# GraderResponse

> **Class** in `deepagents`

📖 [View in docs](https://reference.langchain.com/python/deepagents/middleware/rubric/GraderResponse)

Structured output the grader sub-agent must emit.

Passed as `response_format=GraderResponse` to `create_agent` so the
underlying provider's structured output strategy is auto-selected.

## Signature

```python
GraderResponse()
```

## Extends

- `BaseModel`

## Properties

- `result`
- `explanation`
- `criteria`

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/838433b4dcd9efa0bacba67d07e61440b43c4459/libs/deepagents/deepagents/middleware/rubric.py#L309)