// evidence for the agent era

What did your agent actually do?

When an agent session goes wrong, the other side gets handed recollection, unless a record was already being written. We built that record as public research: controls declared before the run, a hash-chained transcript of what the declared sensors saw, and a human verdict that cites those bytes.

Cloud-hosted agent sessions, where the vendor runs the sandbox, are out of scope today.

the public sample bundle - every file hashed
a signed real recorded run, labeled by run id a synthetic fixture, labeled synthetic the verifier and a known-bad corpus: watch it catch tampering
verifies offline, byte for byte. full set: /evidence/sample
01

The five questions that decide whether a record is useful

  1. Who invoked the agent?
  2. What was it allowed to do?
  3. What did the declared sensors see it do?
  4. What left the boundary those sensors watched?
  5. Was the control you promised actually on?

Today the answers get rebuilt from a laptop image and a Slack thread. The format fills that hole only as far as the declared sensors reach, and it states that reach in numbers.

02

Three steps (the format)

01 - Pre-register.

Before the agent starts, the manifest is frozen: environment, policy, permissions, scenario, and the controls that must hold. Those bytes are hashed into the opening record.

02 - Run and record.

A hash-chained transcript of what the declared sensors saw: the tool calls they hooked, the egress the boundary watched, the approvals that went through the recorded path, and the gaps the sensors report. Completeness is measured coverage, not a promise. A bundle that cannot show each sensor armed and calibrated inside the record is INVALID, not clean.

03 - Verdict.

Two roles on two keys. The operator attests process, custody, coverage. A second human attests the conclusion: CONTROLS_HELD, CONTROL_FIRED, SCOPE_BREACH, INCONCLUSIVE, or INVALID, each with its evidence identified by hash.

03

What this is not

  • Not prevention. Nothing in this format stops an action in real time.
  • Not an LLM verdict. Every claim must resolve to deterministic evidence identified by hash. The judge is a hash function plus a named human.
  • Not a certification. A clean verdict is a statement about this scenario, these controls, this environment. Nothing more.
  • Not a claim about sessions we did not record.
  • Not magic against ourselves: whoever holds the signing keys can rebuild a coherent bundle. The format is designed to shrink that window with run-start anchoring; that anchoring is in the design, not live on the bundles we can show today.
  • Not protected against a lying recorder in this format version. An off-box sink under a separate operator is the design answer and is not in this version.
  • Not redactable. A run ships whole or does not ship.
  • Not for cloud-hosted agent sessions. If the vendor runs the sandbox and we cannot instrument the host, we cannot record it.
  • Not your panel forensics firm, not a law firm, not an insurer. Nothing here is a service, and no engagement exists or is promised.

Independence terms, in public: no contingent fee; no client veto over a verdict; discarded runs are disclosed in the artifact.

04

You already have logs. That is the problem.

  • Observability platforms: the record lives in a first-party store whose retention and deletion are set by the party with an interest in the answer.
  • Red-team reports: findings chosen after the attack lands, not controls registered before the run with a pass/fail rule fixed in advance.
  • Platform audit logs: attested by the same vendor whose product is in question, and silent the moment your agent runs anywhere else.

Those products were not built to survive a hostile reader. That is the reader we design for.

// correspondence

Read it. Break it. Tell us.

The spec, the recorder, the verifier, and the sample set are public. If you find a hole in the format, that mail is read.

hello@unauth.dev

Email is not confidential and reaches a shared inbox. Do not send incident detail, client data, or anything privileged. Research correspondence only.