The books behind the questions

The correct answer to every question rests on a specific chapter of one of these books. After the quiz, the review shows which chapter to read for each mistake. Below, for every book, are the sections it relates to and the chapter numbers.

Core books

AI Agents in Depth: Design Principles and Engineering Practice

Bojie Li · 2026 · topics: 8

Sections and chapters49

Prompt structure and message rolessec. 2.4.2 · sec. 2.4.3 · sec. 2.4.6
System prompt and instructionssec. 2.3.1 · sec. 2.3.2 · sec. 2.4 · sec. 2.4.1 · sec. 2.4.4 · sec. 2.4.7 · sec. 2.5.1
Examples and few-shotsec. 2.4.5 · sec. 2.5.2 · sec. 2.7.2
Stable prefix and cachingsec. 2.3 · sec. 2.3.2 · sec. 2.3.3 · sec. 2.6.4
Context compression and isolationsec. 2.6.4 · sec. 2.7.1 · sec. 2.7.2 · sec. 2.7.3 · sec. 2.7.5 · sec. 2.7.6
Model behavior: tokens, temperature, hallucinationssec. 2.3 · sec. 2.6.1
Document chunking and embeddingssec. 3.2.1 · sec. 3.2.2 · sec. 3.3.5
Hybrid search and rerankingsec. 3.2.3 · sec. 3.2.4 · sec. 3.3.3
Agentic RAGsec. 3.3.4 · sec. 3.3.4–3.3.5
Knowledge graphs and GraphRAGsec. 3.3.1
Organizing and updating knowledgesec. 3.3 · sec. 3.3.2 · sec. 3.3.3 · sec. 3.3.6
Long-term agent memorysec. 3.1 · sec. 3.1, 3.1.2 · sec. 3.1.1, 3.3.5 · sec. 3.1.5 · sec. 3.1.7 · sec. 3.1.8 · sec. 3.3.5
The agent loopsec. 1.1.5 · sec. 2.2.1 · sec. 2.2.3 · sec. 2.2.4 · sec. 2.2.5 · sec. 2.6.1–2.6.2 · sec. 2.6.2
Tool designsec. 1.2.2 · sec. 4.1, table 4-1 · sec. 4.2 · sec. 4.2.1 · sec. 4.2.2 · sec. 4.2.3 · sec. 4.6
MCP and skillssec. 4.2.1 · sec. 4.3
When there are too many toolssec. 4.4
Planning and reflectionsec. 4.6 · sec. 6.5.3 · sec. 10.4.4
Errors and recoverysec. 1.2.5 · sec. 4.6
Code as an agent's toolsec. 4.6
Workflow or autonomysec. 1.2.4
Routing and parallelizationsec. 10.2 · sec. 10.4.2 · sec. 10.4.4
When multiple agents are neededsec. 10.2 · sec. 10.4.3
Sharing context between agentssec. 10.1.1 · sec. 10.3 · sec. 10.4 · sec. 10.4.1 · sec. 10.4.2 · sec. 10.4.5
Agent interaction protocolssec. 10.4.2 · sec. 10.4.6
Human in the loopsec. 1.2.5 · sec. 10.5.4 · sec. 10.5.6
Failures of multi-agent systemssec. 10.5 · sec. 10.5.1 · sec. 10.5.1–10.5.5 · sec. 10.5.2 · sec. 10.5.3 · sec. 10.5.4 · sec. 10.5.5
The harness around the modelsec. 1.2 · sec. 1.2.1 · sec. 1.2.2 · sec. 1.3 · sec. 2.3.1 · sec. 2.4.3 · sec. 5.1.5 · sec. 5.1.9
Specs and task briefssec. 1.3 · sec. 2.4.4 · sec. 5.1.3 · sec. 5.1.4 · sec. 9.2.2
Rules files and skillssec. 2.5.1 · sec. 2.5.2 · sec. 5.1.3 · sec. 5.2.6 · sec. 9.2.2 · sec. 9.3.3 · sec. 10.5.6
Hooks and deterministic guaranteessec. 1.2 · sec. 1.2.4 · sec. 5.1.4 · sec. 5.1.5 · sec. 5.2.2 · sec. 9.2 · sec. 9.2.2 · sec. 9.3.2
Subagents and delegationsec. 2.7.6 · sec. 5.1.3 · sec. 5.1.4 · sec. 7.2.2 · sec. 10.2 · sec. 10.3 · sec. 10.4.2 · sec. 10.4.4 · sec. 10.5.2 · sec. 10.5.3 · sec. 10.5.5
Independent verification and reviewsec. 1.2.4 · sec. 1.3 · sec. 5.1.3 · sec. 7.2.2 · sec. 7.4.6 · sec. 7.5.1 · sec. 7.5.4 · sec. 7.7 · sec. 7.10.1 · sec. 9.1 · sec. 9.3.2 · sec. 10.2 · sec. 10.4.3 · sec. 10.5.6
Autonomy and intent driftsec. 1.2 · sec. 1.2.5 · sec. 1.3 · sec. 2.6 · sec. 5.1.4 · sec. 5.1.5 · sec. 5.1.9 · sec. 7.4.5 · sec. 8.14.1 · sec. 9.1 · sec. 9.3.1 · sec. 10.4.2 · sec. 10.4.3
Datasets and evalssec. 7.1.1 · sec. 7.3.1 · sec. 7.4.2 · sec. 7.4.3 · sec. 7.4.4 · sec. 7.4.5 · sec. 7.4.6 · sec. 7.8
LLM as a judgesec. 7.5 · sec. 7.5.1 · sec. 7.5.1, 7.5.4 · sec. 7.5.4
Agent reliabilitysec. 7.2 · sec. 7.4.2 · sec. 7.5.2 · sec. 7.5.3 · sec. 7.6.1 · sec. 7.9
Statistical significancesec. 7.7
Observability and tracingsec. 7.6.1 · sec. 7.6.3 · sec. 7.8 · sec. 7.10.1 · sec. 7.10.2 · sec. 7.10.3 · sec. 7.10.4
Benchmarks and their limitssec. 7.5.4 · sec. 7.6.1 · sec. 7.6.4
Indirect injectionssec. 2.4.7 · sec. 3.3.4 · sec. 4.3 · sec. 5.1.9
Trust boundaries and least privilegesec. 1.2.5 · sec. 4.6
Data leakssec. 3.3.3
Excessive agent permissionssec. 4.6 · sec. 5.1.9
Attacks on the budgetsec. 7.6.3 · sec. 10.5.5
The supply chainsec. 4.3
Guardrailssec. 7.5.1
Choosing and routing modelssec. 7.6.1
Cachingsec. 7.6.3
Cost and latencysec. 7.6.3

