We learned that an AI-written change can look complete long before it’s safe to merge. The implementation may be coherent, the explanation persuasive and every review comment resolved, but none of that shows how the candidate behaved in the delivery pipeline. That gap changed how we treated the gate. It now fails closed: a positive result has to be observed independently. If the required continuous integration evidence is missing, incomplete, stale or unverifiable, the change stays blocked. ...