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

# Review Insights

> Review Insights work alongside your human reviewers to perform real-time root cause analysis.

As your team reviews completions and traces, the insights agent surfaces patterns and groups them into actionable findings.

<Frame>
  <img src="https://mintcdn.com/freeplay-485a287e/25FgAU7Ux93VTvoI/images/image-2.png?fit=max&auto=format&n=25FgAU7Ux93VTvoI&q=85&s=8bb11ebcd5617ca3d4a9e591fbc0efe4" alt="Review Insights panel showing identified patterns across reviewed completions" width="3232" height="2072" data-path="images/image-2.png" />
</Frame>

## How they work

<Frame>
  <img src="https://mintcdn.com/freeplay-485a287e/25FgAU7Ux93VTvoI/images/image-3.png?fit=max&auto=format&n=25FgAU7Ux93VTvoI&q=85&s=7a34f7da0472bfb5c4911b456a2de488" alt="Review Insights workflow showing how human labels feed into AI analysis" width="3232" height="2072" data-path="images/image-3.png" />
</Frame>

When humans label data in Freeplay the Insights agent analyzes each reviewed item in the background. It identifies common patterns, groups related items into **themes**, and suggests actions based on what it finds.

The inputs to Review Insights include:

* **Human labels** — annotations, notes, and scores from human reviewers
* **LLM-as-a-judge evaluations** — scores and reasoning from your auto-evaluators applied during review
* **Logs** — the completions or traces that were evaluated

## When they run

Review Insights run **anytime a human label is added** to data. Every annotation — notes, human evals, or LLM-as-a-judge evals — triggers the agent to analyze and update insights. When combined with [Review Queues](/core-concepts/review-queues) these review insights can point to key issues in your system.

<Note>
  Review Insights can be disabled in **Project Settings > AI Features**.
</Note>

<Tip>
  Review Insights themes are generated automatically and may occasionally be too broad or too narrow. Regularly review themes and use merge/prune actions to keep them useful.
</Tip>

## Related resources

* [AI Insights Overview](/core-concepts/ai/ai-insights) — How Freeplay's AI Insights work across the platform
* [Review Queues](/core-concepts/review-queues) — Set up human review workflows that generate Review Insights
* [Model-Graded Evaluations](/core-concepts/evaluations/model-graded-evaluations) — Configure the LLM judges that feed into Insights