> ## 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.

# Create Evaluators from Call Logs V3

> Turn up to 50 call logs (a list of ids, or a number of call logs) into evaluators and return them once every call log is processed. Call logs need a transcript. Usually takes 1–3 minutes.



## OpenAPI

````yaml post /observability/v3/call-logs/create_scenarios/
openapi: 3.1.0
info:
  title: Cekura API
  version: v1
  description: >-
    Complete API documentation for the Cekura platform. This API provides
    endpoints for testing, observing, and evaluating AI voice agents — including
    managing agents, running evaluators, defining metrics, and analyzing call
    quality.
servers:
  - url: https://api.cekura.ai
security: []
paths:
  /observability/v3/call-logs/create_scenarios/:
    post:
      tags:
        - observability
      summary: Create evaluators from call logs
      description: >-
        Turn up to 50 call logs (a list of ids, or a number of call logs) into
        evaluators and return them once every call log is processed. Call logs
        need a transcript. Usually takes 1–3 minutes.
      operationId: call-logs-v3-create-scenarios
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SchemaPostCreateScenarios'
          application/x-www-form-urlencoded:
            schema:
              $ref: '#/components/schemas/SchemaPostCreateScenarios'
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/SchemaPostCreateScenarios'
      responses:
        '200':
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    enum:
                      - completed
                      - failed
                    description: >-
                      `failed` when the job could not produce its result; see
                      `error` / `errors`.
                  project_id:
                    type:
                      - integer
                      - 'null'
                  agent_id:
                    type:
                      - integer
                      - 'null'
                  total_scenarios:
                    type: integer
                  completed_scenarios:
                    type: integer
                  failed_scenarios:
                    type: integer
                  scenarios_list:
                    type: array
                    items:
                      type: object
                      description: Full evaluator object, as the evaluators API returns it.
                    description: The created evaluators.
                  errors:
                    type: array
                    items:
                      type: object
                      properties:
                        call_log_id:
                          type: integer
                        error:
                          type: object
                    description: >-
                      Call logs that could not become an evaluator, with the
                      reason.
          description: ''
        '400':
          content:
            application/json:
              schema:
                type: object
                properties:
                  field_name:
                    type: array
                    items:
                      type: string
          description: ''
        '403':
          description: No access to the agent, project or metric the job runs on.
        '504':
          description: >-
            The job did not finish within 15 minutes. It may still complete in
            the background.
      security:
        - api_key: []
        - oauth2: []
        - embedded_session: []
        - supabase_session: []
components:
  schemas:
    SchemaPostCreateScenarios:
      type: object
      properties:
        agent_id:
          type: integer
          description: |

            Agent ID, required if assistant_id is not provided
            Example: `2142`
        assistant_id:
          type: string
          description: |

            Assistant ID, required if agent_id is not provided
            Example: `asst_1234567890`
        call_logs:
          type: array
          items:
            type: integer
          description: >

            List of call log IDs to create scenarios from. Can also be the
            string "all" to process all call logs.

            Example: `[1, 2, 3]` or `"all"`
        copy_to_agent:
          type:
            - integer
            - 'null'
          description: |

            Optional agent ID to copy created scenarios to
            Example: `2142`
        project_id:
          type: integer
          description: |

            Project ID. Required when using folder_path.
            Example: `1376`
        folder_path:
          type:
            - string
            - 'null'
          description: |

            Folder path to assign the created scenarios to.
            Example: `"Sales.Inbound"`
  securitySchemes:
    api_key:
      type: apiKey
      in: header
      name: X-CEKURA-API-KEY
      description: >-
        API Key Authentication. It should be included in the header of each
        request.
    oauth2:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: OAuth access token issued by Cekura for connected apps.
    embedded_session:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Embedded-dashboard session token. Internal.
    supabase_session:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Cekura dashboard session token. Not a customer API credential.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.