> ## 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.

# Run Turn • AI Agent SDK

> run_turn: Execute a single turn using the prepared context.

# run\_turn

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

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

Execute a single turn using the prepared context.

This is the main execution entry point for all runtime types.
The context is immutable and contains all necessary configuration
for the turn execution.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
async def run_turn(context: PreparedTurnContext) -> str
```

## Parameters

<ParamField query="context" type="PreparedTurnContext" required={true}>
  The prepared turn context containing model, tools, transcript, delivery channels, and correlation IDs
</ParamField>

### Returns

<ResponseField name="Returns" type="str">
  The agent's response as a string
</ResponseField>

### Exceptions

<AccordionGroup>
  <Accordion title="RuntimeError">
    If execution fails
  </Accordion>

  <Accordion title="ValueError">
    If context is invalid or incompatible
  </Accordion>
</AccordionGroup>

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/runtime/protocols.py#L54">
  `praisonaiagents/runtime/protocols.py` at line 54
</Card>