> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omni.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Rate an AI job's response

> Rate an AI job's response using the same thumbs up/thumbs down and optional comment a user can give a response in the Omni UI or in Slack. 

The job must have finished or the API returns a `409`. Poll the [Get AI job status](/api/ai/get-ai-job-status) endpoint to retrieve a job's current status. Submit feedback once per job.

<Note>
  Personal Access Tokens can only rate their own jobs. If using an Organization API key, pass `userId` to attribute the feedback to a specific user. This must be the same `userId` the job was submitted with.
</Note>




## OpenAPI

````yaml /api/openapi.yaml post /v1/ai/jobs/{jobId}/feedback
openapi: 3.1.0
info:
  title: Omni API
  description: >
    The Omni REST API provides programmatic access to your Omni instance for
    managing users, documents, queries, schedules, and more.  
  version: 1.0.0
  contact:
    name: Omni Support
    url: https://docs.omni.co
servers:
  - url: https://{instance}.omniapp.co/api
    description: Production
    variables:
      instance:
        default: blobsrus
        description: Your production Omni instance subdomain
  - url: https://{instance}.playground.exploreomni.dev/api
    description: Playground
    variables:
      instance:
        default: blobsrus
        description: Your playground Omni instance subdomain
security:
  - bearerAuth: []
  - orgApiKey: []
tags:
  - name: Who Am I
    description: Inspect your own user permissions
  - name: AI
    description: AI-powered query generation
  - name: AI Credit Controls
    description: Manage organization-level AI credit usage
  - name: AI Credit Usage
    description: Monitor AI credit usage
  - name: AI Evals
    description: >-
      Manage prompt sets and runs used to score AI quality against curated
      prompt suites.
  - name: AI Model Suggestions
    description: Manage AI-generated suggestions for shared models
  - name: AI Routines
    description: >-
      Manage Routines, which are scheduled, recurring AI-powered tasks that run
      automatically on your data
  - name: Apps
    description: Draft and publish app documents.
  - name: App downloads
    description: Download apps as PNG, PDF, XLSX, or CSV files
  - name: Documents v2
    description: >
      A draft-based workflow for creating and editing documents: create a
      document, patch a draft, then publish.
  - name: Documents
    description: Create, retrieve, and manage documents
  - name: API Tokens
    description: >-
      Manage API tokens (Organization keys, Personal Access Tokens, MCP OAuth
      grants)
  - name: IP Allowlist
    description: Manage the organization's IP allowlist
  - name: Connections
    description: Manage database connections
  - name: Connection environments
    description: Manage connection environments database connections
  - name: Color Palettes
    description: Manage custom chart color palettes
  - name: Content
    description: Unified content retrieval (documents and folders)
  - name: Content migration
    description: Export and import dashboards
  - name: Content validator
    description: Validate content against models and perform find/replace operations
  - name: Dashboard downloads
    description: Download dashboards and tiles as PDF, PNG, XLSX, CSV, or JSON files
  - name: Dashboard filters and controls
    description: Read and update dashboard filter and control default values
  - name: dbt
    description: Manage dbt configuration for connections
  - name: Document favorites
    description: Favorite and unfavorite documents
  - name: Document labels
    description: Apply and manage labels on documents
  - name: Document permissions
    description: Manage document-level access
  - name: Embed
    description: Manage embed sessions
  - name: Labels
    description: |
      Manage labels in the organization
  - name: Folders
    description: Create and organize content folders
  - name: Folder favorites
    description: Favorite and unfavorite folders
  - name: Folder labels
    description: Apply and manage labels on folders
  - name: Folder permissions
    description: Manage folder-level access
  - name: Jobs
    description: Check status of asynchronous jobs
  - name: Models
    description: Create and manage data models
  - name: Model branches
    description: Manage model branches and merge changes
  - name: Model git configuration
    description: Manage git configuration for shared models
  - name: Queries
    description: Execute workbook queries
  - name: Schedules
    description: Create and manage scheduled tasks
  - name: Schedule recipients
    description: Manage schedule recipients
  - name: Schema refresh schedules
    description: Manage automated schema refresh schedules for connections
  - name: Skills
    description: >-
      Manage skills, the saved slash-command instructions the Omni AI assistant
      runs
  - name: Topics
    description: Retrieve topic information from models
  - name: Uploads
    description: Manage file uploads
  - name: Users
    description: Manage users
  - name: User attributes
    description: Manage user attribute definitions
  - name: User groups
    description: Manage user groups
  - name: User model roles
    description: Manage model and connection role assignments for users
  - name: User group model roles
    description: Manage model and connection role assignments for user groups
  - name: Uploads
    description: Manage CSV and spreadsheet uploads
paths:
  /v1/ai/jobs/{jobId}/feedback:
    post:
      tags:
        - AI
      summary: Rate an AI job's response
      description: >
        Rate an AI job's response using the same thumbs up/thumbs down and
        optional comment a user can give a response in the Omni UI or in Slack. 


        The job must have finished or the API returns a `409`. Poll the [Get AI
        job status](/api/ai/get-ai-job-status) endpoint to retrieve a job's
        current status. Submit feedback once per job.


        <Note>
          Personal Access Tokens can only rate their own jobs. If using an Organization API key, pass `userId` to attribute the feedback to a specific user. This must be the same `userId` the job was submitted with.
        </Note>
      operationId: aiJobFeedbackSubmit
      parameters:
        - name: jobId
          in: path
          required: true
          schema:
            type: string
            format: uuid
            description: The unique identifier of the AI job
            example: 123e4567-e89b-12d3-a456-426614174000
          description: The unique identifier of the AI job
        - $ref: '#/components/parameters/userId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                comment:
                  type: string
                  minLength: 1
                  maxLength: 5000
                  description: >
                    Free-text feedback about the response, such as what was
                    wrong or what an automated evaluation found. Whitespace is
                    trimmed; null is treated as no comment.
                  example: Grouped by order date instead of ship date.
                rating:
                  type: string
