs). ........................................................................ 53
Section 1: Sustaining AI adoption and development among MSMEs. ........................... 53
Section 2: Policies to support MSMEs in the deployment and uptake of safe, secure,
and trustworthy AI ....................................................................................................................... 55
Bibliography ...................................................................................................................... 57
List of Figures and Tables
Figures
Figure 1 Perceived effect of AI adoption on workers’ skills…………………………….11
Figure 2. % of AI job postings, % of all job postings, for selected G7 countries…... 13
Figure 3. Estimates of AI-related funding across selected agencies ………………...15
Figure 4. Global private investment in AI by investment activity………………….……17
Figure 5. Percentage of businesses adopting AI, OECD average……………….……19
Figure 6. Businesses purchasing cloud computing services/
performing big data analytics……………………………………………………………….21
Figure 7. Generative AI and AI, adoption by function……………………………………26
Figure 8. AI use cases by function, % of adopters………………………………………27
Figure 9. Generative AI use cases by function, % of adopters………………………...28
Figure 10. Skills needed in the age of AI…………………………………………………44
Figure 11. Workers’ perceived value of written policies on the ethical use of AI……...44
Tables
Table 1. Percentage of businesses using artificial intelligence, country-specific ……19
1. Introduction
1. 1 - Framing the report and identifying objectives
The future of our economies is strongly tied to our ability to promote with great
determination an innovative environment. This objective entails facilitating our citizen
and companies in the digital transformation, helping them realize concrete benefits out
of this opportunity and attain the sustainability and resilience goals that are shaping
and will shape the way we do business.
One of the core technologies that is driving transformation in industry and business is
Artificial Intelligence (hereinafter AI). AI and other emerging technologies are going to
play a pivotal role in the realization of such a change and the process of making these
technologies available to citizens and companies is the first and most important step
that our societies, led by the G7 countries, must make. Thanks to the expansion of
computing systems’ capacity and the development of complementary technologies, a
new generation of AI systems has become increasingly prevalent across different
functions of manufacturing firms.
Following the Ministerial Declaration of the G7 Industry, Technology and Digital
Ministerial Meeting, the current report acknowledges the importance of these changes.
This document will delve into the analysis of the driving factors and challenges of AI
adoption and development among companies in manufacturing, especially MSMEs,
providing policy recommendations for G7 governments to ensure safe, secure and
trustworthy AI adoption.
Describing AI in a positive and normative way will provide insights into the integration
of AI in production processes through technology adoption, technical collaboration,
and voluntary knowledge exchanges. Furthermore, best practices are identified thanks
to the collection and assessment of policy strategies and experiences for AI adoption
among MSMEs across G7 countries.
Hence, this report builds on endeavors within the G7 Hiroshima AI Process, which
focuses chiefly on advanced AI systems, including generative AI, and resulted in the
International Guiding Principles for Organizations Developing Advanced AI Systems
and the International Code of Conduct for Organizations Developing Advanced AI
Systems. The aim of both of the aforementioned documents is to promote safe,
secure, and trustworthy AI worldwide and to provide voluntary guidance for actions by
organizations developing the most advanced AI systems. They further the
development of common practices among G7 countries and effective strategies to
support MSMEs through the creation of a common ground for AI development,
deployment and use.
Compounding the work undertaken so far by the G7 countries, this report focuses
primarily on the Manufacturing sector, given its relevance in the wider industrial
scenario. Within this scope, it will center specifically on MSMEs, since companies of
this size have been found to face the most difficulties when tasked with AI adoption.
The report is structured as follows: Chapter 2, titled Data Facts and Trends, introduces
the main trends and statistics related to workforce dynamics and funding trends linked
to AI deployment and development; it also analyses adoption rates, barriers to
adoption and training in specific relation to MSMEs.
Building on this collection of empirics Chapter 3, The potential Impact of AI on
Production Processes, contextualizes emerging technologies within the scope of
Industry 4.0 and Industry 5.0 and delves into the potential impact of AI on production
processes focusing on both the internal and external environment of MSMEs.
Chapter 4, Limits Challenges and Risks, complements such framework with an
overview of the main issues relating to AI diffusion and accessibility, safety and
trustworthiness of AI systems, and potential impacts on the workforce.
Chapter 5 is dedicated to present best practices among public policies designed by
G7 countries in four major thematic areas, namely infrastructure, finance, regulation
and education. Lastly, chapter 6 conclude this report by sharing recommendations
resulting from questionnaires and dialogue with private stakeholders, facilitated thanks
to the collaboration with TECH 7.
1.2 - Defining AI and its potential for industry
Framing Artificial intelligence
Without further ado, we intend, in this paragraph, to introduce the general definition of
AI and highlight what are the aspects that such a technology has an impact on.
The introduction of the term Artificial Intelligence is owed to John McCarthy, an
American academic who gave the following definition in 1956: (Artificial Intelligence is)
“the science and engineering of making intelligent machines”.
Although it was framed in this precise manner only in 1956, the concept of intelligent
machines was already present in a paper by Alan Touring titled “Computing Machinery
and Intelligence”, dating back to 1950.
It is beyond the scope of this report to define more precisely the concept of Artificial
intelligence. Hence, the disambiguation of terms is relegated in here. As previously
stated, given the absence of a shared definition for Artificial Intelligence, it is reported
here the quote that has been proposed by OECD: (Artificial Intelligence is) “a machine-
based system that is designed to operate with varying levels of autonomy and that
may exhibit adaptiveness after deployment, and that, for explicit or implicit objectives,
infers, from the input it receives, how to generate outputs such as predictions, content,
recommendations, or decisions that can influence physical or virtual environments”.
It is worth highlighting three main concepts in this definition: first, in line with
McCarthy’s definition, AI is a machine-based discipline, secondly it can connect inputs
to outputs using mathematical modelling and lastly it has varying degrees of autonomy
and adaptivity after deployment.
Of particular significance for the recent developments of AI is its subcomponent called
Machine Learning. This technology analyses data using sophisticated mathematical
models with the ability to learn the correlations between components in an
autonomous way. One of the most advanced mathematical models of this kind is the
so called “neural network”, a construct that tries to emulate the brain structural
functioning. The technology developed and constructed on neural networks
constitutes the main building block of the subcomponent of AI called “Deep Learning”.
This solution is currently at the forefront of AI development.
Artificial intelligence for industry
Focusing on the industrial potential of AI application, it is rather interesting to
distinguish between vertical and horizontal AI within the comprehensive definition
provided above. This further differentiation allows for a better understanding of the
scope and use of AI solutions within the domain of manufacturing, and for a clearer
vision of their future potential.
Vertical AI solutions are tailored by use case to address the specific challenges and
opportunities within industries. By utilizing domain expertise and industry-specific
data, these applications deliver exceptional results and potentially transform business
practices. Designed to meet unique industry requirements, vertical AI solutions offer
advanced functionalities and specialized capabilities, providing industry-specific
insights, optimizing processes, and enhancing decision-making.
While vertical AI focuses on industry-specific challenges and applications, horizontal
AI focuses on enhancing common cross-functional processes across industries.
These versatile and widely applicable solutions serve as a foundation for various
sectors, integrating into domains such as customer service, content generation, and
information retrieval. Their adaptability allows businesses to quickly tailor these AI
solutions to their specific needs.
Regardless of whether vertical or horizontal solutions are used, it is critical to
understand how AI is integrated into production processes, and what are the
components that constitute the key enablers for its application.
The afore described integration of AI into production can unlock significant potential
for the industrial sector. AI has the ability to increase reliability and automation of
production processes, all while enhancing overall productivity and output quality. In
addition, AI application has a significant impact on the workforce and has the potential
to shift their activities into tasks that result in a higher value added for the enterprise.
1.3 - The transforming potential of Artificial Intelligence
Industrial use of AI has the significant potential to have a transformative impact on
society. This opportunity stems primarily from the fact that AI has introduced a new
automation paradigm, enabling machines to learn from past experiences, adapt to
situations and augmenting their real time decision-making. These unique abilities
constitute the culmination of today’s technology and make AI the most powerful tool to
catalyze and enhance the progress made so far in the digital transformation of our
economies.
Nevertheless, AI comes with a great deal of prerequisites and challenges.
Computational power, digital skills and competences, investment power and
managerial skills, are only few of the main issues addressed in this report. Given
these possible hurdles it is crucial that we recognize the pivotal role that AI is playing
in the modern industry by redefining the industrial landscape. The innovative and
transformative solutions offered by its application will allow companies to prosper in
next future as long as they embrace and ride this revolution. It is thus imperative to
raise awareness on AI, develop and promote practical guidance, and coordinate policy
making among countries. These actions will ensure the presence of an enabling
ecosystem for enterprises that wish to be AI ready.
Before moving on with our discussion, it is worth noting that we are currently in a period
of exceedingly rapid technological change. Moreover, subsequent revolution waves
are closely linked within a unique and continuous process of industrial upgrading.
Remarkably, these features yield relevant consequences for AI adoption and
development within MSMEs. On one hand, the incremental and cumulative way
technological change happens should concentrate efforts towards digitalization before
the adoption of AI and other emerging technologies. On the other hand, the consistent
shrinking of intervals between revolution waves prospects a fast-changing landscape
in AI adoption and calls for raising awareness towards opportunities for MSMEs.
1.4 - AI in the context of MSMEs
All companies are not born equal when it comes to embracing the AI revolution and
organizing the necessary adjustments in business models and practices. Micro, small
and medium-sized firms (hereinafter MSMEs) tend to exhibit more challenges in
tackling barriers to entry the AI market. Hence, they need extra consideration when
crafting AI policy to guarantee a fair transition to the AI age 1. It is indeed crucial that
we encourage fast, secure, safe, and trustworthy adoption of new technologies, so
that regardless of dimensions, every company can grasp the benefits and remain
competitive.
In those sectors in which AI was implemented on a massive scale, a radical
transformation of business process has occurred: some components of tasks that
relied primarily on human intervention, like data analysis, strategic planning and
solutioning can often be enhanced by integrating AI. In this sense AI can function as
a complimentary tool, offering initial insights and creative suggestions for human
experts to validate and refine. With recent advancements in machine learning, AI offers
the potential for a significant shift in business practices. In fact, prior to the emergence
of machine learning, knowledge-intensive jobs and functions in business processes
were only transferred to computer systems using explicit knowledge and developing
classical AI systems necessitated significant codification efforts. Hand in hand with the
increasing growth of AI, the amount of data available has also increased, broadening
the range of applications for AI.
It is thus easy to see why AI has generated and will generate so much impact on
economies, especially in industry, as anticipated above.
MSMEs are to be held at the core of the effort to disseminate AI technology. This
intention must take into account the wider economic context of the last twenty years,
when the ones that bore the blunt of recession were chiefly MSMEs. The biggest price
they paid was in losing the necessary resources to invest in key advancements,
accumulating an ever-growing technological lag over the years.
Therefore, AI represents the innovation they can leverage to reduce this gap and gain
the competitiveness necessary to ensure natural continuation of their business. As we
will later see, on the one hand, AI deployment entails changes in MSMEs' business
models and practices, particularly considering the predicted advantages and
prospects from AI adoption in terms of productivity, innovation, scale-up, and other
factors. On the other hand, the business environment in which MSMEs operate has
been witnessing major changes because of AI dissemination. This typically eases
business circumstances and helps MSMEs to cope with current issues using
innovative instruments 2.
Given the potential impact of AI on industry and the peculiar case presented by
dissemination amongst MSMES, the next chapter will focus on highlighting major
quantitative trends of adoption, as to offer a clearer picture of the current status quo
and the upcoming challenges in the adoption of this technology.
2. Data, Facts & Trends
The rapid advancement of AI adoption, driven by the benefits associated with its
application, have triggered a ripple effect that extends to the programming of
investment in research and development, changes in labor market dynamics, and to
the path to integration of AI in micro, small and medium-sized enterprises.
These trends are accompanied by challenges that relate specifically to the task of AI
dissemination. To mention just a few, the significant disparities in AI adoption rates
between large companies and MSMEs and the wide gap between the demand for AI-
related skills and their supply.
To address these challenges, it is fundamental to accompany the natural diffusion of
AI technology with an adequate policy framework to ensure a sustainable transition to
a uniform, wide scale adoption. The prerequisite to construct well-engineered policies
is dependent on a careful analysis of the trends currently characterizing the path of AI
integration in the production process. Given the fast-paced changes that are
associated with this technology, the latter exercise is therefore fundamental.
As AI technologies evolve, policymakers should focus on creating a supportive
environment that promotes the absorption of innovation, reduces risk, and maximizes
the benefits of AI adoption for all businesses, regardless of size. A strategic approach
therefore becomes essential to address the potential of AI to drive economic growth
and improve productivity.
To give a clear indication of the main challenges that need to be addressed by policy
makers, this chapter aims at presenting the main trends surrounding the world of AI.
2.1 - Significant Trends
The scope of use of Artificial Intelligence in industry has grown wider with time. Its
applicability to a broad range of business sectors and functions has greatly improved
efficiency, innovation and product quality. The rapid growth of investment suggests
strong confidence, among economic operators, in the ability of AI to reduce costs and
increase productivity. This confidence, along with the potential of AI for industry,
explains why governments are paying more and more attention to the issue, planning
strategic interventions to support the integration of AI in their national industrial
networks.
This section will attempt to quantify AI’s impact and opportunities, focusing the analysis
on three strategic indicators: the impact of AI use on the labor market, the potentials
for investment in the technology, and trends related to AI adoption amongst MSMEs.
These specific trends have been selected due their significance in the context of AI
adoption. The impact of AI dissemination on labor market dynamics is of particular
importance given the potential of AI to perform a wide array of tasks that can increase
automation. Monitoring the integration of this technology into the daily activities of the
workforce is a fundamental step to ensure that its application is sustainable at the
human level. Furthermore, the analysis of the job market can provide important
indications on the human capital necessary to support wide scale AI adoption.
Investment in AI is also an important indicator to investigate. This factor can assist in
providing an insight into the growth of the sector and provide a valuable base from
which to assess the applications and enterprises that could benefit from the support
of public investment. Lastly, this chapter will delve deeper into the main trends
regarding MSMEs, a crucial subsector of enterprises in the race for AI adoption. These
companies often face higher barriers to entry when attempting to integrate AI into their
production processes and need to be accompanied in this endeavor by a well-
engineered policy framework.
2.1.1 - Workforce
The following subsection will illustrate the impact of AI adoption on the workforce. This
analysis will be focused on two main topics, the first related to the reception of AI
technology amongst the workforce, and the second illustrating the trends related to AI
in the labor market.
The potential of AI is evident from the results of questionnaires conducted with workers
in the sector. Workers generally perceive AI as a complement to their skills, improving
both performance and job satisfaction. Similarly, employers also highlight the positive
impact of AI introduction, reporting that higher productivity and profitability are the main
reasons for adoption.
As a result of this appreciation, the demand for a skilled AI workforce has increased in
G7 countries and beyond, highlighting the need for upskilling and reskilling programs
3. Still, when considering the demand of AI jobs, it is important to consider two
detrimental factors for policy design: only a limited number of occupations require the
specialized skill set needed to develop, adapt and modify AI systems and still, the
supply of skilled AI workers remains insufficient to meet the demand, with many
employers reporting difficulties in taking on AI roles. In this sense, it is fundamental to
improve the ability of the workforce to interact with AI, also taking advantage of the AI-
enabled user support functionalities provided by technology suppliers.
These unique observations highlight the importance of market analysis for AI positions
as essential for the implementation of effective measures and policies, providing an
overview of current and future needs of the workforce, enabling the implementation of
targeted interventions that affect skills gaps and the promotion of effective training
programs 4.
Impact of AI on the workforce
To serve the purpose of analyzing the impact of AI in the manufacturing sector, we
chose to report some valuable data from OECD surveys. The most significant results
are described below:
(i) Workers side: Manufacturing workers generally believe that AI integrates their skills
rather than diminishing their value. The percentage of workers who agree with the
statement "AI complements my skills" is about 20% higher than those who believe "AI
has made some of my skills less valuable", as shown in Figure 1.
Figure 1: Perceived effect of AI adoption on workers’ skills
SOURCE: authors' personal elaboration of Lane et al., 2023 (OECD). The impact of AI on the workplace: main
findings from the OECD AI surveys.
Overall, workers have a positive view about the impact of adopting AI, particularly in
performance. About 80% of workers reported performance improvements, while less
than 10% reported a decline. In addition, workers indicated increased job satisfaction,
improved physical health, improved well-being and mental health, and reported better
treatment by their managers or supervisors 5.
(ii) Employer side: employers also express confidence in the ability of AI to improve
performance and profitability. Key motivations for adopting AI include improving worker
performance and reducing labor costs. Another significant reason is to address the
skills shortage, which is particularly relevant for employers in the manufacturing sector,
at least when compared to the financial sector. After the adoption of AI solutions,
employers report positive effects on worker productivity and express greater
satisfaction with managers' ability to measure employee performance within the
company 6.
In addition to the positive reception of AI amongst workers and employers, data also
highlights the importance of AI training in the company organization. In firms that have
adopted AI it was noted how providing AI training is an efficient tool to enable workers
to operate more productively and safely. Furthermore, this type of training is a valuable
asset as upskilling or reskilling current employees is often preferred over the
recruitment of new personnel.
Surveys in the manufacturing sector show the availability of such training and assess
its impact on the working environment, job stability and wage expectations. In
manufacturing, workers who have received AI training are more likely to report positive
outcomes, including better performance, better physical and mental health, and
greater job satisfaction. Results suggest that adequate training amplifies the benefits
of AI on performance and working conditions 7.
Therefore, training activities are essential to maximize the benefits of AI for workers.
However, despite the efforts made by governments in recent years, participation rates
in education and training activities remain lower for low-skilled individuals than those
with medium and high skills. Data from the European Union in 2021 show that only
5.28% of low-skilled workers, i.e., those with less than lower secondary education,
participated in formal and non-formal education or training activities before the
investigation, compared to 13.57% of highly skilled workers 8.
AI labor demand and supply
Job vacancies play an important role in understanding the dynamics of the job market,
revealing the preferences of companies in relation to the skills required. To this end,
the report analyses the trends in employment based on online job posting analysis. It
is noted that they reflect a secondary or residual demand for skills rather than the total
demand in the job market, as they only consider vacancies instead of the entirety of
the job supply. Still, their analysis serves as a useful indicator to evaluate the extent
to which companies prioritize AI-related knowledge over other skills.
There are distinct levels of skills often mentioned in online job postings related to
"artificial intelligence": general and specific skills. General skills include competencies
related to AI usage; competences that comprehend the tools necessary to apply AI.
These can encompass programming languages, big data management, and data
analytics and visualization. On the other hand, specific skills are required for building
particular AI applications, methods, or tools. These typically involve specialized
knowledge in making AI, such as machine learning and neural networks.
The main trend in the AI job market can be summarized as follows. While the
percentage of jobs requiring AI skills is still relatively low, the demand for a skilled AI
workforce has increased in OECD countries. Only a few occupations require the
specialized skill set needed to develop, adapt and modify AI systems, as shown in
Figure 2.
Figure 2: % of AI job postings, % of all job postings, for selected G7 countries
Data Source: Lightcast, 2023. Authors' personal graphic elaboration of Artificial Intelligence Index Report 2024
from, Stanford University.
Note: an AI job posting is defined as any job posting that requires at least one skill in AI, such as machine learning
or natural language processing. The decrease observable in 2023 appears to be situational, and perhaps caused
by an exogenous increase in operational job postings among big companies.
General skills are more broadly in demand across various roles and sectors. The most
sought-after is a general knowledge of machine learning, which is required by 34% of
AI vacancies. Most AI job postings are concentrated in professional services, ICT, and
manufacturing sector. In contrast, industries such as hospitality, agriculture, and
transport show less interest in AI-related profiles. While the development of artificial
intelligence systems certainly requires specific, specialized knowledge, it is the
general skills that are more frequently sought in the job market 9.
Studies have shown that AI skills are among the most valuable ones, earning a 21%
premium compared to the average 4% premium paid for a more competent worker,
ceteris paribus. This premium seems to be partly attributed to the complementary
nature of AI skills with a wide range of non-AI-related skills, which increases their
overall value. In addition, the persistent high demand for supply-side AI skills further
explains this premium: as industries increasingly adopt AI, workers with these skills
are in high demand, justifying higher wages 10. However, employers recognize that
while the importance of AI specialized skills has grown, there is an even greater
emphasis on human skills: successful AI adoption requires not only AI skills, but also
skills in creative and social intelligence, reasoning and critical thinking.
AI-specialized labor supply, despite a sharp increase, remains significantly lower than
demand. Comparisons between 2022 and 2023 among various AI-related jobs
indicate that employers continue to face substantial recruitment challenges for these
roles. Although fewer respondents reported difficulties in hiring AI data scientists, data
engineers, and data visualization specialists than in previous years, between 45% and
65% of employers still report difficulties in finding AI-skilled workers for all positions 11.
The |
100 | bcg | aspire-to-ai-leadership-national-strategy-blueprint.pdf | ASPIRE to AI Leadership:
A National Strategy Blueprint
October 2023
Dr. Akram Awad, Frank Felden, Dr. Lars Littig, Nay Germanos,
Rami Mourtada, Alix Dumoulin
Boston Consulting Group partners with leaders
in business and society to tackle their most
important challenges and capture their greatest
opportunities. BCG was the pioneer in business
strategy when it was founded in 1963. Today,
we work closely with clients to embrace a
transformational approach aimed at benefiting all
stakeholders—empowering organizations to grow,
build sustainable competitive advantage, and
drive positive societal impact.
Our diverse, global teams bring deep industry and
functional expertise and a range of perspectives
that question the status quo and spark change.
BCG delivers solutions through leading-edge
management consulting, technology and design,
as well as corporate and digital ventures. We
work in a uniquely collaborative model across
the firm and throughout all levels of the client
organization, fueled by the goal of helping our
clients thrive and enabling them to make the
world a better place.
Contents
02 | Introduction 09 | Investment
03 | ASPIRE:Framing 10 | Research &
a National AI Innovation
Strategy
11 | Ecosystem
04 | Ambition
12 | From Aspiration
06 | Skills to Action
07 | Policy &
Regulation
Introduction
Every nation today needs to devise a robust artificial can be considered significant, while only 3 were released by
intelligence (AI) strategy. It is not about competing with AI academia1 (significant machine learning models refer to AI
giants like the US and China head-on, but about finding a systems that showcase a state-of-the-art improvement, are
specific and competitive foothold in this fast-evolving historically significant, or highly cited: in 2022, 23 of them
digital landscape where data is the new oil. AI, like were AI language systems). Along with its myriad benefits, AI
Prometheus’s gift of fire, is acting as the spine for a broad poses significant risks. Certain types of jobs are likely to
spectrum of ground-breaking technologies - from data disappear. Ethical concerns around privacy and surveillance,
analytics to robotics and IoT. Its influence is sweeping algorithms reinforcing bias and discrimination, the protection
across vital sectors such as healthcare, education, energy, of intellectual property, and the role of human judgment are
manufacturing, and transportation. We are just at the serious and have far-reaching societal implications.
rupture of the AI revolution, with its full impact yet to Governments can and should play a constructive role in
materialize. It’s a bit like watching a thrilling mystery shaping industry developments, educating the general public,
unfold - exciting, unpredictable, and full of opportunities. and promoting responsible AI. But the clock is ticking – they
The recent global frenzy over generative AI models - the must get involved before exponentially growing complexity
new rockstars in the tech world - underscores AI’s and mass adoption make intervention and oversight even
disruptive prowess and its potential to rewrite the art of more challenging.
the possible. Nations now stand at a strategic crossroads; a
window of opportunity is open for them to make judicious If the private sector has been the primary beneficiary of
choices about their positions in the AI race. developments so far, a national AI strategy will pay
dividends to the general public beyond protecting them
It’s a high-stakes game, and the prizes for playing it well from the risks highlighted above. On a practical level,
are monumental: enhanced GDP, increased productivity, governments can leverage AI to target resources and
job creation, improved quality of life, and citizen welfare. improve service delivery. If governments fall too far behind
This endeavor is akin to a carefully orchestrated symphony the private sector, citizens will grow more frustrated with
- with each instrument, each note, representing key the delivery of public services, and private actors will be
enablers and value creators of national AI strategies. A exclusively setting the standards. While trends of the latter
well-coordinated, strategic sequence could lead to are starting to emerge globally, this imbalance risks
exceptional results; a misaligned action, however, could prioritizing private interests without careful attention to
undermine the overall strategic trajectory. Therefore, the the public good.More broadly, governments should drive
call for action is urgent and should echo in every corner of the development of AI standards, norms, and priorities –
national policy-making chambers. nationally and globally – not relegate those decisions to
the private sector. Importantly, they should do so
Currently, the private sector leads the way in AI. The AI Index proactively to keep pace with private sector-driven AI
compiled by Stanford University reports that, in 2022, industry innovation.
players released 32 of the 38 machine learning models that
1. Stanford University HAI “AI Index Report 2023”: https://aiindex.stanford.edu/report/ Salesforce (2023): https://www.salesforce.com/news/stories/
digital-skills-based-experience/
2 ASPIRE TO AI LEADERSHIP: A NATIONAL STRATEGY BLUEPRINT
ASPIRE:
Framing a National AI Strategy
C
ountries approach AI from different starting points. Understanding its starting point and approach to these
They have different priorities for economic growth, trade-offs forms the basis for shaping a nation’s strategy. In
social progress, educational achievement, and so supporting national governments in their AI strategies, BCG
on. They bring unique technological, engineering, and other has developed the “ASPIRE” framework which further defines
strengths as well as limitations and weaknesses. Countries and codifies six foundational elements: 1. Ambition, 2.
also take different approaches to balancing the interests Skills, 3. Policy & Regulation, 4. Investment, 5.
of government, private sector, and individual citizens. Research/innovation, and 6. Ecosystem.
