ProtocolGovGuardFinGuardExplorerPlaygroundAdoptCloudTrustDocsRequest Pilot
Comparison / Audit Logs

Audit logs aren't enough for AI agent actions

Audit logs tell you what happened. EP trust receipts prove what was authorized — before the action executed. For consequential, irreversible actions, post-hoc logs are a forensics tool, not a control.

The detection gap

A wire transfer fired by a compromised AI agent shows up in your audit log seconds after it executes. By then the funds have left, the API call has succeeded, and the only remaining job is investigation. Logs are necessary — they are not sufficient when the cost of an unauthorized action is unrecoverable.

EP shifts the boundary: every high-risk action requires a valid handshake and named human signoff before execution. The trust receipt that emerges is itself the audit record — but issued at the gate, not after the breach.

What's in a trust receipt

Receipts verify offline against a published key set. An IG, GAO, or external auditor can confirm an action was authorized without contacting the issuing system — useful when the issuing system is itself under investigation.

Side by side

DimensionAudit logsEP trust receipts
When evidence is createdAfter the actionBefore — gates execution
Tamper resistanceDepends on log store integrityCryptographic; verifiable offline
Who approvedInferred from session IDNamed principal, signature-bound
What was approvedAPI call shapeExact action parameters, policy version, authority chain
Replay protectionNone inherentOne-time consumable per action
Verifies without DB accessNoYes — receipt is self-contained
UseForensics + detectionPrevention + forensics

See receipts in the explorer

Open the explorerRead the receipt spec
Audit Logs vs Trust Receipts — Why Logs Aren't Enough for AI Agents