AI Engineering

Chip Huyen · 2025 · topics: 6

Sections and chapters26

Prompt structure and message rolesch. 5
System prompt and instructionsch. 5
Examples and few-shotch. 5
Stable prefix and cachingch. 9
Model behavior: tokens, temperature, hallucinationsch. 2 · ch. 4, Factual consistency · ch. 5
Output format and structured answersch. 2 · ch. 4 · ch. 5
Document chunking and embeddingsch. 6
Hybrid search and rerankingch. 6
Query rewriting and contextual retrievalch. 6
Specs and task briefsch. 10
Datasets and evalsch. 4
LLM as a judgech. 3 · ch. 3, How to Use AI as a Judge · ch. 4 · ch. 4, Create scoring rubrics with examples · ch. 4, Instruction-following capability
Agent reliabilitych. 3 · ch. 6, Agent Failure Modes and Evaluation
RAG evaluationch. 4 · ch. 4, Factual consistency · ch. 6
Statistical significancech. 4
Benchmarks and their limitsch. 4
Indirect injectionsch. 5
Trust boundaries and least privilegech. 5, defenses against prompt attacks
Guardrailsch. 10
Choosing and routing modelsch. 10
Cachingch. 10
Cost and latencych. 10
Self-checks and degradation testsch. 2 · ch. 10
Monitoring and driftch. 10
User feedbackch. 10
Prompt, RAG or fine-tuningch. 7

