What do you think?
Rate this book
HBR's 10 Must Reads on AI
The next generation of AI is here—use it to lead your business forward. If you read nothing else on artificial intelligence and machine learning, read these 10 articles. We've combed through hundreds of Harvard Business Review articles and selected the most important ones to help you understand the future direction of AI, bring your AI initiatives to scale, and use AI to transform your organization. This book will inspire you This collection of articles includes "Competing in the Age of AI," by Marco Iansiti and Karim R. Lakhani; "How to Win with Machine Learning," by Ajay Agrawal, Joshua Gans, and Avi Goldfarb; "Developing a Digital Mindset," by Tsedal Neeley and Paul Leonardi; "Learning to Work with Intelligent Machines," by Matt Beane; "Getting AI to Scale," by Tim Fountaine, Brian McCarthy, and Tamim Saleh; "Why You Aren't Getting More from Your Marketing AI," by Eva Ascarza, Michael Ross, and Bruce G. S. Hardie; "The Pitfalls of Pricing Algorithms," by Marco Bertini and Oded Koenigsberg; "A Smarter Strategy for Using Robots," by Ben Armstrong and Julie Shah; "Why You Need an AI Ethics Committee," by Reid Blackman; "Robots Need Us More Than We Need Them," by H. James Wilson and Paul R. Daugherty; "Stop Tinkering with AI," by Thomas H. Davenport and Nitin Mittal; and "ChatGPT Is a Tipping Point for AI," by Ethan Mollick. HBR's 10 Must Reads paperback series is the definitive collection of books for new and experienced leaders alike. Leaders looking for the inspiration that big ideas provide, both to accelerate their own growth and that of their companies, should look no further. HBR's 10 Must Reads series focuses on the core topics that every ambitious manager needs to leadership, strategy, change, managing people, and managing yourself. Harvard Business Review has sorted through hundreds of articles and selected only the most essential reading on each topic. Each title includes timeless advice that will be relevant regardless of an ever‐changing business environment.
176 pages, Paperback
Published September 5, 2023
121 people are currently reading
148 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 15 of 15 reviews
March 24, 2024
This is a compilation of 12 articles: competing in the age of AI, how to win with machine learning, developing a digital mindset, learning to work with intelligent machines, getting AI to scale, why you aren’t getting more from your marketing AI, the pitfalls of pricing algorithms, a smarter strategy for using robots, why you need an AI ethics committee, robots need us more than we need them, stop tinkering with AI, chatGPT is a tipping point for AI. The main takeaways for me are:
In AI an early mover can build a scale based competitive advantage if feedback loops are fast and performance quality is clear. Late movers can carve its own space in the market by: identifying and securing alternative data sources (instead of trying to find untapped sources of training data you can look for new sources of feedback data that enables faster learning than what incumbents are using), differentiate the prediction (even only for some customers). Latecomers can still catch up with AI/ machine learning if they can find sources of superior training data or feedback data or if they tailor their predictions to a specific niche. If the gathering of such data becomes too expensive another opportunity lies in how fast are your feedback loops.
Roadmap for developing digital mindsets in existing talent pool:
When implementing radical change, managers must carefully weigh 2 key dimensions: buy in (the degree to which people believe that the change will produce benefits for them and the organization) and the capacity to learn (the extent to which people are confident that they can gain sufficient literacy to pass muster). The highest level of adoption occurs when employees are motivated to develop competence because they fully buy in in the transformation strategy and feel capable of helping making it reality. To help engage people, who don’t see the value in digital competencies, leaders must increase messaging that stresses digital transformation as a critical frontier of the company. They should launch an internal marketing campaign to help employees imagine the potential of a company, powered by digital technology. Managers should encourage their team members to view themselves as important contributors to the digital organization. Afterwards managers should promote confidence of team members, by sharing stories (learning of the experiences of peers and managers) and encouragement.
The elements of a successful employee training program:
1. Set a company wide goal for training.
2. Design learning opportunities that include all functional roles.
3. Prioritize virtual delivery, making learning scalable and accessible to everyone.
4. Motivate people to learn through campaigns, awards and incentives.
5. Make sure managers understand the offerings so they can effectively guide and inspire employees.
6. Encourage employees to participate in projects with digital components and hands on learning opportunities.
There are 4 classes of behaviour shadow learners exhibit: seeking struggle, tapping frontline know-how, redesigning roles, and curating solutions. To take advantage of these lessons, should ensure that learners get opportunities to struggle near the edge of their capacity in real, not simulated work so they can make and recover from mistakes.