Exhibit 1 - BCG’s ASPIRE Framework
DIMENSION DESCRIPTION
A
Ambition Articulate AI vision (e.g., global leadership, pioneering ecosystem)
S
Skills Attract, develop and retain talent for the workforce to thrive in the new age of AI
P Policy & Foster an environment that offers flexibility and certainty for AI development
Regulations and promotes responsible AI
I
Investment Deploy funding mechanisms to stimulate and attract AI-related businesses
Research &
R
Build and enable core research and innovation institutions in the domain of AI
Innovation
E Foster interconnected ecosystem infrastructure at the national level,
Ecosystem
and AI cooperation at the global level
3 ASPIRE TO AI LEADERSHIP: A NATIONAL STRATEGY BLUEPRINT
1. Ambition
A mbition is the seed of strategy. It imagines what is 2 Specialist. These countries develop specific expertise
possible, determines overall objectives, and directs that they promote globally. France and India are
the allocation of resources. In our review of following variations of this approach with France
approximately 50 existing national AI strategies, we focusing on exportable R&D, and India acting as an
identified three central archetypes: “AI garage,” providing outsourced services.
1 National Enabler. These countries promote AI to 3 Industry Leader. These countries aspire to be global
create and nurture local champions, improve their leaders in a broad set of AI capabilities from R&D to
socio-economic condition, enhance quality of life, implementation. This archetype demands a strong
and pursue other national objectives primarily by foundation, including advanced R&D, cloud
encouraging responsible AI and reskilling their infrastructure, large data sets, and a proven record
workforce. The Nordic nations, small but highly of commercialization. In addition to China and the
educated, exemplify this approach. US, the UK and South Korea are vying to break into
this realm.
Exhibit 2 - The three central AI ambition archetypes and their protagonists
1 2 3
National enabler Specialist Industry leader
AI as an enabler AI specific focus areas Robust AI industry to
for national to serve on the lead on a global level
socio-economic growth international scene
Promote the use of AI in Leverage country-specific Grow a leading global AI industry
societies and local sectors to competitive advantage and play a across the tech value chain (i.e.
improve socio-economy by global role (e.g., thought leadership, research, development,
developing local AI champions CoEs, sectors with global relevance localization, adoption)
and prioritizing strategic sectors for AI community)
“Maintain US
“Where the best of Data & AI is “AI garage”
leadership in AI”
made reality”
KSA India USA
“Lead the world in AI
“AI benefits for “Most advanced … via efficient
theories, technologies,
competitiveness and welfare” and reliable governance”
and applications”
Sweden UAE China
“Growth and wealth for the “World leader for AI research
“Global leader in AI”
Danish people” and innovation”
Denmark France UK
“One of the world's top 3 AI
powerhouses by 2027”
S. Korea
Source: BCG analysis
Most countries fit into one of these archetypes, although Ǖ The level of proven data & AI impact globally
strategic details and progress along their chosen AI paths in the sector
vary substantially.
Ǖ The alignment of the sector with national
One such variation lies in the economic sectors each priorities
country will select as priority beneficiaries of AI’s
transformative power. This prioritization does not rule out Ǖ The readiness of the sector to adopt AI
AI adoption across all sectors; rather, it entails a strategic
allocation of resources towards high-potential sectors – By employing this approach, countries ensure their AI
often 5 to 7. Three criteria can guide this decision and strategy contributes to sectors of national importance and
ensure the concentration of efforts is optimized: where AI could be meaningfully utilized to generate impact.
BOSTON CONSULTING GROUP 4
Sweden
Healthcare
5 ASPIRE TO AI LEADERSHIP: A NATIONAL STRATEGY BLUEPRINT
defiitnedi
srotces
cfiiceps
oN
Exhibit 3 - Sectors prioritized across selected leading countries
Most
recurrent sectors Denmark Singapore France Canada S. Korea UK China USA
Logistic &
transport
Mobility
Public Safety
Environment
Defense &
Security
Energy
Education
Manufacturing
Finance
Government
Other Sector
Priority sector
Source: National AI Strategies, BCG analysis
2. Skills
A
strategy is only as effective as the people possessing • A global shifting labor market, with 85+ million
the proper skills to execute it. A national AI strategy jobs expected to be displaced by AI and machinery
should outline an approach to build the skill base by 2025.6 Countries need to raise awareness of AI and
through education, reskilling, and training. But developing related job opportunities, and develop talent through
and keeping talent with the necessary AI skills is a global reskilling and on-the-job training. Data and AI are
challenge. Countries must deal with: the fastest growing job categories in the world with
97 million new roles expected by 2025, exceeding the
• Limited knowledge of data and AI, including basic number of those displaced. It is critical for nations to
literacy, which slows ecosystem-wide adoption. push retraining and transition to accommodate these
For instance, 67% of leaders globally say their company shifts, and incentivize the private sector to participate
is exploring ways of leveraging generative AI, yet 66% in the effort.
of them report that their employees do not have the
skills to use the technology successfully.2 Key levers • A global supply-demand talent gap. Around the
for addressing this systemic issue include enhancing world demand for AI talent is growing faster than supply,
access, motivation, and talent development. Importantly, and > 50% is located in just three countries (USA, China,
governments and academic institutions around the and India).7 Beyond local initiatives, most countries will
world are embedding data and AI into their formal also need to attract foreign talent, including through
curriculums: The Stanford AI Index reports an increase dedicated programs like Singapore’s Tech@SG. It is
of 102%3 over 2016-2020 in top university courses that important to recognize that this talent extends beyond
teach undergraduate students the skills needed to build the technology itself. An often-overlooked trait is the
and deploy AI models. Higher education institutions are ability to bridge the worlds of deep technology and
also adapting their non-technical degrees to develop business. People who can translate technology into
AI talent in sectors: degrees combining data science or terms that business executives can understand, and
AI with the likes of business administration or social convert business challenges into technology solutions,
science are increasingly popular, as well as compulsory remain a rare breed.
electives for students as illustrated by Saudi University
KFUPM’s AI+ curriculum embedding mandatory AI • Global competition for leadership driving talent
modules within engineering programs. Efforts are not availability and retention challenges. Countries
limited to higher education: the UNESCO identified 11 should focus on attracting AI talent in the context of
countries with endorsed and implemented government- their integrated global innovation and rrecognition
led K-12 AI curricula including Austria, China, India, and efforts, with many using physical employment
the UAE.4 opportunities as a starting point to build their talent
pools. Building a sustainable ecosystem, for example
In addition, a growing number of talent development through work flexibility and immigration policy, is key
initiatives are being conducted outside of formal to integrating overseas talent into the local economy.
education systems, with countries embracing the full Meanwhile, encouraging locally driven innovation,
range of development opportunities besides university, including through startup support, builds worldwide
including training programs, on-the-job training, and recognition of a country’s thriving data and
self-learning. We see countries like the UK, Singapore, AI sector. This in turn makes it easier to attract talent.
and the UAE implementing initiatives to build basic
AI literacy in both students and adults. Some nations
have expanded their initiatives beyond national borders.
Finland, for example, provides free online basic literacy
courses for any individual globally with the goal “to
demystify AI”. Its program has been accessed in 170
countries, and 40% of its students are women.5
2. Salesforce (2023): https://www.salesforce.com/news/stories/digital-skills-based-experience/
3. Based on Mastersportal (AI and Data Science & Big Data sub-disciplines), retrieved in July 2023: www.mastersportal.com/
4. UNESCO “K-12 AI curricula: a mapping of government-endorsed AI curricula” (2022): https://unesdoc.unesco.org/ark:/48223/pf0000380602
5. Elements of AI: https://www.elementsofai.com/
6. World Economic Forum (WEF) “Future of Jobs Report” (2023): https://www.weforum.org/press/2023/04/future-of-jobs-report-2023-up-to-a-quarter-
of-jobs-expected-to-change-in-next-five-years/
7. Everest Group (2022): https://www.everestgrp.com/market-insights/talent/global-data-analytics-and-ai-talent-locations.html
BOSTON CONSULTING GROUP 6
3. Policy & Regulation
R
egulating AI has come into focus as deployed AI state-level legislation inspired by GDPR is on the rise
systems have put users, companies, and government (e.g., the California Consumer Privacy Act). Take data
at risk. Both companies and governments have a role privacy as an example, as data is the raw material for AI
to play. systems. If data privacy laws are too lax, the public will
rightly question whether AI’s value outweighs its risks.
• Companies are starting to self-regulate through Some estimates indicate that up to 2.5% of GDP8 can
responsible AI, hoping to create competitive be unlocked by relaxing data sharing limitations and
advantage. But the same study found that just 16% encouraging access to data, but tapping into this socio-
of the companies surveyed had mature responsible economic potential requires clear legislation fostering
AI (RAI) programs. Of course, companies put varying data as a national asset. Countries have addressed the
degrees of effort and intent behind ensuring the challenge differently. Some, like China, take a highly
responsibility of their AI efforts (a point reinforced by restrictive approach to data regulation and cross-border
recent turnover among some leading names’ AI data flow. On the other end of the spectrum, countries
Ethics teams). like the US and Canada employ a light-touch approach
and encourage free data flows. The European Union
• The central importance of governments in creating and Singapore, among others, have crafted their own
an overall national strategy, and designing AI models leveraging selected restrictions to balance
legislation to orchestrate public, individual, and interests across data economy stakeholders. If AI ethics
private interests is hard to overstate. From a state and data privacy have often been cited as some of the
perspective, taking actions such as controlling cross- most complex and critical areas of legislation, recent
border data flow are key to protecting national security developments in generative AI are also shedding light on
and interests –a priority for China. China’s recent the issue of intellectual property rights.
Measures for Generative Artificial Intelligence draft is
a good illustration of this priority with requirements • Countries have created various governmental
such as the alignment of GenAI systems’ output with bodies to deal with data, establish a supportive but
national values. Meanwhile, safeguarding citizen watchful regulatory environment, and create rapport with
interests requires a focus on personal data protection the private sector. Some, like Saudi Arabia, have highly
and security. This has been a long-standing focus for the centralized government authorities. Others, like the US,
European Union firstly embedded in the General Data are much more decentralized with the implementation
Protection Regulation (GDPR) and more recently in the of broad initiatives delegated to several agencies. The UK
EU AI Act, the world’s first comprehensive AI law. The positions itself in the middle ground, as highlighted in the
Act addresses the ethical implications of AI: it defines a 2023 government whitepaper “A pro-innovation approach
classification of AI systems into four risk categories, each to AI regulation”. There the government sets a national
associated with a set of rules and restrictions, including framework and principles, and while the Office for AI
requirements around data quality, transparency, plays an oversight role, it leaves its implementation to
oversight, and accountability. This Act not only covers sectoral regulators. Beyond data itself, these bodies also
specific use cases such as facial recognition, which falls need to tackle the technologies that will be creating value
into the highest risk category and is effectively prohibited from it, and address increasingly pressing challenges. Are
by the Act, but also general-purpose models such as governments actively setting rules, standards, norms, and
large language models. principles to foster responsible AI? Are they ensuring that
algorithms being used in the country are understandable,
Finally, the private sector will benefit most from light- auditable, and do not present risks for users including
touch legislation favoring open data and prioritizing harm and discrimination? Are they conducting
data value realization – as we see in the USA, although appropriate audits and other forms of oversight?
8. OECD: https://www.oecd.org/digital/data-governance/
7 ASPIRE TO AI LEADERSHIP: A NATIONAL STRATEGY BLUEPRINT
Overall, regulating AI – whether by simply setting core ethics coupled with pro-innovationinitiatives like provided
principles or through proactively introducing protective sandboxes (low-risk high support environments setup by
mechanisms – is necessary to ensure sustainable government entities to fuel cross-sector innovation.)
development of the AI innovation ecosystem, maximization
of value from AI solutions, and protection of citizens from Recent disruptions, like the suddenly accelerated
harm, undesired use of AI, and discrimination. Both private adoption of generative AI systems, have triggered different
companies and government have roles to play in developing reactions worldwide. While certain countries, like Italy,
principles and ethics around AI. UNESCO developed have chosen a temporary ban as a precautionary
recommendations on the AI ethics focused on human rights measure, others, like Portugal, have swiftly seized the
and inclusiveness, and was adopted by all 193 Member opportunity to integrate this technology into their
States. Regulating a fast-changing field like AI is an ongoing government services. In times of fast-paced innovation,
process. Leading countries have typically started their governments often find themselves in a reactive stance
journey with soft legislation focused on principles to guide towards private sector advancements. A strong national
AI players and enable rapid growth of the data and AI AI strategy can equip policymakers and legislators with
economy. Then as understanding and applications become directions, principles, and guidance on key trade-offs that
more sophisticated, mature jurisdictions like the US, EU, can promote efficient and harmonized decision-making
and China have moved toward more restrictive models in the face of rapid technological advancements.
BOSTON CONSULTING GROUP 8
4. Investment
A
nation’s willingness to invest in AI needs to match and ecosystem promotion. Countries can also increase
its ambition. the ease of starting businesses, and establish investment
protections to create a pro-investment climate. They
can offer business advisory and legal support. Finally,
• National governments have allocated extensive they should facilitate connections among stakeholders,
budgets for AI development. Examples include building a pro-partnership environment, and developing
China, France, South Korea, the UK, and the US which clear paths for investors and efficient approaches to
have each announced and committed to investing match-making.
more than USD 1 billion in AI, leaving other nations
far behind.The absolute amount, while important, may • Equity funding has also continued growing
ultimately matter less than its concentration toward in the past years, despite a recent slowdown.
priorities and its ability to unlock other sources of Between 2013 and 2022, corporate investments in AI
funding. Governments, for example, can stimulate globally grew by a factor of 13, reaching an all-time
investment activity through supportive fiscal and high in 2021 with USD ~275B10 invested. Recent AI
regulatory mechanisms. These help establish a culture advancements such as Generative AI are expected to
that incentivizes support for data and AI ecosystem fuel further investments, with over USD 12B worth of
growth, and attracts international and domestic interest. deals announced or completed in the first quarter of
Leading nations utilize diverse funding vehicles and 2023. Notably, large technology companies have been
structured investment support to activate their data and pledging investments in Generative AI startups: it is
AI ecosystems. Funding vehicles include debt (e.g., loads, the case of Salesforce which is doubling the size of its
credit lines etc.), equity, and direct spending. Collectively, Generative AI Find from USD 250M to 500M. Equity
these instruments span the entire value chain from pre- investments are sourced from both public and private
seed to buyout / later stage funding, ensuring a healthy entities with levels varying by country. The USA and UK
ongoing financial pipeline for ecosystem participants. are mostly private sector driven: in 2022, the USA was
leading private investments in AI worldwide with USD
• Technology companies’ debt ratios have been ~47B invested by private actors. China and Singapore
rising (+100% over the last year for European receive the most public contributions including through
technology startups)9 showing increased appetite sovereign funds and government VCs. Countries like
for debt vehicles, including startup-loans, project France and Germany employ a hybrid model including
investment loans, microfinancing, and credit guarantees co-investment initiatives and government investments
which provide countries the opportunity to activate in VCs.
their data and AI sector. They are facilitated by multiple
providers including banks and financial institutions, • Leading nations also provide direct funding
government lending, and NGOs but also non-financial including growth and innovation grants; seed and
private institutions (specifically in the USA). Countries startup support; individual and employee support such
have implemented specific initiatives using targeted as for hiring and training. These can be complemented
debt vehicles to develop data & AI with specific focus on by incentives for businesses focusing on tax breaks,
company size (e.g., Microfinance Ireland which providers subsidies, and special economic zones: Singapore for
short-term loads to startups), on mandate, on industries, instance provides tax exemptions of up to 100% to
or on location. qualifying R&D projects. Finally, ecosystem growth can
be facilitated by national budgets allocated to specific
It is important to note that investment support extends ministries as illustrated by the Canadian national AI
well beyond the monetary. It starts with attracting strategy which allowed direct funding of 3 national AI
businesses and funders through fiscal, financial, and centers of excellence.
regulatory incentives, local market information access,
9. Bloomberg (2023): https://www.bloomberg.com/news/articles/2023-03-21/europe-tech-startups-doubled-debt-financing-in-fundraising-shift
10. Stanford University HAI “AI Index Report 2023”: https://aiindex.stanford.edu/report/ (this includes M&A, minority stake, private investments, and
public offerings)
9 ASPIRE TO AI LEADERSHIP: A NATIONAL STRATEGY BLUEPRINT
5. Research & Innovation
G
overnments can also deploy their R&D budget and by developing centers for basic and applied research,
agenda in support of AI by targeting areas that play investing in technology infrastructure, and strengthening
to the nation’s strengths or are critical to addressing collaboration between industry and academia.
its most pressing challenges. A nation’s ambition
archetype – national enabler, specialist, or industry leader • Meanwhile, industry leaders should invest heavily
– will largely shape the scope and priorities of its AI R&D in applied research, integrating innovation and
agenda. It will also guide the respective roles of industrialization, and commercializing innovation
government, academia, and private players, and how their in advanced sectors. Regardless of a country’s
contributions are orchestrated. There is no one-size-fit-all ambition, collaboration between the public and private
for national priority-setting. Leading nations following sectors and between companies and universities is key.
diverse approaches. Some, like Switzerland, are already
leaders in general R&D, so include AI organically in Typically the public sector can kick-start R&D by creating
auxiliary national strategies. Others, like Singapore, have demand for AI innovation and providing financing.
a dedicated AI strategy with strong R&D focus. Finally Academia is responsible for research, knowledge transfer,
countries like the US make AI R&D a specific priority talent development, and international stakeholder
domain with its own extensive strategy, focusing on attraction. The private sector develops its own research,
moonshot initiatives and requiring heavy investments. fosters collaborations, funds R&D, and captures value. The
orchestration of these stakeholders takes different forms
Generally, countries should focus on supporting basic across leading nations. Some favor a self-orchestrating
research, public-private partnership, and collaboration ecosystem, others delegate organization to area-specific
with global AI organizations. champions. All leading countries, however, seek ways to
proactively develop their ecosystems throughout the AI
• Specialist governmental bodies should go a step R&D cycle.
further in creating a research and innovation
infrastructure
BOSTON CONSULTING GROUP 10
6. Ecosystem
International ecosystems: global ecosystem adjacent to AI is crucial. Many of the most
cooperation efforts effective AI applications are not stand alone, but rather
depend on an interconnected ecosystem infrastructure.
Despite countries competing to become global AI leaders, Self-driving cars, for example, have built-in sensors and
cooperation between nations has never been more critical processing units, cameras, and wireless connectivity built
to address the global challenges raised by AI and better by separate companies that must work seamlessly together.
capitalize on its opportunities. As such, AI cooperation has These ecosystems vary in complexity, depending on a
become a key enabler for nations. nation’s ambitions, but will all involve startup development,
industrial adoption, infrastructure, data access, and
• The ethical implications of AI, ranging from data government support. As with research and innovation,
privacy and algorithmic bias to autonomous decision collaboration is the cement that holds ecosystems together.
-making, transcend national borders: effectively
addressing them demands close international In addition to cross-cutting ecosystem infrastructure
cooperation. This priority was reflected by recent efforts providing security and interoperability, the following
from international organizations and intergovernmental three overarching layers of infrastructure are particularly
forums which constitute critical alignment platforms for important in driving leading countries’ AI success:
nations to jointly address AI ethic challenges, develop
shared principles, standards, and frameworks to be • Computing and cloud: Sophisticated data and AI projects
implemented at the national level. For instance, the require scalable cloud infrastructure with hyperscalers. But
UNESCO published in 2021 its “Recommendation on the global hyperscale cloud resources are failing to meet the
Ethics of Artificial Intelligence”, which defines principles growing demand. To address this, leading nations are
and policies guiding AI policymaking worldwide. Similarly, establishing cloud hubs, and expanding the presence
the OECD established its AI Policy Observatory and of hyperscale cloud providers in the country to run
published AI recommendations that served as a basis for the data and AI workload locally. For example, the Dublin
the G20 AI Principles adopted in 2019. Cloud Computing Hub hosts 70 datacenters operated
by hyperscale11 cloud providers, with state-of-the-art IT
• Cooperation also underpins the economic potential infrastructure, fiber optic speed networks, and advanced
of AI. By fostering AI cooperation, countries can technology telecommunications.
facilitate the development of interoperable AI
systems, harmonize regulatory frameworks, and • Data: Limited data accessibility and low data quality
promote open data sharing. Collaborative initiatives that are key challenges in data and AI enablement.
foster AI cooperation can create a level playing field, Today, ~45% of Smart City applications require cross
enhance market access, and promote fair trade practices, industry consolidated data, and organizations lose
thereby unlocking new avenues for economic collaboration on average USD 15 million annually due to poor
and driving innovation across borders. To capitalize on its data.12 Countries can address this by providing open
economic potential, countries are now specifically access to national data platforms, consolidating
embedding AI in digital trade agreements (e.g., UK- sector-specific data, developing standardized
Singapore Digital Economic Agreement). specifications and guidelines to enhance data
quality and classification, and providing toolkits to
• As a multi-purpose technology, AI has the potential entities on their data journey. An example is Singapore’s
to help address key global challenges such as climate Data.go |
101 | bcg | BCG-Executive-Perspectives-CEOs-Guide-to-Maximizing-Value-from-AI-EP0-3July2024.pdf | Executive
Perspectives
CEO’s Guide to Maximizing Value
Potential from AI in 2024
Introduction
July 2024
Introduction In this BCG
Executive Perspective,
We meet often with CEOs to discuss AI---a topic that is both captivating and rapidly
we will show you how
changing. After working with over 1,000 clients in the past year, we are sharing our
to leverage AI to create
most recent learnings in a new series designed to help CEOs navigate AI.
With AI at an inflection point, the focus in 2024 is on turning AI’s potential into real business value
profit. Here are some key questions CEOs often ask about getting value from AI:
• Where should my organization start?
• What are the highest value and opportunities where GenAI and AI can transform
my business and functions?
• How can I achieve short-term performance with AI and GenAI while building the
necessary capabilities in my organization?
• How can I build enthusiasm for AI across all levels of my organization and drive
adoption among front-line employees?
This document is a guide for CEOs to cut through the hype around AI and
understand what creates value now and in the future. It explains current AI
adoption trends, the technology's capabilities, and how to use it for a complete
enterprise transformation.
11
Executive summary | CEO’s guide to maximizing
value potential from AI in 2024
The maturity of AI brought us to an exciting moment, where Generative AI is complementing Predictive AI, and going
well beyond the hype in delivering superior value for organizations
The time to act AI mature companies (~10%) are also the first to scale GenAI, further widening the gap vs. peers
on AI is now AI technology is also evolving rapidly, from mature value sources ready to scale at the present time to exciting
innovations on the horizon
Companies are embarking on AI transformation journeys; setting ambitious targets both in top line and bottom line
Three strategic initiatives to drive value and achieve end-to-end enterprise transformation:
• 'DEPLOY' utilizes off-the-shelf tools to boost workforce productivity by 10-15%, improve employee satisfaction,
Three strategic
and generate excitement for broader AI change in the organization
plays to create
• 'RESHAPE' allows for re-imagination of functions through workflow re-engineering, to drive 30-50%
value at scale
improvements in efficiency, effectiveness across affected functions
with AI
• 'INVENT' leverages AI to expand revenue streams and "invent before getting disrupted" by introducing new
offers, services, and experiences to the market
To successfully deploy AI at scale and convert it into business impact, organizations need strong foundational
capabilities (e.g., talent, technological infrastructure, etc.) and a 10-20-70 approach in terms of level of emphasis
Executing
anchoring on algorithms (10%), tech & data (20%), and people & processes (70%)
successfully
Long-term competitive advantage will come from data, talent, and culture; the time to act is now, otherwise,
organizations risk being left behind
2
GenAI is extending the value and excitement around AI
broadly, with leading adopters realizing superior outcomes
Companies with the highest AI maturity are further extending …and rewards are clear
their lead by scaling GenAI applications1… for those further ahead in
AI journey2
~ 10%
3-year
+2.6x
~ 50%
companies
revenue growth
companies
~ 40%
companies
3-year
+38%
EBIT growth
Piloting Scaling
Developing few focused MVPs to test value Are scaling 1 or more
No-action yet from GenAI GenAI applications
across functions/ 3-year market
Taking no action on GenAI yet +50%
enterprise
share growth
Majority have historically Majority have historically piloted a Majority have historically
lacked predictive AI project number of predictive AI projects, but scaled several predictive AI
execution capability few have successfully scaled initiatives in a few functions
Customer
+45%
satisfaction score
Higher AI maturity
Read What GenAI's Top Performers do Differently
1. BCG Build for the Future C-level GenAI survey, 2023/2024, N = 159; BCG Client Experience 2. BCG Company of the Future Survey 2022; 33
n=536; Comparison of 'Discovering' companies with none/limited AI solutions vs 'AI driven' companies with multiple at scale AI solutions
AI technology continues to evolve rapidly; while value proofs
exist already, even more exciting opportunities are on the horizon
Non-Exhaustive
Established value sources Emerging applications Early experiments
Video/audio New product
Content generation
content generation development
including text & image
Customer facing
chatbots
Commercial spend
Summarization & Independent
simulation and
recommendations decision-making
allocation
Trend sensing,
from unstructured data without human
product refinement
in the loop
Demand
forecasting Optimization:
operations, price,
promotions,
precision media
4
Three complementary strategic plays to maximize
value potential of AI
DEPLOY RESHAPE INVENT
Enhance efficiency with GenAI tools Elevate business impact by Develop AI-native offerings that
that streamline everyday business transforming workflows with AI, elevate customer value proposition
processes reducing the need for enabling multi-functional reshaping and and unlock new business models &
additional hires & daily operating friction end-to-end organizational transformation revenue opportunities
Examples of 'Deploy' Examples of 'Reshape' Examples of 'Invent'
• Meeting summary • Design and Engineering • Hyper-personalized customer experience
• Code development • Marketing • AI-powered services/products
• Calendar management • Customer Service • Data monetization across value chain
• Invoice reconciliation • Technology • Insights and innovation platform
Read Turning GenAI Magic into Business Impact
End-to-end transformation across all 3 plays
Combine multiple AI initiatives for an end-to- Scale from functional transformation to
end transformation company-wide transformation
55
Key principles and CEO imperatives for scaling strategic plays
DEPLOY RESHAPE INVENT
GenAI in everyday tasks Critical functions New business models
30-50% efficiency, speed, and
AI outcomes 10-15% productivity New revenue play
effectiveness/ROI improvement
Off the shelf software (e.g., Copilot, Assembly of predictive & generative AI
Tech Dedicated platform
ChatGPT Enterprise) systems; function-specific
People Upskilling & adoption Process redesign, workforce planning Advanced design + AI
Risk/
Technical risks Operational risks Client facing risks
Responsible AI
Operating model IT/HR-led Function-led Incubation-led
• Engage CFOs and CHROs (beyond • Shift dialogue from uses case/point • Be prepared to continuously test &
CIOs), as champions solutions to function adapt operational plans
transformations
• Embed tools in existing workstreams • Maintain focus on providing
CEO imperatives with role-specific features • Upskill leaders & use persona-based customer value vs technology
communication to facilitate change capabilities
• Communicate capabilities & goals to
avoid unrealistic expectations • Build a baseline, select priority • Align (Gen)AI initiatives with overall
workflows, & run pilots strategy & inspire C-level to
66
lead/invest
'DEPLOY' Overview | 'DEPLOY' unlocks 10-15% productivity improvement
and prepares organization for broader AI change
How are companies using it?
