> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# stream • AI Agent SDK

> stream: Stream a prompt response as text chunks.

# stream

<div className="flex items-center gap-2">
  <Badge color="blue">Async</Badge>
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**ManagedBackendProtocol**](../classes/ManagedBackendProtocol) class in the [**protocols**](../modules/protocols) module.

Stream a prompt response as text chunks.

Yields text fragments as the managed agent produces them.
Used when Agent is invoked with stream=True.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
async def stream(prompt: str) -> AsyncIterator[str]
```

## Parameters

<ParamField query="prompt" type="str" required={true}>
  The user message. \*\*kwargs: Provider-specific options. Text chunks from the agent's response.
</ParamField>

### Returns

<ResponseField name="Returns" type="AsyncIterator[str]">
  The result of the operation.
</ResponseField>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/protocols.py#L382">
  `praisonaiagents/agent/protocols.py` at line 382
</Card>