What to do in order to get AI to scale:
1. Set the strategy - target areas of the business where AI will make a big difference in a reasonable amount of time (too wide of scope: the work in 1 domain should be completed in 3 or 4 waves of work over 12-15 months, there shouldn’t be more than 12 leaders with different goals on what should happen next and you should have 1 clear business owner with accountability; too narrowly: you are solving a niche challenge while leaving the root causes of problems untouched or not taking into account interrelated processes, the business leader in the target area doesn’t feel ownership because the project won’t move the needle and you haven’t involved leaders from across specific value chain - you’ve created a solution that doesn’t integrate with other up/downstream processes). The chosen domains should be large enough to significantly improve either the company’s bottom line, or customer or employee experiences.
2. Structure the team. Identify an internal business champion, responsible for the entire value chain involved, dedicated senior business staff (to fill the roles of product owner responsible for solution delivery), translator (who bridges the analytics and business realms), and change lead (responsible for change management efforts), a team of AI practitioners (data science, engineers, designers, business analysts, SCRUM master), a cluster of frontline users or knowledge workers, responsible for day to day activities.
3. Reimagine business as usual - reinvent business models, roles, responsibilities, operational processes, using new ways of thinking and working. Typically companies are best served by applying first principles or design thinking techniques and working backward from a key goal or challenge (eg what 5star customer experience would look like and then exploring granular detail how they can achieve it).
4. Adapt for organizational and technological change.
Usually people aren’t getting more from their marketing AI due to 3 reasons: they don’t ask the right questions and direct AI to solve the wrong problem, they don’t recognize the difference between the value of being right and the costs of being wrong, and assume that all prediction mistakes are equivalent, they don’t leverage AI’s ability to make far more frequent and granular decisions and keep following their old practices. To help solve this, ask 3 questions:
1. What is the (marketing) problem that we are trying to solve? The question has to be meaningful and precise, you should get to the atomic level - the most granular level at which it’s possible to make a decision or undertake an intervention. Eg rather than asking who is most likely to leave, they should’ve asked who is best to persuade to stay (which customers considering jumping ship would be most likely to respond to a promotion; instead of increasing player’s engagement should have asked how to increase their in-game spending). Instead of “How can we best spend our budget for retention promotions to reduce churn?” to “Given a budget of X mln $, which customers should we target with a retention campaign?”.
2. Is there any waste or missed opportunity in our current approach? Reflect on what constitutes success and failure. Eg success at atomic level - targeting only customers with high churn risk, who were persuadable and not targeting those, who were not. Airlines and hotels often measure spills (lost trading days on which flights or hotels filled too quickly - results of pricing too low) and spoils (empty seats or rooms - often results of pricing too high).
3. What is causing the waste and missed opportunities?
Asymmetry - failure to recognize the difference between the value of being right and the costs of being wrong . A bad forecast can be super expensive in some cases and others - not so much (waste and missed opportunity). Once you have a clear map that links the AI prediction with the decision and the business outcome, you need to quantify the potential cost of errors in the system, that entails asking “How much are we deviating from the business results we want, given that the AI’s output isn’t completely accurate?”.
Aggregation - failure to leverage granular predictions. Conduct 2 analysis: 1) examine how you could eliminate waste and missed opportunities trough other (marketing) actions that might result from the predictions generated, and 2) quantify the potential gains of making AI predictions more frequently, more granular, or both.
Alignment - the goal is to map the connections between AI predictions, decisions, and business outcomes. The team should answer the questions: In an ideal world what knowledge would you have that fully eliminate waste and missed opportunities? Is your current prediction a good proxy for that? Does the output of your AI fully align with the business objective?
In AI an early mover can build a scale based competitive advantage if feedback loops are fast and performance quality is clear. Late movers can carve its own space in the market by: identifying and securing alternative data sources (instead of trying to find untapped sources of training data you can look for new sources of feedback data that enables faster learning than what incumbents are using), differentiate the prediction (even only for some customers). Latecomers can still catch up with AI/ machine learning if they can find sources of superior training data or feedback data or if they tailor their predictions to a specific niche. If the gathering of such data becomes too expensive another opportunity lies in how fast are your feedback loops.
