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

# Guardrail Tutorials

<a id="guardrails-tutorials" />

Use the following tutorials to learn how to accomplish common guardrail tasks using the NeMo Guardrails API.

Before starting a tutorial, complete [Setup](/documentation/get-started) to configure a `ModelProvider` and discover models. The tutorials assume you have models available in the `default` workspace.

Once a `ModelProvider` is configured, use Model Entity references (`workspace/name` format) as the `model` in your guardrail configurations. The guardrails plugin resolves task model endpoints through IGW's route table. Refer to [Model Routing](/documentation/guardrail-models/core-concepts/running-inference#guardrails-model-routing) for more details.

```python
guardrails_config = {
    "models": [
        {
            "type": "content_safety",
            "engine": "nim",
            "model": "default/nvidia-llama-3-1-nemotron-safety-guard-8b-v3",
        }
    ],
    # ... rest of config
}
```

Deploy NemoGuard NIMs in your environment

<small>
  nemo-guardrails

   

  nemoguard
</small>

Use Content Safety checks to detect and block harmful content

<small>
  nemo-guardrails

   

  nemoguard
</small>

Configure parallel rails for input and output guardrails.

<small>
  nemo-guardrails
</small>

Safety checks for multimodal data with NeMo Guardrails API.

<small>
  nemo-guardrails
</small>

Configure checks for SQL, XSS, template, and code injection.

<small>
  nemo-guardrails
</small>