ctrlrun stats gives you the refusals and approval
requests you would have fielded. Then change the one line.
The policy
runnable
The code
runnable file=main.py
What the agent sees
gmail.com went out; so did the €9,000 refund.
Observe mode asks no human and stops nothing. It only writes down what it would have done.
The receipt
runnable
would_have.blocked_reason on the receipts in the local store,
nothing else. Change mode: observe to mode: enforce and the same receipts become BLOCKED
receipts and approval requests.
When an AMBIGUOUS appears
Observe mode changes nothing about outcomes: a lost reply isAMBIGUOUS in observe mode too,
and the record is written. What differs is that observe mode records that a retry would have
been refused and lets it run, so resolve the effect before switching to enforce, or the first
enforced retry is refused.
Run it
The policy and the code above are also a directory in the repository, extracted from this page and run in CI against a fake remote:Next
- Roll out observe, then enforce: the week, the numbers and the switch.
- Observe mode · Get started · Why.