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
Approvals are sealed and timestamped, so you can show the approval came before the run.
01 / 04
Your teamPolicy
Your team registers the policy the agent must follow.
What the evidence proves
- Which policy version each run ran under.
- That an owner's approval of that version was registered in Sigill, and when.
- Whether that approval was in effect when the run started.
What it does not prove
- That the owner personally signed the approval. Sigill attests that it was registered.
- That the approved policy was a good one.
- That the agent did nothing beyond what was recorded.
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.