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

# Expert analytics

> Inspect runs, status, and trends for an individual expert from the expert detail page.

Each expert has an **Analytics** tab on its detail page where you can review prior invocations and inspect a single run in depth. Use this tab to monitor expert health, diagnose failures, and understand usage patterns.

## Opening the Analytics tab

1. Navigate to the expert detail page at `/experts/<id>` (or open the expert from the marketplace and click its name).
2. Select the **Analytics** tab in the tab strip near the top of the page.

The tab loads the run list for that expert, showing recent invocations in reverse chronological order.

<Frame caption="The expert detail page with the Analytics tab selected, showing the run list and status-badge column.">
  <img src="https://mintcdn.com/devfactory/a8x3J4m-mTnV9e8F/images/expert-analytics-tab.png?fit=max&auto=format&n=a8x3J4m-mTnV9e8F&q=85&s=7f0cae3c6279b8cd62a830aa433e2569" alt="Expert detail page with Analytics tab selected showing run list table" width="1280" height="900" data-path="images/expert-analytics-tab.png" />
</Frame>

## Run list

The run list displays one row per invocation. Each row includes:

| Column         | Description                                                                                                                                                         |
| -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Request ID** | Unique identifier for the invocation (UUID assigned at invoke time).                                                                                                |
| **Status**     | Current or final status of the run, shown as a color-coded badge. See [Status badges](#status-badges) for all values.                                               |
| **Started at** | Timestamp when the invocation began.                                                                                                                                |
| **Duration**   | Wall-clock time from start to completion or failure.                                                                                                                |
| **View**       | Action button that opens the run detail drawer. Only shown for invocations that have a recorded request ID; older runs without one cannot be opened from this list. |

Use the **View** button in the rightmost column to open the run detail drawer for any row that has it. Rows are sorted newest-first. Use the run list to identify failing or slow invocations at a glance.

## Status badges

Each run is labeled with a status badge indicating its outcome. The possible values are:

| Status      | Meaning                                                                                     |
| ----------- | ------------------------------------------------------------------------------------------- |
| `queued`    | The invocation has been accepted and is waiting to be picked up.                            |
| `running`   | The expert is actively processing the request.                                              |
| `succeeded` | The invocation completed successfully and produced output.                                  |
| `failed`    | The invocation ended with an error. Open the run detail drawer for the error message.       |
| `cancelled` | The invocation was cancelled before completion (e.g. via the cancel endpoint or a timeout). |

<Info>
  A run that times out at the platform level is recorded as `failed` with an explanatory error message in the run detail drawer.
</Info>

## Run detail drawer

Click **View** on any row in the run list to open the **Run detail drawer** on the right side of the page. The drawer displays full metadata for that invocation:

* Request ID and status badge
* Started-at timestamp and duration
* Input message sent to the expert
* Output produced by the expert (if the run succeeded)
* Error message (if the run failed)
* Thread token (if the run was part of a multi-turn conversation)

<Info>
  If the trace contains more child runs than can be loaded into the timeline, the drawer shows the message: "Trace has more child runs than we could load — timeline shows the first 300 only." Only the first 300 child runs are rendered; deeper subtrees are truncated.
</Info>

Close the drawer by clicking the **×** button or clicking outside the drawer area.

<Frame caption="The run detail drawer opened over the run list, showing run metadata, status badge, and the close affordance.">
  <img src="https://mintcdn.com/devfactory/a8x3J4m-mTnV9e8F/images/expert-analytics-run-drawer.png?fit=max&auto=format&n=a8x3J4m-mTnV9e8F&q=85&s=9da53ea915d58fd89cb8009d81030e8a" alt="Run detail drawer showing run metadata and status badge over a dimmed run list" width="1280" height="900" data-path="images/expert-analytics-run-drawer.png" />
</Frame>

## Next steps

<CardGroup cols={2}>
  <Card title="Talking to Your Expert" icon="message" href="/experts/talking-to-your-agent">
    Send messages and manage conversations with an expert.
  </Card>

  <Card title="API Reference — Invoke an Expert" icon="code" href="/reference/api-reference#invoke-an-expert">
    Invoke experts programmatically and retrieve run status via the REST API.
  </Card>
</CardGroup>