Skip to main content
PATCH
/
agents
/
{agent_id}
/
evaluation-config
cURL
curl -X PATCH 'https://api.gumloop.com/api/v1/agents/AGENT_ID/evaluation-config' \
  -H 'Authorization: Bearer YOUR_ACCESS_TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
    "enabled": true,
    "criteria": [
      {
        "name": "Accuracy",
        "prompt": "The agent provided factually correct information.",
        "type": "other",
        "priority": "needs_attention"
      }
    ],
    "data_points": [
      {
        "name": "Customer Intent",
        "data_type": "string",
        "description": "Summarize the customer primary intent in 2-5 words."
      }
    ]
  }'
{
  "config": {
    "agent_id": "<string>",
    "enabled": true,
    "is_active": true,
    "model_name": "<string>",
    "frequency": "<string>",
    "language": "<string>",
    "include_auto_tags": true,
    "interaction_types": [
      "<string>"
    ],
    "criteria": [
      {
        "id": "<string>",
        "name": "<string>",
        "prompt": "<string>",
        "type": "<string>",
        "priority": "<string>"
      }
    ],
    "tags": [
      {
        "name": "<string>",
        "description": "<string>"
      }
    ],
    "data_points": [
      {
        "id": "<string>",
        "name": "<string>",
        "data_type": "<string>",
        "description": "<string>"
      }
    ],
    "sentiment": {
      "enabled": true,
      "affects_grade": true,
      "description": "<string>"
    },
    "updated_ts": "<string>"
  }
}

Authorizations

Authorization
string
header
required

A personal API key or an OAuth 2.0 access token. Personal API keys also require the x-auth-key header with your user ID.

Path Parameters

agent_id
string
required

ID of the agent.

Body

application/json
enabled
boolean

Whether evaluations are enabled for this agent.

model_name
string

LLM model to use for evaluation.

include_auto_tags
boolean

Allow the evaluator to suggest tags beyond your predefined vocabulary.

criteria
object[]

Quality criteria to check (replaces existing list). Max 30.

tags
object[]

Tag vocabulary (replaces existing list). Max 50.

data_points
object[]

Data points to extract (replaces existing list). Max 40.

sentiment
object

Response

Updated evaluation configuration.

config
object