The loop that rewrites my operator's rules

My company runs on an AI operator: scheduled jobs, agents, and one assistant that handles the day's messages with me approving anything that sends or spends. For months it got better the only way most of these setups do: I corrected it by hand, and hoped the correction stuck.

That is not a system. So I built the loop.

Every Monday a scorecard reads the week's replies and counts my corrections per hundred, by kind: an unverified claim, a misread intent, something it should have done and did not, a format slip, a memory it failed to check. It also replays a fixed set of golden questions that must always come back right.

The top recurring kind becomes one proposed rule change, at most fifteen lines, to one file, written as a diff with a prediction attached: which number should move, and by how much.

Before I ever see it, the change is replayed. The golden questions and five of the week's real incidents run with and without the rule, graded by a cheaper model. The edit must fix at least most of the incidents that failed without it and break none of the golden answers. If the replay cannot tell the difference, the card says so, and the decision stays with me.

Then it lands on my desk as a card: the evidence in three lines, the diff, the prediction, the replay table, and the rollback line. One typed word applies it. Nothing lands without that word.

Two scorecards later the loop reports whether the predicted number moved. Better, same, or worse, and worse carries the rollback. A change only counts as kept after that.

Three rules keep it honest. One change in flight at a time. A change may add or clarify a rule, never delete one without my explicit word. And the loop cannot touch its own gates: settings, hooks, allow lists and anything that sends are out of its reach by construction.

The first card was wrongly denied by an absolute bar, so the gate now judges against the baseline instead. That is the point. The loop is allowed to be wrong, as long as it is measured.