CEcekura
observability

Run specific metrics against call logs

Changed on

Evaluate one or more metrics against selected call logs. Unlike rerun_evaluation (which re-runs all assigned metrics), this endpoint lets you target specific metrics.

Scope: provide either agent_id or project_id to identify which agent's call logs and metrics to use. Metrics must belong to the specified agent or project.

Credit check: cost scales with the number of call logs and metrics selected. The request is rejected if your balance is insufficient — check your balance first via test_framework_billing_info_retrieve.

Async: evaluation runs in the background. The response returns the call logs in their current state. Retrieve each call log individually to see updated metric results once evaluation completes.

Rate limited. Respect 429 responses — wait for the Retry-After duration.

post/observability/v2/call-logs/evaluate_metrics/

Request

  • Base URL
    https://api.cekura.ai
  • URL
    https://api.cekura.ai/observability/v2/call-logs/evaluate_metrics/
  • Auth
    • API key in header X-CEKURA-API-KEY
    • or HTTP bearer
    • or HTTP bearer
    • or HTTP bearer

Request body

agent_idinteger

Cekura agent ID. Provide this or project_id. Example: 224

project_idinteger

Project ID. Provide this or agent_id. Example: 456

call_logsinteger[] required

IDs of the call logs to evaluate. Example: [123, 456]

metricsinteger[] required

IDs of the metrics to run. Must belong to the agent/project. Example: [789, 790]

Response

idinteger
durationstring

Call duration in minutes in MM:SS format. Example: 01:10

successboolean nullable

Whether the call was successful. Example: true or false

is_reviewedboolean

Whether the call has been reviewed. Example: true or false

status'success' | 'failure' | 'reviewed_success' | 'reviewed_failure'

Status of the call or conversation. Example: "completed" or "failed"

  • success - Success
  • failure - Failure
  • reviewed_success - Reviewed Success
  • reviewed_failure - Reviewed Failure
feedbackstring

Feedback about the call. Example: "Great Call"

call_ended_reasonstring

Reason why the call ended. Example:

  • "customer-ended-call"
  • "agent-ended-call"
customer_numberstring

Customer's phone number or identifier. Example:

  • "+1234567890"
  • "customer_abc123"
agentinteger nullable

Agent ID

agent_namestring

Agent name

call_idstring required

Unique identifier for the call. Example:

  • "call_abc123xyz"
  • "stereo_audio_session_456"
trace_idstring

OpenTelemetry trace ID (32-char hex). Set when OTel tracing is enabled.

is_log_presentboolean

Whether provider execution logs are stored for this call.

timestampstring date-time

When the call occurred. Example: 2024-03-15T10:15:45Z

error_messagestring nullable
dropoff_pointstring

Point in conversation where user disengaged. Example: "end of conversation as no queries remaining"

topicstring

Topic of the call. Example:

  • "product_inquiry"
  • "technical_support"
created_atstring date-time

When this record was created. Example: 2024-03-15T10:30:45Z

updated_atstring date-time

When this record was last updated. Example: 2024-03-15T10:35:11Z

transcriptstring

Full text transcript of the call. Example:

[00:01] Testing Agent: Hello. 
[00:02] Main Agent: Hello, how can I help you today?
[00:03] Testing Agent: Well, I mean, sure. What time exactly are we talking about here
[00:04] Main Agent: 6 PM.
[00:05] Testing Agent: Great. I'll book that for you. Just a sec.
[00:06] Main Agent: Okay.
transcript_objectstring

Structured transcript data with timestamps. Example:

[
    {
        "role": "Testing Agent",
        "content": "Hello",
        "start_time": 1.2,
        "end_time": 1.8
    },
    {
        "role": "Main Agent",
        "content": "Hello, how can I help you today?",
        "start_time": 1.8,
        "end_time": 2.5
    }
]`
evaluationstring

Evaluation of the call

Changes