Skip to main content
POST
/
test_framework
/
v1
/
runs
/
improve_prompt_bg
cURL
curl --request POST \
  --url https://api.cekura.ai/test_framework/v1/runs/improve_prompt_bg/ \
  --header 'Content-Type: application/json' \
  --header 'X-CEKURA-API-KEY: <api-key>' \
  --data '
{
  "evaluation_status": "success",
  "success": true,
  "is_reviewed": true,
  "feedback": "<string>",
  "error_message": "<string>",
  "scenario_instructions": "<string>"
}
'
{
  "id": 123,
  "provider_call_id": "<string>",
  "scenario": 123,
  "scenario_name": "Scenario Deleted",
  "personality": 123,
  "personality_name": "<string>",
  "agent": 123,
  "result_id": 123,
  "result_name": "<string>",
  "expected_outcome_prompt": "<string>",
  "expected_outcome": {
    "score": 123,
    "explanation": [
      "<string>"
    ],
    "outcome_alignments": [
      {
        "outcome": "<string>",
        "prompt_part": "<string>",
        "aligned": true
      }
    ]
  },
  "evaluation": {
    "metrics": [
      {
        "id": 123,
        "name": "<string>",
        "type": "<string>",
        "score": 123,
        "enum": "<string>",
        "value": "<string>",
        "explanation": [
          "<string>"
        ],
        "extra": {}
      }
    ]
  },
  "rubric": "<unknown>",
  "transcript": "<string>",
  "transcript_object": [
    {
      "role": "<string>",
      "content": "<string>",
      "timestamp": 123
    }
  ],
  "duration": "<string>",
  "voice_recording_url": "<string>",
  "email_id": "jsmith@example.com",
  "status": "running",
  "evaluation_status": "success",
  "metadata": "<unknown>",
  "success": true,
  "is_reviewed": true,
  "feedback": "<string>",
  "timestamp": "2023-11-07T05:31:56Z",
  "executed_at": "2023-11-07T05:31:56Z",
  "outbound_number": "<string>",
  "inbound_number": "<string>",
  "critical_categories": [
    {
      "category_id": 123,
      "category": "<string>",
      "deviation": 123,
      "wrongly_marked": true,
      "feedback": "<string>",
      "priority": "critical"
    }
  ],
  "error_message": "<string>",
  "scenario_instructions": "<string>",
  "run_as_text": true,
  "test_profile_data": {
    "id": 123,
    "name": "<string>",
    "information": {}
  },
  "provider_call_details": "<unknown>",
  "agent_number": "<string>",
  "testing_channel_index": 123,
  "run_type": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.cekura.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
X-CEKURA-API-KEY
string
header
required

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

Body

​
evaluation_status
enum<string>
  • success - Success
  • failure - Failure
  • reviewed_success - Reviewed Success
  • reviewed_failure - Reviewed Failure
Available options:
success,
failure,
reviewed_success,
reviewed_failure
​
success
boolean

Whether this run passed its quality evaluation. false means either the call failed to connect or an evaluation check did not pass. Check error_message for connection failures and evaluation for check results.

​
is_reviewed
boolean

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

​
feedback
string
​
error_message
string
​
scenario_instructions
string

Response

200 - application/json
​
id
integer
read-only
​
provider_call_id
string
read-only

Call ID from the Assistant provider Example: call_abc123

​
scenario
integer | null
read-only
​
scenario_name
string
default:Scenario Deleted
read-only
​
personality
integer
read-only

Personality this run belongs to

​
personality_name
string
read-only

Name of the personality this run belongs to

​
agent
integer
read-only

ID of the agent associated with this run

​
result_id
integer
read-only
​
result_name
string
read-only

Name of the result this run belongs to

​
expected_outcome_prompt
string
read-only
​
expected_outcome
object
​
evaluation
object

Run Evaluation

​
rubric
any | null

Detailed rubric evaluation data Example:

[
    {
        "metric_id": 100,
        "metric_name": "Call Quality",
        "value": 5,
        "explanation": ["The response was accurate"],
        "passed": true,
        "conditions": "score gte 5",
        "expected_conditions": {"operator": "and", "conditions": [{"field": "score", "op": "gte", "value": 5}]}
    }
]
​
transcript
string
read-only

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_object
object[]
read-only

Transcript object

​
duration
string
read-only

Duration of the run in MM:SS format

​
voice_recording_url
string
read-only

URL to access the voice recording of this run

​
email_id
string<email> | null
read-only
​
status
enum<string>
read-only
  • running - Running
  • completed - Completed
  • failed - Failed
  • pending - Pending
  • in_progress - In Progress
  • evaluating - Evaluating
  • in_queue - In Queue
  • timeout - Timeout
  • cancelled - Cancelled
  • scaling_up - Scaling Up
Available options:
running,
completed,
failed,
pending,
in_progress,
evaluating,
in_queue,
timeout,
cancelled,
scaling_up
​
evaluation_status
enum<string>
  • success - Success
  • failure - Failure
  • reviewed_success - Reviewed Success
  • reviewed_failure - Reviewed Failure
Available options:
success,
failure,
reviewed_success,
reviewed_failure
​
metadata
any
​
success
boolean

Whether this run passed its quality evaluation. false means either the call failed to connect or an evaluation check did not pass. Check error_message for connection failures and evaluation for check results.

​
is_reviewed
boolean

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

​
feedback
string
​
timestamp
string<date-time>
read-only
​
executed_at
string<date-time> | null
read-only
​
outbound_number
string
read-only

Phone number used to make the outbound call for this run

​
inbound_number
string
read-only

Phone number used to receive the inbound call for this run

​
critical_categories
object[]
read-only

List of critical evaluation categories and their results for this run

​
error_message
string
​
scenario_instructions
string
​
run_as_text
boolean
read-only
​
test_profile_data
object

Test Profile

​
provider_call_details
any
read-only

Details of the call from the provider

​
agent_number
string | null
read-only

Phone number of the agent (only for voice inbound calls)

​
testing_channel_index
integer | null
read-only

The channel index of the testing agent in the audio recording

​
run_type
string | null
read-only

Run Execution Type