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

# Direct Response Mode

> Route requests to specialized agents who respond directly.

Use `mode=TeamMode.route` to route requests to the appropriate agent and return the member response directly. The legacy `respond_directly=True` flag still works, but `mode` is preferred.

This example creates a language router with three agents:

1. **English Agent** - Responds in English
2. **Japanese Agent** - Responds in Japanese
3. **Spanish Agent** - Responds in Spanish

<Steps>
  <Step title="Create a Python file">
    ```python respond_directly.py theme={null}
    from agno.agent import Agent
    from agno.models.openai import OpenAIResponses
    from agno.team.team import Team
    from agno.team.mode import TeamMode

    english_agent = Agent(
        name="English Agent",
        role="You only answer in English",
        model=OpenAIResponses(id="gpt-5.2"),
    )
    japanese_agent = Agent(
        name="Japanese Agent",
        role="You only answer in Japanese",
        model=OpenAIResponses(id="gpt-5.2"),
    )
    spanish_agent = Agent(
        name="Spanish Agent",
        role="You only answer in Spanish",
        model=OpenAIResponses(id="gpt-5.2"),
    )

    language_router = Team(
        name="Language Router",
        model=OpenAIResponses(id="gpt-5.2"),
        mode=TeamMode.route,
        members=[english_agent, japanese_agent, spanish_agent],
        instructions=[
            "Route questions to the appropriate language agent.",
            "If the language is not supported, respond in English.",
        ],
        markdown=True,
        show_members_responses=True,
    )

    # English
    language_router.print_response("How are you?", stream=True)

    # Japanese
    language_router.print_response("お元気ですか?", stream=True)

    # Spanish
    language_router.print_response("¿Cómo estás?", stream=True)
    ```
  </Step>

  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run Team">
    ```bash theme={null}
    python respond_directly.py
    ```
  </Step>
</Steps>