Agent Field Guides · reference
Glossary and further reading
Every technical term from the seven modules in one place, with links back to where each one is explained. Then a short list of official sources to go deeper.
Glossary
Go deeper
Further reading
Official sources only. Tools and rules change quickly, so check dates and versions against what your team uses.
Agents in general
- Building effective agents ↗Anthropic's engineering guide to workflows versus agents, with the common patterns. A good companion to module 1's spectrum.
- Model Context Protocol ↗The official site for MCP: what it is, the specification, and lists of available servers. Modules 1 and 3.
The tools in modules 2 to 5
- LangChain and LangGraph documentation ↗The official docs for both libraries. Check them against the version your team uses.
- Langfuse documentation ↗Tracing, prompt management, evaluation and self-hosting, with current SDK names.
Safety and risk
- OWASP GenAI Security Project ↗Home of the OWASP Top 10 for LLM applications, including prompt injection and excessive agency. Useful for module 1's Stage 4 and module 6's security metrics.
- NIST AI Risk Management Framework ↗A widely used, vendor-neutral framework for governing AI risk. Background for module 6's governance category.
Launching safely
- Canarying releases (Google SRE Workbook) ↗How to roll changes out to a small share of traffic first and compare. The engineering side of module 7's staged rollout.
Regulation in India (for module 6)
- Securities and Exchange Board of India (SEBI) ↗Circulars and regulations for intermediaries, including rules on advice and distribution.
- Association of Mutual Funds in India (AMFI) ↗Guidelines for mutual fund distributors, and the investor education material behind standard disclosures.
- Ministry of Electronics and IT (MeitY) ↗The Digital Personal Data Protection Act and its rules.