Skip to content
AI Systems Handbook
Listening
Your library
Switch books
AI Systems Handbook
Listening now
Senior Engineering Interview Handbook
Listen
Solo Founder Product Engineering Handbook
Listen
Production Data Systems Handbook
Listen
Cybersecurity Engineering Handbook
Listen
The Rust Engineering Handbook
Open book
Performance Engineering and System Design Handbook
Listen
The Change Interface
Listen
CISSP Certification Guide
Open book
Project Management Mastery
Listen
Chapter
Preparing audio…
Read chapter
15s
30s
0:00
Choose Play when you are ready.
Text
Spoken text
Previous
Next
Playback speed
0.85×
1×
1.15×
1.25×
1.5×
2×
Sleep timer
Sleep
End of chapter
15 min
30 min
45 min
60 min
+5
Copy link
Volume
Spoken text is preparing…
Space
Play or pause
← →
Skip 15s / 30s
P N
Previous / next chapter
T
Spoken text
/
Search the text
M
Mute
0:00
/
0:00
Spoken text
Chapters
Follow spoken text
01
What AI Is, and What AI Systems Are
16:04
02
How Machines Learn from Data
18:10
03
Prediction, Classification, Ranking, Recommendation, and Forecasting
19:32
04
Generative AI, LLMs, and Multimodal Models
19:49
05
Agents, Tools, and Autonomy
18:24
06
Why AI Fails
16:48
07
The AI Appropriateness Question
15:23
08
From Vague Idea to Testable Use Case
14:37
09
Risk Triage Before Building
17:01
10
Business Case, Cost, and Value Realization
16:37
11
Data Readiness and Rights Readiness
17:24
12
Data as Product, Evidence, and Liability
18:36
13
Model Selection: Rules, Classical ML, Deep Learning, Foundation Models, and Hybrids
15:45
14
Training, Fine-Tuning, Prompting, and Retrieval
18:17
15
Model Documentation and Release Discipline
18:26
16
The AI Lifecycle: From Idea to Retirement
15:25
17
AI Product Requirements
11:54
18
Human-Centered AI Design
13:53
19
Human Oversight, Escalation, and Accountability
14:39
20
Architecture Patterns for AI Systems
18:36
21
Retrieval-Augmented Generation Systems
19:54
22
Guardrails, Policies, and Control Layers
17:21
23
Security Architecture for AI Applications
18:07
24
Privacy, Confidentiality, and Data Protection by Design
16:24
25
Evaluation Mindset: From Demo to Evidence
18:28
26
Metrics for Predictive Models
14:26
27
Evaluating Generative AI
15:40
28
Evaluating RAG and Knowledge Systems
14:59
29
Evaluating Agents and Tool-Using Systems
12:48
30
Robustness, Fairness, Bias, and Segment Performance
13:55
31
Red Teaming, Adversarial Testing, and Abuse Cases
14:30
32
Online Experiments, Pilots, Shadow Mode, and Launch Decisions
12:47
33
MLOps and LLMOps Foundations
15:42
34
Observability, Monitoring, and Drift
19:14
35
Incident Response for AI Systems
17:25
36
Change Management and Continuous Improvement
13:35
37
Reliability, Resilience, and Fallback Design
12:21
38
Cost, Latency, and Performance Engineering
12:38
39
Decommissioning and End-of-Life
14:01
40
Governance as an Operating System
18:37
41
Accountability, Transparency, and Explainability
13:05
42
Fairness, Harm, and Impact Assessment
14:56
43
Regulatory and Policy Landscape
16:18
44
Third Parties, Vendors, and Foundation Model Providers
16:54
45
Intellectual Property, Content, and Provenance
14:00
46
Environmental and Societal Considerations
13:21
47
Building an AI Operating Model
13:23
48
AI Portfolio Management
12:51
49
AI Literacy, Training, and Change Management
12:47
50
Culture: Skepticism, Evidence, and Responsible Velocity
13:08
