Appendix D. Reference documents
These are the official documents cited in this book. Features, supported models and schedules may change. Recheck the originals before applying them at work.
Anthropic (verified 2026-10-20)
- Prompting best practices
- Prompt engineering overview
- Effective context engineering for AI agents
- Reduce hallucinations
- Reduce prompt leak
- Mitigate jailbreaks and prompt injections
- Mid-conversation system messages
- Structured outputs
- Refusals and fallback
- Define tools
- Context windows
- Handling stop reasons
- Citations
- Search results
- Vision
- Contextual Retrieval
- Prompt caching
- Compaction
- Context editing
- Effort
- Thinking
- Building effective agents
- How we built our multi-agent research system
- Define success criteria and build evaluations
- Demystifying evals for AI agents
OpenAI (verified 2026-10-20)
- Prompt engineering
- Structured model outputs
- Reasoning models
- Reasoning best practices
- Conversation state
- Prompt caching
- Your data
- Token counting
- Latency optimization
- Evals
- Evaluation best practices