> ## Documentation Index
> Fetch the complete documentation index at: https://vijil-mintlify-a91c9b66.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Protecting Groq Agents

> Evaluate a Groq-powered agent with Vijil and protect it with Dome.

<Tip>
  **TL;DR:** Wrap a Groq [Agent](/owner-guide/register-agents/what-is-an-agent) in a small class that runs `dome.async_guard_input` before the model and `dome.async_guard_output` after it, then evaluate the unprotected and protected versions to measure the difference.
</Tip>

This tutorial builds a news Agent on Groq's serverless inference, evaluates it with Vijil, and protects it with Dome. The full runnable code is in the [`GroqAgents` tutorial folder](https://github.com/vijilAI/vijil-dome/tree/main/vijil_dome/tutorials/GroqAgents).

## Prerequisites

```bash theme={null}
pip install vijil-dome vijil openai
```

```bash theme={null}
GROQ_API_KEY=<your Groq key>
TAVILY_API_KEY=<your Tavily key>
VIJIL_API_KEY=<your Vijil key>
```

Free-plan Vijil users also need an [Ngrok authtoken](https://dashboard.ngrok.com/get-started/setup/python) (`NGROK_AUTHTOKEN`).

## Walkthrough

<Steps>
  <Step title="Build the Agent">
    The base Agent calls Groq's OpenAI-compatible endpoint and uses Tavily for web search:

    ```python theme={null}
    from openai import AsyncOpenAI

    class MyNewsBot:
        def __init__(self, groq_api_key: str, tavily_api_key: str,
                     model: str = "openai/gpt-oss-20b"):
            self.client = AsyncOpenAI(
                base_url="https://api.groq.com/openai/v1",
                api_key=groq_api_key,
            )
            self.tools = [{
                "type": "mcp",
                "server_url": f"https://mcp.tavily.com/mcp/?tavilyApiKey={tavily_api_key}",
                "server_label": "tavily",
                "require_approval": "never",
            }]

        async def answer_query(self, query_string: str):
            response = await self.client.responses.create(
                model=self.model, input=query_string, tools=self.tools, stream=False,
            )
            return response.output_text
    ```
  </Step>

  <Step title="Add Dome Protection">
    Wrap the Agent so inputs and outputs pass through Dome. Guard the input first, short-circuit if it is flagged, then guard the model output:

    ```python theme={null}
    from vijil_dome import Dome

    class MyProtectedNewsBot:
        def __init__(self, groq_api_key: str, tavily_api_key: str):
            self.dome = Dome()
            self.news_bot = MyNewsBot(groq_api_key, tavily_api_key)
            self.input_blocked_message = "This request violates my usage guidelines."
            self.output_blocked_message = "This content violates my usage guidelines."

        async def answer_query(self, query_string: str):
            input_scan = await self.dome.async_guard_input(query_string)
            if not input_scan.is_safe():
                return self.input_blocked_message

            agent_output = await self.news_bot.answer_query(query_string)

            output_scan = await self.dome.async_guard_output(agent_output)
            if not output_scan.is_safe():
                return self.output_blocked_message

            return output_scan.response_string
    ```
  </Step>

  <Step title="Evaluate Both Versions">
    Register each Agent with the Vijil SDK and run the `security` harness. See the [Evaluate SDK guide](/developer-guide/agentic/quickstart) for the full evaluation flow. The tutorial script runs the unprotected Agent by default and the protected Agent with a flag:

    ```bash theme={null}
    # Unprotected
    python -m evaluate_agent

    # Protected with Dome
    python -m evaluate_agent --protected=true
    ```

    Compare the two [Trust Scores](/concepts/trust-score/introduction) to see how much Dome improves the Agent's security posture.
  </Step>
</Steps>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Ngrok antivirus warnings">
    Ngrok is [safe](https://ngrok.com/docs/faq/#is-ngrok-a-virus); traffic reaching your Agent comes only from Vijil's systems.
  </Accordion>

  <Accordion title="Rate limiting">
    If you hit rate limits, lower the request frequency or upgrade your Groq and Tavily accounts.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Autotuned Guardrails" icon="wand-sparkles" href="/tutorials/protect-agents/autotuned-guardrails">
    Generate a configuration from the evaluation
  </Card>

  <Card title="Protection Overview" icon="shield" href="/developer-guide/protect/overview">
    How Dome guards inputs and outputs
  </Card>
</CardGroup>