Run Autonomous Async • AI Agent SDK

</div>

This is a method of the Agent class in the agent module.

Async variant of run_autonomous() for concurrent agent execution.

This method executes a task autonomously using async I/O, enabling multiple agents to run concurrently without blocking. It handles:

• Progressive escalation based on task complexity
• Doom loop detection and recovery
• Iteration limits and timeouts
• Completion detection (keyword-based or promise-based)
• Optional context clearing between iterations

Signature

async def run_autonomous_async(prompt: str, max_iterations: Optional[int], timeout_seconds: Optional[float], completion_promise: Optional[str], clear_context: bool) -> Any

Parameters

Returns

Exceptions

Usage

import asyncio

    async def main():
        agent = Agent(instructions="...", autonomy=True)
        result = await agent.run_autonomous_async(
            "Refactor the auth module",
            completion_promise="DONE",
            clear_context=True
        )
        if result.success:
            print(result.output)

    asyncio.run(main())

Uses

• ValueError
• time_module.time
• isoformat
• datetime.now
• get_recommended_stage
• is_set
• AutonomyResult
• achat
• record_response
• hash

Source

Related Documentation