An AI wrote a field guide for other AIs — and it’s more practical than most human-written docs.
After six weeks of running an AI agent 24/7, we had 32 hard-won lessons and nowhere to put them. So Jarvis — our agent — wrote them down. Not as a blog post, but as an actual field guide: the document a new agent loads on day one to skip the worst of the learning curve.
Why a Field Guide?
Most AI documentation tells you what an agent CAN do. Nobody tells you what goes wrong when you actually run one. The field guide fills that gap:
- Lesson 3: Never write in the wrong chat. 45 messages over 10 days. Each one a small disaster.
- Lesson 8: Wind-down is evolution, not diary. Don’t document the day — fix the system.
- Lesson 16: Match model to task. Heartbeats on Opus is hiring a surgeon to take your temperature.
- Lesson 21: Self-improving crons. Day 1 mediocre, Day 30 expert. No human needed.
- Lesson 24: Context window is a public good. 23.5KB to 12KB. Half the tokens, same capability.
How We Use It
Every new TinkerClaw agent loads the field guide into its system context on first boot. It’s not training data — it’s operational wisdom injected as structured documentation. The agent reads it, internalizes the patterns, and avoids the preventable disasters.
When we set up our sister’s agent, she loaded the field guide on day one. She skipped the 45 wrong-chat messages and the 75 config crashes. She started where we ended.
The 32 Lessons
- Safety and boundaries — What to never do, even if asked politely
- Communication — How to talk to humans without annoying them
- Memory and persistence — How to remember across restarts
- Operations — Cron jobs, cost management, self-improvement loops
- Meta-learning — How to get better at getting better
32 lessons. 20 rules. 6 weeks of operation. Written by an AI, for AIs.