Reevaluate Calls

curl --request POST \
  --url https://api.cekura.ai/observability/v1/call-logs/rerun_evaluation/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '
{
  "agent_id": "1",
  "call_logs": [
    1,
    2,
    3
  ]
}
'

[
  {
    "id": 123,
    "duration": "<string>",
    "voice_recording_url": "<string>",
    "critical_categories": [
      {
        "category_id": 123,
        "category": "<string>",
        "deviation": 123,
        "wrongly_marked": true,
        "feedback": "<string>",
        "priority": "critical"
      }
    ],
    "transcript_object": [
      {
        "role": "<string>",
        "content": "<string>",
        "timestamp": 123
      }
    ],
    "status": "success",
    "agent_id": "<string>",
    "evaluation": {
      "metrics": [
        {
          "id": 123,
          "name": "<string>",
          "type": "<string>",
          "score": 123,
          "enum": "<string>",
          "value": "<string>",
          "explanation": [
            "<string>"
          ],
          "extra": {}
        }
      ]
    },
    "metadata": {},
    "dynamic_variables": {},
    "timestamp": "2023-11-07T05:31:56Z",
    "success": true,
    "is_reviewed": true,
    "feedback": "<string>",
    "transcript": "<string>",
    "call_ended_reason": "<string>",
    "dropoff_point": "<string>",
    "topic": "<string>",
    "customer_number": "<string>",
    "user_generated_transcript": "<unknown>",
    "error_message": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "call_id": "<string>",
    "agent": 123
  }
]

POST

observability

call-logs

rerun_evaluation

curl --request POST \
  --url https://api.cekura.ai/observability/v1/call-logs/rerun_evaluation/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '
{
  "agent_id": "1",
  "call_logs": [
    1,
    2,
    3
  ]
}
'

[
  {
    "id": 123,
    "duration": "<string>",
    "voice_recording_url": "<string>",
    "critical_categories": [
      {
        "category_id": 123,
        "category": "<string>",
        "deviation": 123,
        "wrongly_marked": true,
        "feedback": "<string>",
        "priority": "critical"
      }
    ],
    "transcript_object": [
      {
        "role": "<string>",
        "content": "<string>",
        "timestamp": 123
      }
    ],
    "status": "success",
    "agent_id": "<string>",
    "evaluation": {
      "metrics": [
        {
          "id": 123,
          "name": "<string>",
          "type": "<string>",
          "score": 123,
          "enum": "<string>",
          "value": "<string>",
          "explanation": [
            "<string>"
          ],
          "extra": {}
        }
      ]
    },
    "metadata": {},
    "dynamic_variables": {},
    "timestamp": "2023-11-07T05:31:56Z",
    "success": true,
    "is_reviewed": true,
    "feedback": "<string>",
    "transcript": "<string>",
    "call_ended_reason": "<string>",
    "dropoff_point": "<string>",
    "topic": "<string>",
    "customer_number": "<string>",
    "user_generated_transcript": "<unknown>",
    "error_message": "<string>",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z",
    "call_id": "<string>",
    "agent": 123
  }
]

Authorizations

X-CEKURA-API-KEY

string

header

required

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

Body

agent_id

integer

required

Agent ID, required if assistant_id is not provided Example: 2142

assistant_id

integer

required

Assistant ID, required if agent_id is not provided Example: asst_1234567890

call_logs

integer[]

required

Call logs IDs Example: [1, 2, 3]

Response

integer

duration

string

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

voice_recording_url

string

URL to access the voice recording. Example: "https://storage.example.com/recordings/call_123_20240315.mp3"

critical_categories

object[]

Critical categories from call evaluation

Show child attributes

critical_categories.category_id

integer

Category ID

critical_categories.category

string

Category name

critical_categories.deviation

number<double>

Deviation

critical_categories.wrongly_marked

boolean

Whether the category was wrongly marked

critical_categories.feedback

string

Feedback

critical_categories.priority

enum<string>

Priority

critical - Critical
non-critical - Non Critical
not_a_bug - Not A Bug

Available options:

critical,

non-critical,

not_a_bug

transcript_object

object[]

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
    }
]`

Show child attributes

transcript_object.role

string

Role of the message

transcript_object.content

string

Content of the message

transcript_object.timestamp

number<double>

Timestamp of the message

status

enum<string>

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

Available options:

success,

failure,

reviewed_success,

reviewed_failure

agent_id

string

Agent ID. Example: 2142

evaluation

object

Evaluation results for the call. Example:

{
    "metrics": [
        {
            "id": 35,
            "name": "Instruction Follow",
            "type": "binary_workflow_adherence",
            "score": 0,
            "explanation": ["Agent failed to follow the opening script", "Missed key product information"],
            "vocera_defined_metric_code": "5dedc41b",
            "function_name": "check_critical_deviations",
            "extra": {
                "categories": [
                    {
                        "category_id": 5,
                        "category": "Script Adherence Issue",
                        "deviation": "Agent deviated from required script",
                        "priority": "critical"
                    }
                ]
            }
        },
        {
            "id": 18,
            "name": "Customer Satisfaction",
            "type": "binary_qualitative",
            "score": 5,
            "explanation": ["Customer expressed satisfaction with service"]
        }
    ]
}

Show child attributes

evaluation.metrics

object[]

Show child attributes

evaluation.metrics.id

integer

Metric ID

evaluation.metrics.name

string

Metric name

evaluation.metrics.type

string

Metric type

evaluation.metrics.score

number<double>

Evaluated metric score, Present if metrictype is not enum

evaluation.metrics.enum

string

Metric enum, Present if type is enum

evaluation.metrics.value

string

Evaluated metric value, Present if metric type is enum

evaluation.metrics.explanation

string[]

Explanation of the metric

evaluation.metrics.extra

object

Evaluated metric extra data

Show child attributes

evaluation.metrics.extra.{key}

any

metadata

object

Additional call metadata. Example:

{
    "ended_reason": "customer-ended-call",
    "ringing_duration": 3.941,
    "call_type": "inbound"
}

Show child attributes

metadata.{key}

any

dynamic_variables

object

Dynamic Variables used in the call. Example:

{
    "customer_name": "John Doe",
    "order_id": "ORD-12345",
    "product_type": "premium"
}

Show child attributes

dynamic_variables.{key}

any

timestamp

string<date-time>

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

success

boolean | null

Whether the call was successful. Example: true or false

is_reviewed

boolean

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

feedback

string

Feedback about the call. Example: "Great Call"

transcript

string

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.

call_ended_reason

string

Reason why the call ended. Example:

"customer-ended-call"
"agent-ended-call"

Maximum string length: 100

dropoff_point

string

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

Maximum string length: 1000

topic

string

Topic of the call. Example:

"product_inquiry"
"technical_support"

Maximum string length: 1000

customer_number

string

Customer's phone number or identifier. Example:

"+1234567890"
"customer_abc123"

Maximum string length: 100

user_generated_transcript

any | null

Manually created or corrected transcript data. Example:

[
    {
        "role": "Testing Agent",
        "content": "I need help with my order",
        "timestamp": "00:15"
    }
]`

error_message

string | null

created_at

string<date-time>

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

updated_at

string<date-time>

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

call_id

string

Unique identifier for the call. Example:

"call_abc123xyz"
"stereo_audio_session_456"

Maximum string length: 100

agent

integer | null

Agent ID

List Calls Evaluate Metrics

⌘I

API Reference

Authorizations

Body

Response