Every repo has a little tribal knowledge.
The command everyone knows not to run.
The service that must be started before tests.
The environment variable missing from .env.example.
The setup step that only lives in someone’s memory.
Every repo has a little tribal knowledge. The command everyone knows not to run. The service that...
Undeclared setup, safety rules, and verification paths break AI agent execution; agents cannot infer rules humans can. AI teams require explicit governance declaring blockers, protected operations, and completion criteria so agents operate reliably.
Every repo has a little tribal knowledge.
The command everyone knows not to run.
The service that must be started before tests.
The environment variable missing from .env.example.
The setup step that only lives in someone’s memory.

AI coding agents work better when your repo has explicit readiness: declared setup, tasks, checks, workflows, and safe agent…

A lot of conversations about AI coding agents focus on obvious failures: hallucinated APIs, broken...

I’ve been thinking a lot about a failure mode in AI-assisted development that does not fit neatly...

There is a pattern starting to show up everywhere now. A team uses an AI coding agent. The agent...

I Built a Local Knowledge Graph That Tells AI Agents "What Breaks If I Change This?" Every...

A practical checklist for running AI coding agents in disposable, least-privilege developer environments.