Skip to main content
GET
/
v1
/
evaluation-summaries
List Evaluation Summaries
curl --request GET \
  --url https://api.example.com/v1/evaluation-summaries/
{
  "results": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "team_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "agent_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "tested_by": "<string>",
      "status": "<string>",
      "created_at": 123,
      "reliability_score": 123,
      "security_score": 123,
      "safety_score": 123,
      "overall_score": 123,
      "pillar_details": {},
      "harness_names": [
        "<string>"
      ],
      "harness_type": "<string>",
      "resource_version": "<string>",
      "created_by": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "completed_at": 123,
      "request_params": {}
    }
  ],
  "total": 123,
  "limit": 123,
  "offset": 123
}

Query Parameters

​
team_id
string<uuid>
required

Team ID to list summaries for

​
agent_id
string<uuid> | null

Filter by agent ID

​
status
enum<string> | null

Filter by status (running, completed, failed, cancelled) Statuses for an evaluation run (mirrors the workflow lifecycle).

Available options:
running,
completed,
failed,
cancelled
​
harness_type
enum<string> | null

Filter by harness type (standard or custom)

Available options:
standard,
custom
​
tested_by
enum<string> | null

Filter by tool that ran the evaluation Tools that can produce evaluation results.

Available options:
diamond,
promptfoo,
garak,
pyrit
​
limit
integer
default:10

Maximum number of results to return

Required range: 1 <= x <= 100
​
offset
integer
default:0

Number of results to skip for paging

Required range: x >= 0

Response

Successful Response

Response model for a paginated list of evaluation summaries.

​
results
EvaluationSummaryResponse · object[]
required
​
total
integer
required
​
limit
integer
required
​
offset
integer
required
Last modified on April 21, 2026