> ## 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.

# Create Eval Agent Version

> Fork a new editable draft version of an eval agent.

### Headers

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

### Path Parameters

<ParamField path="eval_agent_id" type="string" required>
  The unique identifier of the eval agent.
</ParamField>

### Body Parameters

<ParamField body="name" type="string">
  Display name for the new version. Between 1 and 200 characters.
</ParamField>

<ParamField body="description" type="string | null">
  Optional description for the new version.
</ParamField>

<ParamField body="from_version_id" type="string">
  ID of the version to fork from. Defaults to the current draft if not provided.
</ParamField>

### Response

<ResponseField name="data.id" type="string">
  Unique identifier for the new version.
</ResponseField>

<ResponseField name="data.org_id" type="string">
  ID of the organization that owns this version.
</ResponseField>

<ResponseField name="data.eval_agent_id" type="string">
  ID of the parent eval agent.
</ResponseField>

<ResponseField name="data.version_number" type="integer">
  Sequential version number assigned to the new draft.
</ResponseField>

<ResponseField name="data.name" type="string">
  Name of the new version.
</ResponseField>

<ResponseField name="data.description" type="string | null">
  Description of the new version, or `null`.
</ResponseField>

<ResponseField name="data.state" type="string">
  Always `"editable"` for a newly forked draft.
</ResponseField>

<ResponseField name="data.modality" type="string">
  One of `text` or `audio`, inherited from the source version.
</ResponseField>

<ResponseField name="data.system_prompt_md" type="string">
  The system prompt for the judge LLM, in Markdown.
</ResponseField>

<ResponseField name="data.prompt_md" type="string">
  The grading prompt for the judge LLM, in Markdown.
</ResponseField>

<ResponseField name="data.levels" type="array of objects">
  Verdict levels copied from the source version. Each level contains `level_key`, `label`, `prompt_md`, and optionally `color`.
</ResponseField>

<ResponseField name="data.target_level_keys" type="array of strings">
  Target level keys copied from the source version.
</ResponseField>

<ResponseField name="data.weight" type="number">
  Relative weight copied from the source version. Between 0 and 100.
</ResponseField>

<ResponseField name="data.created_from_version_id" type="string | null">
  ID of the version this was forked from.
</ResponseField>

<ResponseField name="data.created_by" type="string | null">
  Identifier of the user who created this version, or `null`.
</ResponseField>

<ResponseField name="data.created_at" type="string">
  ISO 8601 timestamp for when this version was created.
</ResponseField>

<ResponseField name="data.updated_at" type="string">
  ISO 8601 timestamp for when this version was last updated.
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "errors": null,
    "data": {
      "id": "e5f6a7b8-c9d0-1234-efab-567890123456",
      "org_id": "f0e1d2c3-b4a5-9678-fedc-ba9876543210",
      "eval_agent_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "version_number": 4,
      "name": "Empathy Check v4",
      "description": null,
      "state": "editable",
      "modality": "audio",
      "system_prompt_md": "You are an expert call quality reviewer.",
      "prompt_md": "Did the agent express empathy when the caller described their problem?",
      "levels": [
        {
          "level_key": "excellent",
          "label": "Excellent",
          "prompt_md": "The agent clearly and warmly acknowledged the caller's feelings.",
          "color": "emerald"
        },
        {
          "level_key": "poor",
          "label": "Poor",
          "prompt_md": "The agent ignored or dismissed the caller's feelings.",
          "color": "rose"
        }
      ],
      "target_level_keys": ["excellent"],
      "weight": 10,
      "created_from_version_id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "created_by": "9a8b7c6d-5e4f-3210-9876-543210fedcba",
      "created_at": "2026-05-27T11:30:00.000Z",
      "updated_at": "2026-05-27T11:30:00.000Z"
    }
  }
  ```
</ResponseExample>