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

# Findings

> Discover known and unknown failure patterns in your AI traces

Findings is where you go from "here are a lot of traces" to "here are the specific patterns worth fixing." It has three views.

## Tracking: known patterns

**Tracking** holds pinned collections you monitor over time, the failure patterns you already know matter. Once a pattern is pinned, you can watch how often it recurs as new traces come in.

## Discovery: unknown patterns

**Discovery** is a chat interface over your pulled traces. Ask it questions about your data, let it surface patterns you didn't know to look for, and pin the interesting ones into a Tracking collection.

## Traces: the raw table

**Traces** is a paginated table of every ingested trace (model, latency, tokens, preview). Bulk-select any subset and push it straight into a seed dataset for [generation](/concepts).

## Getting traces in

Findings connects to your observability tool (Langfuse or LangSmith today) and pulls real LLM traces in. See [Connect AI Observability](/user-signals/connect-langfuse-langsmith) for setup, and [Signals & Journeys](/user-signals/overview) if you also want user events correlated with those traces.

<Warning>
  Findings is a UI-only feature today, there's no public API or SDK access yet.
</Warning>

## Next steps

<Card title="Reviews" icon="user-check" href="/reviews/overview">
  Route the patterns you find to a human reviewer
</Card>