AI you can audit — The rest of the trust surface, each one checkable. (2)

One click walks it back Records the AI creates come with an Undo on the confirmation — they move to the Trash, restorable like anything else. Schema changes are confirm-to-apply before they happen: the AI proposes, you approve, nothing lands silently. Honest when it can't Ask answers from your records, never from recall — and when your data can't answer the question, it says exactly what's missing instead of producing a confident number from nowhere. Fair-use limits fail open — a metering hiccup never blocks a paying customer. And when a verification check can't re-run, the receipt says so instead of quietly shrinking the denominator. The industry is racing to make AI do more. We think the harder problem is making it provable. An agent that touches your operational data must be able to show its working, sign its changes, and be walked back. Ours can — and you can check all three right now. The verification tally counts failed checks alongside passed ones. A counter that can only report success is marketing; one that can embarrass us is evidence. We tell you plainly what we don't have — see compliance and security. This page holds AI claims to the same standard.