Reevaluate Metrics

POST /test_framework/v1/results/{id}/evaluate_metrics

cURL

cURL

curl --request POST \
  --url https://api.cekura.ai/test_framework/v1/results/{id}/evaluate_metrics/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '
{
  "run_ids": [
    "<string>"
  ],
  "metric_ids": [
    "<string>"
  ]
}
'

200

{
  "id": 123,
  "name": "<string>",
  "agent": 123,
  "agent_name": "<string>",
  "agent_inbound": true,
  "status": "pending",
  "success_rate": 0,
  "run_as_text": false,
  "is_cronjob": "<string>",
  "runs": {},
  "met_expected_outcome_count": "<string>",
  "total_expected_outcome_count": "<string>",
  "total_runs_count": "<string>",
  "completed_runs_count": "<string>",
  "success_runs_count": "<string>",
  "failed_runs_count": "<string>",
  "scenarios": {},
  "run_type": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z"
}

Authorizations

X-CEKURA-API-KEY · string · header · required

API Key Authentication. It should be included in the header of each request.

Path Parameters

id · integer · required

A unique integer value identifying this result.

Body

application/jsonapplication/x-www-form-urlencodedmultipart/form-data

run_ids · string[] · required

List of run IDs

Minimum array length: 1

metric_ids · string[] · required

List of metric IDs to evaluate

Minimum array length: 1

Response

200 - application/json

id · integer

Unique identifier for the Result Example: 123

name · string

Name of the Result Example: "Test Result 1"

Maximum string length: 255

agent · integer

ID of the AI agent that was tested Example: 123

agent_name · string

Name of the AI agent that was tested Example: "Test Agent 1"

agent_inbound · boolean

Whether the agent is configured for inbound calls (true) or outbound calls (false) Example: true or false

status · enum<string> · default: pending

Current status of the result

• running - Running
• completed - Completed
• failed - Failed
• pending - Pending
• in_progress - In Progress
• evaluating - Evaluating
• in_queue - In Queue
• timeout - Timeout
• cancelled - Cancelled

Available options: running, completed, failed, pending, in_progress, evaluating, in_queue, timeout, cancelled

success_rate · number<double> · default: 0

Success rate of the test runs as a decimal (0.0 to 1.0)

run_as_text · boolean · default: false

Whether this test was run in text mode instead of voice mode Example: true or false

is_cronjob · string

Whether this result was created by a scheduled cronjob Example: true or false

runs · object

List of test runs associated with this result, including run details, status, scenario information, and phone numbers used Example:

{
    "run_id": {
      "id": "integer",
      "scenario": "integer",
      "outbound_number": "string",
      "expected_outcome": {
        "score": 100,
        "explanation": [
          "✅ Positive outcome explanation with checkmark emoji",
          "❌ Negative outcome explanation with X emoji"
        ],
        "outcome_alignments": [
          {
            "outcome": "string",
            "prompt_part": "string",
            "aligned": "boolean"
          }
        ]
      },
      "success": "boolean",
      "evaluation": {
        "metrics": [
          {
            "id": "integer",
            "name": "string",
            "type": "binary_workflow_adherence | binary_qualitative | continuous_qualitative | numeric | enum",
            "score": "number",
            "explanation": "string | array",
            "function_name": "string (optional)",
            "extra": {
              "categories": [
                {
                  "category": "string",
                  "deviation": "string (optional)",
                  "priority": "string (optional)"
                }
              ],
              "percentiles": {
                "p50": "number"
              }
            },
            "enum": "string (for enum type metrics only)"
          }
        ]
      },
      "timestamp": "datetime",
      "executed_at": "datetime",
      "error_message": "string",
      "status": "string",
      "duration": "string (MM:SS format)",
      "scenario_name": "string",
      "personality_name": "string",
      "metadata": "object",
      "inbound_number": "string"
    }
}

Show child attributes

met_expected_outcome_count · string

Number of test runs that met the expected outcome criteria Example: 10

total_expected_outcome_count · string

Total number of test runs that were evaluated for expected outcomes Example: 10

total_runs_count · string

Total number of test runs associated with this result Example: 10

completed_runs_count · string

Number of test runs that have completed successfully Example: 10

success_runs_count · string

Number of test runs that were marked as successful Example: 10

failed_runs_count · string

Number of test runs that failed or encountered errors Example: 10

scenarios · object

List of scenario names used in the test runs for this result Example:

[
    {
        "id": 123,
        "name": "Scenario 1"
    },
    {
        "id": 456,
        "name": "Scenario 2"
    }
]

Show child attributes

run_type · string | null

Run Execution Type

created_at · string<date-time>

Timestamp when this test result was created Example: 2021-01-01 00:00:00

updated_at · string<date-time>

Timestamp when this test result was last updated