Cogitator

Can you prove what your AI agent did?

A tamper-evident audit layer for AI agents. A cryptographic record of what your agent did, tried to do, and was blocked from doing — recomputable by any third party from the recorded run.


Regulated AI needs more than a log file.

AI agents are already operating in financial services, healthcare, and legal workflows. When something goes wrong — a bad trade, a missed diagnostic flag, a contract clause the agent should not have touched — your organisation faces a question it currently cannot answer.

"Can you prove the agent did exactly what you say it did, and nothing it was not supposed to?"

Existing audit logs are mutable. Post-hoc summaries are reconstructions. There is no standard way for a regulator, an insurer, or a counterparty to independently verify your account of what your AI actually did.

This is not a gap most teams notice until they are sitting across from a regulator or a claims adjuster. By then, the only evidence available is the operator's own logs — an inherent conflict of interest.

A cryptographic record that anyone can verify.

Cogitator wraps around an AI agent and produces a cryptographic witness root — a single tamper-evident fingerprint — after every run. Any third party can recompute that fingerprint from the recorded run and check it against a value they hold, detecting whether the committed record was altered after it was sealed.

Before any tool call is dispatched, Cogitator checks it against a declarative policy file. Allowed calls are executed and recorded. Blocked calls are also recorded — proving not just what the agent did, but what it tried to do and was prevented from doing.

The result is a self-contained, independently verifiable bundle: every agent step, every tool call, every policy decision, sealed cryptographically.

01
What it did

Every action taken, recorded in a tamper-evident chain.

02
What it tried

Every blocked call recorded, not just permitted ones.

03
What was prevented

Policy decisions committed into the audit record, before dispatch.

Built for audit, procurement, and legal scrutiny.

  • Regulatory evidence A concrete artifact satisfying EU AI Act Articles 12 and 9 tamper-evident record-keeping requirements, and aligned with FCA, SEC, and FDA SaMD audit trail expectations.
  • Independent verification No need to trust operator infrastructure. Any auditor, regulator, or counterparty can rerun the verification themselves from the same inputs.
  • Pre-call control Every tool call is checked against a declarative policy before any side effect — allowed, blocked, or observed — and each decision is recorded as part of the run.
  • Byte-stable replay A recorded run can be re-executed from its transcript and checked for divergence down to the individual tool call, with deterministic inputs producing the same witness root.
  • Liability clarity In the event of a dispute, both parties work from the same verifiable record. Not competing log extracts. Not operator-provided summaries.

Across the organisation and across the table.

Chief Compliance Officers
Preparing for EU AI Act obligations and demonstrating tamper-evident record-keeping to regulators.
CTOs in Regulated Industries
Deploying AI into workflows that require provable auditability, not just logging.
Risk and Insurance Teams
Underwriting AI liability with a verifiable record both parties can rely on independently.
Legal Counsel
Establishing a clear, third-party-verifiable account of agent behaviour before a dispute arises.
Procurement Leads
Evaluating AI vendors against audit and compliance requirements with a concrete technical standard.
Safety and Red-Team Functions
Evaluating agent behaviour under controlled conditions with a tamper-evident record of what was attempted.

Designed against real regulatory requirements.

Framework Requirement addressed
EU AI Act Articles 12 and 9 — tamper-evident record-keeping and risk management systems for high-risk AI.
FCA / SEC Mandatory audit trails for high-autonomy AI systems acting in financial markets.
FDA SaMD Software as a Medical Device audit trail guidance — verifiable record of AI decision steps.
IEC 61508 Safety-critical systems — policy layer as a capability firewall with committed evidence of blocked commands.
IETF / SCITT The underlying witness protocol has been submitted as an IETF Internet-Draft and is designed to be carried as a SCITT Signed Statement for transparent, timestamped registration.

Start with evaluation. Deploy with confidence.

Cogitator is released under Apache 2.0. The protocol specification is also Apache 2.0 and free to implement independently.

IMPLEMENTATION — Apache 2.0.
PROTOCOL SPEC — Apache 2.0. Free to implement, cite, and build on.

Regulated deployment enquiries, procurement questions, and compliance assessment support are welcome directly.

george.g@tuta.io
github.com/noctem-o/cogitator