> ## 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.

# Auto-Improve Metric

> Improve a metric using feedback from test sets. Returns improved metric configuration. Use the Update Metric endpoint to save changes.



## OpenAPI

````yaml post /test_framework/metric-reviews/process_feedbacks/
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:
  /test_framework/metric-reviews/process_feedbacks/:
    post:
      tags:
        - test_framework
      description: >-
        Improve a metric using feedback from test sets. Returns improved metric
        configuration. Use the Update Metric endpoint to save changes.
      operationId: metric-reviews-process-feedbacks
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ProcessFeedbacksRequest'
          application/x-www-form-urlencoded:
            schema:
              $ref: '#/components/schemas/ProcessFeedbacksRequest'
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/ProcessFeedbacksRequest'
        required: true
      responses:
        '200':
          description: Returns progress_id for tracking progress
      security:
        - api_key: []
components:
  schemas:
    ProcessFeedbacksRequest:
      type: object
      properties:
        metric_id:
          type: integer
          description: ID of the metric to process feedbacks for
        metric_type:
          enum:
            - basic
            - custom_prompt
            - custom_code
            - llm_judge
          type: string
          x-spec-enum-id: b44700c0a6443b40
          description: >-
            Optional metric type


            * `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
        test_set_ids:
          type: array
          items:
            type: integer
          description: >-
            Test set IDs whose feedback drives the optimization. If omitted,
            defaults to every test set already added to this metric's Lab.
        simplified_prompt:
          type: string
          description: >-
            Simplified prompt to use as initial prompt for optimization. If
            provided, the optimizer will start from this prompt instead of the
            metric's original description.
        skip_evaluation:
          type: boolean
          default: false
          description: >-
            If true, skip running LLM evaluations on test sets after
            optimization. This speeds up the process but won't show evaluation
            results.
      required:
        - metric_id
  securitySchemes:
    api_key:
      type: apiKey
      name: X-CEKURA-API-KEY
      in: header
      description: >-
        API Key Authentication. It should be included in the header of each
        request.

````