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

# Analysis Overview

> Use Docent to surface and measure unexpected behaviors

Docent's analysis tools take you from a collection of agent runs to measurable insights about agent behavior.

* **Explore your data.** Docent supports fast structured queries such as "Display average reward by model" and unstructured exploration such as surfacing primary failure modes and grouping traces that display each one
* **Quantify behavior prevalence.** Measure behaviors like "sycophancy" and "reading irrelevant files" by using Docent to create reliable judges.
* **Aggregate expert feedback.** Use Docent to collaboratively annotate and label your traces. Use labels to inform your judges.

## Get started

<CardGroup cols={2}>
  <Card title="Explore with the Docent Agent" icon="eye" href="/analysis/docent-agent">
    Use the Docent Agent to surface new behaviors. Ask for insights like "Identify the main failure modes that explain why my agent fails on Terminal-Bench" or "Display average reward by model" and receive a report of its findings.
  </Card>

  <Card title="Refine a judge" icon="scale-balanced" href="/analysis/rubrics/refinement">
    Use refinement to quantify behavior prevalence. Docent's refinement tools turn fuzzy behaviors like "sycophancy" or "cheating" into detailed decision-procedure that an LLM judge can reliably apply.
  </Card>
</CardGroup>

## Related pages

* **[Behavior rubrics](/analysis/rubrics):** what rubrics are and how judges evaluate them.
* **[Structured queries (DQL)](/analysis/dql):** the query language the agent uses for quantitative questions.
* **[Search and clustering](/analysis/search-and-clustering):** semantic search over runs, with clustering for grouping results.
* **[Labeling](/analysis/labeling):** capture human judgments on specific runs.
* **[Exporting](/analysis/exporting):** download transcripts and metadata for local analysis.