AI-Powered Products
☰
Contents
Table of Contents
Overview
Detailed
Front Matter
FM
Introduction: Defining the Journey from AI Assistant to AI Engine
Part I: Why AI Changes Product Creation
Ch 01
The New Economics of Building with AI
Ch 02
What AI Can and Cannot Reliably Do
Ch 03
The Human-AI Product Stack
Ch 04
Scientific and Philosophical Principles
Part II: AI-Native Product Discovery and Design
Ch 05
Finding Problems Worth Solving with AI
Ch 06
AI Product Strategy and Portfolio Thinking
Ch 07
AI-Native Product Discovery
Ch 08
Designing AI User Experiences
Ch 09
Requirements for Probabilistic Products
Part III: Vibe-Coding and AI-Native Prototyping
Ch 10
What Vibe-Coding Is Really For
Ch 11
AI-Native Prototyping Workflow
Ch 12
Prompting, Context, Memory, and Reusable Skills
Ch 13
Multi-Agent and Tool-Based Build Flows
Ch 14
From Prototype to Reviewable System
Part IV: Engineering AI Products
Ch 15
Reference Architectures for AI Products
Ch 16
Models, Routing, and Capability Allocation
Ch 17
Retrieval and Knowledge Systems
Ch 18
State, Memory, and Workflow Orchestration
Ch 19
Building with Protocols and Interoperability
Ch 20
Security, Privacy, and Abuse Resistance
Part V: Evaluation, Reliability, and Governance
Ch 21
Evals as the Core Development Discipline
Ch 22
Observability, Debugging, and Failure Analysis
Ch 23
Reliability, Guardrails, and Recovery
Ch 24
Cost, Latency, and Unit Economics
Ch 25
Governance, Compliance, and Trustworthy AI
Part VI: Shipping, Scaling, and Operating the Product
Ch 26
Launching AI Features and Products
Ch 27
Post-Launch Learning Loops
Ch 28
Team Topologies and AI-Native Operating Models
Ch 29
Building the AI Product Organization
Ch 30
Strategic Positioning and Future-Proofing
Part VII: End-to-End Practice and Teaching Kit
Ch 31
End-to-End Capstone Playbook
Ch 32
Case Studies in Full
Ch 33
Teaching the Material as a Course
Appendices
A
Glossary
B
Tool Comparison Matrices
C
Templates
D
Evaluation Rubrics
E
Architecture Checklists
F
Prompts and Skills Examples
G
Executable Product Artifacts
H
AI Product Anti-Patterns
I
Economics of the AI Product Loop
Back Matter
BM
Conclusion: Your AI Product Mastery Roadmap
Front Matter
FM
Introduction: Defining the Journey from AI Assistant to AI Engine
Part I: Why AI Changes Product Creation
Ch 01
The New Economics of Building with AI
1.1 The 50x Cost Reduction
·
1.2 AI as Compression of Artifact Creation
·
1.3 Build/Buy/Bake Decisions
·
1.4 The New Economics Summary
·
1.5 Lab: Calculate Your AI Economics
Ch 02
What AI Can and Cannot Reliably Do
2.1 Capabilities vs. Limitations
·
2.2 Hallucination Mitigation Strategies
·
2.3 Knowing When AI Is Unreliable
·
2.4 Designing for AI Failure
Ch 03
The Human-AI Product Stack
3.1 Human-AI Interaction Patterns
·
3.2 Feedback Loops and Continuous Learning
·
3.3 Anti-Patterns in Human-AI Collaboration
Ch 04
Scientific and Philosophical Principles
4.1 Cognitive Load Theory for AI Products
·
4.2 Complementary Change Theory
·
4.3 Ethics and Responsible AI Product Development
·
4.4 The Four Questions Framework
·
4.5 Lab: Apply the Four Questions
·
4.6 Part I Summary
Part II: AI-Native Product Discovery and Design
Ch 05
Finding Problems Worth Solving with AI
5.1 User Research for AI Products
·
5.2 Identifying AI-Appropriate Problems
·
5.3 Problem Prioritization Frameworks
·
5.4 Case Study: From Problem to AI Solution
·
5.5 Lab: Find Your AI Problem Space
Ch 06
AI Product Strategy and Portfolio Thinking
6.1 AI Product Taxonomy
·
6.2 Build/Buy/Bake Framework
·
6.3 Value Proposition Design for AI
·
6.4 Portfolio Thinking and Roadmapping
Ch 07
AI-Native Product Discovery
7.1 Discovery Methods for AI
·
7.2 Rapid Prototyping with AI
·
7.3 Testing AI Product Hypotheses
·
7.4 From Hypothesis to Validation
·
7.5 Lab: Run an AI Discovery Sprint
Ch 08
Designing AI User Experiences
8.1 UX Patterns for AI Products
·
8.2 Trust Design and Calibration
·
8.3 Expectation Management
·
8.4 Handling Uncertainty in UI
·
8.5 Lab: Design an AI Trust Experience
Ch 09
Requirements for Probabilistic Products
9.1 USID.O Framework
·
9.2 Eval-First PRDs
·
9.3 LLM-as-Judge for Requirements
·
9.4 Lab: Write an Eval-First PRD
Part III: Vibe-Coding and AI-Native Prototyping
Ch 10
What Vibe-Coding Is Really For
10.1 Discovery Tool, Not Just Implementation
·
10.2 When to Use Vibe Coding
·
10.3 Limits of Vibe Coding
·
10.4 Lab: Run a Vibe Coding Discovery Session
Ch 11
AI-Native Prototyping Workflow
11.1 From Idea to Prototype
·
11.2 Iteration Patterns
·
11.3 Evaluating Prototypes
