HomeUse cases › How to audit AI agent actions
Use case

How to audit AI agent actions

Keep a tamper-evident record of every decision — allow or deny — so you can prove after the fact exactly what each agent did and under whose authority.

Logs you can trust

An ordinary log can be edited. Liceat records every authorization decision as a leaf in an append-only Merkle transparency log, signed by the issuer key. Anyone can verify that a record is present and that the log has only ever grown — the same guarantee that secures the web's certificates, computed instantly and without a blockchain.

What each entry captures

Export a self-verifying compliance bundle for an auditor: they recompute the Merkle root and re-run the hash chain to confirm the record is complete and unaltered — with zero trust in you.

Frequently asked

What is Liceat?

Liceat is permission infrastructure for AI agents. You issue a warrant — a scoped, spend-capped, revocable token — that grants an agent narrow authority; the agent presents it at the point of action; Liceat enforces it (scope, spend, rate, holder-binding, revocation) and records every decision in a tamper-evident log. It is open source with a zero-dependency SDK for TypeScript and Python.

Is it free?

The SDK and self-hosted gateway are free and open source. The hosted gateway at liceat.com gives 10,000 free decisions with no card, then meters at fractions of a cent per decision — payable by card or USDC.

Give your agents permission, not your keys.

Free to self-host. 10,000 free decisions on the hosted gateway — no card.

Get an API key Read the docs