List Metrics

This API is used to list all the metrics associated with an agent or a project or both.

Filtering behavior:

• If only agent_id is provided: Returns metrics associated with that agent only
• If only project_id is provided: Returns metrics associated with that project only
• If both agent_id and project_id are provided: Returns metrics from both the agent and the project
• If agents is provided: Returns metrics where any of the specified agents are in the M2M agents field

GET /test_framework/v1/metrics

cURL

cURL

curl --request GET \
  --url https://api.cekura.ai/test_framework/v1/metrics/ \
  --header 'X-CEKURA-API-KEY: <api-key>'

200

MetricList

[
  {
    "id": 123,
    "agent": 123,
    "name": "<string>",
    "description": "<string>",
    "function_name": "<string>",
    "type": "basic",
    "eval_type": "binary_workflow_adherence",
    "enum_values": [
      "<string>"
    ],
    "audio_enabled": true,
    "observability_enabled": true,
    "simulation_enabled": true,
    "prompt": "<string>",
    "evaluation_trigger": "always",
    "evaluation_trigger_prompt": "<string>",
    "priority_assignment_prompt": "<string>",
    "vocera_defined_metric_code": "<string>",
    "configuration": {
      "infra_issues_timeout": "<integer>",
      "key": "value"
    },
    "kb_file_ids": [
      "<integer>"
    ],
    "knowledge_base_files": [
      {
        "id": "<integer>",
        "agent": "<integer>",
        "file_url": "<string>",
        "file_name": "<string>",
        "file_type": "<string>",
        "file_size": "<integer>",
        "created_at": "<datetime>",
        "updated_at": "<datetime>"
      }
    ],
    "metric_cost": "<float>"
  }
]

Authorizations

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

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

Query Parameters

agent_id · integer

Filter by agent ID Example: 123

project_id · integer

Filter by project ID Example: 456

assistant_id · string

Filter by assistant ID Example: asst_1234567890

agents · string

Filter metrics by agent IDs. Supports comma-separated list. Example: 1,2,3 to filter metrics associated with any of these agents

filters · object

JSON filter parameter for advanced filtering.

Example:

{"operator":"and","conditions":[{"field":"agents__id","op":"in","value":[1,2,3]}]}

Supported fields: agents__id, eval_type, type, name Supported operators: in, eq, contains

include_scores · boolean

Include Overall and Total scores in Metric List Example: true or false

Response

200 - application/json

id · integer

project · integer | null

agent · integer | null

agent_name · string

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

agents · (integer | null)[]

agent_names · string

name · string

Name of the metric. Example: "Customer Satisfaction" or "Appointment Booking"

Maximum string length: 255

description · string

Description of what the metric measures. Example: "Measures how satisfied customers are with the service provided"

function_name · string | null

Predefined function name Example: "get_latency" or "check_critical_deviations"

Maximum string length: 255

type · enum<string>

Type of metric

• basic - Basic (Deprecated in favor of LLM Judge)
• custom_prompt - Custom Prompt ( Deprecated in favor of LLM Judge)
• custom_code - Custom Code
• llm_judge - LLM Judge

Available options: basic, custom_prompt, custom_code, llm_judge

eval_type · enum<string>

Type of evaluation

• binary_workflow_adherence - Binary Workflow Adherence
• binary_qualitative - Binary Qualitative
• continuous_qualitative - Continuous Qualitative
• numeric - Numeric
• enum - Enum

Available options: binary_workflow_adherence, binary_qualitative, continuous_qualitative, numeric, enum

enum_values · any

List of possible enum values for enum type metrics. Example: ["satisfied", "unsatisfied"]

audio_enabled · boolean

Whether this metric requires audio analysis. Example: true or false

observability_enabled · boolean

Enable this metric for observability. Example: true or false

simulation_enabled · boolean

Enable this metric for simulations. Example: true or false

sampling_enabled · boolean

Enable sampling for this metric using project-level sample rate

prompt · string

Evaluation prompt for the metric. Example: "Evaluate customer satisfaction based on conversation"

display_order · integer

Display order for the metric. Example: 1

Required range: -2147483648 <= x <= 2147483647

evaluation_trigger · enum<string>

• always - Always
• automatic - Automatic
• custom - Custom

Available options: always, automatic, custom

trigger_type · enum<string> · default: llm_judge

• llm_judge - LLM Judge
• custom_code - Custom Code

Available options: llm_judge, custom_code

evaluation_trigger_prompt · string

Evaluation trigger prompt for the metric. Example: "Evaluate metric only if call ended reason is main-agent-ended-call"

evaluation_trigger_custom_code · string

Python custom code to determine metric relevance. Code should set _result (bool) and _explanation (str). Example:

_result = True
_explanation = "Metric is relevant"
if "call_end_reason" in data and data["call_end_reason"] == "customer-hung-up":
    _result = False
    _explanation = "Customer hung up, metric not applicable"

priority_assignment_prompt · string

Priority assignment prompt for the metric.

vocera_defined_metric_code · string

Vocera defined metric code for the metric. Example: "7fd534f5"

Maximum string length: 255

configuration · any

Custom configuration parameters for specific metrics if metric supports it. Example:

• For Infrastructure issues

{
    "infra_issues_timeout": 10
}

kb_file_ids · integer[]

List of knowledge base file IDs for the metric. Example: [123, 456]

knowledge_base_files · object[]

Show child attributes

metric_cost · number<double>

Metric Cost Example: 0.10

alert_type · enum<string> · default: disabled

• disabled - Alerts Disabled
• normal - Normal Alerts
• significant_change - Significant Change Alerts

Available options: disabled, normal, significant_change

significant_change_alert_status · enum<string>

Alert status: enabled or disabled.

• enabled - Enabled
• disabled - Disabled

Available options: enabled, disabled

significant_change_alert_direction · enum<string>

Alert direction: increase only, decrease only, or both (empty = both). Example: "increase", "decrease", or "both"

• `` - Both (Increase and Decrease)
• increase - Increase Only
• decrease - Decrease Only

Available options: , increase, decrease

window_size · integer

Window size for rolling statistics calculation. Example: 50

std_multiplier · number<double>

Standard deviation multiplier for threshold calculation. Example: 2.0

ewma_alpha · number<double>

Alpha value for exponentially weighted moving average (EWMA) calculation. Example: 0.1

add_to_new_agents · boolean | null

When enabled, this metric is automatically assigned to new agents created in the project.