Ch 12
Prompting, Context, Memory, and Reusable Skills
12.1 Advanced Prompting Techniques
·
12.2 Context Management
·
12.3 Building Reusable Skills
Ch 13
Multi-Agent and Tool-Based Build Flows
13.1 Multi-Agent Orchestration
·
13.2 MCP Connectors
·
13.3 Lab: Build a Multi-Agent Prototype
Ch 14
From Prototype to Reviewable System
14.1 Transitioning to Production-Ready Code
·
14.2 Code Review for AI-Generated Code
·
14.3 Testing AI Features
·
14.4 Lab: Refactor Prototype to Production
Part IV: Engineering AI Products
Ch 15
Reference Architectures for AI Products
15.1 Architecture Spectrum
·
15.2 Copilot Architecture
·
15.3 Agentic Architecture
·
15.4 Multi-Agent Systems
·
15.5 Lab: Choose Your Architecture
Ch 16
Models, Routing, and Capability Allocation
16.1 Router Strategies
·
16.2 Model Selection
·
16.3 Cost-Performance Optimization
·
16.4 Fallback Strategies
·
16.5 Lab: Implement Model Routing
Ch 17
Retrieval and Knowledge Systems
17.1 Vector Databases
·
17.2 Graph RAG
·
17.3 Self-Correcting RAG
·
17.4 Hybrid Search
·
17.5 Lab: Build a RAG System
Ch 18
State, Memory, and Workflow Orchestration
18.1 Memory Patterns
·
18.2 Conversation Context Management
·
18.3 Orchestration Frameworks
·
18.4 Workflow Design Patterns
·
18.5 Lab: Implement Stateful Workflow
Ch 19
Building with Protocols and Interoperability
19.1 Model Context Protocol (MCP)
·
19.2 Agent-to-Agent Protocol (A2A)
·
19.3 Building MCP Servers
·
19.4 Interoperability Patterns
·
19.5 Lab: Build an MCP Server
Ch 20
Security, Privacy, and Abuse Resistance
20.1 Prompt Injection Defense
·
20.2 Data Privacy in AI Products
·
20.3 Adversarial Robustness
·
20.4 Rate Limiting and Abuse Detection
·
20.5 Lab: Security Audit Your AI Product
Part V: Evaluation, Reliability, and Governance
Ch 21
Evals as the Core Development Discipline
21.1 LLM-as-Judge
·
21.2 Building Eval Pipelines
·
21.3 Eval-Driven Development
·
21.4 Eval Metrics Selection
·
21.5 Lab: Build Your First Eval
Ch 22
Observability, Debugging, and Failure Analysis
22.1 Tracing AI Systems
·
22.2 Debugging AI Failures
·
22.3 Root Cause Analysis
·
22.4 Lab: Set Up Observability
Ch 23
Reliability, Guardrails, and Recovery
23.1 Circuit Breakers
·
23.2 Graceful Degradation
·
23.3 Guardrails and Content Filtering
·
23.4 Lab: Implement Guardrails
Ch 24
Cost, Latency, and Unit Economics
24.1 Cost Optimization Strategies
·
24.2 Latency Management
·
24.3 Unit Economics Modeling
·
24.4 Lab: Analyze Your Unit Economics
Ch 25
Governance, Compliance, and Trustworthy AI
25.1 NIST AI RMF
·
25.2 ISO 42001
·
25.3 EU AI Act Compliance
·
25.4 Lab: Conduct a Compliance Audit
Part VI: Shipping, Scaling, and Operating the Product
Ch 26
Launching AI Features and Products
26.1 GTM Strategies for AI
·
26.2 Pricing Models
·
26.3 Onboarding and Education
Ch 27
Post-Launch Learning Loops
27.1 User Feedback Integration
·
27.2 Continuous Improvement Pipelines
·
27.3 Model Retraining Strategies
·
27.4 A/B Testing AI Features
·
27.5 Lab: Build a Learning Loop
Ch 28
Team Topologies and AI-Native Operating Models
28.1 Cross-Functional AI Teams
·
28.2 AI-First Culture
·
28.3 Roles and Responsibilities
·
28.4 Case Study: Spotify's AI Organization
·
28.5 Lab: Design Your AI Team Topology
Ch 29
Building the AI Product Organization
29.1 Organizational Structures
·
29.2 Career Paths for AI Product Roles
·
29.3 Hiring AI Talent
·
29.4 Lab: Create an AI Product Role
Ch 30
Strategic Positioning and Future-Proofing
30.1 Competitive Positioning
·
30.2 2026+ Trend Analysis
·
30.3 Building Defensibility
·
30.4 Lab: Conduct a Strategic Review
Part VII: End-to-End Practice and Teaching Kit
Ch 31
End-to-End Capstone Playbook
31.1 Complete Workflow Overview
·
31.2 Discovery Phase
·
31.3 Design Phase
·
31.4 Development Phase
·
31.5 Launch Phase
·
31.6 Capstone Project Guidelines
Ch 32
Case Studies in Full
32.1 Case Study: AI Coding Assistant
·
32.2 Case Study: AI Customer Service
·
32.3 Case Study: AI Content Platform
·
32.4 Case Study: AI Data Analysis Tool
·
32.5 Lab: Analyze Your Own Case
Ch 33
Teaching the Material as a Course
33.1 Course Design Principles
·
33.2 Curriculum Structure
·
33.3 Hands-On Exercises
·
33.4 Assessment Strategies
·
33.5 Adapting for Different Audiences
Appendices
A
Glossary
B
Tool Comparison Matrices
C
Templates
D
Evaluation Rubrics
E
Architecture Checklists
F
Prompts and Skills Examples
G
Executable Product Artifacts
H
AI Product Anti-Patterns
I
Economics of the AI Product Loop
Back Matter
BM
Conclusion: Your AI Product Mastery Roadmap