Skip to main content
POST
/
eval_configs
/
{id}
/
runs
Run Eval
curl --request POST \
  --url https://api.vogent.ai/api/eval_configs/{id}/runs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "versionedPromptId": "<string>",
  "callAgentId": "<string>",
  "evalRecordIds": [
    "<string>"
  ]
}
'
{
  "id": "<string>",
  "callAgentId": "<string>",
  "versionedPromptId": "<string>",
  "createdAt": "2023-11-07T05:31:56Z",
  "aggregateResult": {
    "numFailing": 123,
    "numPassing": 123
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.vogent.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

In the form Bearer <api_key_here>. You can find your api key in your dashboard.

Path Parameters

​
id
string
required

ID of the eval config.

Body

application/json
​
versionedPromptId
string
required

The ID of the versioned prompt to use for this eval run.

​
callAgentId
string
required

The ID of the call agent to evaluate.

​
evalRecordIds
string[]

Optional list of specific eval record IDs to run. If omitted, all records in the config are evaluated.

Response

Successful operation

​
id
string
required
​
status
enum<string>
required

The status of an evaluation run.

Available options:
PENDING,
RUNNING,
SUCCESS,
FAILED,
CANCELLED
​
callAgentId
string
required
​
versionedPromptId
string
required
​
createdAt
string<date-time>
required
​
aggregateResult
object
required