Roadmap for developing digital mindsets in existing talent pool:
When implementing radical change, managers must carefully weigh 2 key dimensions: buy in (the degree to which people believe that the change will produce benefits for them and the organization) and the capacity to learn (the extent to which people are confident that they can gain sufficient literacy to pass muster). The highest level of adoption occurs when employees are motivated to develop competence because they fully buy in in the transformation strategy and feel capable of helping making it reality. To help engage people, who don’t see the value in digital competencies, leaders must increase messaging that stresses digital transformation as a critical frontier of the company. They should launch an internal marketing campaign to help employees imagine the potential of a company, powered by digital technology. Managers should encourage their team members to view themselves as important contributors to the digital organization. Afterwards managers should promote confidence of team members, by sharing stories (learning of the experiences of peers and managers) and encouragement.
The elements of a successful employee training program:
1. Set a company wide goal for training.
2. Design learning opportunities that include all functional roles.
3. Prioritize virtual delivery, making learning scalable and accessible to everyone.
4. Motivate people to learn through campaigns, awards and incentives.
5. Make sure managers understand the offerings so they can effectively guide and inspire employees.
6. Encourage employees to participate in projects with digital components and hands on learning opportunities.
There are 4 classes of behaviour shadow learners exhibit: seeking struggle, tapping frontline know-how, redesigning roles, and curating solutions. To take advantage of these lessons, should ensure that learners get opportunities to struggle near the edge of their capacity in real, not simulated work so they can make and recover from mistakes.
What to do in order to get AI to scale:
1. Set the strategy - target areas of the business where AI will make a big difference in a reasonable amount of time (too wide of scope: the work in 1 domain should be completed in 3 or 4 waves of work over 12-15 months, there shouldn’t be more than 12 leaders with different goals on what should happen next and you should have 1 clear business owner with accountability; too narrowly: you are solving a niche challenge while leaving the root causes of problems untouched or not taking into account interrelated processes, the business leader in the target area doesn’t feel ownership because the project won’t move the needle and you haven’t involved leaders from across specific value chain - you’ve created a solution that doesn’t integrate with other up/downstream processes). The chosen domains should be large enough to significantly improve either the company’s bottom line, or customer or employee experiences.
2. Structure the team. Identify an internal business champion, responsible for the entire value chain involved, dedicated senior business staff (to fill the roles of product owner responsible for solution delivery), translator (who bridges the analytics and business realms), and change lead (responsible for change management efforts), a team of AI practitioners (data science, engineers, designers, business analysts, SCRUM master), a cluster of frontline users or knowledge workers, responsible for day to day activities.
3. Reimagine business as usual - reinvent business models, roles, responsibilities, operational processes, using new ways of thinking and working. Typically companies are best served by applying first principles or design thinking techniques and working backward from a key goal or challenge (eg what 5star customer experience would look like and then exploring granular detail how they can achieve it).
4. Adapt for organizational and technological change.
Usually people aren’t getting more from their marketing AI due to 3 reasons: they don’t ask the right questions and direct AI to solve the wrong problem, they don’t recognize the difference between the value of being right and the costs of being wrong, and assume that all prediction mistakes are equivalent, they don’t leverage AI’s ability to make far more frequent and granular decisions and keep following their old practices. To help solve this, ask 3 questions:
1. What is the (marketing) problem that we are trying to solve? The question has to be meaningful and precise, you should get to the atomic level - the most granular level at which it’s possible to make a decision or undertake an intervention. Eg rather than asking who is most likely to leave, they should’ve asked who is best to persuade to stay (which customers considering jumping ship would be most likely to respond to a promotion; instead of increasing player’s engagement should have asked how to increase their in-game spending). Instead of “How can we best spend our budget for retention promotions to reduce churn?” to “Given a budget of X mln $, which customers should we target with a retention campaign?”.
2. Is there any waste or missed opportunity in our current approach? Reflect on what constitutes success and failure. Eg success at atomic level - targeting only customers with high churn risk, who were persuadable and not targeting those, who were not. Airlines and hotels often measure spills (lost trading days on which flights or hotels filled too quickly - results of pricing too low) and spoils (empty seats or rooms - often results of pricing too high).
