> ## 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.

# Follow Up • AI Agent SDK

> follow_up: Ask a follow-up question based on a previous research interaction.

# follow\_up

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

> This is a method of the [**DeepResearchAgent**](../classes/DeepResearchAgent) class in the [**deep\_research\_agent**](../modules/deep_research_agent) module.

Ask a follow-up question based on a previous research interaction.

Only supported for Gemini provider.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def follow_up(query: str, previous_interaction_id: str, model: Optional[str]) -> DeepResearchResponse
```

## Parameters

<ParamField query="query" type="str" required={true}>
  The follow-up question
</ParamField>

<ParamField query="previous_interaction_id" type="str" required={true}>
  ID from a previous research response
</ParamField>

<ParamField query="model" type="Optional" required={false}>
  Model to use (defaults to gemini-3-pro for follow-ups)
</ParamField>

### Returns

<ResponseField name="Returns" type="DeepResearchResponse">
  DeepResearchResponse with the follow-up answer
</ResponseField>

## Uses

* `NotImplementedError`
* `create`

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/deep_research_agent.py#L1261">
  `praisonaiagents/agent/deep_research_agent.py` at line 1261
</Card>