Score this workflow against the production checklist

The prompt

Score your current agent-assisted workflow against six criteria: named owner and business outcome; documented trust boundary and data path; scoped workload identity and explicit tool inventory; independent validation and security gates; human approval for high-consequence actions; observable execution, rollback, and retained evidence. Where does it fail?

Why it's built that way

A workflow is production-ready only when permissions are bounded, validation is repeatable, rollback is tested, evidence is retained, and performance is measured against a human-only baseline — this is the handbook's own chapter checkpoint, applied to your own system instead of a hypothetical one.

What to do with the answer

Treat any "no" on this list as a blocker for expanding the agent's access further, not a note for later.