Prove what your agent did.
Every checked action leaves a proof of what was checked, which policy applied, and what was allowed or refused.
An agent audit trail is evidence another system can check: what was verified, which policy applied, and what actually happened.
Every decision leaves a proof.
Allowed, blocked, verified, or revoked, each one is recorded with the agent, its owner, and the result. Paste a Proof ID to check one yourself.
Action records
- 0x8f2c...4a19Refund order 4821Allowed
- 0x51d0...9c3eRun a script on the serverBlocked
- 0x7a44...e210GitHub account ownershipVerified
- 0x2b9e...07cdOperator permission updatedCurrent
- 0x93f1...6b52Refund order 5530 for $240Blocked
- 0x0c7a...d418Stripe key used in a jobAllowed
- 0x6e25...a9f3Domain ownershipVerified
- 0x48bd...12e0Research agent accessRevoked
Check any proof
- Who acted
- The agent and the owner it acts for
- Under which permission
- The exact allowed and blocked actions
- What happened
- The action and its result
- Is it still valid
- Current, expired, or revoked
Read the record after the action
receipt.ts

Keep evidence of every decision.
Checked actions leave proof with the agent, its owner, and the result. Another system can verify it later.