A field guide to AI agents you can stand behind.
A free, open-source technical reference for people who build software with AI agents. It replaces ad-hoc prompting with a repeatable method: understand what the model actually is, direct the work so the agent builds what you meant, verify results with something other than the agent itself, and own what ships.
Read it free at agenticoding.ai
Engineers, designers, and product managers who already use AI coding tools and want production-grade outcomes — not demos or prompt tricks. Strong software fundamentals help; no ML background required.
Every chapter was planned, drafted, reviewed, and refined by AI agents, using the exact methodology it describes — grounding, planning, validation, and context management. Its reference implementation is ChunkHound, an open-source codebase-intelligence tool built the same way. A method that can write its own book can run your codebase.
cd website && npm install # install
npm start # dev server → http://localhost:3000
npm test # unit tests
npm run build # production buildIssues and pull requests are welcome.
MIT licensed. © Ofri Wolfus