Product managers working with artificial intelligence will be able to put their knowledge to work with this practical guide to applied AI. This book covers everything you need to know to drive product development and growth in the AI industry. From understanding AI and machine learning to developing and launching AI products, it provides the strategies, techniques, and tools you need to succeed.
The first part of the book focuses on establishing a foundation of the concepts most relevant to maintaining AI pipelines. The next part focuses on building an AI-native product, and the final part guides you in integrating AI into existing products.
You’ll learn about the types of AI, how to integrate AI into a product or business, and the infrastructure to support the exhaustive and ambitious endeavor of creating AI products or integrating AI into existing products. You’ll gain practical knowledge of managing AI product development processes, evaluating and optimizing AI models, and navigating complex ethical and legal considerations associated with AI products. With the help of real-world examples and case studies, you’ll stay ahead of the curve in the rapidly evolving field of AI and ML.
By the end of this book, you’ll have understood how to navigate the world of AI from a product perspective.
What you will learn
Build AI products for the future using minimal resources
Identify opportunities where AI can be leveraged to meet business needs
Collaborate with cross-functional teams to develop and deploy AI products
Analyze the benefits and costs of developing products using ML and DL
Explore the role of ethics and responsibility in dealing with sensitive data
Understand performance and efficacy across verticals
Who this book is for
This book is for product managers and other professionals interested in incorporating AI into their products. Foundational knowledge of AI is expected. If you understand the importance of AI as the rising fourth industrial revolution, this book will help you surf the tidal wave of digital transformation and change across industries.
Author(s): Irene Bratsis
Publisher: Packt
Year: 2023
Language: English
Pages: 250
Cover
Title Page
Copyright and Credits
Dedication
Contributors
Table of Contents
Preface
Part 1 – Lay of the Land – Terms, Infrastructure, Types of AI, and Products Done Well
Chapter 1: Understanding the Infrastructure and Tools for Building AI Products
Definitions – what is and is not AI
ML versus DL – understanding the difference
ML
DL
Learning types in ML
Supervised learning
Unsupervised learning
Semi-supervised learning
Reinforcement learning
The order – what is the optimal flow and where does every part of the process live?
Step 1 – Data availability and centralization
Step 2 – Continuous maintenance
Database
Data warehouse
Data lake (and lakehouse)
Data pipelines
Managing projects – IaaS
Deployment strategies – what do we do with these outputs?
Shadow deployment strategy
A/B testing model deployment strategy
Canary deployment strategy
Succeeding in AI – how well-managed AI companies do infrastructure right
The promise of AI – where is AI taking us?
Summary
Additional resources
References
Chapter 2: Model Development and Maintenance for AI Products
Understanding the stages of NPD
Step 1 – Discovery
Step 2 – Define
Step 3 – Design
Step 4 – Implementation
Step 5 – Marketing
Step 6 – Training
Step 7 – Launch
Model types – from linear regression to neural networks
Training – when is a model ready for market?
Deployment – what happens after the workstation?
Testing and troubleshooting
Refreshing – the ethics of how often we update our models
Summary
Additional resources
References
Chapter 3: Machine Learning and Deep Learning Deep Dive
The old – exploring ML
The new – exploring DL
Invisible influences
A brief history of DL
Types of neural networks
Emerging technologies – ancillary and related tech
Explainability – optimizing for ethics, caveats, and responsibility
Accuracy – optimizing for success
Summary
References
Chapter 4: Commercializing AI Products
The professionals – examples of B2B products done right
The artists – examples of B2C products done right
The pioneers – examples of blue ocean products
The rebels – examples of red ocean products
The GOAT – examples of differentiated disruptive and dominant strategy products
The dominant strategy
The disruptive strategy
The differentiated strategy
Summary
References
Chapter 5: AI Transformation and Its Impact on Product Management
Money and value – how AI could revolutionize our economic systems
Goods and services – growth in commercial MVPs
Government and autonomy – how AI will shape our borders and freedom
Sickness and health – the benefits of AI and nanotech across healthcare
Basic needs – AI for Good
Summary
Additional resources
References
Part 2 – Building an AI-Native Product
Chapter 6: Understanding the AI-Native Product
Stages of AI product development
Phase 1 – Ideation
Phase 2 – Data management
Phase 3 – Research and development
Phase 4 – Deployment
AI/ML product dream team
AI PM
AI/ML/data strategists
Data engineer
Data analyst
Data scientist
ML engineer
Frontend/backend/full stack engineers
UX designers/researchers
Customer success
Marketing/sales/go-to-market team
Investing in your tech stack
Productizing AI-powered outputs – how AI product management is different
AI customization
Selling AI – product management as a higher octave of sales
Summary
References
Chapter 7: Productizing the ML Service
Understanding the differences between AI and traditional software products
How are they similar?
