> ## Documentation Index
> Fetch the complete documentation index at: https://docs-beta.actrail.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# See it work

> From a captured trail to an enforced policy.

Once Claude Code is connected and you've used it a little:

<Steps>
  <Step title="Find your trail" icon="timeline">
    Open **Trails** in the [console](https://app.actrail.ai). Your session is a
    **trail** — the timeline of what the agent did.
    <Note>Risks are detected when a session **closes**. A still-open session is normal.</Note>
  </Step>

  <Step title="Review a flag" icon="inbox">
    Flagged risks land in the **Inbox**, each with a short explanation and the evidence.
  </Step>

  <Step title="Make a policy" icon="gavel">
    Resolve the flag into a **policy**. It starts in **shadow** — it reports what it
    *would* block, without blocking anything yet.
  </Step>

  <Step title="Enforce" icon="shield-halved">
    When you trust it, switch the policy to **enforce**. The matching action is blocked
    on the agent's next run.
  </Step>
</Steps>