What may it do? When should a person decide? How do you know what actually happened?
Independent guides for developers building AI agents.
Start with the decision guidePractical decisions. Sources you can inspect.
Decide when an AI agent may act, when it should ask, and when it must stop. Includes an original allow/ask/deny worksheet and a worked email example.
Includes: Allow / ask / deny worksheet
You approved one email. Then the recipient changed. See when an agent should stop, with a visual walkthrough and a runnable lab covering 24 checks.
Includes: Runnable approval lifecycle lab
A downloadable MCP starter for Codex and Claude Code: check Markdown, request human approval, and export the exact reviewed file. Includes setup and real file tests.
Includes: MCP starter and Markdown setup guide
We separate documented behavior from proposed designs. Every guide should leave you with something useful: a decision table, a reproducible example, or a clearly labeled experiment.
How we research and review →