                  enum:
                    - good
                    - bad
                  description: >
                    The verdict on the response. `good` is a thumbs up, `bad` a
                    thumbs down.
                  example: bad
              required:
                - rating
              additionalProperties: false
            example:
              rating: bad
              comment: Grouped by order date instead of ship date.
      responses:
        '200':
          description: Feedback recorded.
          content:
            application/json:
              schema:
                type: object
                properties:
                  comment:
                    type: string
                    description: The comment as recorded, or null when none was sent.
                    example: Grouped by order date instead of ship date.
                  conversationId:
                    type: string
                    format: uuid
                    description: >-
                      The conversation the rated job belongs to. Analytics keys
                      feedback by job id and conversation id.
                    example: 660e8400-e29b-41d4-a716-446655440001
                  jobId:
                    type: string
                    format: uuid
                    description: The job whose response was rated.
                    example: 550e8400-e29b-41d4-a716-446655440000
                  rating:
                    type: string
                    enum:
                      - good
                      - bad
                    description: >-
                      The verdict on the response. `good` is a thumbs up, `bad`
                      a thumbs down.
                    example: bad
                  submittedAt:
                    type: string
                    format: date-time
                    description: When the feedback was recorded.
                    example: '2025-01-15T10:00:00.000Z'
                required:
                  - comment
                  - conversationId
                  - jobId
                  - rating
                  - submittedAt
              example:
                jobId: 550e8400-e29b-41d4-a716-446655440000
                conversationId: 660e8400-e29b-41d4-a716-446655440001
                rating: bad
                comment: Grouped by order date instead of ship date.
                submittedAt: '2025-01-15T10:00:00.000Z'
        '400':
          description: >-
            Invalid job ID (must be a UUID) or request body — unknown rating,
            unrecognized field, or a comment that is empty or over 5000
            characters.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError400'
        '401':
          description: Missing or invalid API key.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError401'
        '403':
          description: >-
            Permission denied. AI query generation is disabled for the
            organization, the caller lacks AI access on the job's model, or a
            user-scoped key passed a different user's `userId`.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError403'
        '404':
          description: >-
            Job not found. The job may not exist, may belong to a different
            organization, or — for user-scoped keys — may belong to a different
            user. `userId` not found in the organization also returns 404.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError404'
        '409':
          description: >
            The job is not `COMPLETE` or `FAILED`. For a `QUEUED`, `EXECUTING`,
            or `DELIVERING` job, poll the [Get AI job
            status](/api/ai/get-ai-job-status) endpoint and retry once it
            finishes. A `CANCELLED` job can never be rated.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ApiError409'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '500':
          $ref: '#/components/responses/InternalServerError'
      security:
        - bearerAuth: []
components:
  parameters:
    userId:
      name: userId
      schema:
        type: string
        format: uuid
      required: false
      description: >
        **Organization API key required.** The membership ID of the user to act
        as.
      in: query
  schemas:
    ApiError400:
      type: object
      properties:
        detail:
          type: string
          description: Human-readable error message describing what went wrong.
        status:
          type: integer
          description: HTTP status code of the error.
          example: 400
      required:
        - detail
        - status
    ApiError401:
      type: object
      properties:
        detail:
          type: string
          description: Human-readable error message describing what went wrong.
          example: 'Unauthorized: Missing or invalid API key'
        status:
          type: integer
          description: HTTP status code of the error.
          example: 401
      required:
        - detail
        - status
    ApiError403:
      type: object
      properties:
        detail:
          type: string
          description: Human-readable error message describing what went wrong.
        status:
          type: integer
          description: HTTP status code of the error.
          example: 403
      required:
        - detail
        - status
    ApiError404:
      type: object
      properties:
        detail:
          type: string
          description: Human-readable error message describing what went wrong.
        status:
          type: integer
          description: HTTP status code of the error.
          example: 404
      required:
        - detail
        - status
    ApiError409:
      type: object
      properties:
        detail:
          type: string
          description: Human-readable error message describing what went wrong.
        status:
          type: integer
          description: HTTP status code of the error.
          example: 409
      required:
        - detail
        - status
    Error:
      type: object
      properties:
        error:
          type: string
          description: HTTP response code for the error
          example: <response_code>
        message:
          type: string
          description: Detailed error description
          example: <error_reason>
  responses:
    TooManyRequests:
      description: Too Many Requests - Rate limit exceeded (60 requests/minute)
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    InternalServerError:
      description: Internal Server Error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: >
        Can be either an [Organization API
        Key](/api/authentication#organization-api-keys) or [Personal Access
        Token (PAT)](/api/authentication#token-types).


        Include in the `Authorization` header as: `Bearer YOUR_TOKEN`
    orgApiKey:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: >
        Requires an [Organization API
        Key](/api/authentication#organization-api-keys). Personal Access Tokens
        (PATs) are not supported for this endpoint.


        Include in the `Authorization` header as: `Bearer ORGANIZATION_API_KEY`

````

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