Async Task Mode Example

Demonstrates task mode using the async API (arun / aprint_response).

Demonstrates task mode using the async API (arun / aprint_response). Useful for applications that need non-blocking execution, such as web servers.

async_task_mode.py

"""
Async Task Mode Example

Demonstrates task mode using the async API (arun / aprint_response).
Useful for applications that need non-blocking execution, such as web servers.

Run: .venvs/demo/bin/python cookbook/03_teams/02_modes/tasks/07_async_task_mode.py
"""

import asyncio

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
# ---------------------------------------------------------------------------

planner = Agent(
    name="Planner",
    role="Creates structured plans and outlines",
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=[
        "You are a planning specialist.",
        "Create clear, actionable plans with numbered steps.",
        "Consider dependencies between steps.",
    ],
)

executor = Agent(
    name="Executor",
    role="Implements plans and produces deliverables",
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=[
        "You are an execution specialist.",
        "Take a plan and produce the requested deliverable.",
        "Be thorough and detailed in your output.",
    ],
)

reviewer = Agent(
    name="Reviewer",
    role="Reviews deliverables for quality and completeness",
    model=OpenAIResponses(id="gpt-5-mini"),
    instructions=[
        "You are a quality reviewer.",
        "Check deliverables for completeness, accuracy, and quality.",
        "Provide specific improvement suggestions.",
    ],
)

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

project_team = Team(
    name="Project Team",
    mode=TeamMode.tasks,
    model=OpenAIResponses(id="gpt-5.2"),
    members=[planner, executor, reviewer],
    instructions=[
        "You are a project team leader.",
        "For each request, follow this workflow:",
        "1. Have the Planner create a plan",
        "2. Have the Executor implement the plan",
        "3. Have the Reviewer check the deliverable",
        "Use task dependencies to enforce the correct ordering.",
    ],
    show_members_responses=True,
    markdown=True,
    max_iterations=10,
)


# ---------------------------------------------------------------------------
# Run Team
# ---------------------------------------------------------------------------
async def main():
    """Run multiple task-mode requests concurrently."""
    # Single async call
    response = await project_team.arun(
        "Create a 5-step onboarding checklist for new software engineers "
        "joining a startup. Include what to do in the first week."
    )
    print("--- Final Response ---")
    print(response.content)


if __name__ == "__main__":
    asyncio.run(main())

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno openai
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

   Save the code above as async_task_mode.py, then run:

   python async_task_mode.py
   

Full source: cookbook/03_teams/02_modes/tasks/07_async_task_mode.py