Appendix Guide: Your Reference Library

These appendices are a reference library, not required reading. Use them on-demand when you need specific information. Here’s when to reach for each one.

Quick Navigation

When you need…	Go to…
Definition of a term	Appendix A: Glossary
Which tool/framework to use	Appendix B: Tool & Framework Reference
Papers to read on a topic	Appendix C: Paper Reading List
Interview preparation	Appendix D: Interview Preparation
A project to build	Appendix E: Capstone Projects
Help debugging an issue	Appendix F: Debugging & Troubleshooting
Example architecture decisions	Appendix G: Architecture Decision Records
Guided reading order	Appendix H: Learning Paths
One-page topic summaries	Appendix I: Quick Reference Cards
Real-world production stories	Appendix J: Production Case Studies
LLM provider comparison	Appendix K: LLM Provider Comparison
Find a code example	Appendix L: Code Example Index
Avoid common mistakes	Appendix M: Common Mistakes & Anti-Patterns

Appendix Descriptions

Appendix A: Glossary

Use for: Looking up unfamiliar terms while reading chapters.

Comprehensive definitions organized by category: ML/training, inference/deployment, RAG, evaluation, and agents. If a chapter uses a term you don’t recognize, start here.

Appendix B: Tool & Framework Reference

Use for: Choosing between tools when starting a project.

Current landscape of AI engineering tools with selection guides. Covers: orchestration frameworks, vector databases, observability tools, and evaluation frameworks. Updated for 2026.

Appendix C: Paper Reading List

Use for: Going deeper on topics after reading chapters.

Annotated list of essential papers organized by topic. Each entry explains what the paper contributed and why it matters. Good for interview prep and expertise development.

Appendix D: Interview Preparation

Use for: Preparing for AI engineering interviews.

Interview questions by level (IC2, Senior, Staff), sample answers, STAR examples for behavioral questions, and system design practice problems. Use alongside Chapter 22 for system design prep.

Appendix E: Capstone Projects

Use for: Applying what you’ve learned to real projects.

Four end-to-end projects with starter code: RAG system, agent with tools, evaluation harness, and production deployment. Each includes requirements, architecture guidance, and evaluation criteria.

Appendix F: Debugging & Troubleshooting

Use for: Diagnosing production issues.

Systematic diagnosis guides for common problems: retrieval failures, generation quality issues, latency problems, and cost spikes. Decision trees to identify root causes.

Appendix G: Architecture Decision Records

Use for: Documenting technical decisions.

Seven example ADRs for common AI engineering decisions: vector database selection, model choice, caching strategy, and more. Use as templates for your own ADRs.

Appendix H: Learning Paths

Use for: Planning your reading order.

Six guided paths through the book based on your background and goals: new to AI, backend engineer adding AI, senior to staff transition, interview prep, ML engineer to LLM, and tech lead establishing AI practice.

Appendix I: Quick Reference Cards

Use for: Fast lookups and desk reference.

One-page summaries of key topics: LLM fundamentals, prompt patterns, RAG pipeline, agent patterns, deployment options, evaluation metrics, security threats, and cost estimation. Print-friendly.

Appendix J: Production Case Studies

Use for: Learning from real-world AI production experiences.

Ten detailed case studies from companies deploying AI at scale. Each includes context, what happened, root cause, resolution, and lessons learned.

Appendix K: LLM Provider Comparison

Use for: Choosing between LLM providers.

Detailed comparison of OpenAI, Anthropic, Google, Meta, Mistral, and others. Covers: model capabilities, pricing, context windows, and use case recommendations.

Appendix L: Code Example Index

Use for: Finding code examples by topic.

Searchable index of all code implementations in the book and reference files. Organized by topic with links to source files.

Appendix M: Common Mistakes & Anti-Patterns

Use for: Avoiding pitfalls before you hit them.

40+ documented mistakes with explanations and fixes. Organized by category: prompting, RAG, agents, deployment, evaluation, and security. Read proactively or reference when debugging.