3. What is causing the waste and missed opportunities?
Asymmetry - failure to recognize the difference between the value of being right and the costs of being wrong . A bad forecast can be super expensive in some cases and others - not so much (waste and missed opportunity). Once you have a clear map that links the AI prediction with the decision and the business outcome, you need to quantify the potential cost of errors in the system, that entails asking “How much are we deviating from the business results we want, given that the AI’s output isn’t completely accurate?”.
Aggregation - failure to leverage granular predictions. Conduct 2 analysis: 1) examine how you could eliminate waste and missed opportunities trough other (marketing) actions that might result from the predictions generated, and 2) quantify the potential gains of making AI predictions more frequently, more granular, or both.
Alignment - the goal is to map the connections between AI predictions, decisions, and business outcomes. The team should answer the questions: In an ideal world what knowledge would you have that fully eliminate waste and missed opportunities? Is your current prediction a good proxy for that? Does the output of your AI fully align with the business objective?
January 26, 2024
Its a collection of articles on AI and Machine Learning from HBR. The articles are quite dated and I could not find any new information in this book. However, if you are not working in the field of IT already, these may provide some good information on what's going on in the world with GenAI and likes.
August 21, 2025
My main takeaways were the need for a growth mindset but also a human focused mindset as we approach AI. There is amazing opportunity with AI, but also serious concerns that need to be accounted for. How do we approach the future of new employee training and general learning. AI can help us all be better at what we do, but it could also end up a race to the middle. Even more than other technology changes, purposeful deployment will be critical.
November 26, 2023
this had insightful and interesting articles in it! that being said, for something published in september of this year, it had many articles that were a few years old. in the fast moving world of AI, this makes these articles out of date. giving this a 3 for that reason
January 30, 2024
This collection of articles is a little outdated and I find some of them more interesting than others. Some of them are also ripetitive. But overall it’s a great introduction to on several aspects of the introduction of AI in the economy, industry and our everyday life.
July 11, 2024
Interesting cases and discussion of AI. Mostly focused on machine learning and neural networks. Only briefly touching on large language models. A reasonable non-technical primer on some uses for AI in business.
December 8, 2023
Not a bad read but it’s a lot more evident that it’s just magazine articles pulled into a book than I was expecting. What I mean by that is that each article has very little depth or substance.
Read
January 4, 2024A bit shallow but good to start thinking about AI
January 29, 2024
informative
Great read to get a broad understanding of where AI is today and how companies are implementing it. Sparked a lot of ideas
Great read to get a broad understanding of where AI is today and how companies are implementing it. Sparked a lot of ideas
March 5, 2024
Very good book that I listened on Storytel.
Thanks HBR for the clear and crisp thoughts
Thanks HBR for the clear and crisp thoughts
May 18, 2024
This book was pretty good but it wasn’t quite what I hoped it would be. Quite a few good articles on good ways to implement AI and things to consider while doing it.
February 7, 2025
Solid overview of AI and how it’ll continue to impact our lives. Some of the articles did feel repetitive after a while, but overall the main themes stick.
March 19, 2025
As of early 2025, most of the articles presented in this compilation are not dated. Still, as a data scientist, I didn't get much out of them. I learned a couple new ideas and a different way of thinking about how AI teams should direct their efforts within an organization, but I was largely disappointed with this offering.
June 23, 2025
Interesting. Not a single word on the environmental toll of AI. A full star deducted for such an omission.
March 31, 2025
Very timely
I trust Harvard Business Review, so I appreciated this set of narrated articles on artificial intelligence. I found it put a lot in context for me in terms of how businesses have been using AI until now, how that is impacting entire business models, how the latest developments with ChatGPT fit in, and what might be in store. For leaders, there are specific strategies laid out. Definitely worth a listen.
I listened to the Audible audiobook.
I trust Harvard Business Review, so I appreciated this set of narrated articles on artificial intelligence. I found it put a lot in context for me in terms of how businesses have been using AI until now, how that is impacting entire business models, how the latest developments with ChatGPT fit in, and what might be in store. For leaders, there are specific strategies laid out. Definitely worth a listen.
I listened to the Audible audiobook.
Displaying 1 - 15 of 15 reviews