> ## 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.

# Multi-Run Session with Task Mode

> Demonstrates that task state persists across multiple runs within the same session.

Demonstrates that task state persists across multiple runs within the same session. The first run creates and executes tasks; the second run can reference prior task results.

```python multi_run_session.py theme={null}
"""
Multi-Run Session with Task Mode

Demonstrates that task state persists across multiple runs within the same
session. The first run creates and executes tasks; the second run can
reference prior task results.

Run: .venvs/demo/bin/python cookbook/03_teams/02_modes/tasks/10_multi_run_session.py
"""

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.team.mode import TeamMode
from agno.team.team import Team

# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------

researcher = Agent(
    name="Researcher",
    role="Research specialist",
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=["Provide concise, factual research summaries."],
)

analyst = Agent(
    name="Analyst",
    role="Data analyst who draws conclusions from research",
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=["Analyze data and draw actionable conclusions."],
)

# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------

team = Team(
    name="Research Analysis Team",
    mode=TeamMode.tasks,
    model=OpenAIResponses(id="gpt-5.2"),
    members=[researcher, analyst],
    session_id="task-mode-demo-session",
    instructions=[
        "You are a research and analysis team leader.",
        "Decompose requests into research and analysis tasks.",
    ],
    show_members_responses=True,
    markdown=True,
    max_iterations=8,
)

# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    print("=" * 60)
    print("RUN 1: Initial research")
    print("=" * 60)
    response1 = team.run(
        "Research the pros and cons of microservices architecture "
        "vs monolithic architecture for a startup."
    )
    print(response1.content)

    print("\n" + "=" * 60)
    print("RUN 2: Follow-up request (same session)")
    print("=" * 60)
    response2 = team.run(
        "Based on the previous analysis, which architecture would you "
        "recommend for a team of 5 engineers building a B2B SaaS product? "
        "Provide a concrete recommendation."
    )
    print(response2.content)
```

## Run the Example

<Steps>
  <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 the example">
    Save the code above as `multi_run_session.py`, then run:

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

Full source: [cookbook/03\_teams/02\_modes/tasks/10\_multi\_run\_session.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/02_modes/tasks/10_multi_run_session.py)