Skip to main content
POST
/
v1
/
evals
/
agents
/
{eval_agent_id}
/
versions
Create Eval Agent Version
curl --request POST \
  --url https://api.bland.ai/v1/evals/agents/{eval_agent_id}/versions \
  --header 'Content-Type: application/json' \
  --header 'authorization: <authorization>' \
  --data '
{
  "name": "<string>",
  "description": {},
  "from_version_id": "<string>"
}
'
{
  "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"
  }
}

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.

​
Headers

​
authorization
string
required
Your API key for authentication.

​
Path Parameters

​
eval_agent_id
string
required
The unique identifier of the eval agent.

​
Body Parameters

​
name
string
Display name for the new version. Between 1 and 200 characters.
​
description
string | null
Optional description for the new version.
​
from_version_id
string
ID of the version to fork from. Defaults to the current draft if not provided.

​
Response

​
data.id
string
Unique identifier for the new 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 assigned to the new draft.
​
data.name
string
Name of the new version.
​
data.description
string | null
Description of the new version, or null.
​
data.state
string
Always "editable" for a newly forked draft.
​
data.modality
string
One of text or audio, inherited from the source version.
​
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
Verdict levels copied from the source version. Each level contains level_key, label, prompt_md, and optionally color.
​
data.target_level_keys
array of strings
Target level keys copied from the source version.
​
data.weight
number
Relative weight copied from the source version. Between 0 and 100.
​
data.created_from_version_id
string | null
ID of the version this was forked from.
​
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.
{
  "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"
  }
}