Skip to main content
Once Claude Code is connected and you’ve used it a little:

Find your trail

Open Trails in the console. Your session is a trail — the timeline of what the agent did.
Risks are detected when a session closes. A still-open session is normal.

Review a flag

Flagged risks land in the Inbox, each with a short explanation and the evidence.

Make a policy

Resolve the flag into a policy. It starts in shadow — it reports what it would block, without blocking anything yet.

Enforce

When you trust it, switch the policy to enforce. The matching action is blocked on the agent’s next run.