What is 'DEPLOY'? Tech is being deployed across various workflows and everyday tasks,
with a few standing out as the most common
Deploy efforts take the “toil” out of work;
investments in early wins that prepare
Q: How is your company deploying GenAI in everyday tasks today? (N=188)1
organizations for an AI-powered future
Knowledge management 69%
of companies employing
60%
GenAI solutions have Code development 67% 10-15%
'DEPLOY' plays in motion1
productivity
Meeting summaries 62%
gains
Content drafts 55%
'DEPLOY' tools in the market
Image/visual
48%
content generation
ChatGPT Microsoft Research extraction
"Personalized recommendations are now at
44%
Enterprise Copilot and synthesis the fingertips of all our developers. [With
GitHub Copilot], they are coding faster,
Contract/SOW drafts 33%
collaborating more effectively, & building
GitHub Adobe
better outcomes."
Copilot Firefly Calendar management 31%
– Engineering Manager at a leading
Illustrative, non-exhaustive Invoice reconciliation 31% technology company
7
1. BCG Deploy, Reshape, Invent Survey 2023; 2. GitHub; 3. Microsoft; 4. BCG Henderson Institute; 5. Adobe
'RESHAPE' Overview | Companies are reshaping support functions with AI,
then quickly moving on to transform core functions crucial to their industry
Non-Exhaustive
What is 'RESHAPE'?
Companies across industries are reshaping beyond their support
functions, expanding towards core functions
Companies are elevating business impact
by transforming functional workflows
• Streamline talent sourcing & hit-rate of best candidates
with AI HR
• Increase employee satisfaction with augmented HR services
Support • Drive efficiency in tech ops & vendor spend model
of companies employing IT & Development
68% • Accelerate software development timelines
GenAI solutions have functions
'RESHAPE' plays in motion1
• Drive efficiency in quality, customer service, and logistics
Supply Chain
• Reduce lead times in production and logistics
…
'RESHAPE' is …
• Improve overall response time by extracting information more
Underwriting in
• Functional transformation leveraging AI quickly and accelerating summary & review processes
Insurance
and GenAI • Enhance assessment accuracy
Core
• Holistic and centrally coordinated effort Marketing • Deliver superior productivity, creativity, insights in less time
functions
• Enhance customer-centric delivery with hyper-personalized
• Complete re-imagination of how work gets (varies by in CPG content and campaigns at scale
done and who does it
industry)
R&D • Improve product development (e.g., drug discovery, scientific
• Building underlying capabilities via strategic
in BioPharma research), quality, testing, and design generation
investments in core tech, people and RAI2
…
8
Source: 1. BCG Deploy, Reshape, Invent Survey 2023 2. Responsible AI – the approach to developing and implementing AI in a legal and ethical manner; 2. BCG analysis and client experience
'INVENT' Overview | Select companies are inventing with AI, ushering in a new
era of innovation & taking the lead in shaping the future of their industries
What is 'INVENT'? What does 'INVENT' look like?
'INVENT' develops AI-native offerings that
elevate customer value proposition and New customer experiences [Our company] has always lived at the
unlock new business models & revenue AI enhances businesses' ability to craft intersection of tech and creativity.
engaging, personalized customer
opportunities Recent developments in AI represent
experiences, driving greater loyalty,
an opportunity to take this
of companies employing
engagement, and brand advocacy
46%
convergence to the next level. We view
GenAI solutions have
'INVENT' plays in motion AI [and GenAI] as an exciting new
New line of products
creativity tool to open avenues for
How are enterprises reinventing AI empowers businesses to create
imagination and explore premium
themselves?1 data-driven, dynamic products,
product offerings that allow us to
leveraging insights to enhance
New customer value proposition
88% profitability and competitiveness innovate with our clients and partners
for existing products or services
on a new frontier in media.
New products or services 64%
New business models – CEO at leading internet
AI drives business model innovation by media company
New target customers 52%
evolving & learning from existing
operations, enhancing competitive
New pricing/cost structure
46%
for existing products or services advantage and enabling novel models
Source: BCG Deploy, Reshape, Invent Survey 2023; 1. Survey question: How will your company invent new business models with AI? Please select the type of new business models AI will generate at 9
your company (N=142, companies pursuing Invent)
Across the 3 plays, leading companies are setting ambitious targets
when embarking on AI transformation journeys
Non-exhaustive
Productivity improvement Cost transformation Top-line growth
Boost productivity with 'deploy' & 'reshape' 'Reshape' functions and leverage predictive Speed up time-to-market & drive revenue
plays to level up the company, especially AI to maximize productivity of assets and by 'reshaping' core processes, 'inventing'
across heavily people-driven organizations reduce costs new offerings and full end-to-end
transformations
Energy Financial Institution Insurance
4 hrs $1B+ *500+ 50%
basis points
Productivity boost (per week) Productivity program (cost, revenues, Reduction in time required for underwriting,
to support growth strategy balance sheet optimization); Includes Engineering, driving top line growth
Research, Investment Banking, Wealth Management,
Risk Management
Professional Services Biopharma Consumer Goods
6 hrs $1B *250 3pts+
basis points
Productivity benefits (per week) Value potential by 2027; 'Reshaped' Incremental sales
through broad deployment across 30k users multiple core functions, starting with through digital services
Marketing, R&D, Manufacturing
More detail on following pages
10
Source: BCG Experience
Example 1/2 | How a Biopharma company is reducing cost through
AI transformation with a focus on reshaping multiple functions
Vision Execution Value capture
Non-Exhaustive
Company-wide program under CEO 1 Adopted iterative approach and started
and ExCo sponsorship with several pilots 20-30% agency cost
reduction and improved
Mandate to unlock value fast, by 2 Setup rigorous measurement with GenAI
reshaping multiple functions, mirror processes engagement & campaign ROI
Commercial
engaging all employees; position as
3 Developed lighthouse in Commercial
pioneer in AI within sector
function and then expanded to Research &
Vision to transform via: Development and Marketing & Sales 20-40% medical writer
efficiency gain – 3-6 months
1. Productivity improvement 4 Each wave focused on outcomes and
Research &
saving in time-to-market
(e.g. content summarization) operating model redesign (e.g., as-is content
Development
2. Work reduction via automating development insight-powered & always-
end-to-end processes on content development augmented/
3. Improving employee assisted sales)
80% of reports approved
engagement via reducing
repetitive tasks 5 Assessed portfolio of investments, with no edits – from
projected ROI based on first impact; adjust
4. Competitive advantage via Marketing
20 to 1-3 days
accordingly
business model reinvention, cost & Sales
advantage, capability building
Deploy Reshape Invent
111111
Fill % represents level of emphasis for each strategic play
Source: BCG analysis and client experience
Example 2/2 | How a CPG company is driving topline growth by
inventing new business model and reshaping functions with AI
Vision Execution Value capture
Global CPG seeking to reinforce its Invested in AI capabilities over the last 7 years,
1
core competitive advantages through a mix of organic and inorganic moves
through AI 15-25% improvement in
2 Transformed its R&D and Marketing marketing spend ROI
1. Product superiority and
capabilities through Predictive and increasingly
speed to market
Generative AI, for formula success prediction, cycle
time reduction, Marketing ROI optimization,
2. Marketing creativity and
content production automation at large scale
effectiveness Time to Market
acceleration by
3. Direct and meaningful 3 Launched AI-powered digital services and
consumer connections virtual assistants to augment consumer 3-6 months
experience, build direct connections, influence the
consumer journey
4 In parallel, set up an Enterprise-wide $200M+ of incremental
productivity lift effort with internal GPT
sales through digital
services
Deploy Reshape Invent
Fill % represents level of emphasis for each strategic play 1122
Source: BCG analysis and client experience
Algorithms
10%
Build new algorithms and the science
behind them
Three pillars for Technology & Data
20%
successful (Gen)AI
Deploy the tech stack and ensure the right
data feeds into the right systems
transformation
The 10-20-70 Rule:
Focus 10% of your AI efforts on
algorithms, 20% on the underlying
technology and data, and 70% on
people and processes
People & Processes
70%
Drive change management and other
processes related to people
1133
Algorithms (the ‘10’)/Tech & Data (the ‘20’) | Key AI trends for executives
to keep in mind across algorithms, technology, and data
10% 20%
Algorithms Technology Data
AI models will continue to grow in size New tech stacks are required to The value of Data increasing with
& capability in the next 3-5 years, support AI needs, driving AI, requiring companies to develop
offering an increasingly wide set of companies to simplify legacy new capabilities to deal with
options to choose from when systems and adopt new AI platforms unstructured data (i.e., knowledge)
balancing performance needs & costs
Non-exhaustive Non-exhaustive
Recent trends: Recent trends:
• Tech companies building AI factories (e.g., • Enterprise system solutions launching GenAI • Unstructured data becoming more valuable;
Microsoft $100bn data center investment1) features (e.g., Salesforce, Einstein) increasing need to break “data silos”
• Autonomous agents performing tasks & • New applications (e.g., Jasper, Writer) & • External data becoming more valuable; need to
making decisions without human oversight platforms (e.g., Scale AI, Groq) emerging develop data partnerships & ecosystems
• AI being deployed on mobile devices • Companies using GenAI to support system • Need for CDOs2 to help functions create & rank
migration (via software automation) unstructured data across enterprise
Note: Trends as of June 2024; 1. Forbes: "Microsoft And OpenAI Partner On $100 Billion U.S. Data Center"; 2. CDO = Chief Data Officers 14
People & Processes (the ‘70’) | New roles, evolved operating models, &
rigorous change management required for successful AI transformation
70%
Organization & operating model Talent & skills
Emergence of new roles/departments Changing skillset requirements
New roles will be created to unlock the potential GenAI will automate some tasks, recommend
of AI (e.g., Chief AI Officer) next actions & improve knowledge management
New operating models Revamped talent acquisition
Changes in roles, responsibilities, and decision Greater access to candidate pool web scraping,
rights would bring about significant changes in auto-scheduling, and AI-based interviewing would
operating models greatly increase hiring efficiency
Greater productivity & redesigned work AI-enabled performance management
GenAI will automate many types of creative work (e.g., coding, New observational data (e.g., conversation summaries)
writing) and enhance employee support (e.g., next best action) will make performance management more objective
Personalized training
Purpose, culture, & change management
Employee Learning & Development will be
tailored to individual needs & questions, and new
Extensive change management needs
training content around AI will emerge
New talent needs, ways of working, and job
responsibilities must be managed thoughtfully
15
Source: BCG Marketing Org & Op Benchmarks
However, change is hard, and executives face challenges
across the ‘10-20-70’ during their AI transformation
Top challenges with AI transformations1 % of executives who reported as
top challenge within each category
Over 2/3
• Trouble reaching sufficient accuracy and reliability of models
10%
Algorithms
• Difficulty ensuring security and compliance of the technology
Of transformations fall
• Difficulty integrating new AI technology with existing IT systems
short of expectations
• Lack of access to high-quality data for model training
(in terms of time, budget, 20%
Tech & data
meeting ambition)1 • IT cost constraints limiting sufficient investments into (Gen)AI
• Difficulty realizing cost takeout/savings
$1T
• Challenges prioritizing AI opportunities when compared to other company-wide
concerns (e.g., cost reduction initiatives)
• Issues with assigning a target ROI for identified opportunities
With backdrop of $1T
of wasted IT spend
People &
70%
• Insufficient (Gen)AI literacy throughout the organization
collectively2 processes • Lack of specialized (Gen)AI engineers in the market
• Resistance, opposition, and fear about AI impacting jobs
• Lack of accountability & measurement of set KPIs (e.g., adoption, value realized)
• Challenges with implementing new processes and reimagining workflows
16
Sources: BCG Experience; 1. 2023-24 BCG Build for the Future C-level (Gen)AI Survey(s), N = 735; 2. Across S&P 1200; Harvey ball fill represents the % of executives who ranked
the challenge in the top 3 challenges when presented with a set of challenges for each of the categories.
Core questions for CEOs to consider looking ahead
Non-exhaustive
• How do I empower my C-suite to stay up to date with the rapidly evolving AI landscape?
10%
• How do I think about whether to Build, Buy or Partner for the model(s) needed? Which model
Algorithms
and model platform partnership(s) do I need to make to stay ahead?
• What kind of (new) data capabilities do I need to leapfrog my competition?
20%
• How do I simplify my legacy systems to adopt new AI tech stacks and platforms?
Tech & Data
• I've invested significantly already. How do I control my costs & ensure a return going forward?
• How do I mobilize senior leaders to embrace & actively champion our (Gen)AI ambition?
70% • How must our roles, departments, & operating model adapt to capture value from AI?
People & • What are the best ways to fill the AI talent gap within my organization (e.g., upskill, reskill)?
Processes
• How do I effectively manage change across my enterprise? How do I communicate our ambition
and set the right expectations, while promoting trust and preventing misconceptions?
Source: BCG Experience 17
AI Transformation Overview | End-to-end transformation integrates strategy
& multiple functional transformations while building requisite foundations
(Gen)AI SETUP DEPLOY
(Gen)AI in everyday tasks across the enterprise
Define value pools RESHAPE critical functions
• BCG (Gen)AI Maturity Assessment
• BCG Workforce Diagnostic In every business function:
Transformation of function 1
Build MVPs, re-design workflows and pilot to
Articulate vision based on strategy prove value…
Transformation of function 2
…while designing future state operating model
Select priority opportunities across
Cascade changes and scale E2E Transformation of function 3…
Deploy, Reshape, Invent PLAYS
Build the business case INVENT
new business models and products
E2E CHANGE MANAGEMENT & DELIVERY
Enable leaders and upskill
Drive adoption, engagement & culture change,l everaging behavioral science
Steer through central governance and measure impact via AI delivery office
ENTERPRISE FOUNDATIONS
Make coordinated investments in core tech & data, people, and responsible AI
Read about BCG's perspective on Responsible AI
18
Getting started | Practical next steps for your AI journey
Understand your Identify the largest opportunities for action & benchmark AI maturity against peers
1
starting point Assess the potential for total productivity impact across your workforce
Prioritize few high Select 3-5 functions/processes for 'DEPLOY', 'RESHAPE', & 'INVENT' plays
2
value initiatives Setup transformative efforts & resource adequately; target ~2-3x return on investment
Embrace AI tools in daily work, upskill the workforce, & scale initiatives broadly
3 Upskill & scale broadly
Remember that this is a people transformation not a tech transformation
Optimize tech/digital costs in the first 6-12 months by centralizing resources,
4 Fund the journey rationalizing legacy applications, and reducing third-party spend
Prioritize & refocus portfolio on value creating initiatives
Invest in foundational Build capabilities that will drive & sustain transformation (e.g., tech, people, RAI)
5
capabilities Improve the quantity/quality of data – it will be a competitive advantage long-term
Launch an AI Develop a structure that allows for broad but controlled experimentation
6
governance structure Operate according to RAI framework while maintaining focus on prioritized initiatives
19
NAMR
BCG Experts |
Dylan Vladimir David Amanda Matthew
Key contacts
Bolden Lukic Martin Luther Kropp
for AI
Sesh Julie Beth Djon Steve
Iyer Bedard Viner Kleine Mills
transformation
Dan Renee Tauseef
Martines Laverdiere Charanya
EMESA APAC
Nicolas Jessica Marc Jeff Romain de
De Bellefonds Apotheker Schuuring Walters Laubier
Dan Andrej Marcus Julian Aparna
Sack Levin Wittig King Kapoor
Robert Akira Nipun
Xu Abe Kalra
2200 |
102 | bcg | five-must-haves-for-ai-upskilling.pdf | Five Must-Haves for Effective
AI Upskilling
OCTOBER 08, 2024
By Hean-Ho Loh, Vinciane Beauchene, Vladimir Lukic, and Rajiv Shenoy
READING TIME: 15 MIN
The need for AI upskilling is clear. But upskilling is also a major bottleneck for companies that want
to scale AI and GenAI across their organizations. Even though corporate leaders know it’s important,
many have been slow to provide people with opportunities to learn the skills required to use it.
There’s an argument to be made for initiating AI upskilling sooner rather than later. Companies that
invest in AI gain a competitive advantage through superior innovation and readiness for the
unexpected. They also improve productivity and customer experience, and boost revenue.
© 2024 Boston Consulting Group 1
But until now, it’s been unclear which approach to AI upskilling yields the biggest return on the twin
investments of time and resources.
We decided to find out. We studied early adopters’ AI upskilling efforts, and ran AI upskilling
workshops for thousands of executives to glean best practices. We also interviewed dozens of
industry experts. We determined that the most effective approach incorporates five distinct actions. It
starts with assessing what’s needed and putting systems in place to measure successful outcomes. It
includes preparing people for change, building in incentives that appeal to their varied motivations to
learn, and putting the C-suite at the forefront of the initiative. Finally, it means using AI to upskill
people in AI.
Amid an AI-Inspired Sea Change, Upskilling Is
Lagging
AI is ushering in a tsunami of change. Already, 80% of organizational leaders regularly use AI tools,
according to a BCG global survey of 13,000 people.
Companies that don’t invest in AI capabilities tend to be more susceptible to disruption. BCG’s
research on future-ready companies identified AI as one of six key attributes that help them
withstand shocks and disruptions and exploit innovation for value-creating growth. These standouts
outperform their peers across multiple financial and nonfinancial metrics.
The same research found that early adopters of GenAI use it to improve efficiencies, enhance
customer experience, and boost revenue. For an organization with $20 billion in revenue, using GenAI
leads to estimated additional profits of $500 million to $1 billion, with nearly a third of those gains
coming in the first 18 months. Separate research by BCG Henderson Institute and Harvard Business
School found that adopting AI leads to 40% higher quality and 25% faster output.
AI isn’t without risks, including risks associated with fairness and equity, privacy, accuracy, and
security. To realize AI’s gains and minimize associated risks, companies must connect the technology
to organizational change. Our experience and research indicate that adopting a structured approach
to “deploy, reshape, and invent” AI-based processes and experiences throughout an organization
yields high-impact results.
That’s where upskilling comes in. To succeed, organizations must upskill their workforce to
understand and embrace AI.
But upskilling efforts are off to a slow start.
The vast majority of 1,400 C-suite executives whom BCG surveyed earlier this year ranked AI and
GenAI among their three top technology priorities for 2024, but 66% expressed ambivalence or
© 2024 Boston Consulting Group 2
dissatisfaction with their progress. Close to the same number (62%) cited a shortage of talent and
skills as their biggest challenge, ahead of unclear investment priorities (47%), and lack of a
responsible AI strategy (42%). Only 6% said that they had already begun upskilling in a meaningful
way. (See Exhibit 1.)
Lack of training extends to companies’ top echelon. Of the leaders we polled, 59% reported having
limited or no confidence in their executive team’s proficiency in GenAI.
Five AI Upskilling Success Factors
Although the need for AI upskilling is well established, the approach that yields the greatest benefits
remains unsettled.
To learn more, we performed quantitative and qualitative research, including studying best practices
of organizations that have been quick to adopt AI. We gleaned additional best practices from
collaborating with Google Cloud and ran more than 150 AI upskilling workshops for 3,000 executives
who use Google Cloud. We also interviewed more than 50 human resources and learning and
development industry leaders who are well-known talent development innovators.
Our analysis revealed five actions that organizations need to take to ensure successful AI upskilling.
1. Assess Needs and Measure Outcomes
Organizations that fall behind on skills training are apt to deploy a “watering can” approach to
improving—launching learning programs that are undifferentiated, costly, and poorly aligned with
overall strategy. A better approach is to launch an upskilling initiative predicated on an assessment
of what’s needed and then to measure the outcomes it produces.
Assessing Need. In evaluating what’s needed, companies must determine the upskilling
requirements of each specific workforce group. C-suite leaders need to define the organization’s AI
vision and strategy and lead AI upskilling initiatives. Managers need to know how to build awareness
© 2024 Boston Consulting Group 3
among direct reports. Workers need to know how to use AI tools. The entire workforce needs to
understand how the organization plans to integrate AI into operations and how work will get done.
The workshops that BCG and Google Cloud ran helped Fortune 1000 clients upskill their executive
leadership teams on GenAI.
Prior to the workshop, Google Cloud assessed where each client was in the process of deploying
GenAI in production. The company then used this information to tailor workshops to individual
needs, develop the optimal industry-specific use cases, and identify the AI applications that would
create the most value for each client’s business.
Once an organization has assessed its needs, it can evaluate and invest in the appropriate AI tools.
Measuring Outcomes. Assessing the effectiveness of AI upskilling and analyzing the return on
learning investment (ROLI) can justify a company’s spending and guide future improvements.
To measure an upskilling program’s ROLI, we recommend using the Kirkpatrick method, which
evaluates effectiveness on four levels:
• Level 1: Learning experience quality and program satisfaction, as gauged by conducting surveys
of learners
• Level 2: Competency development, as measured by assessing learners’ post-upskilling abilities
• Level 3: Individual productivity gains and behavioral changes, as appraised by observing
learners’ improved productivity—for example, in sales lead conversion or customer satisfaction
—over time
• Level 4: Business outcomes
Business outcomes are the hardest to measure because when multiple factors change at the same
time, it’s difficult to determine which caused a positive result. We recommend that organizations
measure them by conducting A/B tests or pilots with control groups.
A retailer that we worked with used A/B testing as part of an upskilling initiative to make its chain of
more than 500 stores more customer centric. The company determined key metrics by working
backward from desired outcomes, including higher sales per square foot, stronger employee
engagement, and improved feedback from customers. The company ran tests to analyze the effects
of upskilling efforts in one group of stores against a control group of stores that had not
implemented an upskilling program. By testing various upskilling methods and measuring their
results, the retailer eventually implemented training that helped the workforce increase sales by 150
basis points, double employee engagement, and receive more positive comments from customers.
© 2024 Boston Consulting Group 4
2. Prepare People for Change
Business or technology transformations such as adopting AI have three key components: people and
processes, technology and IT, and algorithms. Of the three, the changes involving people and process
are the most critical. (See Exhibit 2.)
For a transformation of any kind to succeed, people must be prepared. And a crucial part of
preparing them for an AI transformation involves raising awareness of what’s going to happen
within the three distinct groups in which people work:
• Individuals. AI represents a chance for people to work in new ways that make tasks easier,
enhance productivity, and optimize workflow. For this to happen, people need to understand
how AI tools automate routine tasks, provide data-driven insights, and support decision making.
They need to understand how their roles may evolve as the organization deploys AI and GenAI.
• Teams. People need to recognize how the organization will be integrating AI into complex
workflows and collaborations within and between teams. They need to see how teams will
benefit from AI-based project management tools and how AI-run collaborative platforms will
enhance communication and coordination, leading to greater innovation, streamlined
processes, and better outcomes.
• Across the Organization. People need to comprehend how AI fits into the company’s culture
and strategy, what effects AI may have on its operating model or business value, what potential
pitfalls may accompany the transformation, and what guardrails may protect against them. To
that end, the company must establish an organization-wide AI change management program to
provide the entire workforce with a basic understanding of AI concepts and applications. By
© 2024 Boston Consulting Group 5
embedding AI into the fabric of the organization, the company can create a culture that
supports continuous improvement, innovation, and equitable opportunities for employees to
grow in their careers.
Organizations can raise awareness in multiple ways, including by running enterprise-wide
communications campaigns and celebrating people when they successfully adopt AI to improve their
personal productivity or automate tasks. Other awareness-building tools include AI hackathons,
continuous improvement workshops, and safe spaces for experimenting with AI tools.
3. Unlock Employees’ Willingness to Learn
Part of AI upskilling consists of giving people a strong impetus to get on board with change and
offering a psychological safety net so they don’t fear what’s to come.
Employees may not be keen to adopt AI skills. Instead of viewing AI as a tool that enhances their
roles, they may see it as a threat that could displace them. They may have the impression that AI is
complex and hard to understand, and so feel intimidated by it. For people without a technical
background, the prospect of learning AI may be overwhelming, making them reluctant to take it on.
Discovering what motivates people can help a company shi their attitudes toward adopting AI
skills. Some people are motivated by intrinsic incentives, such as an internal drive to improve or
personal values. Others appreciate external incentives, such as earning a digital badge or recognition
that could help them get ahead in their job. Providing people with autonomy and responsibility for
their own upskilling journey can motivate them to engage in upskilling in a way that they enjoy. It can
also transform them into AI ambassadors, with cutting-edge skills.
Making upskilling fun by turning it into a game is another way to persuade people to try something
new, as are digital nudges, peer groups, and weaving learning into daily work. Removing barriers to
learning and letting people choose how to learn can increase their openness to change.