Recommended Appendix Reading by Role

For Beginners (AI Engineer I): - Start with Appendix H to choose a learning path - Keep Appendix A open for term lookups - Use Appendix I as a study aid

For Practitioners (AI Engineer II / Senior): - Appendix M to avoid common mistakes - Appendix B when choosing tools - Appendix F when debugging issues

For Leaders (Staff+): - Appendix G for decision documentation - Appendix J for case study discussions - Appendix C for research depth

For Interview Prep: - Appendix D (obviously) - Appendix I for quick review - Appendix C for paper knowledge

# Appendix Guide: Your Reference Library {.unnumbered} These appendices are a **reference library**, not required reading. Use them on-demand when you need specific information. Here's when to reach for each one. --- ## Quick Navigation | When you need... | Go to... | |------------------|----------| | Definition of a term | **Appendix A: Glossary** | | Which tool/framework to use | **Appendix B: Tool & Framework Reference** | | Papers to read on a topic | **Appendix C: Paper Reading List** | | Interview preparation | **Appendix D: Interview Preparation** | | A project to build | **Appendix E: Capstone Projects** | | Help debugging an issue | **Appendix F: Debugging & Troubleshooting** | | Example architecture decisions | **Appendix G: Architecture Decision Records** | | Guided reading order | **Appendix H: Learning Paths** | | One-page topic summaries | **Appendix I: Quick Reference Cards** | | Real-world production stories | **Appendix J: Production Case Studies** | | LLM provider comparison | **Appendix K: LLM Provider Comparison** | | Find a code example | **Appendix L: Code Example Index** | | Avoid common mistakes | **Appendix M: Common Mistakes & Anti-Patterns** | --- ## Appendix Descriptions ### Appendix A: Glossary **Use for**: Looking up unfamiliar terms while reading chapters. Comprehensive definitions organized by category: ML/training, inference/deployment, RAG, evaluation, and agents. If a chapter uses a term you don't recognize, start here. ### Appendix B: Tool & Framework Reference **Use for**: Choosing between tools when starting a project. Current landscape of AI engineering tools with selection guides. Covers: orchestration frameworks, vector databases, observability tools, and evaluation frameworks. Updated for 2026. ### Appendix C: Paper Reading List **Use for**: Going deeper on topics after reading chapters. Annotated list of essential papers organized by topic. Each entry explains what the paper contributed and why it matters. Good for interview prep and expertise development. ### Appendix D: Interview Preparation **Use for**: Preparing for AI engineering interviews. Interview questions by level (IC2, Senior, Staff), sample answers, STAR examples for behavioral questions, and system design practice problems. Use alongside Chapter 22 for system design prep. ### Appendix E: Capstone Projects **Use for**: Applying what you've learned to real projects. Four end-to-end projects with starter code: RAG system, agent with tools, evaluation harness, and production deployment. Each includes requirements, architecture guidance, and evaluation criteria. ### Appendix F: Debugging & Troubleshooting **Use for**: Diagnosing production issues. Systematic diagnosis guides for common problems: retrieval failures, generation quality issues, latency problems, and cost spikes. Decision trees to identify root causes. ### Appendix G: Architecture Decision Records **Use for**: Documenting technical decisions. Seven example ADRs for common AI engineering decisions: vector database selection, model choice, caching strategy, and more. Use as templates for your own ADRs. ### Appendix H: Learning Paths **Use for**: Planning your reading order. Six guided paths through the book based on your background and goals: new to AI, backend engineer adding AI, senior to staff transition, interview prep, ML engineer to LLM, and tech lead establishing AI practice. ### Appendix I: Quick Reference Cards **Use for**: Fast lookups and desk reference. One-page summaries of key topics: LLM fundamentals, prompt patterns, RAG pipeline, agent patterns, deployment options, evaluation metrics, security threats, and cost estimation. Print-friendly. ### Appendix J: Production Case Studies **Use for**: Learning from real-world AI production experiences. Ten detailed case studies from companies deploying AI at scale. Each includes context, what happened, root cause, resolution, and lessons learned. ### Appendix K: LLM Provider Comparison **Use for**: Choosing between LLM providers. Detailed comparison of OpenAI, Anthropic, Google, Meta, Mistral, and others. Covers: model capabilities, pricing, context windows, and use case recommendations. ### Appendix L: Code Example Index **Use for**: Finding code examples by topic. Searchable index of all code implementations in the book and reference files. Organized by topic with links to source files. ### Appendix M: Common Mistakes & Anti-Patterns **Use for**: Avoiding pitfalls before you hit them. 40+ documented mistakes with explanations and fixes. Organized by category: prompting, RAG, agents, deployment, evaluation, and security. Read proactively or reference when debugging. --- ## Recommended Appendix Reading by Role **For Beginners (AI Engineer I)**: - Start with Appendix H to choose a learning path - Keep Appendix A open for term lookups - Use Appendix I as a study aid **For Practitioners (AI Engineer II / Senior)**: - Appendix M to avoid common mistakes - Appendix B when choosing tools - Appendix F when debugging issues **For Leaders (Staff+)**: - Appendix G for decision documentation - Appendix J for case study discussions - Appendix C for research depth **For Interview Prep**: - Appendix D (obviously) - Appendix I for quick review - Appendix C for paper knowledge