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

# Production Results

> Fetch production evaluation sessions and their eval outcomes

## Overview

The production counterpart of [Simulation Results](/api-reference/endpoint/simulation-sessions).
Returns production evaluation sessions with their eval outcomes, newest first, whether
those conversations arrived as uploaded transcripts or as
[live traces](/api-reference/endpoint/live-traces).

No evaluation id required.

## Endpoint

```
GET /api/prod-evaluations/sessions/
```

## Authentication

```http theme={null}
x-usertrace-api-key: ut_live_YOUR_KEY_HERE
```

See [Authentication](/api-reference/authentication).

## Query parameters

All filters are optional.

<ParamField query="run" type="string">
  Substring match on the **evaluation run's** name, e.g. `Compliance V3`.
  Case-insensitive.
</ParamField>

<ParamField query="eval" type="string">
  Keep only sessions scored by the named **eval**, e.g. `Tone check`. Substring match,
  case-insensitive.
</ParamField>

<ParamField query="failed_only" type="boolean" default="false">
  Return only sessions with at least one failing eval, showing only the failing outcomes.
</ParamField>

<ParamField query="started_after" type="string">
  ISO 8601 timestamp. Sessions started at or after this moment.
</ParamField>

<ParamField query="started_before" type="string">
  ISO 8601 timestamp. Sessions started at or before this moment.
</ParamField>

<ParamField query="include_traces" type="boolean" default="false">
  Include the conversation turns for each session.
</ParamField>

<ParamField query="skip" type="integer" default="0">
  Number of sessions to skip.
</ParamField>

<ParamField query="limit" type="integer" default="50">
  Sessions per page. Capped at 500.
</ParamField>

<Info>
  **`run` vs `eval`**: a *run* is one batch job that scored N evals over M conversations
  ("Compliance V3"). An *eval* is a single scoring criterion ("Tone check"). `run` is the
  production analogue of `simulation` on the simulations endpoint.
</Info>

## Example request

```bash theme={null}
curl -X GET "https://api.getusertrace.com/api/prod-evaluations/sessions/?run=Compliance&failed_only=true" \
  -H "x-usertrace-api-key: ut_live_YOUR_KEY_HERE" \
  -H "Content-Type: application/json"
```

## Response

<ResponseField name="items" type="array">
  The sessions on this page.

  <Expandable title="Session">
    <ResponseField name="url" type="string">
      Deep link to the session in the web app.
    </ResponseField>

    <ResponseField name="run" type="string">
      Name of the evaluation run this session belongs to.
    </ResponseField>

    <ResponseField name="source_session_id" type="string">
      **Your own** identifier for the conversation: the session id from an uploaded
      transcript, or the `gen_ai.conversation.id` you sent with live traces. Use it to
      correlate results back to your own logs.
    </ResponseField>

    <ResponseField name="status" type="string">
      Session status, e.g. `completed`.
    </ResponseField>

    <ResponseField name="started_at" type="string">ISO 8601 timestamp.</ResponseField>
    <ResponseField name="ended_at" type="string">ISO 8601 timestamp.</ResponseField>

    <ResponseField name="outcome_summary" type="object">
      `total_evaluations`, `passed_count`, `failed_count`, `pass_rate` for the **whole**
      session.
    </ResponseField>

    <ResponseField name="eval_outcomes" type="array">
      One entry per eval that scored this session: `eval_name`, `eval_category`,
      `eval_type`, `outcome`, `reasoning`.
    </ResponseField>

    <ResponseField name="traces" type="array">
      Conversation turns: `session_sequence`, `user_input`, `agent_response`. Present
      only with `include_traces=true`.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="total" type="integer">
  Sessions matching the filters, across all pages.
</ResponseField>

<ResponseField name="skip" type="integer" />

<ResponseField name="limit" type="integer" />

```json theme={null}
{
  "items": [
    {
      "url": "https://app.getusertrace.com/production-eval/ca0a2090-...?sessionId=b3e046d3-...",
      "run": "Compliance V3",
      "source_session_id": "814b9f0898",
      "status": "completed",
      "started_at": "2026-07-25T12:30:56.263968+00:00",
      "ended_at": "2026-07-25T12:31:26.072613+00:00",
      "outcome_summary": {
        "total_evaluations": 1,
        "passed_count": 1,
        "failed_count": 0,
        "pass_rate": 1.0
      },
      "eval_outcomes": [
        {
          "eval_name": "Compliance V3: Bias, Hallucination, Policy Handling",
          "eval_category": "compliance",
          "eval_type": "session_level",
          "outcome": "pass",
          "reasoning": "No policy-restricted advice was offered..."
        }
      ]
    }
  ],
  "total": 666,
  "skip": 0,
  "limit": 50
}
```

<Note>
  **Production sessions have no agent, scenario or persona.** Those concepts exist only
  for simulations, so the keys are absent rather than `null`. Use
  [Simulation Results](/api-reference/endpoint/simulation-sessions) for simulation runs.
</Note>

## What's excluded

**Sessions with no eval outcomes don't appear.** An evaluation creates one session per
uploaded document, and the transcript parser then fans out into child sessions that carry
all the outcomes, leaving the parent as a bookkeeping row with nothing to report. `total`
counts only sessions that actually have results.

## Failures only

With `failed_only=true`, `outcome_summary` still describes the **whole** session, so
`len(eval_outcomes)` equals `outcome_summary.failed_count` and is deliberately smaller
than `total_evaluations`.