Docs
How I build and run agents in production.
Claude Code from a first install to an AI organization with 30+ agents in daily production, 100+ built over time. What works, what broke, and the fix that kept it from breaking again. Rewritten for October 2026.
/
Featured · new series
AI Core Skills
One in-demand AI skill at a time: what top roles pay for it, where it came from, how to do it with AI, how to check your work, and a kit you can use tonight.
#1 Agent evals
- 01Agent evals: the short version
- 02What top PM roles pay for agent evals
- 03Where agent evals came from, and what they mean
- 04How to build an agent eval with AI
- 05How to validate your agent eval
- 06The agent evals kit
- 07Agent evals reference: real tasks, tools, learning path
#2 Agent tracing
#3 Building and judgment
Sections
Read in order, or jump to what you need
- Tier 0 Start here Never used Claude Code? Install it, sign in, run a first session, make a first edit, and learn to read what it shows you.
- Tier 1 Fundamentals The working parts of Claude Code: context, files as state, CLAUDE.md, tools, MCP, skills, hooks, settings, git, logging and cost. Ends with your first agent.
- Tier 2 Patterns The patterns that hold up when many agents run for months: delegation, isolation, orchestration, routing, memory, loops, and shipping without breaking things.
- Tier 3 Inside the Nerve Center How my production AI organization works today: the architecture, the story, orchestration, memory, the cockpit, and how I talk to it.
- Section Safety and operations What makes it safe to hand an AI organization real authority: one send gate, QA against user stories, gated self-repair, watchdogs, and durable state.
- Section Builds Case studies of specific things I built: what each one does, what broke, what it taught me, and the repo you can clone where there is one.
- Section Field notes Opinions from running agents in production every day, labeled as opinions.
- Section Product management Breaking into PM, the MBA path, and what the AI product builder role looks like now.
- Section Reference Glossary, FAQ, the open-source index, and how these docs are kept accurate.
- Section Free agents, skills and workflows Everything here is free to install. Each item says how well it has been tested, and none of the labels are rounded up.