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

# Background Workflow Execution

> How to execute workflows as non-blocking background tasks

Execute workflows as non-blocking background tasks by passing `background=True` to `Workflow.arun()`. This returns a `WorkflowRunOutput` object with a `run_id` for polling the workflow status until completion.

<Note>
  Background execution requires async workflows using `.arun()`. Poll for results using `workflow.get_run(run_id)` and check completion status with `.has_completed()`.

  Ideal for long-running operations like large-scale data processing, multi-step research, or batch operations that shouldn't block your main application thread.
</Note>

## Example

```python theme={null}
import asyncio

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.yfinance import YFinanceTools
from agno.utils.pprint import pprint_run_response
from agno.workflow.step import Step
from agno.workflow.workflow import Workflow

# Define agents
hackernews_agent = Agent(
    name="Hackernews Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from Hackernews posts",
)
finance_agent = Agent(
    name="Finance Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[YFinanceTools()],
    role="Get stock prices and financial data",
)

# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    members=[hackernews_agent, finance_agent],
    instructions="Research tech topics and related stocks",
)

content_planner = Agent(
    name="Content Planner",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=[
        "Plan a content schedule over 4 weeks for the provided topic and research content",
        "Ensure that I have posts for 3 posts per week",
    ],
)

# Define steps
research_step = Step(
    name="Research Step",
    team=research_team,
)

content_planning_step = Step(
    name="Content Planning Step",
    agent=content_planner,
)

content_creation_workflow = Workflow(
    name="Content Creation Workflow",
    description="Automated content creation from blog posts to social media",
    db=SqliteDb(
        session_table="workflow_session",
        db_file="tmp/workflow.db",
    ),
    steps=[research_step, content_planning_step],
)


async def main():
    print("Starting Async Background Workflow Test")

    # Start background execution (async)
    bg_response = await content_creation_workflow.arun(
        input="AI trends in 2024", background=True
    )
    print(f"Initial Response: {bg_response.status} - {bg_response.content}")
    print(f"Run ID: {bg_response.run_id}")

    # Poll every 5 seconds until completion
    poll_count = 0

    while True:
        poll_count += 1
        print(f"\nPoll #{poll_count} (every 5s)")

        result = content_creation_workflow.get_run(bg_response.run_id)

        if result is None:
            print("Workflow not found yet, still waiting...")
            if poll_count > 50:
                print(f"Timeout after {poll_count} attempts")
                break
            await asyncio.sleep(5)
            continue

        if result.has_completed():
            break

        if poll_count > 200:
            print(f"Timeout after {poll_count} attempts")
            break

        await asyncio.sleep(5)

    final_result = content_creation_workflow.get_run(bg_response.run_id)

    print("\nFinal Result:")
    print("=" * 50)
    pprint_run_response(final_result, markdown=True)


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

<Note>
  You can also use WebSocket for background workflows. See the [Workflow Websocket](https://github.com/agno-agi/agno/tree/main/cookbook/05_workflows/_06_advanced_basics/_05_background_execution/background_execution_using_websocket) example.
</Note>

## Developer Resources

* [Background Execution Poll](https://github.com/agno-agi/agno/blob/main/cookbook/05_workflows/_06_advanced_basics/_05_background_execution/background_execution_poll.py)
* [Background Execution Websocket](https://github.com/agno-agi/agno/tree/main/cookbook/05_workflows/_06_advanced_basics/_05_background_execution/background_execution_using_websocket)