# Research Team (/agent-os/usage/interfaces/a2a/team)



## Code [#code]

```python title="a2a_research_team.py"
from agno.agent.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.os import AgentOS
from agno.team import Team

researcher = Agent(
    name="researcher",
    role="Research Assistant",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions="You are a research assistant. Find information and provide detailed analysis.",
    markdown=True,
)

writer = Agent(
    name="writer",
    role="Content Writer",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions="You are a content writer. Create well-structured content based on research.",
    markdown=True,
)

research_team = Team(
    members=[researcher, writer],
    name="research_team",
    instructions="""
    You are a research team that helps users with research and content creation.
    First, use the researcher to gather information, then use the writer to create content.
    """,
    show_members_responses=True,
    get_member_information_tool=True,
    add_member_tools_to_context=True,
)

# Setup our AgentOS app
agent_os = AgentOS(
    teams=[research_team],
    a2a_interface=True,
)
app = agent_os.get_app()


if __name__ == "__main__":
    """Run our AgentOS.

    You can see the configuration and available apps at:
    http://localhost:7777/config

    """
    agent_os.serve(app="a2a_research_team:app", reload=True)
```

## Usage [#usage]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Set Environment Variables">
    ```bash
    export OPENAI_API_KEY=your_openai_api_key
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U "agno[os,a2a]" openai
    ```
  </Step>

  <Step title="Run Example">
    ```bash
    python a2a_research_team.py
    ```
  </Step>
</Steps>

## Key Features [#key-features]

* **Multi-Agent Collaboration**: Researcher and writer working together
* **Specialized Roles**: Distinct expertise and responsibilities
* **Transparent Process**: See individual agent contributions
* **Coordinated Workflow**: Structured research-to-content pipeline
* **A2A Endpoints**: The team is served over the protocol routes `POST /a2a/teams/{id}/v1/message:send` and `message:stream`

## Team Members [#team-members]

* **Researcher**: Information gathering and analysis specialist
* **Writer**: Content creation and structuring expert