Top leaders can offer a psychological safety net by making it clear that the purpose of AI is to
enhance people’s roles and create new opportunities, not to replace jobs. Leaders can further
motivate people by elevating an initiative’s visibility and ensuring that the company’s investment in it
is sufficient to meet its upskilling goals. Contrarily, trying to do too much with too little can result in
program failure and cause people to lose faith in the upskilling effort.
4. Make Adopting AI a C-Suite Priority
Efforts to raise awareness and train and motivate people can fizzle out if the C-suite doesn’t make
adopting AI a top priority. Even at organizations with chief AI officers, the CEO and other C-level
executives must function as AI’s top advocates and as AI upskilling champions. Top executives must
have clear responsibilities for upskilling programs to drive adoption and realize anticipated impact
© 2024 Boston Consulting Group 6
and value. At the same time, organizations must centralize AI governance to avoid creating an every-
department-for-itself mentality with regard to adoption and upskilling requirements.
The CEO and the leadership team can embrace the AI skills transformation by modeling desired
behaviors and actively participating in AI initiatives. That level of commitment will cascade through
the organization to foster a culture of continuous learning and innovation. The CEO should oversee
the development of AI objectives and lead the effort to make them clear to the organization. The
chief operating officer should ensure that AI use cases match business objectives and that the
organization is implementing them with a minimum of obstacles. Top risk and information security
executives should maintain proper controls to minimize risks.
At CMA CGM, a leading global shipping and logistics company, leaders from the top down
participated in launching an AI skills accelerator program. CEO Rodolphe Saadé attended the
launch event and further underscored the importance of upskilling in the company’s plans by
regularly visiting training facilities to meet learners. Saadé also closely tracked the performance of
the third-party upskilling providers that the company retained. Other C-suite leaders participated in
AI upskilling sessions, answering questions and collecting possible use cases that learners created as
part of their training. Senior managers upskilled with other learners, which helped the initiative cross
business lines and functions. Getting early buy-in from key leaders helped foster a culture of
continuous AI learning and promote AI adoption for innovation and efficiency at all levels.
Given how quickly the technology is evolving, AI upskilling will be an ongoing effort. Having C-suite
support demonstrates to the rest of the organization the necessity of building upskilling muscle at
every level.
5. Use AI for AI Upskilling
Upskilling that requires people to use AI on the job is an effective way to connect the dots between
theoretical learning and practical application. We’ve found several methods that are effective for on-
the-job AI upskilling.
Using AI Tools. Using AI to upskill people on AI will be unavoidable in the future to keep costs down
and make learning impactful, scalable, customizable, and fast. New AI-based upskilling tools are
emerging almost daily: more than 100 learning tools launched in 2023 and the first half of 2024, and
the influx of new options shows no sign of stopping. Some tools have AI as their core function.
Others use AI to support the application’s main function.
© 2024 Boston Consulting Group 7
AI learning and support tools fall into four categories: skills, content, knowledge and performance
support, and personalization. (See Exhibit 3.) Understanding where specific tools exist in this
framework can help companies navigate what’s available, which in turn can help them implement
upskilling initiatives faster and more efficiently.
The Network Effect. Embedding AI in daily tasks at all levels creates a network effect: the more
people use and understand it, the more the entire organization gains in knowledge, innovation, and
efficiency.
Companies can support the network effect in several ways:
• Center AI training around real-world projects.
• Offer sessions to teach individuals the AI tools they will be using in their roles, thereby creating
ambassadors to propagate AI’s value across the organization.
• Use peer influence to amplify learning. In this regard, CMA CGM scheduled joint AI upskilling for
employees from diverse geographies, business lines, levels, functions, and backgrounds to
create synergies across company sectors.
A Tailored Approach. AI upskilling can be easier to digest when the organization customizes
learning to match tangible business objectives and high-priority use cases. Whether the company
© 2024 Boston Consulting Group 8
orchestrates upskilling programs on its own or with outside help, it should adapt the training to its
specific business context and embed hands-on learning into people’s daily tasks.
Building multiple complete customized AI upskilling training programs from scratch can be costly. A
less expensive approach involves creating learning units for in-demand topics that trainers can pair
with customized content in building-block fashion.
Putting AI Upskilling into Action
Upskilling people on AI must be a C-suite priority. To unlock the full potential of AI upskilling,
organizations should keep the following considerations in mind.
Identify gaps, and tailor programs to fill them. When assessing the workforce's current skill level,
identify specific gaps in AI competencies that customized training programs can address. Tailor
programs to the needs of individuals, teams, and the organization. Collaborate with outside AI and
upskilling experts to tap into high-quality resources and practical experiences.
Integrate upskilling into long-term strategic plans. Incorporating learning programs into
broader strategies makes them more sustainable and increases the benefits that the organization
will derive from them. Integrating training into strategy means creating well-defined career pathways
for employees who acquire new AI skills, and recognizing and rewarding people who obtain them.
Establish internal AI centers of excellence. AI learning hubs can promote knowledge sharing,
mentorships, and collaborative projects, all of which can help promulgate the application of AI
across business functions. Embedding AI upskilling into the organizational culture will foster a
resilient, future-ready workforce capable of driving innovation and maintaining a competitive edge in
the rapidly evolving market.
Treat upskilling as a marathon, not a sprint. It may take several years for the workforce to reach
AI proficiency at scale. To facilitate AI upskilling efficiently, the organization should share
accountability for initiatives. Create upskilling working groups that consist of C-level leaders, learning
and development heads, and business unit leaders. Use the network effect to sustain success.
AI upskilling is an organization-wide, large-scale movement that will transform how work is done and
how companies operate. Organizations that fail to heed that imperative or delay commencing
upskilling initiatives risk fall behind, while those that follow best practices can put themselves ahead
of the curve.
The authors would like to thank Zhdan Shakirov, Susanne Dyrchs, and Wanjun Fang for their research,
insights, and other support.
© 2024 Boston Consulting Group 9
Authors
Hean-Ho Loh
MANAGING DIRECTOR & SENIOR PARTNER
Singapore
Vinciane Beauchene
MANAGING DIRECTOR & PARTNER
Paris
Vladimir Lukic
MANAGING DIRECTOR & SENIOR PARTNER; GLOBAL LEADER,
TECH AND DIGITAL ADVANTAGE
Boston
Rajiv Shenoy
ASSOCIATE DIRECTOR
Dallas
ABOUT BOSTON CONSULTING GROUP
Boston Consulting Group partners with leaders in business and society to tackle their most
important challenges and capture their greatest opportunities. BCG was the pioneer in business
strategy when it was founded in 1963. Today, we work closely with clients to embrace a
transformational approach aimed at benefiting all stakeholders—empowering organizations to
grow, build sustainable competitive advantage, and drive positive societal impact.
Our diverse, global teams bring deep industry and functional expertise and a range of perspectives
that question the status quo and spark change. BCG delivers solutions through leading-edge
management consulting, technology and design, and corporate and digital ventures. We work in a
uniquely collaborative model across the firm and throughout all levels of the client organization,
fueled by the goal of helping our clients thrive and enabling them to make the world a better place.
© Boston Consulting Group 2024. All rights reserved.
For information or permission to reprint, please contact BCG at [email protected]. To find the
latest BCG content and register to receive e-alerts on this topic or others, please visit bcg.com. Follow
© 2024 Boston Consulting Group 10
Boston Consulting Group on Facebook and X (formerly Twitter).
© 2024 Boston Consulting Group 11 |
103 | bcg | gpt-was-only-the-beginning-autonomous-agents-are-coming.pdf | GPT Was Just the Beginning. Here Come
Autonomous Agents.
NOVEMBER 28, 2023
By Mikhail Burtsev, François Candelon, Gaurav Jha, Daniel Sack, Leonid Zhukov, and David Zuluaga Martínez
READING TIME: 8 MIN
The power of generative AI took the business world by surprise. It wasn’t until the release of ChatGPT that
many executives truly appreciated the seismic impact of these large language models (LLMs), and many
companies were le scrambling to keep up. As we enter what’s likely to be a period of permanent revolution,
during which GenAI’s capabilities will progress much faster than businesses will be able to adapt, companies
simply can’t afford to sit and wait. The next leap in AI—autonomous agents—could enter the mainstream in
the next few years and promises to be even more transformative than today’s LLMs.
Although most current LLM-based applications change how information is gathered and delivered, they stop
short of operating independently. Some can automate specific tasks, but they still require a human to input a
© 2024 Boston Consulting Group 1
Although most current LLM-based applications change how information is gathered and delivered, they stop
short of operating independently. Some can automate specific tasks, but they still require a human to input a
series of prompts and monitor the output. In contrast, autonomous agents—which are in part made up of
LLMs—will be capable of redesigning and automating entire workflows. They plan how to execute tasks end
to end, iteratively querying LLMs (through application programming interface (API) calls, where one
application requests data or services from another), monitoring output, and using other digital tools to
accomplish a given goal. As we discuss in examples below, autonomous agents could be used to design,
execute, and refine entire marketing campaigns or undertake R&D testing through at-scale simulation.
Autonomous agents are, in effect, dynamic systems that can both sense and act on their environment. In other
words, with stand-alone LLMs, you have access to a powerful brain; autonomous agents add arms and legs.
With stand-alone large language models, you have access to a powerful brain;
autonomous agents add arms and legs.
The arrival of autonomous agents into the mainstream isn’t far off. Today’s agents still lack the controllability
and predictability needed for widespread use, but technology firms are making constant improvements.
OpenAI’s recently announced custom bots are a clear step in this direction; they are able to use external APIs
to find specific information or to carry out simple actions like assisting with an e-commerce purchase.
Companies should start preparing for wide-scale adoption of autonomous agents today by adjusting their
generative AI strategic planning—including their technology architecture, workforce planning, operating
model, and policies—to ensure their transformation roadmap is robust and ready.
The Explosive Potential of Autonomous Agents
Autonomous agents use the power of LLMs to sense and act on their environment by creating, executing, and
prioritizing tasks. The process starts when the agent receives an objective. The agent then breaks down the
goal into individual tasks and creates a set of bite-sized prompts to tackle each one. These prompts are fed to
an LLM iteratively and, as tasks are completed, the agent creates new, better prompts that incorporate the
results of the preceding iterations. The agent’s process of generating prompts and building on the results may
be parallel or sequential depending on the system design. The agent also actively reorders and prioritizes the
tasks according to the results. The system continues this cycle of breaking down the goal into tasks, generating
prompts, evaluating results, and prioritizing until the goal is met or deemed unattainable (in which case, the
agent shuts down the process).
In an enterprise setting, agents’ potential to automate whole sets of tasks can have multiple uses, two of which
we will explore here: their ability to reduce the need for human intervention in workflows, and their ability to
facilitate the testing of products, services, and scenarios at scale.
© 2024 Boston Consulting Group 2
Automating Entire Workflows. To fully appreciate the workflow automation potential of autonomous
agents, it is important to understand that they can actually use digital tools when they are properly integrated
with them. When configuring an agent, humans can feed the documentation for digital tools to the agent,
which will then “know” how to use them; it will then be able to send instructions to these tools and get results
back through API calls. That is, autonomous agents can directly “tell” other enterprise systems what to do.
This could fundamentally change how a company operates, enabling it to deploy automation more holistically
and significantly reduce labor costs.
Autonomous agents can directly “tell” other enterprise systems what to do. This could
fundamentally change how a company operates, enabling it to deploy automation
more holistically.
Moreover, autonomous agents have the potential to surpass traditional robotic process automation (RPA).
RPA already enables workflow automation, but it is based on “if-then,” preset rules for processes that can be
broken down into strictly defined, discrete steps. This makes it expensive to build and considerably limits its
range of applications. In contrast, agents are universal; they are not limited by hard-coded scenarios, nor do
they require explicit rules spelled out in advance. They promise to produce adaptive automation that can be
applied to a broader range of tasks.
Given these characteristics, the impact of agents will be much deeper than today’s use of LLMs as (primarily)
copilots. For instance, in the near future, an autonomous agent could allow a marketing executive to carve out
and automate whole segments of work. Based on a company’s past marketing campaigns, the agent could
determine what worked and what didn’t, making its own decisions for future email design, scheduling,
graphics, and subject lines. It could also identify the types of consumers a campaign should target and then
assess whether the results—opens, views, clicks, and responses—are worth reporting back to management. If
the results fail to meet the campaign’s objective, the agent could independently start again, creating a new,
more refined list of target customers based on responses to the previous campaign.
Simulations at Scale. Companies are already using LLMs as simulators of human behavior, particularly in
the form of AI-based focus groups of virtual personae to assess market fit for new products or services. (LLMs
are also being used in this way to model social systems for academic research, building on traditional agent-
based modeling methodologies.) However, these simulations still require humans to interact with the LLM to
gain relevant insights and, more importantly, they are prone to bias grounded in the LLM’s underlying training
data.
Autonomous agents may go a long way toward addressing these issues, making it possible to run simulations
at scale and for a wider range of applications. To start with, agents may generate more realistic virtual
personae by conducting primary research in the form of surveys and interviews, which would help anchor
simulations to the real characteristics of relevant user segments. More significantly, because agents
© 2024 Boston Consulting Group 3
circumvent the need for humans prompting an LLM to guide and extract insights from a simulation, it would
be possible to conduct multiple AI-enabled tests of greater complexity at lower cost and greater speed. In
other words, agents would give companies access to the valuable tool of automated, large-scale scenario
simulations.
Autonomous agents will not replace the depth and richness of in-person qualitative investigations that
companies oen use as strategic inputs. On the contrary: by enabling sophisticated simulations at low cost,
they will help businesses identify the questions or issues that call for those more laborious and expensive
market research methodologies.
How Companies Can Prepare
Autonomous agents still have limited applicability because of the risks and limitations associated with
reliability, potential for malicious use, and a greater fallout from cyberattacks. However, none of these
challenges appears to be a deal breaker. Technology companies are addressing them, and the experts we
interviewed estimate that autonomous agents will be ready to go mainstream within three to five years; some
believe that we may see reliable systems with limited autonomy before then.
The experts we interviewed estimate that autonomous agents will be ready to go
mainstream within three to five years; some believe that we may see reliable systems
with limited autonomy before then.
A three- to five-year time frame may seem like a long time for technologies to evolve, but from the perspective
of companies that need to plan and undertake extensive transformation programs, it might as well be
tomorrow. The message is clear: companies will struggle to absorb these technologies if they don’t start
preparing today. Leaders should focus on the following four actions:
Prepare your architecture for agents. Companies focused on deploying today’s LLMs will likely focus on
setting up one-way flows for LLMs to retrieve information from enterprise systems. However, in anticipation of
autonomous agents, they should also ensure that LLMs be able to both retrieve data and communicate
instructions to those systems through bidirectional APIs.
Scout and prepare to experiment. Companies should scout for new developments in autonomous agent
technology and select solutions that can be tested—even if they are still in early stages of development—to
create new sources of competitive advantage in terms of products, services, or operating model. Investment in
R&D currently underway for generative AI applications should be expanded to identify workflows suitable for
(future) end-to-end automation with autonomous agents as well.
© 2024 Boston Consulting Group 4
Stress-test your people strategy. GenAI today can support tasks in a copilot role, whereas agents will be
able to automate entire workflows. Companies should keep this future state in mind during their workforce
planning exercises and be prudent about prioritizing skill sets that are likely to stay relevant. For example,
professional services firms may encounter a future where autonomous agents commoditize seemingly
complex, multistep activities that have thus far proven resistant to automation. Such firms may need to take a
hard look at current hiring practices to ensure they are selecting for skills that can support the adoption and
expansion of automated substitutes of today’s labor-intensive workflows.
Anticipate the need for a social license. To support the widespread deployment of this technology,
securing a social license is crucial. Regulation may take some time to catch up to the technology; until then,
companies should enforce self-imposed guardrails to ensure the appropriate and safe use of this technology,
both within the organization and in customer-facing applications. While robust self-regulation can lay the
foundations of a social license, it is not a sustainable solution on its own. For that reason, companies should
also actively engage with regulators to help them cra the right approach for governing and monitoring the
use of autonomous agents and similar technologies in future.
For many executives, the rapid rise of generative AI has triggered months of exhilaration and trepidation;
adoption has felt like a necessity, but one that comes with serious risks and challenges. Yet even as they
grapple with the present, they have to focus on the future. The GenAI revolution has only just begun—and is
likely to continue at breakneck speed.
The BCG Henderson Institute is Boston Consulting Group’s strategy think tank, dedicated to exploring and
developing valuable new insights from business, technology, and science by embracing the powerful
technology of ideas. The Institute engages leaders in provocative discussion and experimentation to expand
the boundaries of business theory and practice and to translate innovative ideas from within and beyond
business. For more ideas and inspiration from the Institute, please visit our website and follow us on LinkedIn
and X (formerly Twitter).
© 2024 Boston Consulting Group 5
Authors
Mikhail Burtsev
OUTSIDE CONSULTANT
BCG X – Manhattan Beach
François Candelon
MANAGING DIRECTOR & SENIOR PARTNER; GLOBAL DIRECTOR, BCG
HENDERSON INSTITUTE
Paris
Gaurav Jha
CONSULTANT
Mumbai - Nariman Point
Daniel Sack
MANAGING DIRECTOR & PARTNER
Stockholm
Leonid Zhukov
VICE PRESIDENT - DATA SCIENCE
New York
David Zuluaga Martínez
PARTNER, BCG HENDERSON INSTITUTE AMBASSADOR
New York
ABOUT BOSTON CONSULTING GROUP
Boston Consulting Group partners with leaders in business and society to tackle their most important
challenges and capture their greatest opportunities. BCG was the pioneer in business strategy when it was
founded in 1963. Today, we work closely with clients to embrace a transformational approach aimed at
benefiting all stakeholders—empowering organizations to grow, build sustainable competitive advantage, and
drive positive societal impact.
Our diverse, global teams bring deep industry and functional expertise and a range of perspectives that
question the status quo and spark change. BCG delivers solutions through leading-edge management
consulting, technology and design, and corporate and digital ventures. We work in a uniquely collaborative
© 2024 Boston Consulting Group 6
model across the firm and throughout all levels of the client organization, fueled by the goal of helping our
clients thrive and enabling them to make the world a better place.
© Boston Consulting Group 2024. All rights reserved.
For information or permission to reprint, please contact BCG at [email protected]. To find the latest BCG
content and register to receive e-alerts on this topic or others, please visit bcg.com. Follow Boston Consulting
Group on Facebook and X (formerly Twitter).
© 2024 Boston Consulting Group 7 |
104 | bcg | how-to-attract-develop-retain-ai-talent.pdf | How to Attract, Develop, and Retain AI
Talent
MAY 16, 2023
By Vinciane Beauchene, Julie Bedard, Julie Jefson, and Nithya Vaduganathan
READING TIME: 12 MIN
The companies that capture the most value from AI follow the 10-20-70 rule: 10% of their AI effort goes to designing
algorithms, 20% to building the underlying technologies, and 70% to supporting people and adapting business
processes. To get the most from people and processes, companies need to address the following questions: (1) How do I
attract, develop, and retain data and analytics talent to build sustainable AI capabilities? (2) How do I boost adoption
of AI solutions at speed and at scale and drive real business transformation? (3) How do I rewire my organization to
unlock the full benefits of AI at scale? This article, the start of a three-part series, focuses on the first question: how to
attract, develop, and retain AI talent.
© 2024 Boston Consulting Group 1
Artificial intelligence is having a moment. The release of ChatGPT, AI-enabled Bing, and Google Bard has
electrified public debate on the radical potential of AI. To be an industry leader in five years, companies need
a clear and compelling AI talent strategy today, but many organizations are hitting a brick wall. Although
demand for AI talent is at an all-time high, supply is extremely limited. With so few skilled professionals
available, companies must find ways to stand out from the competition.
Incumbents beware: the approach to attracting, developing, and retaining AI talent is not business as usual.
Companies must offer a unique and compelling value proposition to attract—and hold onto—these highly
prized recruits. To build a first-rate AI workforce that will stick around for the long haul, companies must
anticipate what mix of AI skills (rather than jobs) is needed, understand what AI workers want and how to
attract them, invest in reskilling and advancement opportunities, and keep AI talent fully engaged.
Common Mistakes to Avoid
AI and machine learning emerged as the most in-demand skills in 2022, and jobs for data scientists more than
tripled over the past five years. Demand continues to outpace supply. Because AI employees have different job
expectations than traditional workers do, recruiting and retention efforts need to be tailored to their unique
needs.
Because AI employees have different job expectations than traditional workers do,
recruiting and retention efforts need to be tailored to their unique needs.
Consider just a few common mistakes companies make when recruiting and hiring AI talent:
• Competing head-to-head with tech companies without highlighting non-tech-related differentiators that
will entice AI hires
• Trying to recruit AI talent with the standard slow process led by generalist recruiters
• Paying premium prices for cutting-edge data scientists without considering the broader mix of skills
needed
• Onboarding AI employees without creating a community and embedding them into the organization
under AI-trained leaders
• Fiercely recruiting AI talent without providing advancement opportunities
• Overlooking reskilling opportunities within the organization
When companies make these kinds of mistakes, they not only struggle to hire the best and brightest but also
face high levels of attrition. This is a serious problem in today’s job market where as many as 40% of
© 2024 Boston Consulting Group 2
employees working in digital fields are actively job hunting, and nearly 75% expect to leave their current role in
the near future. The good news is that hiring AI talent doesn’t have to turn into a costly bidding war.
Companies must understand what motivates these highly sought-aer employees to take a job—and what it
takes for them to stick around.
Four Strategies to Recruit and Retain AI Talent
To build an AI advantage, companies need to excel in four areas: anticipate talent needs, attract best-in-class
candidates, develop talent quickly, and engage AI talent with an unmatched value proposition. (See the
exhibit.)
Anticipate
Hiring the right talent to drive an AI transformation is not as simple as luring a strong team of data scientists
and machine-learning specialists. An AI transformation requires talent with a mix of skills, including people
who can build the data infrastructure (data architects, solution architects, data engineers, and soware
engineers), employees who manage data governance (data governance analysts and data stewards), and
those who engage with the business (product owners and domain experts).
Start by developing a taxonomy of the skills you need and then figure out how best to acquire those skills. This
approach is particularly important in a tight job market where top talent is scarce. When building an AI team,
companies tend to reflexively hire people to fill predefined jobs. But businesses oen struggle to fill those
roles because AI talent is so expensive and hard to find. By focusing on the skills they need, companies can
assemble effective AI teams more quickly.
For example, a global pharma company wanted to recruit a team of four data scientists to build up its AI
capabilities, but the competition was fierce. By thinking creatively about the skills the company needed,
executives realized they could hire just one high-caliber data scientist, supported by three data analysts, which
© 2024 Boston Consulting Group 3
are much easier to source. By finding the right mix of skills, rather than filling predefined roles, the firm
quickly assembled a strong team and hit the ground running.
Companies also need to decide how to organize for AI. Most begin their AI journey in an ad hoc fashion. IT
owns the data architecture, systems, and analytics, and data capabilities are sprinkled throughout the
business, but no standardized roles or “communities of practice” are in place for sharing AI knowledge. This
type of IT-focused organization makes it difficult to share solutions across the business and fails to give AI
workers a clear path for internal advancement. As companies mature, the majority of AI talent will begin to
work together in a centralized data and analytics hub, and roles will become standardized. Eventually, AI
capabilities will be pushed back into the business while a small, centralized AI team remains in place to
govern data management, develop capabilities, and codify best practices.
Last but not least, it is critical to anticipate the effect that incoming AI talent will have on the overall
workforce. AI experts will become embedded in business processes, which means business experts will need to
gain a working knowledge of data and analytics. As AI solutions are deployed, other employees’ roles will
evolve over time, likely requiring them to acquire new skills or augment existing ones. In addition, processes
will be redesigned and operating models will need to adjust.
It is critical to anticipate the effect that incoming AI talent will have on the overall
workforce.
Attract
In the fiercely competitive AI environment, companies must think proactively about how to attract talent. Here
are some key concepts to bear in mind.
Understand what AI workers want. Our research shows that potential AI hires have different job
expectations than traditional job seekers do, and companies should tailor their employee value proposition to
meet these expectations. Two things, in particular, matter to AI employees: (1) working on exciting products,
topics, and technologies, and (2) knowing the company has a clear strategy for advancement. People involved
in the fast-growing, constantly evolving environment of AI want to work on cutting-edge projects; 44% of AI
workers ranked this as a top need (compared with just 27% of non-AI talent). When asked about deal
breakers, AI talent ranked “interesting job content” much higher than non-AI talent did. AI job candidates also
want answers to some important questions: Does the company think about data strategically? Where will I be
at this company five years down the road? Will I have advancement opportunities? To keep AI talent engaged,
companies need to articulate a detailed data strategy that highlights clear advancement opportunities.
Seek out untapped talent. It’s tempting to go aer AI talent in the usual cities—San Francisco, Seattle, New
York City, Bangalore, and London—but that guarantees you’ll be competing with all the hottest tech
companies. This is particularly problematic for nontech incumbents striving to get an AI transformation off
© 2024 Boston Consulting Group 4
the ground. By looking at secondary talent pools in other cities and countries, organizations can gain access to
extraordinary talent at more affordable rates.
Many of these hidden markets offer companies an edge because job candidates may be seeking something
unique, such as a position located in their home state or more flexible work. In addition, our survey found that
68% of digital employees are willing to work remotely for a foreign employer. This opens up new options for
hiring hard-to-find AI talent. Because visa limitations don’t apply to remote work, businesses can explore
sources of talent that previously were not attractive or feasible. Start by evaluating your competitive
advantage in various regions in terms of compensation packages, attrition rates, size, and unique value
proposition. BCG analysis shows that companies using a targeted location strategy save 7% to 10% in labor
costs.
Create the right AI talent-sourcing strategy for your maturity. Customize your talent sourcing by making
a clear-eyed assessment of your maturity. If you are new to AI, focus on recruiting an “anchor” hire; that is, a
high-caliber AI expert who acts as a magnet to attract a broader network of AI specialists and establishes a
strong starting strategy. As you scale up, elevate your approach to recruiting AI talent: leverage specialized AI
recruiters, tailor hiring processes and compensation packages to meet AI talent needs, and ensure that
leaders have complete transparency into recruiting outcomes. If you are fully mature and need to supplement
existing data and analytics teams, build talent-sensing capabilities to understand where to find specialized AI
talent and develop relationships with that talent in advance of your needs.
