> ## 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.

# Update Eval Agent Version

> Edit a draft version's prompt, levels, targets, or weight.

### Headers

**authorization** `string` *required*

Your API key for authentication.

### Path Parameters

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

The unique identifier of the eval agent.

**version\_id** `string` *required*

The unique identifier of the version to update. Must be in the `editable` state.

### Body Parameters

**name** `string`

Updated display name for this version. Between 1 and 200 characters.

**description** `string | null`

Updated description, or `null` to clear it.

**modality** `string`

The modality for this version. One of `text` or `audio`.

**system\_prompt\_md** `string`

Updated system prompt for the judge LLM, in Markdown. Maximum 8000 characters.

**prompt\_md** `string`

Updated grading prompt for the judge LLM, in Markdown. Maximum 8000 characters.

**levels** `array of objects`

Verdict levels for graded mode. Pass an empty array for pass/fail mode. Maximum 5 levels. Each level object requires:

* `level_key` (string, 1-64 characters): unique key within this version.
* `label` (string, 1-80 characters): display label shown in results.
* `prompt_md` (string): description used in the grading prompt.
* `color` (string, optional): one of `rose`, `amber`, `gold`, `emerald`, `blue`, `indigo`, `violet`, `fog`.

**target\_level\_keys** `array of strings`

Which level keys count as a target match. Must be empty for pass/fail agents. Every key listed must match a defined level.

**weight** `number`

Relative weight of this agent in aggregate scoring. Between 0 and 100.

### Response

**data.id** `string`

Unique identifier for this version.

**data.org\_id** `string`

ID of the organization that owns this version.

**data.eval\_agent\_id** `string`

ID of the parent eval agent.

**data.version\_number** `integer`

Sequential version number.

**data.name** `string`

Name of this version.

**data.description** `string | null`

Description of this version, or `null`.

**data.state** `string`

State of this version. One of `editable` or `archived`.

**data.modality** `string`

One of `text` or `audio`.

**data.system\_prompt\_md** `string`

The system prompt for the judge LLM, in Markdown.

**data.prompt\_md** `string`

The grading prompt for the judge LLM, in Markdown.

**data.levels** `array of objects`

Updated verdict levels. Each level contains `level_key`, `label`, `prompt_md`, and optionally `color`.

**data.target\_level\_keys** `array of strings`

Updated target level keys.

**data.weight** `number`

Updated weight. Between 0 and 100.

**data.created\_from\_version\_id** `string | null`

ID of the version this was forked from, or `null`.

**data.created\_by** `string | null`

Identifier of the user who created this version, or `null`.

**data.created\_at** `string`

ISO 8601 timestamp for when this version was created.

**data.updated\_at** `string`

ISO 8601 timestamp for when this version was last updated.

```json Response theme={null}
{
  "errors": null,
  "data": {
    "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
    "org_id": "f0e1d2c3-b4a5-9678-fedc-ba9876543210",
    "eval_agent_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "version_number": 3,
    "name": "Empathy Check v3",
    "description": "Refined grading criteria with clearer level descriptions.",
    "state": "editable",
    "modality": "audio",
    "system_prompt_md": "You are an expert call quality reviewer specializing in empathy.",
    "prompt_md": "Did the agent acknowledge and validate the caller's feelings? Review the full transcript and select the most appropriate verdict.",
    "levels": [
      {
        "level_key": "excellent",
        "label": "Excellent",
        "prompt_md": "The agent proactively acknowledged the caller's feelings with warmth and specificity.",
        "color": "emerald"
      },
      {
        "level_key": "adequate",
        "label": "Adequate",
        "prompt_md": "The agent showed some empathy but responses were generic or brief.",
        "color": "amber"
      },
      {
        "level_key": "poor",
        "label": "Poor",
        "prompt_md": "The agent ignored, dismissed, or failed to acknowledge the caller's feelings.",
        "color": "rose"
      }
    ],
    "target_level_keys": ["excellent"],
    "weight": 15,
    "created_from_version_id": "c3d4e5f6-a7b8-9012-cdef-123456789012",
    "created_by": "9a8b7c6d-5e4f-3210-9876-543210fedcba",
    "created_at": "2026-05-15T08:00:00.000Z",
    "updated_at": "2026-05-27T12:00:00.000Z"
  }
}
```


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