> ## 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 Snapshots

> List the frozen agent configurations a run scored against.

### Headers

<ParamField header="authorization" type="string" required>
  Your API key for authentication.
</ParamField>

### Path Parameters

<ParamField path="run_id" type="string" required>
  The ID of the eval run.
</ParamField>

<Note>
  Snapshots freeze each agent's prompt, levels, and targets at submission time, so historical results never change if you later edit the agent.
</Note>

### Response

<ResponseField name="object" type="string">
  Always `"list"`.
</ResponseField>

<ResponseField name="data" type="array of objects">
  All agent snapshots for the run. Returns all snapshots in a single page.

  <Expandable title="EvalRunAgentSnapshot fields">
    <ResponseField name="id" type="string">
      Unique identifier for this snapshot.
    </ResponseField>

    <ResponseField name="org_id" type="string">
      The organization that owns this snapshot.
    </ResponseField>

    <ResponseField name="eval_run_id" type="string">
      The eval run this snapshot belongs to.
    </ResponseField>

    <ResponseField name="eval_agent_id" type="string">
      The source eval agent.
    </ResponseField>

    <ResponseField name="eval_agent_version_id" type="string">
      The specific version of the eval agent that was frozen.
    </ResponseField>

    <ResponseField name="position" type="integer">
      The ordering position of this agent within the run's agent roster.
    </ResponseField>

    <ResponseField name="key" type="string">
      Machine-readable key identifying this agent in the run.
    </ResponseField>

    <ResponseField name="name" type="string">
      Human-readable name of the agent at snapshot time.
    </ResponseField>

    <ResponseField name="modality" type="string">
      Scoring modality for this agent. One of `text` or `audio`.
    </ResponseField>

    <ResponseField name="system_prompt_md" type="string">
      The system prompt used by the judge, frozen at submission time.
    </ResponseField>

    <ResponseField name="prompt_md" type="string">
      The evaluation prompt, frozen at submission time.
    </ResponseField>

    <ResponseField name="prompt_version" type="string">
      Version identifier for the prompt.
    </ResponseField>

    <ResponseField name="levels" type="array of objects">
      The scoring levels defined for this agent, frozen at submission time.

      <Expandable title="Level fields">
        <ResponseField name="level_key" type="string">
          Machine-readable key for this level.
        </ResponseField>

        <ResponseField name="label" type="string">
          Human-readable label for this level.
        </ResponseField>

        <ResponseField name="prompt_md" type="string">
          Description of what qualifies a call for this level.
        </ResponseField>

        <ResponseField name="color" type="string">
          Optional display color for this level.
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="target_level_keys" type="array of string">
      Level keys that are considered a passing result, frozen at submission time.
    </ResponseField>

    <ResponseField name="weight" type="number">
      Relative weight of this agent in the overall score, 0-100.
    </ResponseField>

    <ResponseField name="created_at" type="string">
      ISO 8601 timestamp when this snapshot was created.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="has_more" type="boolean">
  Always `false`. All snapshots are returned in a single page.
</ResponseField>

<ResponseField name="next_cursor" type="null">
  Always `null`.
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "data": {
      "object": "list",
      "data": [
        {
          "id": "33333333-aaaa-bbbb-cccc-dddddddddddd",
          "org_id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
          "eval_run_id": "e5f6a7b8-c9d0-1234-efab-345678901234",
          "eval_agent_id": "11111111-aaaa-bbbb-cccc-dddddddddddd",
          "eval_agent_version_id": "22222222-aaaa-bbbb-cccc-dddddddddddd",
          "position": 0,
          "key": "resolution_quality",
          "name": "Resolution Quality",
          "modality": "text",
          "system_prompt_md": "You are an expert call quality analyst evaluating customer service interactions.",
          "prompt_md": "Did the agent fully resolve the customer's issue without requiring a callback?",
          "prompt_version": "v3.1.0",
          "levels": [
            {
              "level_key": "pass",
              "label": "Pass",
              "prompt_md": "The agent resolved the issue completely and the customer confirmed satisfaction.",
              "color": "#22c55e"
            },
            {
              "level_key": "partial",
              "label": "Partial",
              "prompt_md": "The agent addressed the issue but the customer expressed some remaining concern.",
              "color": "#f59e0b"
            },
            {
              "level_key": "fail",
              "label": "Fail",
              "prompt_md": "The issue was not resolved or the customer was transferred unnecessarily.",
              "color": "#ef4444"
            }
          ],
          "target_level_keys": ["pass"],
          "weight": 100,
          "created_at": "2026-05-27T10:00:00.000Z"
        }
      ],
      "has_more": false,
      "next_cursor": null
    },
    "errors": null
  }
  ```
</ResponseExample>