Tailor the recruiting process. The standard recruiting process does not work well when it comes to
attracting AI talent. The process is too slow. By the time a hiring decision is made, the AI candidate may have
taken another offer. In our survey, 66% of respondents said the number one way for an employer to stand out
when recruiting AI talent is with a “smooth, timely recruitment process.”
Digital and data experts also want to be interviewed by people who understand their value. Managers
involved in hiring should be staff who are integral to the AI mission, not only because they’re well equipped to
assess candidates’ AI skills and judge their talent, but because it sends a signal that the company is serious
about data and analytics. When managers who have little digital knowledge or expertise interview AI
candidates, it dampens the potential hires’ enthusiasm for taking the job.
We recommend reviewing each recruiting step to expedite the process, particularly minimizing the time from
final interview to offer, with the goal of following up in hours or days, not weeks. A global industrial company
began daily standups with specialty recruiters and hiring managers to coordinate quickly on the hiring
process. They prepared offer letters in parallel with final interviews, and a small, dedicated group of digital
and data experts interviewed AI talent to improve decision making and calibration across candidates.
Develop
Approximately 80% of AI talent leave companies because they either want a more interesting position or don’t
see opportunities for career advancement; however, BCG research shows that only 10% of new roles are filled
by existing staff. A clear opportunity is at hand to support more internal mobility of talent. Reskilling internal
employees offers a wealth of baked-in benefits. These workers are already committed to the organization,
grounded in the business, and embedded in the company’s ways of working—all characteristics that take a
great deal of time and effort to cultivate in new hires.
© 2024 Boston Consulting Group 5
A clear opportunity is at hand to support more internal mobility of talent. Reskilling
internal employees offers a wealth of baked-in benefits.
There’s another advantage to internal reskilling. The existing workforce can, in many cases, feel threatened by
new AI hires, particularly if they are positioned as a separate group of young, highly compensated individuals
poised to transform the organization. By offering reskilling opportunities, the business sends the message that
anyone with the right skill sets, and a desire to learn, can play an integral role in the AI transformation. Not all
jobs will lend themselves to reskilling; it’s unlikely that companies will train from within for the position of
data scientist, for example. But many less specialized positions, such as product owners, data stewards, and
domain experts, can be recruited internally. These opportunities for upward mobility, in turn, strengthen job
satisfaction and loyalty to the organization. According to research from LinkedIn, employees stay 41% longer
at companies that regularly hire from within.
For AI talent recruited externally, companies need to articulate a clear career path. When organizations try to
quickly spin up an AI team, they don’t always take the time to develop a taxonomy that allows candidates to
envision their progression within the organization. If young, ambitious AI analysts can be promoted to become
senior AI analysts but are offered no other advancement opportunities, they will begin to look elsewhere just
as they’re achieving peak productivity. In-demand recruits, such as data scientists and data analysts, also
expect to be promoted more frequently. The tech culture has instilled the expectation that digital talent will be
promoted every 12 to 18 months (as opposed to every two to three years).
Engage
For organizations that are not viewed first and foremost as tech companies or for those with a long product
development cycle (such as aerospace and defense, where security constraints exist), it can be difficult to keep
AI talent engaged. These organizations may have no trouble attracting AI talent, but employees’ enthusiasm
can wane when they realize the development of next-generation hardware or products will take five or more
years and they may not get to work in cutting-edge programming languages or platforms. In this case, it’s
important to sharpen your storytelling so that you aren’t trying to compete with the best tech companies but
instead can focus on your unique purpose and mission.
To become a purpose-driven organization, companies must answer two fundamental questions: What are our
authentic and distinctive strengths? Why do we exist beyond what we make, do, or sell? Whether you’re an up-
and-coming renewable-energy company, a 100-year-old cosmetics business, or a global tech giant, it’s essential
to convey a strong narrative about what sets your company apart. Purpose-driven organizations energize
people and keep them engaged.
The other key to keeping AI talent engaged is ensuring that they are seamlessly embedded within the
organization as a whole. Onboarding should involve much more than a swi orientation. It should be a 6- to
12-month process that provides ample opportunities for new AI hires to work on meaningful, “quick hit”
projects that have an immediate impact on the business. To make sure that top talent isn’t bogged down with
data management challenges (building the data platform, accessing data, cleaning data, and so forth),
© 2024 Boston Consulting Group 6
companies should adopt a two-speed approach. Allow a team of engineers to build digital capabilities while AI
specialists deliver high-impact AI initiatives that offer clear, compelling results for the business. The executive
team should also include data and analytics initiatives in their annual goals so that AI teams aren’t fighting
for mindshare, business sponsorship, and budget allocations.
Case Study
By implementing many of these techniques simultaneously, a leading biopharma firm quickly ramped up its
AI team. Here’s what the company did:
• Reshaped job architecture and skills taxonomy to focus on hiring for skills that were most relevant in the
market, defining roles for machine-learning engineers for the first time
• Redefined its employee value proposition and created stronger communities of practice for AI talent,
connecting AI practitioners across the R&D, commercial, and IT organizations
• Reframed the company’s talent acquisition strategy to better communicate its value proposition, created
a dedicated team of specialized AI recruiters, and changed hiring processes
In just six months, the company boosted the size of its AI drug discovery team by approximately 10%,
increased its commercial analytics organization by about 25%, and dramatically reduced its attrition rate for
data and analytics talent.
Talent scarcity is one of the main concerns for executives worldwide. To date, few companies have successfully
scaled AI, but this will change as organizations are ramping up very quickly. By embracing a smart approach
to recruiting, retaining, and engaging AI talent, companies will gain a long-term competitive advantage in a
field that is fundamentally redefining the future of business.
The authors thank the following experts for their contributions to this article: Romain Gailhac, Orsolya Kovács-
Ondrejkovic, and Anne-Françoise Ruaud.
© 2024 Boston Consulting Group 7
Authors
Vinciane Beauchene
MANAGING DIRECTOR & PARTNER
Paris
Julie Bedard
MANAGING DIRECTOR & PARTNER
Boston
Julie Jefson
MANAGING DIRECTOR & PARTNER
Chicago
Nithya Vaduganathan
MANAGING DIRECTOR & PARTNER
Boston
ABOUT BOSTON CONSULTING GROUP
Boston Consulting Group partners with leaders in business and society to tackle their most important
challenges and capture their greatest opportunities. BCG was the pioneer in business strategy when it was
founded in 1963. Today, we work closely with clients to embrace a transformational approach aimed at
benefiting all stakeholders—empowering organizations to grow, build sustainable competitive advantage, and
drive positive societal impact.
Our diverse, global teams bring deep industry and functional expertise and a range of perspectives that
question the status quo and spark change. BCG delivers solutions through leading-edge management
consulting, technology and design, and corporate and digital ventures. We work in a uniquely collaborative
model across the firm and throughout all levels of the client organization, fueled by the goal of helping our
clients thrive and enabling them to make the world a better place.
© Boston Consulting Group 2024. All rights reserved.
For information or permission to reprint, please contact BCG at [email protected]. To find the latest BCG
content and register to receive e-alerts on this topic or others, please visit bcg.com. Follow Boston Consulting
Group on Facebook and X (formerly Twitter).
© 2024 Boston Consulting Group 8 |
105 | bcg | Companies-Need-to-Leverage-Ecosystems-to-Deploy-Generative-AI.pdf | WHITE PAPER
Companies Need to
Leverage Ecosystems to
Deploy Generative AI
May 2023
By Alex Koster, Harsha Chandra Shekar and Richard Maué
Boston Consulting Group partners with leaders
in business and society to tackle their most
important challenges and capture their greatest
opportunities. BCG was the pioneer in business
strategy when it was founded in 1963. Today,
we work closely with clients to embrace a
transformational approach aimed at benefiting all
stakeholders—empowering organizations to grow,
build sustainable competitive advantage, and
drive positive societal impact.
Our diverse, global teams bring deep industry and
functional expertise and a range of perspectives
that question the status quo and spark change.
BCG delivers solutions through leading-edge
management consulting, technology and design,
and corporate and digital ventures. We work in a
uniquely collaborative model across the firm and
throughout all levels of the client organization,
fueled by the goal of helping our clients thrive and
enabling them to make the world a better place.
“
The most focused of business models…can be blown to bits by new information
technology.”1 This prediction is more relevant than ever, as many clear use cases of
Generative AI have revolutionized functions and industries. Companies are deploying
Generative AI to address specific market needs across a wide range of industries, from
Airbus using Generative AI to design aircraft parts with an estimated 40% reduction in
weight and drag, to chatbot assistants that cut customer service costs by an estimated 30%,
to stress testing proposed trading strategies.2 The latest research shows the generative AI
market is expected to hit $60 billion of the total addressable market by 20253, accounting for
10% of all data generated.4
F
ew companies, however, have yet embedded Generative AI across their full matrix
through a strategic bottom-up approach. This would require thinking exhaustively
through the outcomes and use cases, the technology and data to enable the use cases,
and the human resources required for implementation and execution. It would also require
companies that seek to leverage Generative AI to lean on an ecosystem of partners to deploy
Generative AI cohesively.
Exhibit 1 - Generative AI ecosystem view
Vertical Providing solutions that are vertically integrated
ecosystem along multiple layers of the Gen AI stack, typically
partners serving specific business/workflow functions
1. Evans, P. and Wurster, T.S. (2000). Blown to bits: how the new economics of information transforms strategy.
Boston, Mass.: Harvard Business School Press, C.
2. www.autodesk.de. (n.d.). Generatives Design bei Airbus | Kundenprojekte | Autodesk. [online] Available at:
https://www.autodesk.de/customer-stories/airbus [Accessed 2 Mar. 2023]. www.ibm.com. (n.d.). IBM Watson
Assistant - Customer Service Chatbot. [online] Available at: https://www.ibm.com/products/watson-assistant/
customer-service [Accessed 2 Mar. 2023].
3. Generative AI (2023) BCG Global. Available at: https://www.bcg.com/x/artificial-intelligence/generative-ai
(Accessed: March 17, 2023).
4. Nguyen, T., Casey, D., Goodness, E. and Woodward, A. (n.d.). Emerging Technologies and Trends Impact Radar:
2022 Research Excerpt. [online] Available at: https://artillry.co/wp-content/uploads/2022/02/Emerging-Tech-
and-Trends-2022.pdf [Accessed 2 Mar. 2023]. www.deere.com. (n.d.). Deere adds seven companies to its 2022
BOSTON CONSULTING GROUP 1
Co-innovation
partners
Regulators Industry incumbents
(Finance, Procurement, HR, …)
stripe Zurich SAP ADP
JP Morgan Chase & Co.
New GenAI Players
AI/ML Providing large foundation Open source models Eleuther Stability.ai (Text, Image, Code, Video, 3D)
model models, pre-trained with Closed source models GPT-4 Lambda KEELVAR GitHub Copilot
partners vast amounts of data
Model hubs Hugging Face Meta AI co:here HubSpot Jasper
Providing raw or labeled data suitable aws marketplace IBM Watson MidJourney
Data
partners to train and fine-tune AI models - either Quandl kaggle Metabob tabnine
in bulk or continuously via APIs
Google Data Search Socrata runway synthesia
Providing high-performance computing Nvidia CoreWeave
Technology
partners resources and storage at scale, exposed to OpenAI aws …
developers in cloud deployment models
Microsoft Azure Google Cloud
Deploying Gen AI requires partners in six major areas:
• Vertical Ecosystem Partners: Multiple layers must be put together for successful ap-
plication of Generative AI: underlying computing/hosting technologies, available training
data, well-constructed foundational models that are trained and fine-tuned for the specific
use case, and accessibility of these through either APIs or front-ends. Organizations de-
ploying AI for mature, strategic use cases should consider building up internal capabilities
to orchestrate technology, data and models, but orchestrating these layers may not always
be possible within an organization, depending on the organization’s maturity and the
specific use case. Collaboration with vertical ecosystem partners that provide end-to-end
packaged Generative AI solutions may be necessary. Standardized use cases (fields such
as workplace/collaboration, procurement, payment, customer service) are typical candi-
dates for the use of vertical ecosystem partners. This means either partnering with incum-
bents on Generative AI-powered services in finance, procurement, HR, etc., or leveraging
emerging Generative AI players with vertically integrated solutions (e.g., Jasper, GitHub
Copilot, Synthesia). Additionally, like industry-specific cloud solutions that have grown in
popularity, industry-specific generative AI solutions are likely to gain traction going forward.
• AI/ML Model Partners: For clients looking for a more out-of-the-box solution, model
partners can play a major role in reducing the heavy lifting and time-to-results. In these
cases, the heavy ML development and data collection and training are already done, and
the client needs to focus only on fine-tuning the model with enterprise domain data. Ex-
amples include the massive Foundation models of Open AI, Google’s LaMDA, or Meta AI;
open-source models like Stability.AI and GPT-neoX; accessible via model hubs like Hug-
ging Face. The choice of and collaboration with model partners must weigh the benefits
and risks of a vendor/model-specific vs. agnostic approach.
• Data Partners: A critical challenge in training Generative AI models is obtaining large
amounts of high-quality data that includes training data – depending on the use case, also
including auxiliary data such as labels, metadata, and conditioning variables. While there
are significant opportunities to train models based on available internal data, obtaining
external data can unlock specific use cases. Organizations can acquire this external data
from data marketplaces such as Kaggle, AWS Data Marketplace, or Google Dataset Search
for more broadly available data, or by building strategic partnerships with organizations
that have access to the specific data the organization needs.
• Technology Partners: Companies must make significant investments in technology
to deploy Generative AI successfully. Training Generative AI models requires superior
processing power, where cloud providers have significant scale/cost advantages. Cloud
partners also have either their own mature Generative AI offerings (Google, AWS) or close
ties to Generative AI providers (e.g., Microsoft’s share in OpenAI), allowing them to offer
added services around the bare offerings (e.g., Azure providing a private GPT environment
via APIs). Technology service partners such as managed service providers and/or software
integrators are needed to build and maintain the various data pipelines required to ingest/
extract the vast amounts of data to ensure appropriate deployment of the hardware and
software within the cloud infrastructure.
COMPANIES NEED TO LEVERAGE ECOSYSTEMS TO DEPLOY GENERATIVE AI
• Co-Innovation Partners: Working closely with co-innovation partners with shared IP
can often accelerate value creation. A diversified think tank can help unlock a plethora
of creative applications for new technologies. Through its Startup Collaborator program,
John Deere leveraged an ecosystem of several companies to co-innovate new technologies
around smart farming, including robotic harvesting and analytics for high-value crops.5
• Regulators: Participants at the World Economic Forum in Davos this year underscored
the need to regulate AI, especially in the light of the upcoming EU AI Act,6 which is ex-
pected to set the global standard for AI technologies. The European Commission’s impact
assessment on the EU AI proposal forecast a 17% overhead increase for businesses on
AI investment, while the act itself proposes significant fines for noncompliance.7 Besides
responsible AI, issues around data IP and “data-laundering” need to be managed. Compa-
nies must proactively build the right mechanisms to comply with upcoming regulations,
through a network of partners that can deliver cross-industry insight and precedent while
maintaining impartial governance. SAP, for example, has commissioned an internal AI
ethics steering committee composed of senior leaders, as well as an external AI ethics
advisory panel with “experts from academia, politics, and business whose specialisms are
at the interface between ethics and technology—AI in particular.”8
The barriers to building a digital ecosystem to effectively address
Generative AI
Companies typically face several obstacles in pulling together the ecosystem needed to truly
embed Generative AI into their business.
• Early stages
Generative AI ecosystems are still at an early stage of development, and the landscape of
players is evolving rapidly. While large players such as Google and Microsoft have made
early moves, there needs to be a lot more investment in the ecosystem before Generative
AI can be widely adopted.
Businesses want to make sure that they select the right ecosystem partners before they
commit to significant investments in adopting Generative AI. At the same time, ecosystem
participants often want to see demand before they invest in product development. This
“chicken or egg” situation can slow down value creation through ecosystem development.
• Modularity
Businesses want to build modularity into their Generative AI architecture to avoid over-
reliance on critical partners or build redundancy through a multi-partner setup. This may
not always be possible, however, due to critical partners offering unique solutions, binding
5. www.deere.com. (n.d.). Deere adds seven companies to its 2022 Startup Collaborator program. [online]
Available at: https://www.deere.com/en/news/all-news/2022-startup-collaborator-program/.
6. World Economic Forum. (n.d.). These were the biggest AI developments in 2022. Now we must decide how to
use them. [online] Available at: https://www.weforum.org/agenda/2023/01/davos23-biggest-ai-developments-
how-to-use-them/ [Accessed 2 Mar. 2023].
7. Mueller, B. (2021). How Much Will The Artificial Intelligence Act Cost Europe? [online] datainnovation.org.
Center for Data Innovation. Available at: https://www2.datainnovation.org/2021-aia-costs.pdf.
8. SAP News Center. (2018). SAP’s Guiding Principles for Artificial Intelligence. [online] Available at: https://
news.sap.com/2018/09/sap-guiding-principles-for-artificial-intelligence/.
BOSTON CONSULTING GROUP 3
contractual commitments around term and exclusivity, and sometimes even the high
costs of integration. This can be compared to the selection of cloud partners several years
ago, when specific functionalities required vendor-specific approaches, while today the
commonalities and integrability across hyperscalers shift toward agnostic approaches.
• Value creation vs. value sharing
While ecosystem functions such as data-sharing and co-innovation can create outsized
value, how the value is distributed amongst partners remains the proverbial million-dollar
question. Ecosystem orchestrators that bring the participants together often define the val-
ue sharing terms. However, uniquely valuable participants and enablers can independently
seek value-based pricing for their contributions. For instance, while Microsoft is an estab-
lished ecosystem orchestrator that is deploying Open AI’s models across its consumer and
enterprise products, Open AI is bringing the core Generative AI capability and is therefore
able to command sizable investments from Microsoft.
• Data sharing, protection, and sourcing
Data is a critical ingredient for training Generative AI tools, but companies that sit on
valuable piles of data are often either unsure of how a partner would use shared data or
concerned about giving away too much value in the absence of a clear valuation method-
ology. Value-based pricing for data is inherently hard, as companies often lack visibility into
how partners are using their data to generate value.
Serious concerns also persist about the protection of the proprietary enterprise data that
are fed into the models when used for training or prompting. Owners of the data would
need assurances that the data will stay in a “controlled” environment and will not be used
for purposes other than training or prompting the models.
On the other hand, Generative AI can present a solution to the data sharing barrier. Com-
panies that are hesitant to share proprietary data with partners can use their data to train
or fine-tune a foundation model and share only this trained model, commercializing their
proprietary data without actually sharing it.
• Accuracy and risk sharing
While Generative AI is a powerful technology that can drive significant efficiencies, in
some instances Generative AI not only fails to return results, but delivers incorrect or
biased ones. This can prove very damaging to the company or the end user. A recruitment
tool developed by Amazon, for example, posed challenges because the underlying model
was trained to vet applicants through pattern detection in hiring over the last 10 years—
which was historically skewed toward men.9 Concerns can also arise around how training
data is obtained, and whether it can be used legally for commercial purposes.10
In these cases, the question of ultimate responsibility arises: would it lie with the company
that leveraged Generative AI for a critical function, the organization that built the founda-
tional model (typically non-profits that collect training data under the “fair use policy”), or
the tech company that commercializes the model (e.g., Open AI or Google)?
9. Dastin, J. (2018). Insight - Amazon scraps secret AI recruiting tool that showed bias against women. Reuters.
[online] 11 Oct. Available at: https://www.reuters.com/article/amazon-com-jobs-automation/insight-amazon-
scraps-secret-ai-recruiting-tool-that-showed-bias-against-women-idINKCN1MK0AH?edition-redirect=in.
10. Brittain, B. (2023), OpenAI, Microsoft want court to toss lawsuit accusing them of abusing open-source code.
[online] Available at: https://www.reuters.com/legal/litigation/openai-microsoft-want-court-toss-lawsuit-
accusing-them-abusing-open-source-code-2023-01-27/
COMPANIES NEED TO LEVERAGE ECOSYSTEMS TO DEPLOY GENERATIVE AI
It can be expected that reputational risks will typically be borne by the companies that
make the ultimate use of Generative AI, while tech/model companies will likely need to
shield IP/copyright risks.
Recommendations for successfully leveraging an ecosystem of partners for
Generative AI
• Start with mapping out the entire range of use cases for Generative AI, quantify impact of
each use case, identify key dependencies and resourcing needs, and prioritize use cases
based on impact and return on investment. Identify any gaps in technology, resources, and
regulation before embarking on the Generative AI journey. Seek to “fund the journey” in
phases by reinvesting the value captured from Generative AI adoption.
• Select partners that are willing to share the upside and risks from the partnership over the
long term, as the Generative AI landscape evolves with new opportunities and challenges.
Collaborate with technology partners to make strategic choices about whether to fine-tune
existing LLMs or to train a custom model. Choose co-innovation partners whose interests
are largely aligned, and can therefore accelerate learning through transparent creation and
sharing of IP.
• Focus on value creation in initial partnerships, especially with co-innovation and data
partners where value measurement is complicated. Start with pilots/proofs of concepts to
prove and quantify value creation, align on value measurement methodology, and agree
on principles of value sharing before making extensive efforts towards negotiating value
sharing.
• Preserve agility in a quickly evolving Generative AI landscape by building modularity and
vendor independence into the partner ecosystem and reduce overreliance on specific part-
ners. This can also mitigate value gouging in future rounds of negotiations with partners.
Both technology architecture and commercial agreements should be structured to support
this modularity.
• Where privacy and data-protection issues arise with sharing data between partners, Gen-
erative AI models can be trained on partner data before being deployed in a business.
This overcomes some of the complications around actual data sharing while still capturing
many of its benefits.
• Even as the regulatory landscape on generative AI evolves, self-regulate and stay ahead
of ethical issues around use of Generative AI, as well as issues around data sharing and
“data laundering.” For businesses to mitigate risk and take greater accountability around
AI, CEOs must champion the responsible AI agenda, aligning it to the mission statement
and core values of their business. BCG’s Responsible AI (RAI) approach is designed to help
business leaders take the right measures on the governance, strategy, and culture of AI
use across their organizations.11
11. Mills, S. et al. (n.d) Deliver Powerful Business Results with Responsible AI, BCG. Available at: https://www.bcg.
com/beyond-consulting/bcg-gamma/responsible-ai (Accessed: March 17, 2023).
BOSTON CONSULTING GROUP 5
About the Authors
Alex Koster is Managing Director and Senior Partner in the Zurich office of Boston
Consulting Group. You may contact him by email at [email protected].
Harsha Chandra Shekar is a Partner and Associate Director in the Seattle office of Boston
Consulting Group. You may contact him by email at [email protected].
Richard Maué is Associate Director in the Hamburg office of BCG Platinion. You may
contact him by email at [email protected].
For Further Contact
If you would like to discuss this report, please contact the authors.
COMPANIES NEED TO LEVERAGE ECOSYSTEMS TO DEPLOY GENERATIVE AI
Add Co-Sponsor
logo here
Boston Consulting Group partners with leaders Uciam volora ditatur? Axim voloreribus moluptati
in business and society to tackle their most autet hario qui a nust faciis reperro vitatia
important challenges and capture their greatest dipsandelia sit laborum, quassitio. Itas volutem
opportunities. BCG was the pioneer in business es nulles ut faccus perchiliati doluptatur. Estiunt.
strategy when it was founded in 1963. Today, we Et eium inum et dolum et et eos ex eum harchic
help clients with total transformation—inspiring teceserrum natem in ra nis quia disimi, omnia
complex change, enabling organizations to grow, veror molorer ionsed quia ese veliquiatius
building competitive advantage, and driving sundae poreium et et illesci atibeatur aut que
bottom-line impact. consequia autas sum fugit qui aut excepudit,
omnia voloratur? Explige ndeliaectur magnam,
To succeed, organizations must blend digital and
que expedignist ex et voluptaquam, offici bernam
human capabilities. Our diverse, global teams
atqui dem vel ius nus.
bring deep industry and functional expertise
and a range of perspectives to spark change. Nem faccaborest hillamendia doluptae
BCG delivers solutions through leading-edge conseruptate inim volesequid molum quam,
management consulting along with technology conseque consedipit hillabo. Imaio evelenditium
and design, corporate and digital ventures— haribus, con reictur autemost, vendam am ellania
and business purpose. We work in a uniquely estrundem corepuda derrore mporrumquat.
collaborative model across the firm and
throughout all levels of the client organization,
generating results that allow our clients to thrive.
For information or permission to reprint, please contact BCG at [email protected].
To find the latest BCG content and register to receive e-alerts on this topic or others, please visit bcg.com.
Follow Boston Consulting Group on Facebook and Twitter.
© Boston Consulting Group 2023. All rights reserved.
05/23
bcg.com |
106 | bcg | BCG-Executive-Perspectives-Risk-and-Compliance-in-AI-EP7-25Nov2024.pdf | Executive
Perspectives
Managing Risks and
Accelerating the AI Transformation
Risk & Compliance
November 2024
In this BCG
Introduction
Executive Perspective,
We meet often with CEOs to discuss AI---a captivating and rapidly changing topic.
we articulate the vision
After working with over 1,000 clients in the past year, we are sharing our most
recent learning in a new series designed to help CEOs and the C-suite and value of risk and
navigate AI. With AI at an inflection point, the focus is on turning AI’s potential
compliance in the
into real profit.
context of the AI
In this edition, we discuss how risk and compliance can accelerate the AI revolution
transformation of any business. We take an end-to-end risk management view of
the problem, defining implications for R&C functions. Key questions to guide a
company towards success in an uncertain future business environment:
• Which risks are generated by AI and how can they be managed effectively?
• How can I leverage the power of AI to better manage the risks of my business?
