> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-docs-scavio-google-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Support Team

> A multi-agent team that routes support questions to the right specialist.

A multi-agent team that routes support questions to the right specialist. Technical Support handles code and API questions; Documentation Specialist searches Slack history and the web for existing answers.

```python support_team.py theme={null}
"""
Support Team
============

A multi-agent team that routes support questions to the right specialist.
Technical Support handles code and API questions; Documentation Specialist
searches Slack history and the web for existing answers.

Key concepts:
  - ``Team`` with a coordinator model routes questions to the best member.
  - One member uses ``SlackTools`` to find past answers in Slack threads.
  - Both members use ``WebSearchTools`` for external documentation.

Slack scopes: app_mentions:read, assistant:write, chat:write, im:history,
             search:read, channels:history

Environment variables:
    SLACK_TOKEN         Bot token (xoxb-) for standard Slack APIs
    SLACK_USER_TOKEN    User token (xoxp-) required for search_messages
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os.app import AgentOS
from agno.os.interfaces.slack import Slack
from agno.team import Team
from agno.tools.slack import SlackTools
from agno.tools.websearch import WebSearchTools

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

team_db = SqliteDb(session_table="team_sessions", db_file="tmp/support_team.db")

# Technical Support Agent
tech_support = Agent(
    name="Technical Support",
    role="Code and technical troubleshooting",
    model=OpenAIChat(id="gpt-4o"),
    tools=[WebSearchTools()],
    instructions=[
        "You handle technical questions about code, APIs, and implementation.",
        "Provide code examples when helpful.",
        "Search for current documentation and best practices.",
    ],
    markdown=True,
)

# Documentation Agent
docs_agent = Agent(
    name="Documentation Specialist",
    role="Finding and explaining documentation",
    model=OpenAIChat(id="gpt-4o"),
    tools=[
        SlackTools(
            enable_search_messages=True,
            enable_get_thread=True,
        ),
        WebSearchTools(),
    ],
    instructions=[
        "You find relevant documentation and past discussions.",
        "Search Slack for previous answers to similar questions.",
        "Search the web for official documentation.",
        "Explain documentation in simple terms.",
    ],
    markdown=True,
)

# The Team with a coordinator
support_team = Team(
    name="Support Team",
    model=OpenAIChat(id="gpt-4o"),
    members=[tech_support, docs_agent],
    description="A support team that routes questions to the right specialist.",
    instructions=[
        "You coordinate support requests.",
        "Route technical/code questions to Technical Support.",
        "Route 'how do I' or 'where is' questions to Documentation Specialist.",
        "For complex questions, consult both agents.",
    ],
    db=team_db,
    add_history_to_context=True,
    num_history_runs=3,
    markdown=True,
)

agent_os = AgentOS(
    teams=[support_team],
    interfaces=[
        Slack(
            team=support_team,
            reply_to_mentions_only=True,
        )
    ],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="support_team:app", reload=True)
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os,slack]" ddgs openai
    ```
  </Step>

  <Step title="Export environment variables">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      export SLACK_SIGNING_SECRET="your_slack_signing_secret_here"
      export SLACK_TOKEN="your_slack_token_here"
      export SLACK_USER_TOKEN="your_slack_user_token_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      $Env:SLACK_SIGNING_SECRET="your_slack_signing_secret_here"
      $Env:SLACK_TOKEN="your_slack_token_here"
      $Env:SLACK_USER_TOKEN="your_slack_user_token_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Configure Slack">
    Complete [Slack setup](/agent-os/interfaces/slack/setup): create the app, expose the local server through public HTTPS, and set the event request URL to `<public-url>/slack/events`. Add `search:read` under User Token Scopes, reinstall the app, and export its `xoxp-` User OAuth Token as `SLACK_USER_TOKEN`.
  </Step>

  <Step title="Run the example">
    Save the code above as `support_team.py`, then run:

    ```bash theme={null}
    python support_team.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/interfaces/slack/support\_team.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/interfaces/slack/support_team.py)