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

# List Agent Results

> List every individual judge verdict in an eval run.

### Headers

**authorization** `string` *required*

Your API key for authentication.

### Path Parameters

**run\_id** `string` *required*

The ID of the eval run.

### Query Parameters

**limit** `integer` (default: 25)

Number of results to return. Between 1 and 100.

**starting\_after** `string`

Cursor: return results after this object ID.

**ending\_before** `string`

Cursor: return results before this object ID. Cannot be combined with `starting_after`.

### Response

**object** `string`

Always `"list"`.

**data** `array of objects`

The list of agent result objects, one per call-by-agent evaluation.

**EvalRunAgentResult fields**

**id** `string`

Unique identifier for this agent result.

**org\_id** `string`

The organization that owns this result.

**eval\_run\_id** `string`

The eval run this result belongs to.

**eval\_run\_call\_result\_id** `string`

The call result this agent verdict is part of.

**eval\_run\_agent\_snapshot\_id** `string`

The frozen agent snapshot used to produce this verdict.

**eval\_agent\_id** `string`

The eval agent that produced this verdict.

**eval\_agent\_version\_id** `string`

The specific version of the eval agent used.

**call\_id** `string`

The call that was scored.

**selected\_level\_key** `string or null`

The level key the judge selected, or `null` if scoring failed or evidence was insufficient.

**selected\_level\_label** `string or null`

Human-readable label for the selected level.

**score\_normalized\_0\_100** `number or null`

Normalized score for this verdict, 0-100.

**is\_target\_match** `boolean or null`

Whether the selected level is one of the configured target levels.

**is\_insufficient\_evidence** `boolean`

Whether the judge determined there was not enough evidence to produce a verdict.

**confidence** `number or null`

Judge confidence in the verdict, 0-1.

**reasoning\_md** `string or null`

Markdown-formatted reasoning from the judge.

**evidence** `array of objects`

Transcript or audio quotes the judge cited as evidence.

**Evidence quote fields**

**source** `string`

Where the evidence came from. One of `transcript` or `audio`.

**speaker** `string or null`

Who spoke this quote. One of `agent`, `customer`, `unknown`, or `null`.

**start\_ms** `integer or null`

Start time of the quote in milliseconds, if available.

**end\_ms** `integer or null`

End time of the quote in milliseconds, if available.

**text** `string`

The quoted text.

**failed** `boolean`

Whether this evaluation failed to complete.

**failure\_code** `string or null`

Machine-readable failure code, if `failed` is `true`.

**failure\_message** `string or null`

Human-readable failure description, if `failed` is `true`.

**billable\_cost\_usd** `number or null`

Billable cost for this individual verdict in USD.

**audit** `object`

Audit metadata for the judge call.

**Audit fields**

**prompt\_version** `string`

Version of the judge prompt used.

**input\_tokens** `integer or null`

Number of input tokens consumed.

**output\_tokens** `integer or null`

Number of output tokens produced.

**latency\_ms** `integer or null`

Latency of the judge call in milliseconds.

**created\_at** `string`

ISO 8601 timestamp when this result was created.

**has\_more** `boolean`

Whether more results exist beyond this page.

**next\_cursor** `string or null`

Cursor to use in `starting_after` to retrieve the next page, or `null` if there are no more results.

```json Response theme={null}
{
  "data": {
    "object": "list",
    "data": [
      {
        "id": "c2d3e4f5-a6b7-8901-cdef-234567890123",
        "org_id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
        "eval_run_id": "e5f6a7b8-c9d0-1234-efab-345678901234",
        "eval_run_call_result_id": "b1c2d3e4-f5a6-7890-bcde-f12345678901",
        "eval_run_agent_snapshot_id": "33333333-aaaa-bbbb-cccc-dddddddddddd",
        "eval_agent_id": "11111111-aaaa-bbbb-cccc-dddddddddddd",
        "eval_agent_version_id": "22222222-aaaa-bbbb-cccc-dddddddddddd",
        "call_id": "a1b2c3d4-0000-0000-0000-000000000001",
        "selected_level_key": "pass",
        "selected_level_label": "Pass",
        "score_normalized_0_100": 88.0,
        "is_target_match": true,
        "is_insufficient_evidence": false,
        "confidence": 0.93,
        "reasoning_md": "The agent correctly identified the account issue and offered a resolution within the first two minutes of the call.",
        "evidence": [
          {
            "source": "transcript",
            "speaker": "agent",
            "start_ms": 45200,
            "end_ms": 52100,
            "text": "I can see your account has a pending charge from last week. Let me reverse that for you right now."
          }
        ],
        "failed": false,
        "failure_code": null,
        "failure_message": null,
        "billable_cost_usd": 0.02,
        "audit": {
          "prompt_version": "v3.1.0",
          "input_tokens": 2840,
          "output_tokens": 312,
          "latency_ms": 1843
        },
        "created_at": "2026-05-27T10:00:48.000Z"
      }
    ],
    "has_more": false,
    "next_cursor": null
  },
  "errors": null
}
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.