> This page is for version Dev (default).
> For other versions, use one of these documentation indexes:
> - Dev (default): https://docs.nvidia.com/agent-policy-fabric/dev/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/agent-policy-fabric/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/agent-policy-fabric/_mcp/server.

# Tutorials

> Hands-on walkthroughs that set up a governance scenario with APF, configure its policy, show the expected behavior, and verify the audit evidence.

Each tutorial sets up one governance scenario end to end: the setup, the policy, the behavior you should see, and the audit evidence that proves it. The scenarios are introduced in [Use Cases](/agent-policy-fabric/about/use-cases).

Start with [Your First Signed Policy](/agent-policy-fabric/get-started/your-first-signed-policy) and [Your First Governed Agent](/agent-policy-fabric/get-started/your-first-governed-agent). The tutorials assume APF is running and registered with OpenShell as described there.

#### [Govern a Coding Agent](/agent-policy-fabric/tutorials/govern-a-coding-agent)

Give a coding agent read-only source control, approved inference endpoints, and nothing else.

#### [Protect Sensitive Data](/agent-policy-fabric/tutorials/protect-sensitive-data)

Deny tool calls that carry credentials, redact them from plain requests, and withhold personal data.

#### [Update a Signed Policy](/agent-policy-fabric/tutorials/update-a-signed-policy)

Change a rule, publish a new revision, and watch the gateway swap its evaluator without a restart.

#### [Reject a Tampered Bundle](/agent-policy-fabric/tutorials/reject-a-tampered-bundle)

Tamper with a signed bundle in three ways and see each one refused with a precise reason.