Essential GraphRAG

Tomaž Bratanič, Oskar Hane · 2025 · topics: 2

Sections and chapters6

Document chunking and embeddingsch. 3
Hybrid search and rerankingch. 2 · ch. 3
Query rewriting and contextual retrievalch. 3 · ch. 4
Agentic RAGch. 5
Knowledge graphs and GraphRAGch. 7
RAG evaluationch. 8

Generative AI Design Patterns

Valliappa Lakshmanan, Hannes Hapke · 2025 · topics: 2

Sections and chapters3

Hooks and deterministic guaranteesch. 2, Pattern 2
Cachingch. 8, Pattern 25
Cost and latencych. 8, Pattern 27

Building Applications with AI Agents

Michael Albada · 2025 · topics: 1

Sections and chapters1

Autonomy and intent driftch. 12

The Developer's Playbook for Large Language Model Security

Steve Wilson · 2024 · topics: 1

Sections and chapters8

OWASP Top 10 for LLMch. 2 · ch. 4 · ch. 4, Pessimistic Trust Boundary Definition · ch. 7 · ch. 8 · ch. 10, table 10-1
Direct injections and jailbreaksch. 4 · ch. 4, Examples of Prompt Injection Attacks · ch. 4, Mitigating Prompt Injection
Indirect injectionsch. 4 · ch. 4, Direct Versus Indirect Prompt Injection · ch. 7
Trust boundaries and least privilegech. 3 · ch. 4
Data leaksch. 5 · ch. 7
Excessive agent permissionsch. 7 · ch. 7, Securing Your Output Handling · ch. 7, Watch for Excessive Agency
Attacks on the budgetch. 8
The supply chainch. 9

Agentic Design Patterns

Antonio Gullí · 2025 · topics: 4

Sections and chapters10

MCP and skillsch. 10
Planning and reflectionch. 4 · ch. 6
Errors and recoverych. 12
Routing and parallelizationch. 2 · ch. 3
Agent interaction protocolsch. 15
Human in the loopch. 13
Specs and task briefsch. 16
Guardrailsch. 18
Choosing and routing modelsch. 16
Cost and latencych. 16

Prompt Engineering for LLMs

John Berryman, Albert Ziegler · 2024 · topics: 1

Sections and chapters1

Prompt structure and message rolesch. 5 · ch. 6

Practice

Agents and Vibe Coding

a community-sourced compilation · 2026 · topics: 4

Available in Russian only

Sections and chapters14

Output format and structured answersch. 24
When multiple agents are neededch. 20
Human in the loopch. 29
The harness around the modelch. 14 · ch. 24
Specs and task briefsch. 6 · ch. 7 · ch. 8 · ch. 9
Rules files and skillsch. 10 · ch. 11 · ch. 12
Hooks and deterministic guaranteesch. 13 · ch. 24
Subagents and delegationch. 19 · ch. 20 · ch. 21
Independent verification and reviewch. 22 · ch. 23 · ch. 25
Autonomy and intent driftch. 26 · ch. 27 · ch. 28 · ch. 29
Datasets and evalsch. 23
LLM as a judgech. 23
Agent reliabilitych. 23
Statistical significancech. 23

The books behind the questions

Core books

AI Agents in Depth: Design Principles and Engineering Practice

AI Engineering

Essential GraphRAG

Generative AI Design Patterns

Building Applications with AI Agents

The Developer's Playbook for Large Language Model Security

Agentic Design Patterns

Prompt Engineering for LLMs

Practice

Agents and Vibe Coding

How the quizzes and the fair ranking work

01Modes

02Time and answers

03Limits on ranked attempts

04How points are counted

05A fair ranking