.d
e
v
• How do my R&C capabilities need to evolve?
re
se
r
sth
g
• How do I get started…and how do I get this right? ir
llA
.p
u
o
rG
g
n
This document is a guide for CEOs, chief risk officers, chief compliance
itlu
s
n
o
C
officers, and business leaders facing risks, to cut through the hype around n
o
ts
o
B
AI and understand what creates value now and in the future.
y
b
4
2
0
2
©
th
g
iry
p
11 o
C
Executive summary | Managing risks and accelerating the AI
transformation
In an uncertain world, managing business requires proactively managing related risks
Risk management
AI and GenAI bring vast benefits to risk management as well as unprecedented new risks that need to be
at the core of AI managed – but with proper guardrails, the AI transformation can be accelerated
revolution In support functions, R&C has the highest adoption rate of AI/GenAI, with health care and financial
institutions the most advanced sectors
Managing risks of these technologies while adopting and embedding AI and GenAI within the organization
can unlock the potential for AI transformation:
Managing risks in
• Manage AI risks related to proficiency, reputation, security, and regulatory compliance to ensure ethical
the organization to and accountable use, increasing the AI benefits up to 3x
unlock AI value • Improving efficiency and effectiveness of risk processes, reducing human errors, synthesizing
along 3 critical unstructured information, and enabling advanced analysis – up to 40-50% gains
.d
e
dimensions • Enable risk-based decision making by balancing business with risk considerations, enabling v re
se
operational resilience and risk-based planning – up to 30pp on total shareholder return (TSR) during r sth
g
crises ir
llA
.p
u
R&C functions must prepare to support the transformation: o
rG
g
n
• Elevating R&C positioning within the AI program itlu
s
n
R&C function to get o
• Upskilling resources on data, technology, and associated risks through training with AI and GenAI C
n
o
ready for a radical ts
• Moving to scalable risk technology platforms that facilitate seamless integration of AI and third- o B
y
change in the role party data/solutions b 4
2
0
2
©
• Promoting an organizational mindset shift from low- to high-value-added activities, learning "with the
th
g
machine" to generate key insights and redefine risk management approaches iry
p
2 o
C
Risk and compliance emerges as the top support function
in AI/GenAI adoption, driving innovation across the organization
Risk and compliance is expectedtogenerate6th most …yetranksasthetopsupportfunction
valuefrom AI/GenAIamongsupportfunctions… intermsofAI/GenAI opportunity adoption
ShareofGenAIvaluecaptureacrossallfunctions1 Adoption rateofGenAIacrosssupportfunctions2
Supportfunctions
Operations 25%
Sales and marketing 19%
R&D 13%
1 Risk and compliance 13%
Customer service 9%
1 Procurement 7% 2 IT/Tech 9%
2
Finance 6%
3
3
IT/Tech 5%
Procurement 6% .d
e
v
re
se
Human resources 5%
Finance 5%
r
sth
g
Legal 5%
ir
llA
.p
6 Risk and compliance 3% Legal 4% u o rG
g
n
Supply chain 3% itlu
s
n
Human resources 3% o
C
n
o
Support functions Core functions
ts
o
B
y
b
Source: BCG Build for the Future 2024 Global Study (merged with Digital Acceleration Index (DAI)), n=1,000 4 2
0
1. On left-hand side to estimate value, survey questions cover both cost and revenue growth dimensions. Questions are (A): What % cost reduction do you expect to achieve through 2
©
AI/GenAI efficiency gains (in % of total operational expenses) in your company? (B): How much revenue growth do you expect from AI/GenAI (in % of annual revenues) in your company? th
g
(C): Thinking of AI/GenAI's contribution to revenues and costs, please specify the contribution of each of the domains below so that they sum to 100% iry
p
2. On right-hand side to calculate adoption, the number of respondents who reported adopting the opportunity is divided by the total number of respondents within each support function 33 o
C
Health care and financial institutions are the leading
sectors in adoption of R&C AI/GenAI
Healthcare/ Banking Fintech Tech components Public sector Software
insurance
e
t
Ia
Ar .d
nn e v
e
G /
I
Ao
i t p
o
d
a
22% 15% 11% 8% 8% 6% re se
r sth
g ir
llA
.p
u
o
rG
g
n
vs 13% itlu
s
n
o
C
n
AI/GenAI adoption average rate across all sectors o
ts
o
B
y
b
4
2
0
2
©
Source: BCG Build for the Future 2024 Global Study (merged with DAI), n=1,000. th
g
Note: Financial institutions include insurance, banking, and fintech. Adoption is calculated as the number of respondents who reported adopting AI/GenAI divided by iry
p
the total number of respondents within each sector 4 o
C
AI can help manage uncertainty, yet exposes organizations to new risks
• In times of uncertainty,
Uncertain outlook and Inflation or negative economic reports 70% managing risks has become a
key differentiating factor to
regulatory pressure
Diminishing consumer demand 48%
win in the market
are at the top of CEO
challenges1… Rising cost of capital / interest rates 41% • AI can be a key success
enabler in managing risks…
The presidential election in the US 41%
• …however, it also introduces
New regulations 38%
new risks, requiring proactive
management
.d
e
v
re
• CEOs should look at how to se
…and risk accelerate the AI
r
sth
g
Risks and data protection 39%
ir
llA
management is top transformation by creating the .p
u
o
priority2 when choosing Quality and performance 32% right "guardrails" – risk
rG
g
n
an AI or GenAI management should be
itlu
s
n
Cost 19% o
C
solution seen as an enabler to n
o
ts
o
unlock value, not as a B
y
b
4
2
“brake” on innovation 0
2
©
1 Source: CEO Confidence Index Jun. 2024, Chief Executive Group th
g
2 Source: BCG AI RADAR, Jan 2024; n = 1,406 in 50 markets. Survey question: What are the iry
p
most important considerations when choosing an AI and GenAI solution? 55 o
C
R&C can unlock AI's full potential across 3 critical dimensions
Enable risk-based
decision making
Transform
Application to strategic decisions,
risk processes
dynamically adapting to evolving
Manage risks, ensuring maximized
Enhancing efficiency and
AI risks economic value
effectiveness of risk processes
through AI and GenAI applications • Design of operations based on
Strong focus on mitigating AI-
"resilience" logic
.d
e
v
related risks by establishing a • 40-60% cost efficiency from a re
responsible AI (RAI) framework faster know your customer (KYC)
• Risk-based scenario planning
se
r
sth
g
process in banking
and leading risk indicators ir
llA
• Leaders in RAI also excel in
identification
.p
u
• Up to 50% time saved from o rG
business performance: realizing g
n
automated risk report generation itlu
3x benefits from AI s n
o
C
n
o
ts
o
B
y
b
4
2
0
2
©
th
g
iry
p
6 o
C
Manage AI risks
.d
e
v
re
se
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
y
b
4
2
0
2
©
th
g
iry
p
7 o
C
Manage AI risks
Adopting AI brings new risks, but R&C ensures
effective management for successful implementation
Proficiency Reputational shield Security
Systems consistently generate Systems promote fairness and Systems and sensitive data are
the intended value for users do not produce harm or offense safeguarded against bad actors
Inaccurate information and predictions Unintended bias Private data leakage
Key
System produces incorrect, irrelevant, Systems may inadvertently cater to the needs of some Systems may leak sensitive private or proprietary data
risks or incomplete responses, framed as comprehensive groups more than others
Disclosing system information
Poorcontent quality Harmful stereotypes Systems may share sensitive system details, which
System produces responses that are incoherent or Outputs reinforce historical or current harmful enable cyberattacks
lacking diversity, creativity, or rationale stereotypes
System manipulation
.d
e
v
Poor interactivity Malicious use Interactions or code injections alter the behavior of the
re
se
Rigid constraints lead to unclear, emotionally System enables bad actors, such as trolling, criminal system or increase its vulnerability
r
sth
mismatched, and scope-inappropriate responses activity, or social engineering
System disruption
g ir
llA
.p
Misaligned responses Offensive content System is vulnerable to attacks that disrupt its normal u o
rG
System misrepresents the brand or mission of the Users may trigger offensive outputs due to input error functioning
g
n
organization and drastically alters responses based on or system failure to handle idiosyncrasies of language itlu
s
user inputs n
o
C
n
o
ts
o
B
y
b
Systems must adhere to relevant legal, policy, regulatory, and ethical standards for the region, industry, and company 4
2
0
2
• Compliance considerations span the other responsible GenAI goals of security, safety, equitability, and proficiency ©
Compliance th
• Additional key regulatory considerations for GenAI systems include sustainability, transparency, and IP protection g iry
p
88 o
C
Manage AI risks
Best-in-class GenAI test and evaluation (T&E)
solutions can ensure quality and risk resilience of AI systems
Systematic risk Expertise in Scale through Building T&E
landscaping test design automation capability
Identify relevant risks and Craft representative test Scale up by using automatic Make informed decisions on
define KPIs to track progress data to challenge the system tests to enhance and validate acceptable risks and quality
e A holistic overview is GenAI testing is much more Manual testing doesn't scale. Embed manual and automated
l
a required to ensure all aspects complex than that of classic AI, Using GenAI to automatically T&E and unify insights
n
o of the system's proficiency, requiring deep GenAI and create and evaluate test across GenAI build teams to
i .d
t safety, and security are domain expertise to craft variations boosts efficiency address key risks and inform e v
a re
R thoroughly evaluated comprehensive test data and scalability key stakeholders
se
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
Addressing these key pillars helps organizations develop a best-in-class T&E process, y b
4
2
ensuring proficient, safe, and compliant GenAI 0
2
©
th
g
iry
p
99 o
C
Manage AI risks
Global authorities increase regulatory pressure on AI, introducing
comprehensive guidelines and AI-specific laws
Timeline of key regulator activity
UK Dept of
Science, Cyberspace
Innovation Admin. of
EU FTC EU and Tech EU, US EU China US EU EU EU
2018 April 2021 Nov 2022 March 2023 Feb/Apr 2023 June 2023 July 2023 Oct 2023 Mar 2024 May 2024 Aug 2024
.d
e
v
re
se
Enforcement of Pro-innovation Data Act—the right US executive order for Final version of the
r
sth
g
algorithmic policy to access and use agencies to promote guidelines on risk data ir
llA
discrimination user-generated data safe development of AI aggregation and reporting .p
u
compliance o rG
g
n
GDPR Digital Services Act and Digital NIS-2, NIST National laws on Enactment of AIA, which AI Act comes
itlu
s
n
Markets Act—rules for cybersecurity deployment and use regulates AIbased on into force o
C
n
platforms, content regulation update of foundational a”risk-based”approach o
ts
o
moderation, and antitrust law models/GenAI tools B
y
b
for digital world Dedicated 4
2
0
deep dive 2
©
th
g
iry
p
10 o
C
Manage AI risks
Deep dive: EU AI Act sets new global standard for RAI
Definition of three-tiered risk classification (unacceptable Fines for noncompliance
risk, high-risk, minimal-risk) for AI systems
4-7
%
Comprehensive set of requirements for high-risk AI
of annual
systems, including third-party audit and registration global turnover
.d
e
Additional transparency requirements for all AI Time for implementation v re
se
systems interacting with natural persons
r
sth
g
6-24
ir
llA
.p
u
o
rG
g
n
itlu
Obligation to ensure compliance dependent s
n
o
C
months n
on role (e.g., provider vs distributor) o
ts
o
B
y
b
4
2
0
2
©
th
g
iry
p
Note: BCG does not provide legal advice | Source: BCG, EU AI Act 1111 o
C
Manage AI risks
Deep dive: EU AI Act addresses both traditional and generative AI across
the entire value chain, with special requirements for systemic risk models
Preliminary
Scope Regulatory regime
"AI System"
Unacceptable
Prohibited in the EU
(EU AI Act Art. 3.1)
risk
Fixed-purpose AI system
(Traditional AI)
• Machine-based system
Mitigation measures,
High
• Varying levels of autonomy including conformity
risk
assessment, registration
• Maybe: adaptiveness after Transparency
deployment General- Conventional obligations
purpose AI GPAI1 Minimal Voluntary codes
• Infers, from the input it
risk of conduct
system
receives, how to generate
.d
e
outputs that can influence
(Generative • Notification of the EU
v re
se
physical or virtual
AI)
Systemic risk
• External risk assessment
r sth
g
environments GPAI1
• Registration in EU database
ir
llA
.p
u
o
rG
g
n
itlu
Value chain s n
o
C
n
o
ts
o
B
y
Provider Deployer Manufacturer Importer Distributor Representative b
4
2
0
2
©
th
g
1. Systemic risk GPAI models are classified as all GPAI models with more than 10^25 floating point operations (FLOPs) iry
p
Note: BCG does not provide legal advice | Source: BCG, EU AI Act 12 o
C
Manage AI risks
Deep dive: Compliance with EU AI Act requires development
of an AI inventory and (differentiated) risk mitigation measures
Risk mitigation measures, differentiated
AI inventory by AI system risk level where applicable
Registration and auditor-ready documentation Identification, mitigation, and management of AI system risks in accordance with regulatory
of all AI systems in an organization provisions and industry standards (as far as developed)
Comprehensive list of AI systems, 2a Governance
1a
acc. to EU definition
.d
e
2b Process guidelines (including templates, e.g., for documentation) v re
se
r
sth
g
1b
Assessment of risk level
2c Technical standards (e.g., for data security, cybersecurity)
ir
llA
of each AI system .p
u
o
rG
g
n
2d (Workflow) Tools itlu
s
n
o
Assessment of value chain C
n
1c
position for each AI system 2e Trainings
o ts
o B
y
b
4
2
0
2
©
th
g
iry
p
Note: BCG does not provide legal advice | Source: BCG, EU AI Act 13 o
C
Manage AI risks
Managing these risks requires a holistic RAI
program that is implemented across the enterprise
Comprehensive RAI strategy that
connects risk approach, AI Real-life application example in next slide
strategy, and purpose and values
Rigorous processes to monitor and
review products to ensure that RAI
e K criteria are met
c e
n y
a
n p
r
r
e o
Defined RAI leadership, v c
e
o
oversight committee(s), and s
G s
e
escalation pathways s
.d
e
RAI strategy v re
se
r
sth
g
ir
llA
.p
u
o
rG
g
Data and tech infrastructure, Strong understanding and n
itlu
s
including RAI-specific tools and Tech and tools adherence among all staffon their n o C
n
o
tech design patterns roles and responsibilities in ts
o
B
y
Culture
upholding RAI b
4 2
0
2
©
th
g
iry
p
14 o
C
Manage AI risks
Implement a dedicated KRI framework to evaluate compliance of
AI and GenAI use cases with internal RAI and assess associated risk levels
Real client applications
Design of an AI-specific inherent risk matrix based on Processes defined for selected KRIs to trigger a heightened
operational Key Risk Indicators (KRIs) to determine the level of scrutiny and control proactively on AI systems:
adherence of various systems to RAI principles
• Approval by committee or board of directors
• Mandatory training
RAI implementation policy • Weekly monitoring
High risk
Measurement of key metrics to evaluate use case • Remediation plan/legal opinion
risk levels against implementation guidelines
.d
e
v
re
Use case relevance se
A adss oe ps ts iom ne on rt po rf
o
t ch ee
s
sim esp aa fc fet cin
te
t de r bm
y
s
th
o ef uu ss ee r
c ase
M •e Cd oiu mm
m
r iti ts ek
e notification
r sth
g ir
llA
• Training required exclusively for new users .p
u
• Monthly monitoring with escalation if issues arise o rG
g
Minimal • Corrective actions/compliance review as needed n
Expert judgment itlu
s
risk n
Inclusion of qualitative analysis to ensure an o C
ethical and compliance risk assessment split into Low risk n o ts
2 subcategories • Automatic approval o B
y
b
• Standard reporting and monitoring 4
2
0
2
©
th
g
iry
p
1155 o
C
Manage AI risks
RAI is a value Organizations that integrate RAI practices into
enhancer and the AI product life cycle realize meaningful
market differentiator benefits
in addition to
mitigating risks % of respondents reporting business benefit
50%
48%
50
42%
40%
40
33% 3x
31%
30
19% more likely to realize
20 17%
14% 15% benefits from AI when
11% adopting a RAI approach
9% .d
10 e v
re
se
r
sth
g
0
Improved Brand Increased Improved Accelerated Better
ir
llA
.p
u
recruiting differentiation customer long-term innovation products/services o
rG
and retention retention profitability g
n
itlu
s
n
o
C
n
o
ts
o
B
y
b
Leaders in RAI Nonleaders 4 2
0
2
©
th
g
Source: Elizabeth M. Renieris, David Kiron, and Steven Mills, “To Be a Responsible AI Leader, Focus on iry
p
Being Responsible,” MIT Sloan Management Review and Boston Consulting Group, September 2022. 1166 o
C
Transform risk processes
.d
e
v
re
se
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
y
b
4
2
0
2
©
th
g
iry
p
17 o
C
Transform risk processes
How to get it right | Our perspective on winning with AI in R&C processes
• Implementing AI-driven automation to streamline R&C processes,
Using AI to reshape R&C
Reshaping to reducing manual tasks and increasing operational efficiency
processes, enhancing
drive new value • Utilizing advanced analytics to enable faster and more accurate
efficiency and effectiveness
risk assessments
• Identifying and prioritizing the best AI use cases to align with the
Transforming the risk
Choosing high- company’s strategic goals and specific risk needs
.d
value chain to gain e
v
impact use cases
competitive advantage
• T sca arg lae bti ln eg
A
c
I
r sit oi lc ua tl
i
oa nre sas in the risk value chain by integrating re se
r
sth
g
ir
llA
.p
u
o
rG
g
n
• Accelerating scalable solutions by designing the target
itlu
s
n
o
C
Unlocking Combining AI and GenAI architecture and leveraging the right ecosystem of partnerships n
o
ts
o
data and tech to maximize value creation • Unlocking data value with GenAI as the “next layer” to drive risk- B
y
b
4
based decision making and forecasting 2 0
2
©
th
g
iry
p
18 o
C
Transform risk processes
Wide range of opportunities to adopt AI/GenAI across
the whole value chain, with untapped potential in risk processes
Ease of implementation
High
(<6months)
Creditprocessoptimization,e.g. Commswriting /summarization
creditmemowriting
Logic bug/errordetection
Automated claim solution
Suspicious Activity Report filings
Unittestbuildingandautomatedtesting
Creditriskratings
Sentiment-guided
C shy ib ee ldr risk credit collection1 ( wjn ac rnlu indi gn )gearly
KYC assistant Integratedand aligned systemthat
.d
e
v
automaticallypreparesclaims
re
se
Policybot
Cyber risk identification
Anti-money-laundering
r sth
Climatea rn isd
k
monitoring Creditunderwriting
transactionmodeling
g ir
llA
assessment1 Facilitated
.p
u
o
payment
rG
Analysisofmed g n
legislationand
Accurateclaimsoutcomewithprice processing itlu
regulation R twis ink 1 digital C anre dd ri et pri os rk tim ngonitoring P dere ted cic tt fi rv ae um dodelsto t er xa pn lasp na ar te ion ncy o a f n bd enp ea ft ii te sn (t E-f Ori Ben )dly (>H 30ig %h ) s n o C n
o
ts
Low o B
(>12months,<3%) Legend for productivity gains: Adoption y b
4
2
Source: BCG Build for the Future 2024 Global Study (merged with DAI), n=1,000 Health care/ 0 2
Adoption ranges between 5-23%; deployment timelines between 5 -12 months. Bubble Banking Insurance Cross sectors ©
th
sizes are relative to each other but overall productivity gains range between 10%-38% g iry
1. Use cases added to the Global Study based on BCG's market experience Low (relatively) High Dedicated deep dive 19 p o
C
Transform risk processes
Focus on boosting efficiency of risk processes: driving cost
savings, with focus on automation of labor-intensive and repetitive tasks
Real client applications
A B C D
Policy KYC Credit risk monitoring Cyber
Dedicated Dedicated
bot deep dive assistant deep dive and reporting risk shield
• Extract new regulatory • Automate data collection, • Use natural language for • Automate code for
obligations streamlining the process data query vulnerability detection
• Evaluate impact on • Automatically produce KYC • Instantly generate data • Speed risk identification with
.d
internal policies risk assessment file visualizations and organize a virtual expert e v re
se
• Provide real-time • Prioritize actions with a early-warning alerts • Simulate “red teaming1” to
r
sth
g
compliance support risk-based approach • Reduce effort with no code model adversarial strategies
ir
llA
.p
u
needed and test scenarios o
rG
g
n
itlu
s
n
o
30-40% time saved 40-60% cost efficiency Up to 50% time saved 30-35% efficiency gains C
n
o
via quicker identification of from faster KYC processing from automated report from automated prevention2
ts
o
B
y
b
policies to update generation 4
2
0
2
©
th
g
iry
p
1. Independently simulating cyber attacks to test and improve an organization’s security defenses; 2. Up to 60-70% for most advanced use cases implemented 20 o
C
Transform risk processes
Focus on boosting effectiveness of risk processes: enabling
better decisions and quality of output to pave the way for business growth
Real client applications
E F G H
Risk Sentiment-guided Climate risk Automated claim
Dedicated
digital twin deep dive credit collection assessment solution
• Create a digital replica of • Conduct real-time analysis • Analyze exposure to • Automate claim verification
controls, processes, and IT of sentiment behind the physical and transition risks and clustering
systems tone and words chosen in • Identify options to mitigate • Detect inconsistencies to
• Run "what-if" scenarios on human interactions climate threats flag potential fraud or .d
e
v
the digital system • Provide suggestions on next- • Detect greenwashing risks errors re se
• Identify actions to reduce best actions to increase in public disclosures • Provide operational
r
sth
g
nonfinancial risks probability of recovery support for approval steps
ir
llA
.p
u
o
rG
g
n
itlu
s
n
~10x faster 6-8pp recovery Greenwashing risk +10-15% fraud detected o
C
n
o
time-to-response increase from next-best reduced on claims processing ts
o
B
to urgent requests recovery strategy y b
4
2
(including regulatory) 0 2
©
th
g
iry
p
21 o
C
Transform risk processes
Policy bot | GenAI simplifies compliance by ensuring automated update
of internal policies and enabling employees to become compliance-savvy
Efficiency: A Policy bot
Regulatory Compliance
Ever-changing
landscape update empowerment
regulatory landscape
automatically
New regulations automatically Employees and clients can search
embedded in the .d
e
scanned to identify potential impacts for policies and procedures using v re
on internal policies and procedures
organization
natural language on an AI-powered
se
r
sth
g
• Highlight a set of tasks for the
bot integrated with current platforms
ir
llA
.p
u
compliance officer to follow • Employee: Supported intelligent o
rG
g
search and co-bot assistant n
• Suggest methods to handle the itlu
s
n
o
regulatory changes • Clients: AI-driven web search and C
n
o
virtual bot (Web, SMS, Voice) ts
Update internal policies and o B
y
b
procedures automatically using GenAI 4 2
0
2
©
th
g
iry
p
22 o
C
Transform risk processes
KYC assistant | Enhance the onboarding process for new clients or suppliers by
managing 5 end-to-end KYC activities with AI and GenAI
Efficiency: B KYC assistant
Real-time dashboard (portfolio view) and dispatching
KYC assistant
CRR entry Low
Previous KYC info
Tiering med-high
Automated data collection (internal and external sources)
Related Fin.
