this is my evidence backed guide to working with coding agents, whether you are a student having an existential crisis, a startup founder working with real money for yourself and other people, or an engineer at one of the biggest technology companies in the world. the guidance is organized around the scale and consequences of the work.
read the handbook or go directly to a principal guide:
- codex
- claude code
- grok
- working with coding agents
- how coding agents got here
- choosing a coding agent setup
- where this comes from
the handbook separates the surface where you steer work, the harness that runs the agent loop, the model that supplies inference, and the orchestration used for parallel work. it also covers repository instructions, permissions, review, evidence, hardware, and the operating costs that appear after the first demo.
tested: reproduced by the author in a named environment and versionofficial source: confirmed in current primary documentation or source codeanalysis: a judgment derived from stated evidenceopen question: current evidence is missing or incomplete
citations sit beside the claims they support. field runs publish inspectable artifacts and keep their limits visible.
bun install --frozen-lockfile
bun run check:readme
bun run check
bun run build
bun run test:site
bun run test:a11ybuilt and maintained by ani potts. corrections with primary sources or reproducible field evidence are welcome.
MIT