How are they different?
B2B versus B2C – productizing business models
Domain knowledge – understanding the needs of your market
Experimentation – discover the needs of your collective
Consistency and AIOps/MLOps – reliance and trust
Performance evaluation – testing, retraining, and hyperparameter tuning
Feedback loop – relationship building
Summary
References
Chapter 8: Customization for Verticals, Customers, and Peer Groups
Domains – orienting AI toward specific areas
Understanding your market
Understanding how your product design will serve your market
Building your AI product strategy
Verticals – examination into four areas (FinTech, healthcare, consumer goods, and cybersecurity)
FinTech
Healthcare
Cybersecurity
Anomaly detection and user and entity behavior analytics
Value metrics – evaluating performance across verticals and peer groups
Objectives and key results
Key performance indicators
Thought leadership – learning from peer groups
Summary
References
Chapter 9: Macro and Micro AI for Your Product
Macro AI – Foundations and umbrellas
ML
Robotics
Expert systems
Fuzzy logic/fuzzy matching
Micro AI – Feature level
ML (traditional/DL/computer vision/NLP)
Robotics
Expert systems
Fuzzy logic/fuzzy matching
Successes – Examples that inspire
Lensa
PeriGen
Challenges – Common pitfalls
Ethics
Performance
Safety
Summary
References
Chapter 10: Benchmarking Performance, Growth Hacking, and Cost
Value metrics – a guide to north star metrics, KPIs and OKRs
North star metrics
KPIs and other metrics
OKRs and product strategy
Hacking – product-led growth
The tech stack – early signals
Customer Data Platforms (CDPs)
Customer Engagement Platforms (CEPs)
Product analytics tools
A/B testing tools
Data warehouses
Business Intelligence (BI) tools
Growth-hacking tools
Managing costs and pricing – AI is expensive
Summary
References
Part 3 – Integrating AI into Existing Non-AI Products
Chapter 11: The Rising Tide of AI
Evolve or die – when change is the only constant
The fourth industrial revolution – hospitals used to use candles
Working with a consultant
Working with a third party
The first hire
The first AI team
No-code tools
Fear is not the answer – there is more to gain than lose (or spend)
Anticipating potential risks
Summary
Chapter 12: Trends and Insights across Industry
Highest growth areas – Forrester, Gartner, and McKinsey research
Embedded AI – applied and integrated use cases
Ethical AI – responsibility and privacy
Creative AI – generative and immersive applications
Autonomous AI development – TuringBots
Trends in AI adoption – let the data speak for itself
General trends
Embedded AI – applied and integrated use cases
Ethical AI – responsibility and privacy
Creative AI – generative and immersive applications
Autonomous AI development – TuringBots
Low-hanging fruit – quickest wins for AI enablement
Summary
References
Chapter 13: Evolving Products into AI Products
Venn diagram – what’s possible and what’s probable
List 1 – value
List 2 – scope
List 3 – reach
Data is king – the bloodstream of the company
Preparation and research
Quality partnership
Benchmarking
The data team
Defining success
Competition – love your enemies
Product strategy – building a blueprint that works for everyone
Product strategy
Red flags and green flags – what to look for and watch out for
Red flags
Green flags
Summary
Additional resources