Personal data Neg. news Customer ID
subjects Statements
KYC files tiering and anomaly detection
Other info Lists Transactions SARs KYC summary
.d
Customer e v
Interaction with customer/Web (chatbot) report PDF re se
r
sth
g
ir
llA
.p
u
Automated generation of KYC file report o rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
"KYC AI assistant" tool can be integrated 40-60% Cost efficiency from AI/GenAI y b
4
2
into clients' existing workflow tools solutions from 5 KYC activities 0 2
©
th
g
iry
p
23 o
C
Transform risk processes
Risk digital twin | Digital twin is a cutting-edge technology to
dramatically improve nonfinancial risk management (banking example)
Efficiency: E Risk digital twin
Complexity puzzle Digital twin simplifies and augments Impact
Large international banks face Digital twin supports operational resilience Digital twin delivers substantial value
high operational complexity and industrializing OpRisk management while its build is lean, low-risk, and low-cost
Typical LEs Improve risk effectiveness and resilience
~3.5k+ ~5k+ Real world Disparate, Digital twin ~2x More efficient risk identi-
fication and remediation1
business IT systems big data
processes • Complex • Virtual replication of
banking operations
• Nontransparent, siloed,
• Integrated 360° view
often manual Insights Get ahead of regulator expectations
~5k+ ~20k+
• Single source of truth
Third parties controls
• Rapidly changing and actions
~10x Faster time-to-response to
.d
e v
urgent requests2
re
se
r
sth
g
ir
llA
Selected use cases .p
u
Generate capacity and productivity o
• Back
oIm psp al ri ec a at i “o bn las
ck box”
• T rer aa ln -ts impa
e
r men oncy it:
o
3 r6 in0 g° bv yis Aua Ilization of operational landscape; near- ~15%+
Productivity in addressable
rG
g n itlu
s n
areas from industrialized o C
• C efh fea cll te ivn eg ne es
s
w sith controls
• O efp fet cim tivi ez na et sio
s
n an: A
d
u at uo tm omat ae td
io
d no ;c tu am rge en teta dt rio en
m
a en dd
ia
o tiv oe nrsight; controls
($200-350M)3 OpRisk management n o
ts o B
y
• Increased regulatory scrutiny • Prediction: Using GenAI to anticipate the impact of events b 4
2
0
2
©
th
g
1. Drivers: Faster and less resource-intense risk detection, problem discovery and remediation 2. Examples: Transparency on third-party risks or foreign data flows 3. Assuming ~5% of iry
p
noninterest expense related to controls, compliance, and related tech spend; this approach can have ~10-15% reduction on that cost base; Source: BCG analysis and case experience 2244 o
C
Enable risk-based decision
making
.d
e
v
re
se
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
y
b
4
2
0
2
©
th
g
iry
p
25 o
C
Risk-based decision making
The next frontier: enable truly risk-based strategic decisions
with future AI applications
Risk-based operational resilience Risk-based scenario planning
1 Simulate and assess multiple AI-based disruption scenarios to 1• Current scenario of uncertainty highlighted the
guide resilient decision making according to the limitations of medium- to long-term planning (example
company’s risk tolerance for geopolitical risk management)
• E.g., What is the cost of maintaining client service
2• Organizations can develop through AI multiple scenarios
continuity during business disruptions?
and calibrate dynamically each scenario’s risks/
opportunities vs the plan ambition
2 Monitor each scenario evolution to highlight
potential deviation from company risk tolerance and
3• Additionally, leading risk indicators can be defined to
identify mitigation actions
simulate impact on business portfolio in different scenarios
.d
e
• E.g., AI suggests alternatives, evaluated within the and dynamically adapt strategies and scope with disruption v re
se
company’s risk boundaries using visual dashboards r sth
g
Scenario
ir
llA
.p
u
o
New pandemic wave Prolonged war in Ukraine rG
g
n
itlu
s
n
o
C
n
o
t
c
ts
o
a B
p y
m b
4
I 2 0
2
©
th
g
iry
p
2266 o
C
Timeline of the plan
Risk-based decision making
Example for geopolitical risk| Quantify risk in portfolios with a data-driven
approach to inform strategic decisions for financial institutions
Risk-based scenario planning
Geopolitical Scenario impact Transmission to Impact quantification
scenario selection on key indicators macro/sector drivers on key risks and actions
1 2 3 4
.d
• Identification of relevant • Identification of set of key • Assessment through • Using the macro/sector drivers, e v
re
g (be ao sp eo
d
l oit nic ta hl
i
nr kis tk
a
nsc ke cn oa nr teio ns
t
i tn hedi sc ca et no ar rs
io
a f (f ee .gct .,e d by m ima pc aro cte c oo nn do rm ivi ec
r
m
s
oo fd be rl os ao df
e r
e fis nt aim nca it ae
ls
o af nim
d
p caa pct
it
o an
l, based
se
r
sth
g
and AI-driven momentum tool) commodityprices) based on economy (e.g., GDP, inflation) on credit, market, liquidity,
ir
llA
.p
historical shocks and sectors (e.g., sector gross and operational risk impact u o
• Prioritization and selection of rG
value added), which g
scenarios to be tested, • Estimate of quantitative
typically drive financials and
• Definition of mitigating n itlu
s
combining impact, acuteness, impact of scenario/sub- actions (diversification, portfolio n
o
capital impact C
and relevance of scenario scenario on each indicator rebalancing, insurance, exit …) n
o
ts
based on AI models o B
y
b
4
2
0
2
©
th
g
iry
p
27 o
C
4 steps for R&C to
Establish strong AI governance (e.g., appoint a head of AI ethics,
begin the AI journey create a dedicated committee) that actively partners with business
units to strategically prevent risks and fully unlock AI and GenAI
potential
Enhance the capabilities of the R&C team through training and
upskilling, in sync with tech platform advancements, to promote
innovation
Adapt scalable risk technology platforms for seamless integration
.d
of GenAI and AI, ready to incorporate third-party data/solutions e
v
re
se
r
sth
g
ir
llA
.p
u
o
rG
g
n
Manage the AI-driven mindset shift, transitioning from low-value itlu
s
n
activities like controls and data gathering to strategic risk analysis, o C
n
o
"learning with the machine" ts
o
B
y
b
4
Dedicated deep dive 2 0
2
©
th
g
iry
p
2288 o
C
Risk management shifts to focus on high-value-added activities
and redefine the approach to risk management
3 key impacts from AI and GenAI … requiring relevant shift to fully benefit
integration in the organization… across the R&C function
Adoption of new ways of working
Automated operational tasks
Transition from operational to high-value-added tasks,
Automation of repetitive/operational tasks, allowing
progressively evolving the risk management approach in
employees to dedicate more time to strategic activities
alignment with AI developments (i.e., learning with the machine)
.d
e
Enhanced risk prediction and mitigation
Proactive risk management v re
se
Predictive analytics via AI to anticipate upcoming risk
Anticipating and mitigating risks before they materialize, r sth
g
trends and regulator priorities
moving beyond the reactive approaches and enabling more ir
llA
robust and preemptive risk management .p
u
o
rG
g
n
itlu
s
Evolution of risk mindset n o
Holistic risk approach C
n
Unlocking an entrepreneurial mindset, leveraging the cross- o ts
Data aggregation across multiple functions to promote o
B
functional approach to act as a business enabler rather than y
a holistic approach to risk management b
4
just a control function 2 0
2
©
th
g
iry
p
2299 o
C
EMESA
BCG experts |
Key contacts
Matteo Marianna Stiene Stefan
Coppola Leoni Riemer Bochtler
for AI transformation
Anne Giovanni Kirsten Jakob
Kleppe Lucini Rulf Liss
NAMR APAC
Steve Jeanne Abhinav Nisha
Mills Bickford Bansal Bachani
.d
e
v
re
se
r
sth
g
Bernhard Paras Eric
ir
llA
Gehra Malik Kuo .p
u
o
rG
g
n
itlu
s
n
o
C
n
o
Vanessa Hanjo ts
o
B
Lyon Seibert y
b
4
2
0
2
©
th
g
iry
p
Note: EMESA: Europe, Middle East, and South America; NAMR: North America |
107 | bcg | BCG-Executive-Perspectives-Value-Creation-with-AI-EP10-17Dec2024.pdf | Executive
Perspectives
AI Unlocked: Value Creation with AI
(Including Generative AI)
Real-Life Examples of Value and Impact
December 2024
Introduction In this BCG
Executive Perspective,
We meet often with CEOs to discuss AI—a topic that is both captivating and rapidly
we showcase the immense
changing. After working with over 1,000 clients in the past year, we are sharing our most
value from AI across a variety
recent learnings in a new series designed to help CEOs navigate AI. With AI at an
of topics, with
inflection point, the focus in 2025 continues to be turning AI’s potential into real profit.
real-life case examples
This document provides a set of examples for CEOs to cut through the hype around AI
and witness the immense potential of AI to deliver real value, and the key success
factors to executing a successful AI transformation
.d
e
v
re
s
e
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
sn
o
C
n
o
tso
B
y
b
4
20
2
©
th
g
iry
1 p o
C
Three strategic plays to maximize value from AI
DEPLOY RESHAPE INVENT
Enhance efficiency with GenAI tools Elevate business impact by Develop AI-native offerings that
that streamline everyday business transforming workflows with elevate customer value proposition
processes, reducing the need for AI, enabling multi-functional and unlock new business models and
additional hires & daily operating reshaping and end-to-end revenue opportunities
friction organizational transformation
Examples Examples Examples
• Meeting summary • Design and Engineering • Hyper-personalized customer .d
e
v
re
experience s e
• Code development • Marketing r sth
g
• Calendar management • Customer Service
• AI-powered services/products
ir
llA
.p
u
o
• Data monetization across value chain rG
• Invoice reconciliation • Technology g n
itlu
• Insights and innovation platform
sn
o
C
n
o
tso
B
y
b
4
AI leaders focus on reshaping functions
20
2
©
th
g
iry
2 p o
C
What leaders do differently | Key success factors
Bold ambitions: 80% focus on reshape/invent plays, enabled by 2x investment in
AI capabilities, and 2x people in AI
Focus on both core and support: 62% of AI value potential comes from core
business functions
Investment in few high-priority opportunities: Few high-value opportunities with
2x ROI impact instead hundreds of use cases
Read our latest
.d
Faster adoption of GenAI: AI leaders leverage both predictive AI and GenAI, and e v
publication:
re
s
e
rapidly adopt the latter
r
sth
g
Where's the
ir
llA
.p
u
o
Integration of AI in transformation: 45% of leaders embed AI in cost rG
g
transformation efforts & focus more on revenue growth
Value in AI? n itlu
sn
o
C
n
o
tso
Embracing the 10-20-70: Leading companies see AI transformation as a people B y
b
4
20
transformation vs. tech-only 2
©
th
g
iry
3 p o
C
Many functions have been reshaped end-to-end with AI
Sales Customer Pricing and Revenue Marketing Manufacturing and
Service Management Supply Chain
.d
e
v
re
s
e
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
R&D Field Forces Technology Functions Business Operations
sn
o C
n
o
tso
B
y
b
4
20
2
©
Many leading organizations are driving transformative impact across multiple functions th
g
iry
4 p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Sales
Technology solutions
Logistics company CPG company provider Universal bank Telecoms provider
Enhanced RFP process Reshaped customer Augmented call center Transformed bank's Uplifted customer
with “RFP responder”, engagement and sales sales with AI, 7%+ wealth advisory and engagement and sales
AI-supported generation with AI virtual assistant, revenue growth with sales with co-pilot and with AI-enabled chatbot,
of proposals with 30% - 2x higher ROI vs. +60% productivity in pitch builder, leading to leading to
50% gain in efficiency traditional touchpoints outbound calls 5%–10% increase in +20% conversion rate for ..dd
ee
vv
AUM and 3x portfolio ~1% annual revenue rree
ss
ee
reviews uplift
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
5 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Customer service
Telecoms and media Business process
company Telecoms provider outsourcing provider Asset manager Universal bank
Augmented customer Enhanced call center Transformed call center Reshaped customer Uplifted remote
servicing with AI operations with AI, with customer support with support with a ~35% customer service with AI
solutions for call agents, 25% reduction in After AI-powered solutions for reduction in call volume for chat support,
resulting in 20% Call Work time, 15%–18% reduction in and ~20% reduction in reduced AHT by 18%
reduction in Avg. impacting 20%–25% of AHT driving up to AHT, leading to OPEX ..dd
ee
vv
Handling time (AHT) customer operations $200M savings reduction (~$500M) rree
ss
ee
cost baseline
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
6 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Pricing and revenue management
Heavy machinery Spirits and wine
Convenience chain manufacturer Fashion retailer Pharmacy chain manufacturer
Enhanced fuel pricing Deployed AI-powered AI solution for pricing Leveraged AI solutions to Augmented advertising
optimization basis pricing engine for and promotion strategy transform pricing and and promotion
unique local conditions aftermarket parts with leading to multi - promotions, resulting in effectiveness with +2%–
to see estimated uplift of +2%–3% sales and +3%– hundred million $ over $1B+ in revenue 3% FY EBIT and +20–30
20%–30% of annual 4% profit impact transformation and gross profit increase pts Advertising and ..dd
ee
vv
gross profit at full scale Promotion effectiveness rree
ss
ee
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
7 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Marketing
Financial services Gas and renewable Alcoholic beverage Consumer health Pharma and healthcare
company energy producer company company company
Reshaping search, AI-supported SEO AI-assisted E2E campaign AI solution for insight AI-augmented reshaping
creative development content generation creation, leading to and concept of content generation &
and email marketing leading to 95% cost ~80% external agency development; localization resulting in
campaigns for 30 - 40% reduction with 50x cost saving along with Productivity uplift on 50% time saved and
productivity increase faster content creation ~40% - 60%uplift in resulting in 20% savings €70M–150M reduction ..dd
ee
vv
and 10% - 20% reduction click-through rate in marketing costs in agency costs rree
ss
ee
on cost per action
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
8 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Manufacturing and supply chain
Electronics
manufacturer Biotech company Chemicals producer MedTech company BioPharma company
Successful AI pilot across 4 AI-embedded digital Cost transformation AI-assisted inventory AI-enabled digitized
use cases in transferring supply chain which program across entire reduction by $100M and supply chain to deliver
skills and experience in reshaped end-to-end value chain with AI: 8%– improved forecasting £400M value delivered
highly automated factories, operations, leading to 12% reduction in cost accuracy by 15 p.p.; with operational
reducing human ~$750M inventory with €420M value backorders reduced by excellence ..dd
ee
vv
intervention by 70-80%; reduction, ~10% savings confirmed 60% rree
ss
ee
estimated $1Bn in value at in transportation
rr
sstthh
gg
full scale in global roll out
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
9 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Field Forces
Integrated energy Infrastructure developer
Oil and gas company company HVAC solutions provider and investor
Reshaped maintenance strategy Developed AI/data-enabled Deployed AI powered product AI assisted asset maintenance
and planning optimization with inspection workflow for reshaping Maintenance, processes for front line workers;
AI, achieving 40% reduction in optimization to achieve Repair and Overhaul (MRO) productivity uplifted by 5%–
preventative maintenance, 10% 62% efficiency gain programs; witnessed 5%–10% 10%, 15%–20% decrease in job
reduction in maintenance OPEX (50% faster on-ground increase in revenue via first durations; 10%–20% ..dd
ee
vv
and 10% reliability response and 67% faster year sales improvement in rework rate rree
ss
ee
improvement reporting)
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
10 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
R&D
Pharmaceutical Biopharma and Pharma and healthcare Biopharma and
Eye care company company medtech company company healthcare company
4 AI use cases prioritized AI-powered solutions 10%–15% faster clinical AI solutions to quicken Acceleration of drug
to reshape marketing, enabled acceleration of trials with AI-based medical documents discovery through AI;
software and knowledge clinical trials by ~25% identification of high- generation, leading to 25% cycle time
search; Over $50M FTE and 5%–10% faster recruitment sites and cycle-time reduction, reduction and $25M cost
productivity gain over 5 completion of site optimization of patient 3+months drug reduction, $50M–150M ..dd
ee
vv
years activation recruitment advancement, €40M+ rev. uplift rree
ss
ee
impact
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
11 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Technology functions
Global insurer Oil and gas retailer Payments provider Universal bank
Software development IT operations Data management Software development
25% productivity gain across 30%–40% productivity ~40-70% productivity gain 70% uplift in quality software
software development life improvement for IT in processes like metadata and testing, 60% reduction in bugs
cycle; 20%–30% improvement department through AI-based lineage management for roles with AI-enabled testing co-pilot ..dd
ee
vv
rree
in software quality legacy tech modernization in data management and ss ee
governance
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
12 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Business operations
Integrated energy Global automobile
company Global insurer Universal bank manufacturer
Procurement Underwriting Loan processing Procurement
RFP assistant to save 5 hrs per Transforming underwriting with >50% FTE productivity gains with 50% faster tender drafting and
draft; reduction of 1% of AI for 2x productivity AI transformation for mortgages offer comparison; €5M–10M FTE
external spend with $80M– improvement and 10x reduction and consumer loans processing savings and €40M–80M savings
..dd
ee
vv
120M at full scale in wait time on external services rree
ss
ee
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
Value delivery Value delivery Value delivery
Select deep-dive ahead
©©
tthh
gg
on pilots on initial scope at full scale
iirryy
13 pp oo
CC
Leaders with large-scale end-to-end AI transformations
Pharma and healthcare Technology and consulting
Investment bank Consumer health company company firm
of cost base
>$1B 20%–30% ~2% >$2B
program reduction EBIT gain program
..dd
ee
vv
With AI-enabled With company-wide With E2E AI transformative To improve productivity in
rree
ss
ee
automation to achieve Enterprise AI program use cases across 3 pillars customer support, IT
rr
sstthh
gg
iirr
llllAA
enterprise-wide step (commercial, R&D, and modernization, and HR ..pp
uu
oo
rrGG
change in efficiency, scale, manufacturing and supply transformation gg
nn
iittlluu
and resilience chain) ssnn
oo
CC
nn
oo
ttssoo
BB
yy
bb
44
2200
22
©©
tthh
gg
iirryy
14 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
GenAI Co-pilot for Relationship Managers in a universal bank
Content summarization to retrieve quick
& accurate customer, product, and market insights
5%-10%
Increase in AUM
Personalized product recommendations with AI-
driven conversational assistant
Wealth
Agent orchestrator calling upon relevant "virtual
Relationship Reduction in
assistants" to perform autonomous tasks (e.g, Planner 50%
pitchbook & proposal
manager
"agent" to schedule meetings & events)
generation time
.d
e
v
re
s
e
Key unlocks to scale r sth
g
• Op model Transformation: Shifting RMs from product pushers to bionic advisors with
2-3x
More portfolio
ir
llA
.p
u
incentives realigned with GenAI products & workflows
reviews o rG
g
n
by RMs
itlu
• User-Centric Design: Embedding guided flows, smart nudges, and circuit breakers into
sn
o
C
n
o
GenAI products for behavior change and adoption tso
B
y
b
• Robust Measurement: Establishing North Star metrics, monitoring leading/lagging 4 20
2
©
indicators, and linking inputs to outcomes effectively th
g
iry
15 p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
AI solution for call agents at a business process outsourcing provider
AI solution features
A Request status H Call metadata
A B G M ~15% - Reduction in avg.
H I B Call intent I Customer data
C N 18% handling time
Supporting Pre-call
D C J
documents summary
J
QA & intent Last bills
D K
Agents reported
K L checklists information
90% improved
AI-generated Previous calls
E F E L efficiency
notes and issues
Root cause
F Manual notes M
analysis code
.d
225K+ Calls supported e v re
s
G Account lookup N Post-call summary e r
sth
g
ir
llA
.p
u
o
rG
g
n
Key unlocks to scale $200M In cost savings
itlu
sn
o
C
n
o
• Building, scaling industry-grade GenAI solutions with clear proposition for end-clients tso
B
y
b
• Link to broader transformation effort: radical triple-digit million cost out and fundamental re- 4 20
2
©
design of op model, ways of working and culture
th
g
iry
• Strong working relationship and buy-in with ExCo and broader leadership team 16 p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
AI-based pricing optimization for a convenience chain
Pricing process and E2E pricing Enhanced
operating model optimization tools capabilities
• Develop best-practice • Improve transparency of • Enable client to have full
fuel pricing process with recommendations and ownership of pricing
capability to tailor reporting optimization algorithm
20%–30%
strategies
• Evolve price optimization
• Re-define operating engine and elasticity model,
model, embedding core factoring in competitor
Estimated uplift in
capabilities response
Annual Gross Profit at
.d
e
full scale (fuel v
re
s
e
contributes >50% of
r
sth
g
gross profits)
ir
llA
.p
u
o
rG
g
n
itlu
Key unlocks to scale
sn
o
C
n
o
tso
B
y
• AI-first operating model to govern pricing, freeing capacity for strategic decisions b
4
20
2
©
• Establish in-house AI/data science capability to own and evolve system over time
th
g
iry
17 p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
AI for insights & concept development in marketing at consumer health co.
• Connect automatically between diverse, previously disparate data
Data retrieval
Faster insights to
& synthesis sources to develop real-time, actionable insights 3–5x
innovation
Concept
generation & • Generate 10+ product & comms concepts at the touch of a button
refinement
15%
FTE savings
Synthetic • Provide qualitative feedback from focus groups in <1 min
testing &
• Narrow down list of 20+ ideas to winning idea in <1 day
final validation
• Deliver quantitative panel results in mins instead of weeks
.d
e
v
Cost savings on re
40% s e
qualitative research
r
sth
g
Key unlocks to scale
ir
llA
.p
u
o
rG
• AI program integrated into cost transformation effort: value tracking, g
n
itlu
governance… sn
o
C
n
o
• Redesign of processes & op model alongside AI deployment: centralization of
30%–50%
Higher Marketing tso
B
y
activities, reorganization of teams… content ROI b 4
20
2
©
• Build of a Marketing-specific AI app factory, leveraging a low-code app-building
th
g
platform 18
iry
p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Chemical producer leveraging AI across manufacturing and supply chain
AI operator Negotiation AI Automated order Engineering AI Intelligence Supply chain
Operations & Procurement entry Engineering & platform planner
Site Service Maintenance
Customer Service Supply Chain Supply Chain
Chatbot for plant
Automate Insource and Cost-effective GenAI assistant for MS co-pilot-
maintenance &
negotiation of reduce external modeling and enhanced enabled efficiency
process control
C-level supplier spend through plant digitalization efficiency— increase through
order automation inventory & safety information
..dd
ee
stock reduction transparency vv rree
ss
ee
rr
sstthh
gg
iirr
llllAA
..pp
uu
oo
rrGG
gg
Key unlocks to scale nn
iittlluu
ssnn
oo
CC
• Lead with value at board discussions and make it tangible with firm-specific examples nn oo
ttssoo
BB
yy
• Select willing early adopter units to prove value to the wider organization bb
44
2200
22
• Substantiate the value ambitions in a short period with expert support ©©
tthh
gg
iirryy
19 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Energy company leveraging AI for end-to-end asset integrity management
Review and
Planning and prioritization Execute inspections approve reports to prioritize
repairs
Historical report Automatic defect detection Semi-automated report review
digitization and and digitization of reporting and approval
AI/GenAI
recommendation action with enhanced UI/UX
features
optimization
Clerks are 160x more Enabled inspectors to be 62% efficiency gain to overall
Impact
efficient in large-scale 10x faster documenting inspection workflow; (50%
.d
e
v
re
data ingestion to plan and annotating defects faster on-ground, 67% faster s
e
r
sth
inspections in-office reporting) g ir
llA
.p
u
o
rG
g
n
itlu
sn
Key unlocks to scale o C
n
o
tso
B
• Utilize GenAI to unlock insights from historical data for smarter inspections y b
4
20
2
• Digitize workflows to cut processing time and seamlessly integrate with ERP tools ©
th
g
iry
20 p o
C
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Global pharmaceutical leveraging AI for R&D cycle-time reduction
Hit ID Lead Optimization PCC
Current Target ID and Docking and
Analog search, order, and testing Lead
workflow validation selecting
• Screens ultra-large libraries up to • Automated lead optimization allows chemists to review 10x
100x faster more transformations in less time
• Expands amount of chemical • Possible reduction in number of molecules ordered due to
matter available to chemists broader initial coverage
• Increases Hit PoS by 5% • Decreases cycle time by ~25%, increases Hit PoS by 5%
..dd
ee
vv
Target ID and Generative AI Algorithmic multi-property
rree
ss
AI based
validation docking optimization
Lead ee rr sstthh
gg
workflow iirr
llllAA
..pp
uu
oo
rrGG
gg
Potential for ~1 year saved in drug discovery nn
iittlluu
ssnn
oo
CC
nn
oo
ttssoo
Key unlocks to scale BB
yy
bb
44
2200
22
• Show early proof of technology (MVP via impact in R&D) by bringing together deep scientific and GenAI expertise ©©
tthh
gg
• Detailed process (re)design to achieving best-in-class cycle time at scale 21
iirryy
pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
Payments provider using GenAI to strengthen data governance
Foundation build Context enrichment Insights generation
• Consistent cataloguing of • Improved enterprise and • Data discovery and
data data risk management utilization (insights for Impact
Productivity gain
business)
• Detection and mitigation • Accelerated data quality
in processes like
40-70%
of issues at root cause management
metadata and lineage
management
Initial focus Launched
Two use cases completed and deployed in production
% lead time reduction
for critical data
~50%
1 Lineage annotation 2 Metadata labeling
management
• Accelerated data lineage capture by generating initial • AI generated "first draft" of activities ..dd
ee
vv
suspected lineage and expanding code parsing metadata…
rree
ss
ee
rr
sstthh
• Speed up debugging/data quality issue resolution • …and was refined through gg iirr
llllAA
leveraging diagnostics tool human feedback Accelerated ..pp
uu
oo
5-6 yrs. rrGG
timeline to full gg
nn
iittlluu
data governance ssnn
oo
CC
nn
oo
Key unlocks to scale
ttssoo
BB
yy
bb
44
2200
• Alignment of the operating model alongside the deployment, streamlining 22 ©©
tthh
processes and integration into adjacent capabilities gg iirryy
22 pp oo
CC
Sales Cust Service Pricing & RM Marketing Manufacturing Field Forces R&D Technology Business Operations
European bank leveraging AI to transform credit processing
Context Transformation initiatives
• Unstructured information on GenAI automation: Development of DokAI to
Impact
credit worthiness support the credit process
Faster time-to-yes,
10x
• Collateral checked and • Documents automatically categorized, up to 90 % straight-
processed manually structured, and scanned through processing
• Complex processes leading to • Real-time fraud checks and
long handling times, errors, communication with customers for
costs, and low client missing documents
>50%
FTE productivity gains
satisfaction
• Escalation of tasks for manual review
..dd
ee
vv
rree
ss
ee
rr
sstthh
gg
iirr
llllAA
..pp
uu
Key unlocks to scale <12 Months payback oo rrGG
gg
nn
period iittlluu
• GenAI-powered Zero Ops: Focus on standard products, ease verification steps,
ssnn
oo CC
nn
oo
zero-base all requirements ttssoo
BB
yy
bb
•
Client-focus: Aim for superior service efficiency and reduced errors 44 2200
22
©©
tthh
Enhanced productivity leveraging automatically generated outputs gg
• iirryy
23 pp oo
CC
Only 26% of companies have managed to scale value from AI
Designing &
Activating piloting Scaling More revenue growth
Revenue 1.5x
(3 yr avg)
25% 49% 26%
Total shareholder return
1.6x Higher 3 yr TSR
(TSR)
AI leaders (26%)
Global average Higher ROIC
Returns 1.4x
(3 yr avg)
.d
e
v
re
s
e
r
sth
Innovation 1.9x More patents g ir
llA
.p
u
o
0 25 50 75 100 rG
g
n
itlu
Developing Developing Rolling out across org & driving
sn
Employee Better overall o C
strategy, defining strategy, defining 1.4x n o
satisfaction glassdoor indicator tso
value pools, value pools, P&L value capture B
y
b
creating roadmap creating roadmap 4 20
2
©
th
g
iry
Source: BCG Build for the Future 2024 Global Study (merged with DAI), n=1000 24 p o
C
NAMR
BCG Experts |
Dylan Vladimir David Amanda Matthew
Bolden Lukic Martin Luther Kropp
Key contacts
Sesh Julie Beth Djon Steve
for AI
Iyer Bedard Viner Kleine Mills
transformation
Dan Japjit Justin Michael Silvio
Martines Ghai McBride Demyttenaere Palumbo
Dustin Andy Tauseef
Burke Lin Charanya
EMESA APAC
Nicolas
Jessica Apotheker
Marc Jeff Romain de .d
e
De Bellefonds Schuuring Walters Laubier v
re
s
e
r
sth
g
Dan Andrej Marcus Julian Aparna
ir
llA
.p
Sack Levin Wittig King Kapoor u o
rG
g
n
itlu
sn
o
Robert Tristan Mikaël Le Akira Nipun C
n
Xu Mallet Mouëllic Abe Kalra o tso
B
y
b
4
20
2
Chris ©
th
Meier g
iry
25 p o
C |
108 | bcg | BCG-Executive-Perspectives-Unlocking-Impact-from-AI-Supply-Chains-EP4-7Oct2024.pdf | Executive
Perspectives
Unlocking the Value Potential
of AI and GenAI Transformation
Supply Chains
October 2024
In this BCG
Introduction
Executive Perspective,
we articulate the vision
AI holds massive value creation potential for supply chain management (SCM). But
many companies still struggle to draw value from it. In this Executive Perspective, we discuss
and value of the future
how GenAI can turbocharge the value generated by AI and can by itself bring significant new
of supply chains with
opportunities for SCM, making supply chains future-proof.
