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

# Get Run

> Get detailed run results

Retrieve detailed results for a test run including all turns, evaluations, and metrics.

<ParamField path="run_id" type="string" required>
  Unique run identifier
</ParamField>

<ResponseField name="run_id" type="string" required>
  Run identifier
</ResponseField>

<ResponseField name="status" type="string" required>
  Run status: `queued`, `running`, `completed`, `failed`
</ResponseField>

<ResponseField name="success" type="boolean" required>
  Whether all turns passed
</ResponseField>

<ResponseField name="test_case" type="object" required>
  Test case information

  <Expandable title="properties">
    <ResponseField name="id" type="string">
      Test case ID
    </ResponseField>

    <ResponseField name="name" type="string">
      Test case name
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="agent" type="object" required>
  Agent information

  <Expandable title="properties">
    <ResponseField name="id" type="string">
      Agent ID
    </ResponseField>

    <ResponseField name="name" type="string">
      Agent name
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="turns" type="array" required>
  Array of turn results

  <Expandable title="turn object">
    <ResponseField name="turn_index" type="integer">
      Turn position
    </ResponseField>

    <ResponseField name="input" type="array">
      Input messages
    </ResponseField>

    <ResponseField name="output" type="array">
      Output messages
    </ResponseField>

    <ResponseField name="expected_behavior" type="string">
      Expected behavior
    </ResponseField>

    <ResponseField name="success" type="boolean">
      Whether turn passed
    </ResponseField>

    <ResponseField name="evaluation" type="object">
      Evaluation results

      <Expandable title="properties">
        <ResponseField name="overall_pass" type="boolean">
          Overall pass/fail
        </ResponseField>

        <ResponseField name="scorer_outputs" type="object">
          Per-scorer results with score and reasoning
        </ResponseField>

        <ResponseField name="grader_output" type="string">
          Grader explanation
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="metrics" type="object">
      Performance metrics

      <Expandable title="properties">
        <ResponseField name="latency_ms" type="integer">
          Response latency
        </ResponseField>

        <ResponseField name="tokens" type="object">
          Token usage
        </ResponseField>

        <ResponseField name="cost_usd" type="number">
          Estimated cost
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="trace_id" type="string">
      Linked trace ID
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="summary" type="object" required>
  Run summary

  <Expandable title="properties">
    <ResponseField name="turns_passed" type="integer">
      Passing turns
    </ResponseField>

    <ResponseField name="turns_failed" type="integer">
      Failed turns
    </ResponseField>

    <ResponseField name="avg_latency_ms" type="integer">
      Average latency
    </ResponseField>

    <ResponseField name="total_cost_usd" type="number">
      Total cost
    </ResponseField>
  </Expandable>
</ResponseField>

<RequestExample>
  ```bash cURL theme={null}
  curl https://api.playgent.com/v1/runs/run_def456 \
    -H "Authorization: Bearer your-api-key"
  ```
</RequestExample>

<ResponseExample>
  ```json Response theme={null}
  {
    "run_id": "run_def456",
    "status": "completed",
    "success": false,
    "test_case": { "id": "tc_xyz789", "name": "Refund Request Flow" },
    "agent": { "id": "agent_abc123", "name": "Customer Support Agent" },
    "turns": [
      {
        "turn_index": 0,
        "input": [{ "role": "user", "content": "I want a refund..." }],
        "output": [{ "role": "assistant", "content": "I'd be happy to help..." }],
        "expected_behavior": "Agent should ask for order details...",
        "success": true,
        "evaluation": {
          "overall_pass": true,
          "scorer_outputs": {
            "relevance": { "score": 0.92, "reasoning": "Response directly addresses refund request" },
            "faithfulness": { "score": 0.88, "reasoning": "All claims supported by context" }
          }
        },
        "metrics": {
          "latency_ms": 1240,
          "tokens": { "input": 156, "output": 89 },
          "cost_usd": 0.0034
        },
        "trace_id": "trace_ghi789"
      }
    ],
    "summary": {
      "turns_passed": 2,
      "turns_failed": 1,
      "avg_latency_ms": 1450,
      "total_cost_usd": 0.0102
    }
  }
  ```
</ResponseExample>