transparency log
Transparency Log · append-only log
An append-only, publicly auditable record of events in which entries cannot be altered or removed without detection, proven by inclusion and consistency proofs.
In our briefings
The claim each of the newest briefings on transparency log would have you leave with.
Figuera's Sello protocol moves the record of an AI agent's actions from the agent to the services it calls. Each Sello-aware service seals a receipt body with HPKE to an owner key that the agent's JWS authorization token carries as a signed claim (owner_hpke_pk), signs the envelope with its own Ed25519 key and submits it to a public transparency log, where the owner finds it by the token's SHA-256 hash. In the paper's words, "The agent never holds any of the signing keys involved." The design assumes at least one service the agent calls is honest and uncompromised within the relevant time window: if every service colludes with the agent's operator, Figuera says, Sello cannot detect what they fabricate.
Sello has the services an AI agent calls sign its receipts; the agent can't fake them, but it can go around themBI-FIND-2026-2275
Kühlewind and Birkholz start from an agent that is not trusted: "the entire point of the architecture is to make the Agent itself the auditable object." An agent that records itself, they write, "can produce useful telemetry but cannot, by itself, deliver non-repudiation to a third party." The check on it comes from the service, tool or resource server, which enforces the agent's presented authorization at the point of effect and records each request "as observed at the boundary, not as reported by the Agent." Section 8 says the Audit Store is only partly trusted: its records are corroborated by independent service-side records and, for consequential actions, by registration with a Transparency Service. The authors also list what the design does not solve: a Service that refuses to record what happened at its boundary, operator collusion across all roles, and the alignment of the model behind the agent.
An agent audit draft says the agent is not trusted, yet lets the agent's operator run the audit storeBI-FIND-2026-1950
Revision -04 of Chris Hood's AGTP Agent Certificate Extension lets infrastructure check an agent's identity and scope once per connection, at the TLS handshake. The three X.509 v3 extensions it marks critical, out of eight, carry the agent's ID, its accountable owner and its committed Authority-Scope token list, and the connection MUST use TLS 1.3 mutual authentication. A Scope-Enforcement Point, the draft's name for the infrastructure that enforces an agent's scope, parses that list once per session and returns 455 Scope Violation for any request token outside it, without forwarding the request to the application. The handshake replaces the per-request Request-Signature check only under the RECOMMENDED same-key option, where the certificate key is the agent's document key: the server then MAY skip that check. With distinct keys the server MUST verify both. The binding of the ID to the agent's signed Genesis record is still checked at the application layer, and a certificate that fails that check MUST be treated as TLS-only. The extension is OPTIONAL, and the scope is fixed for the certificate's life: a change to it is one of the events on which the certificate MUST be revoked.
An unadopted AGTP draft would let gateways refuse an agent's out-of-scope requests from its TLS certificateBI-FIND-2026-1925
›Cited in 16 briefings
Every briefing that discusses this term, newest first.
- Sello has the services an AI agent calls sign its receipts; the agent can't fake them, but it can go around them
Paper · · arXiv · Juan Figuera · Jun 2, 2026
- An agent audit draft says the agent is not trusted, yet lets the agent's operator run the audit store
Draft · · IETF Datatracker · Mirja Kühlewind et al. · Sep 7, 2026
- An unadopted AGTP draft would let gateways refuse an agent's out-of-scope requests from its TLS certificate
Draft · · IETF Datatracker · Chris Hood, Nomotic, Inc. · Oct 30, 2026
- A draft has each company sign its own half when one company's agent acts at another's request, refusals included
Draft · · IETF Datatracker · Steven Mih, Action State Group · Oct 29, 2026
- An agent audit draft makes its first change under its format freeze, ahead of the tests for it
Draft · · IETF Datatracker · Sankalp Gilda · Oct 16, 2026
- AGTP checks that an agent ID is signed; binding it to the connection is an add-on in the author's patent notice
Draft · · IETF Datatracker · Chris Hood, Nomotic, Inc. · Jun 28, 2026
- Delegation receipts for AI agents, revision 15: holding a copy of a receipt no longer lets you extend the chain
Draft · · IETF Datatracker · Ryan Nelson, Authproof · Oct 22, 2026
- RFC 9943 makes a log prove who signed a statement, not that it is true or that nothing was left out
Article · · IETF (RFC Editor) · Henk Birkholz et al. · Jun 30, 2026
- Anthropic says agents should never use static API keys, yet its sub-agents can carry the parent's permissions
Article · · Anthropic · Anthropic · May 18, 2026
- Munoz's agent Permit is signed before the action runs, but the profile does not make the action wait for it
Draft · · IETF Datatracker · Christian Munoz, Keel API, Inc. · Jul 19, 2026
- OpenA2A's protocol proves an agent holds a key and scores its behaviour, but never says who it works for
Draft · · IETF Datatracker · Abdel Fane, OpenA2A · Oct 6, 2026
- An agent audit record that shows when a 'deny' went through anyway
Draft · · IETF Datatracker · Sankalp Gilda · Oct 5, 2026
- Coetzee's agent token is good for one declared call, and the hard part is hashing that call the same way twice
Draft · · IETF Datatracker · Rudolf Jacobus Coetzee · Jul 19, 2026
- The Agent Name Service draft was rebuilt on DNS, with a GoDaddy author, and no standards body has adopted it
Draft · · IETF Datatracker · Scott Courtney et al. · Apr 13, 2026
- An agent certificate draft ties access to a trust score set by the issuing CA, usually the agent operator's own
Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Apr 10, 2026
- One shared MCP token makes a whole company one identity in the logs; this paper wants per-user OAuth at a gateway
Paper · · arXiv · Herman Errico et al. · Nov 25, 2025