AI and GenAI
We address key GenAI-related questions for supply chains, including:
• What tangible value can GenAI deliver in SCM?
• Where and how can GenAI be applied in SCM today and in the mid term? Where to start?
• What is the longer-term, full-potential vision of GenAI in SCM?
• How can organizations align people, processes, tech, & data to effectively enable GenAI?
• What are the limitations and risks of using GenAI in supply chains?
.d
e
v
re
This document guides CEOs and supply chain leaders in navigating through GenAI's se
role, identifying real value opportunities, and preparing for the future. It outlines a
r
sth
g
holistic approach to transform your supply chain with GenAI.
ir
llA
.p
u
o
rG
g
n
Key takeaways: itlu
s
n
o
• GenAI unlocks value in supply chains by simplifying access to & step-changing adoption of AI C
n
o
ts
• It bolsters SCM digital transformations by enhancing data backbone & augmenting analytics o B
y
b
4
• It unlocks new grounds for intelligent process automation through advanced GenAI agents 2
0
2
©
• Successful GenAI implementations in SCM come with specific requirements for the people, th
g
iry
tech, and data enablers 1 p o
C
Executive summary | Supercharge your supply chain
and your competitive edge with AI
AI has significant • Predictive and prescriptive AI such as forecasting, optimization, disruption detection, and scenario simulation can generate major impacts
potential for SC, on revenue (+2-5pp), ops cost (-10-20pp), as well as cash (-15-30% inventory), and can enhance the agility and resilienceof supply chains
but execution often • But companies across sectors often fail to deliver on their goals and business cases despite large amounts invested, mainly because of poor
falls short adoption rates, misaligned processes, lack of trusted data and connectivity between SC systems
• GenAI will enhance organizations' data backbones (e.g., improving master data, capturing market data, detecting early warning signals,
GenAI can turbocharge augmenting supplier knowledge base) and bolster AI analytics (e.g., leveraging unstructured data in forecasts, embedding human knowledge
digital & AI-driven SC in algorithms)
transformation • GenAI will also ease and accelerate adoption of advanced supply chain solutions by enabling users to interface with them in natural language
(e.g., explain outputs of AI models, simply define and automatically run simulations, improve user experience)
• GenAI has the potential to profoundly automate end-to-end processes with large language model-based agents (think: smart bots)
autonomously engaging within an ecosystem of tools and stakeholders to achieve activities in a given field (e.g., sourcing planning)
GenAI itself will also
• Outsized impact will come from advanced implementation where a coalition of such autonomous agents will collaborate across processes,
bring new
taking care of several steps in the value chain, increasing efficiency and speed of execution .d
opportunities through e v
intelligent process
• T floh wis oim
f
ip nl fe om rmen at ta iot nio
.
n
G
w enill
A
e
I
n ea nb al be
l
es se a am hl ue bs s
m
G oe dn eA
l,
I
a
i cn tit ne gg r aa
s
t aio wn
i
nw di ot wh e thx ais
t
t ri en dg
i
rs ey cs tt se m wos rt ko ti om op tr ho ev re
A
u Is mer
o
e dx ep lserience by managing the internal
re
se
r
sth
automation g
• GenAI-driven automation will bolster cross-functional collaboration of the supply chain with other teams (e.g., sales, customer care,
ir
llA
innovation) as well as external partners (e.g., joint business planning/automatic synchronization with suppliers and customers) .p
u
o
rG
g
n
itlu
s
• The operating model and ways of working must be profoundly reimagined (e.g., implementing digital-native, automated processes; enabling n o
C
more centralized SC oversight and decision making; organization reskilling to foster adoption; establishing the right controls with human oversight n
o
GenAI SC ts
on the most important decisions) o
B
implementation y
b
• The data fabric must be strengthened to handle bigger volumes of higher-frequency signals, including external inputs from the market and 4
comes with specific 2 0
ecosystem partners, and curated content for consumption by agent-based systems 2
requirements
• Organizations' tech platforms must include a robust GenAI tech stack (e.g., orchestration, evaluation, guardrails, scalability), well integrated
©
th
g
iry
with/sitting on top of core systems, with appropriate controls in place p
2 o
C
AI/GenAI will help unlock massive value creation
potential for supply chains
… to drive tangible business outcomes that
Set of critical benefits… are achievable in the short- to mid-term
Revenue EBITDA Working
Less manual • Less data hunting • Dashboards enhanced
upside capital
work • Less Excel with prompts
• Less application switching • No data reconciliation
+2-5% +2-4pp 15-30%
Revenue uplift Profitability Inventory reduction
Full automation Everything that can be automated is fully automated
of simple • E.g., forecasting for >80% of SKUs
decisions • E.g., inventory target settings Service and Throughput Costs
• Admin tasks, e.g., reporting, recurring analyses satisfaction
.d
e
+5-15pp +5-10pp 10-20% v re
Augmented
Faster decision making across silos, bringing resilience
Service rate OEE uplift Reduction in manufacturing,
se
r
sth
and flexibility g
h fou rm coa mn pa lb ei xli ties
• Enhanced integration of data from suppliers to customers
w dia sr te rih bo uu tis oin ng c, oa sn tsd ir
llA
.p
u
decisions • Easy what-if scenarios, e.g., capacity setting, commercial levers o rG
• Prediction/optimization recommendations CO emissions Resilience Flexibility g n
2 itlu
s
n
o
GenAI + AI capabilities leading to best-of-both-worlds C
Reaping applications 20-50% Divide by 10 Divide by 5 n o ts
o
benefits of B
GenAI + AI • GenAI enables insight extraction from unstructured data Average near-term CO 2 Time to understand Time needed to make plan y b 4 2
combination • GenAI enables intuitive/easy interfacing with AI applications reduction upstream scenarios and and execute 0 2 ©
• Increasing AI adoption--broader user base for greater impact actions needed vs. suppliers th
g
iry
p
3 o
C
Source: BCG supply chain case experience
But many companies have yet to realize
the full benefits of supply chain technologies
Despite the range of advanced data-driven … companies have struggled to
supply chain capabilities… unlock value for common reasons
Demand Scenario Control Insufficient redesign of processes and ways of working
forecast simulation tools tower
Processes
Packaged solutions that don't fit with desired processes
Digital SC
twin
Multiple disconnected data foundations and systems of
record1
Tech and
.d
data e v
Lack of comprehensive data availability and usability re
se
RFID
r
sth
g
ir
llA
Non-intuitive tech with high skill requirements
.p
u
o
rG
g
n
Advanced
itlu
s
Change Insufficient change management and lack of n o
planning systems C
Joint Transportation Blockchain and skills understanding and trust driving adoption gap n o ts
o
B
business management y
b
4
planning systems Ambiguity in roles, skills, and KPIs of doers and 2 0
2
change agents ©
th
g
iry
p
44 o
C
1. Such as ERP, WMS, CRM, SRM, MES, etc.
GenAI directly accelerates supply chain transformations by making them
more agile, increasing adoption rates, and improving value capture
GenAI impacts supply chain Key outcomes in successful
in four main ways supply chain transformations
Enhances data backbone Agility:
E.g., cleans and augments master data such as GenAI accelerates the development of complex applications,
>30%
BOM, searches supplier knowledge base interfaces, and SC solutions by
Augments supply chain analytics User adoption:
E.g., creates features from unstructured data to GenAI-enabled supply chain increases overall user
enhance new product demand forecasting satisfaction and use of the system by >60%
.d
e v re
se
r
sth
g
Overhauls user experience Value focus: ir
llA
.p
E.g., steers advanced planning system with natural GenAI-aided processes reduce administrative and data u
o
rG
language, explains outputs of AI models reconciliation tasks by >50% g n
itlu
s
n
o
C
n
Deeply automates processes Speed: o
ts
o
B
E.g., drives workflow, navigating toward outcomes, GenAI-driven advanced analytics improve decision-making y b
4
coordinates multiple capabilities/tools speed by >30% 2 0 2
©
th
g
iry
p
5 o
C
Disruptive potential of process automation
is unlocked by GenAI in four levels
Deploy Reshape
Level 1 Level 2 Level 3 Level 4
Task-specific Process step Deep process Cross-functional
point solutions enhancements transformation process automation
Continuously verify and
Think … Deploy chatbot Scan web and report alerts Automate IBP process
update master data
Daily operational tasks Improved performance Profound transformation of Orchestrated supply chain
Description supported by vanilla and usability of processes processes powered by through consortia of increasingly
GenAI capabilities and existing tools constrained AI agents self-organizing agents
Core GenAI Core GenAI Core GenAI Core GenAI
.d
e
v
GenAI
re
se
modality
GenAI plus AI and tools GenAI plus AI and tools GenAI plus AI and tools GenAI plus AI and tools r
sth
g
employed AI agents AI agents AI agents AI agents
ir
llA
.p
u
Consortia of agents Consortia of agents Consortia of agents Consortia of agents o rG
g
n
Out-of-the-box Proven Emerging Visionary
itlu
s
n
o
Maturity
Mature plug-and-play First products released, First announcements of Precursors in research, C
n
o
solutions entering market solutions in active dev solutions, few releases R&D stage for industry ts
o
2024 B
y
b
4
2
0
2
©
Primary source of value in the next 3-5 years th
g
iry
p
6 o
C
Current solutions are not yet addressing the
Select, representative
disruptive potential within supply chains examples. Not exhaustive
Example market offerings on Example market offerings on Market outlook:
GenAI point-solutions GenAI process enhancement Trends for GenAI in SC in 2024
and beyond
Level 1 Level 2
Supports risk management
Allows usersto interact with
and optimization in Offerings emerging: Market evolving fast
Specialized SC visibility platform
combination with Dynamics 360
in natural language SC platform with increasing number of SC-specific
copilot
offerings emerging
Ensures supplier coordination
s Enables users to dig into
nr and mitigates shortages via
i ae y supplier knowledge base thanks real-time insights, risk analysis,
h ca l
p
to natural-language requests and action recommendations Bundled capabilities: SC players
y c integrating GenAI capabilities – native
l pi
f Explains demand forecast
Utilizes GenAI to automate
pi c routine decisions including bundling reduces integration overhead for
u Se
p
a Gn end
A
p
I
l ca hn an ting decisions using documentation and risk factor
organizations
.d
e
s analysis v re
se
Conducts commercial
Analyzes unstructured data
Increased sophistication: Rising level of
r
sth
g
n use ig no
g
t Aia I-t pio owns
e
ra eu
d
t so yn sto em mo susly
u qus ein stg
i
oA ng se an bt
o
t uo
t
a on rdsw ere sr
, sophistication vs 2023, but adaption or in-
ir
llA
.p
generate shipping quotes, etc. u
house development key to reaching o rG
g
Provides a platform unifying
Increases developer productivity
potential, such as Level 3 automation n itlu
industrial data and giving s n
using a GenAI-powered code o
s
r e
a nc ac te us rs a/ lin -lasi ng gh uts
a
gth
e
r ro eu qg uh
e sts assistant
C
n o ts
l Enabler dualism: SC-specific capabilities o
b B
a y b
n Enables problem solving Enables users to deploy LLMs continuing to be flanked by powerful 4 2
E 0
through oral exchanges with in other AI applications to enablers such as coding co-pilots 2 ©
conversational assistants create AI agents th
g
iry
p
7 o
C
Example | Level 3: Recent BCG project reshaped supply chain processes
with GenAI tools running complex scenarios/root-cause analysis
Context Execution Business value capture
Impact from underlying AI capability
Leading Europe-based industrial goods We interconnected two powerful BCG
company making thousands of X assets with a seamless natural >2pp
EBITDA increase year 2+
supply chain decisions daily language interface:
Impact from GenAI agent
• AgentKit: GenAI agent toolkit
Aim to supercharge existing supply
(open-sourced) 25+
chain simulation capability Planning professionals trained
• End-to-end Plan by BCG X: E2E
3x
Overarching goal to optimize supply planning suite Process cycle time reduction
.d
e
chain operations and make informed v re
se
decisions by: Live solution streamlines S&OP
r
sth
g
processes and enables supply planners
ir
llA
• Identifying bottlenecks .p u
to independently: o rG
• Testing different strategies g
n
• Running complex scenarios • Create simulation scenarios
itlu
s n
o
C
• Analyze root causes n
o
ts
o
• Summarize KPIs B
y
b
4
• Run sensitivity analyses 2 0
2
©
• Share key simulations outputs th
g
iry
p
88 o
C
Source: BCG experience
What the future
Human
IBP PREPARATION
may hold | Deep
SC actors
Procurement Supply Demand Manufacturing Logistics
Level 4 process … Specialist Planner Planner Expert Coordinator …
automation
via team of
Agent
Demand
collaborative
Supply Control tower
ecosystem agent
agent agent
agents Logistics Financial
agent review agent
Example
Advanced E2E planning
workflow vision
Meta-agent acts as
orchestration layer planning Orchestration .d e
v
Meta agent re
sub-tasks and coordinating layer se
r
sth
access to data sources g ir
llA
and tools .p
u
Data and tool o rG
g
n
landscape itlu
s
n
o
C
… ....
n
o
ts
o
B
Central y
b
Legacy database 4 2
0
ERP 2
APS Intranet ERP © th
g
iry
p
99 o
C
Whether to make or buy AI/GenAI in supply chains:
follow the adopt-adapt-assemble framework
Choose the right approach Key questions to ask
y ADOPT off-the-shelf AI/GenAI products How strategically important is this transformation?
o
Consider: Supply chain differentiation, market dynamics,
l Plug-and-play established offerings for general-
p
competitor abilities
e purpose assistance and daily business tasks
D
(e.g., ChatGPT for email drafts)
What outcomes and ROI are we seeking?
Consider: Service differentiation/customer satisfaction,
e cost sensitivity, potential for automation
ADAPT
p existing AI/GenAI tools
a
h
Tailor existing offerings to integrate organizational .d
e
s data and enhance existing workflows (e.g., custom How capable are our teams and our partners v re
e
R
GPT instances for new-hire onboarding) of undertaking this?
se
r
sth
g
Consider: Internal data science team, partner network,
ir
llA
.p
understanding of architecture, core competencies required u
o
rG
ASSEMBLE bespoke in-house g n
t
itlu
s
n applications How customized does this solution need n o
C
e n
v Build fully custom solutions for truly differentiating to be for our organization and context? o ts
o
n
capabilities (e.g., custom-trained LLM to accelerate Consider: Existing standard processes, standardized ERP,
B
y b
I 4
2
product design in R&D department) legacy practices 0 2
©
th
g
iry
p
1100 o
C
AI/GenAI-fueled transformation of supply chains
will require changes in process, people, and tech
Processes People Tech
More seamless human/machine New people structure and roles will GenAI solutions will bridge
interaction will supercharge daily need to be established, and dedicated AI disconnected system entities,
activities roles should be enabled (e.g., RAI2, CoE) integrating with existing systems
Increased accessibility of analytics When sourcing talent and tech, orgs will Tech stack will evolve to propel and
will unlock further value through need to centrally orchestrate AI capabilities safeguard GenAI solutions, building
more widespread use and workforce planning within platforms beyond AI/ML operation stacks
.d
e
v
Standardization will shift from Change management, upskilling, and Organizational SOPs, guidelines, etc., re
se
manual spot-checks and corrections targeted messaging will be required will need to be codified to instruct
r
sth
g
to central orchestration to increase adoption of new tools and guide agents
ir
llA
.p
u
o
GenAI will facilitate and require Leaders will be empowered to champion New building blocks required for
rG
g
n
changes in roles, organizational responsible AI culture and support AI GenAI-powered data mgmt., e.g., itlu
s
n
o
structure, and operating models learning, experimentation, and ethics MDM, data acquisition and curation C
n
o
ts
o
B
Organizations will need to embed AI Teams will have additional capacity Diversify beyond one model, y
b
4
governance within POM1 and apply to shift to strategic work as AI/GenAI including open-source options for 2 0
2
©
iterative development and deployment automates routine tasks competitive advantage th
g
iry
p
11 o
C
1. Platform Operating Model 2. Responsible AI
Process | AI/GenAI automation
will transform how processes are run
Illustrative
Supply issue Alternative Estimated time
Target setting Decision making
resolution identification allocation
Targets are established Future delivery disruptions Determine which parts Bad news is
60%
based on historical are phoned in by and products will be communicated
information and latest supplier/buyer teams – impacted via BOM internally, and an action
40%
plan – exchanges disruption already plan is created
Sites are informed after
between planning occurred, but impact
Current process 3 weeks of manual Communication is
system and Excel files, not yet measurable
example of impact sizing prepared for customers
plus manual plugs
supply planning
Administrative Strategic
.d
e
v
re
se
r
sth
g
Data and systems are GenAI web scanner Alternative suppliers are AI-generated
70% ir
llA
.p
examined with natural detects supplier instantly identified by assessment is shared u o
rG
language disruptions in real-time GenAI database search internally g
n
30%
itlu
GenAI supply plan Models are Automatically A scenario is prioritized s n o
C
recommendations are automatically updated generated action plans and a GenAI tool n o
Future process reviewed and validated with projected impacts are reviewed validates the
ts
o B
y
With GenAI optimization plan b 4
2
Administrative Strategic 0
2
©
th
g
iry
p
12 o
C
People | AI/GenAI automation will
transform roles across supply chains
Demand Supply Sourcing and Transport and Customer
Manufacturing
planning planning procurement logistics services
Selected example Demand Material Procurement Manufacturing Logistics Customer
personas
planner planner specialist engineer manager relations agent
• Less time in • Less research • Boosted • Reduced • Improved timing, • Increased efficacy
planning across silos productivity through reconciliation including last-mile in responding to key
IMPACT ON discussions • Sharper focus on automation across channels delivery requests
• More focus on root- critical stock issues • Improved savings • Greater • Decreased • Reduced admin
PERSONAS
cause analysis • Faster request by prioritizing key effectiveness in overhead workload
.d
e
v
re
leading to better turnaround suppliers urgent task via automation • Greater customer se
forecasts resolution satisfaction
r
sth
g
ir
llA
• Self-service for • Easy access to raw • Automated RFP • Standardized BOMs • Auto-generated • Direct access to .p u
o
automatic forecast material stocks and and contract drafts across sites and route plans from customer history
rG
g
n
GEN AI updates inflows • Instant access to products alerts and and company itlu
s
USE CASES • User-friendly APS • Decision support supplier and • AI assistant for work disruptions policies n o C
interface for shortages and contract data orders and • Automated drafting • Auto-generation n o
ts
o
disruptions maintenance and review of of customer B
y
b
logistics documents documents 4
2
0
2
©
Expected level of
Low impact High impact
th
g
impact on roles iry
p
13 o
C
Tech | Tech stacks will evolve with transformative
impact on analytics stack and user-facing layer
Typical current tech stack AI/GenAI-enabled tech stack Key takeaways
• Co-pilots and natural-language interfaces are
Smart business layer Smart business layer
transforming end-user experiences
Dashboards and Dynamic dashboards and Co-pilot solutions and • Entry barriers to complex applications (e.g.,
Decision-support systems
self-service analytics self-service analytics decision aids analytics tools, advance planning systems) are
reduced
Chatbot interfaces to
Software tools and HMI Low/no-code solutions
existing applications
• Emphasis is on versatile analytics layer (off-
the-shelf models, hybrid AI/GenAI solutions, etc.)
Analytics layer Analytics layer
GenAI orchestration brick GenAI monitoring and • For GenAI, LLM ops for continuous monitoring
Existing AI solutions
safeguarding tools and evaluation is paramount
Existing AI solutions
Orchestration and CI/CD
Orchestration and CI/CD Vendor integration
Development environment • Data layer will be enriched with bigger volumes of
Development environment
unstructured data, including external
.d
e
ML ops Model garden v
ML and LLM ops re
• GenAI tools accelerate data consistency and se
Data layer Data layer taxonomy reconciliation
r
sth
g
Repository and storage Data model and taxonomy Exchange, repository, storage Data model and taxonomy
ir
llA
• Interaction with core systems abstracted via .p
u
Data versioning tools Ingestion and distribution Data versioning tools Ingestion and distribution co-pilots and/or GenAI agents (wrappers) o rG
g
n
• GenAI tools and interfaces used as easy-access itlu
Core transaction layer ERP APS TMS Others Core transaction layer ERP APS TMS Others interfaces to legacy landscape s n o
C
n
o
Infrastructure Infrastructure ts
• Cloud resources should minimize vendor o B
y
On-prem Cloud Hybrid On-prem Cloud Hybrid TPU / GPU dependencies in a fast-changing market b
4
2
0
• It’s key to make cost-aware infra decisions based 2
Layer interfaces/capabilities
on information-security and cybersecurity needs
©
th
upgraded and impacted by GenAI g iry
p
14 o
C
Limitations and risks of AI/GenAI in supply chains
should be carefully addressed
Reliability and Fragmentation Limited AI/GenAI Data availability
Data privacy control challenges and rapid tech talent and for training
and cybersecurity at scale evolution experience AI models
• Regulations and • No standard practices • The ecosystem has • Scarce talent with • Limited supply chain
responsible AI focus can fully handle 450+ GenAI companies hands-on GenAI/LLM data for training AI
could limit use hallucinations and counting expertise due to novelty models may limit
scaling and hinder
• Proprietary transfers • Cost control • GenAI gaps for SC- • "Mainstream" data
Limitations output quality
may create vulnerabilities challenges are an issue specific players will be scientists will need
and risks
• Training with proprietary
when scaling rapidly filled growth or upskilling • This could cause .d
e
v
overdependence on re
data raises IP • Many partner choices • Internal upskilling se
infringement risk and models have no will require time and
external LLMs r sth
g
clear leaders resources
ir
llA
.p
u
o
rG
• Adopt advanced •Deploy whiteboxing •Continuously evaluate • Organize workshops, • Implement policies to g n
itlu
Example encryption and secure techniques for partners and models webinars, and ensure data source s n
o
C
mitigating
storage to protect transparency and AI to ensure alignment with certification programs transparency while
n o
sensitive information decision control organizational goals to upskill the team developing internal
ts
o
actions
and bridge the data repositories
B
y b
•Monitor agent actions 4
(non-exhaustive) 2
talent gap 0 2
closely ©
th
g
iry
p
15 o
C
Key learnings to consider within the AI/GenAI
transformation of supply chain operations
Left brain and Sequenced journey
10-20-70 paradigm
right brain from vision to scale
• Use AI and GenAI roadmap synergy • Conduct baseline assessment • GenAI value creation:
(vendor options, key partnerships) 10% algorithms/models
• Select Hybrid AI/GenAI use cases
20% tech/data .d
e
and staffing • Scope and prioritize initiatives
70% people/processes/organization
v re
se
(adopt-adapt-assemble)
r
sth
• Lower AI entry barriers with GenAI
• Rethink roles/responsibilities,
g ir
llA
• Define roadmap, lighthouse to .p
• Streamline the workflows for buy-in talent strategy, and acquisition u o rG
scale up including people/data/
g
n
(e.g., chatbot)
tech enablers • Org change with use cases:
itlu
s
n
o
C
• Establish Integrated value tracking address concerns, embed in n o
• Build MVPs to show value
ts
o
and improvements
processes, upskill users/owners B
y
b
quickly and scale fast 4
2
0
2
©
th
g
iry
p
16 o
C
Concrete actions | What it takes to be successful
in AI/GenAI supply chain transformations
Use a people-first lens: At every turn, consider end-users to drive adoption
and generate impact
Think big: Be bold in your supply chain aspirations by targeting high-impact
transformations and ROI
Get the basics right: Address data and tech foundations from the start
Partner effectively: Establish early, tight collaboration between business and
AI/tech/data experts .d
e
v
re
se
Manage change intentionally: Bring people along as you rethink processes
r
sth
g
ir
llA
and ways of working .p
u
o
rG
g
n
itlu
s
n
o
C
Start by shaping a prioritized SC transformation n
o
ts
o
B
journey to be delivered in incremental steps y
b
4
2
0
2
©
th
g
iry
p
1177 o
C
BCG experts |
Key contacts
for GenAI in Dustin Burke Olivier Bouffault Dan Sack Tristan Mallet
Managing Director Managing Director Managing Director Managing Director
and Senior Partner and Senior Partner and Partner and Partner
supply chains
Chicago Paris Stockholm Paris
Abhijeet Shetty Paari Rajendran Markus Weidmann Kosuke Uchida
Managing Director Managing Director Managing Director Managing Director
and Partner and Partner and Partner and Senior Partner
.d
e
v
re
Miami San Francisco Munich Nagoya se
r
sth
g
ir
llA
.p
u
o
rG
g
n
itlu
s
n
o
C
n
o
ts
o
B
Camille Engel Stefan Gstettner Gregor Jossé Ashish Pathak y
b
4
2
Managing Director Partner and Director Principal Data OPS Offer Director - 0
2
©
and Partner Frankfurt Scientist Supply Chain th
g
New Jersey Munich Gurugram iry
p
1188 o
C |
Subsets and Splits