What would you like to secure?
AI agents in production
Can you stop an AI agent, and prove what it did?
An agent that can approve a claim or release a payment can also do the wrong thing. Sigill Guard stops actions your policy forbids before they run, and every run leaves a record that can be checked independently of the system that ran the agent.
03 · How Sigill helps
Sigill Guard checks every action before it runs, and stops the ones your policy forbids.
01 / 04
Your teamApproved policy
Your team writes the rules, for example which tools an agent may never use. They are written in an open policy language, and an owner approves them before they are used.
What the evidence proves
- Every decision the guard recorded: allowed, refused or halted, and under which rule.
- That a refused call has no recorded result.
- Sigill's own check of the record against the approved policy, sealed and timestamped.
What it does not prove
- That a refused tool did not run some other way. The guard stops calls that go through the SDK.
- Steps the agent did not record. No rule sees them.
- That the policy covers every risk.
04 · Go deeper
Technical depth, when you want it.
Policy and enforcement Where the guard runs, a policy example, and what happens when Sigill is unreachable.Agent evidence in the API docs Recording runs, policies, approvals and findings.Open-source SDKs Python and .NET recorders and verifiers, Apache 2.0.Verify a run bundle Check an exported run in your browser, no account needed.
Try it yourself, or run a pilot
Create an account and an API key to evaluate Sigill on your own, or talk to us about a pilot.