Skip to content

Start Here

This is an operating manual for building complex software with AI coding agents — primarily Claude Code, with patterns that transfer to Codex, Cursor, Copilot, and whatever ships next. It is written for engineers who already ship production software and want agents to do most of the typing without degrading the system.

The operating model in one diagram

Everything on this site elaborates one loop:

Five claims behind it, each defended in depth elsewhere:

  1. The agent is a compiler for intent. Ambiguity in, invented requirements out. Quality of output is bounded by quality of specification, not by prompting tricks. → Prompts vs. Specs
  2. The repository is the agent's memory. Context windows are ephemeral; CLAUDE.md, ARCHITECTURE.md, and specs are what persist across sessions and agents. → Docs as Agent Memory
  3. Verification is the human's job, and it must be structural. Reading the diff is necessary but insufficient; you verify scope, architecture fit, and behavior separately. → Verification Strategy
  4. Failures are predictable. Agents fail in recurring, catalogable ways. Recognizing a failure mode early is worth more than any prompt template. → Failure Catalog
  5. You own the decisions; the agent owns the diffs. Architecture, tradeoffs, and "is this actually done" never delegate cleanly. → The Responsibility Split

Where to go, by situation

Your situation this weekRead in this order
First serious project with Claude CodeMental ModelsPrompt AnatomyStarting a New Project
Agents produce plausible junk on your large codebaseWhy Agents FailRepository StructureCLAUDE.md & AGENTS.md
Shipping a feature into production codeAdding a Feature SafelyReviewing AI Pull RequestsVerification Checklists
An agent has made a messFailure CatalogRecovering From Bad Output
Scaling beyond one agentAgent RolesCoordination Without ChaosMulti-Agent Feature Delivery
Rolling agents out to a teamCTO path or Engineering Manager path

For a structured curriculum instead of à-la-carte reading, pick a learning path.

What this site refuses to do

  • Teach programming, Git, testing, or CI/CD — assumed known.
  • Cover prompt-engineering parlor tricks that don't survive contact with a 200-file codebase.
  • Pretend agents are senior engineers. They are extremely fast, well-read, literal-minded collaborators with no memory and no stake in the outcome. The entire discipline is engineering around exactly that.

Conventions used throughout

  • Prompts appear in fenced code blocks with a copy button. Text in <angle brackets> is a placeholder you fill in.
  • Weak → strong examples show the failing version first, then the fix. The delta is the lesson.
  • Failure tables use the columns Symptom / Cause / Fix so you can scan them mid-incident.
  • Claude Code specifics (e.g. CLAUDE.md, subagents, plan mode, hooks) are called out by name; everything else is written to survive tool churn.

A field manual for AI-native software engineering.