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

# Replace prohibited topics

> Replace the full list of prohibited topics. Use when managing Autopilot settings from code.



## OpenAPI

````yaml put /autopilot/prohibited-topics
openapi: 3.1.0
info:
  title: OpenCX API
  description: >

    OpenCX is an AI-powered, all-in-one platform for customer support and
    outbound communications.


    Use this API to manage your OpenCX organization's AI agents, actions,
    conversations, contacts, and more.


    To get started, generate a new API key from the dashboard.


    ## Authentication

    All API endpoints require authentication using a Bearer token. You can
    generate an API key from your OpenCX dashboard.


    ## Rate Limiting

    API requests are rate limited to ensure fair usage. The current limits are:

    - 100 requests per minute for standard endpoints

    - 1000 requests per minute for streaming endpoints


    ## Error Handling

    The API uses standard HTTP status codes and returns detailed error messages
    in the response body.
  version: 1.0-beta
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
servers:
  - url: http://localhost:8080
    description: Development
  - url: https://api.open.cx
    description: Production
security:
  - bearerAuth: []
paths:
  /autopilot/prohibited-topics:
    put:
      summary: Replace prohibited topics
      description: >-
        Replace the full list of prohibited topics. Pass an empty array to clear
        all topics. Blank entries and case-insensitive duplicates are removed.
        When the AI detects a conversation about any of these topics, it hands
        off to a human.
      operationId: updateProhibitedTopics
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpdateProhibitedTopicsInputDto'
      responses:
        '200':
          description: Default Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ProhibitedTopicsResponseDto'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorDto'
components:
  schemas:
    UpdateProhibitedTopicsInputDto:
      $schema: https://json-schema.org/draft/2020-12/schema
      $id: '#/components/schemas/UpdateProhibitedTopicsInputDtoInput'
      type: object
      properties:
        topics:
          type: array
          items:
            anyOf:
              - type: string
              - type: object
                properties:
                  name:
                    type: string
                    maxLength: 255
                  description:
                    description: >-
                      Guidance for when a session matches this topic. Omit it to
                      keep the stored description; pass null to clear it.
                    anyOf:
                      - type: string
                        maxLength: 500
                      - type: 'null'
                required:
                  - name
          description: >-
            Full replacement list of prohibited topics. Each entry is either a
            name string or an object with a name and an optional description. A
            name-only entry keeps whatever description that topic already has.
            Empty array clears all topics. Duplicates and blank entries are
            removed.
      required:
        - topics
    ProhibitedTopicsResponseDto:
      $schema: https://json-schema.org/draft/2020-12/schema
      $id: '#/components/schemas/ProhibitedTopicsResponseDto'
      type: object
      properties:
        topics:
          type: array
          items:
            type: string
          description: >-
            Topic names only. When a session matches any of these, the AI hands
            off to a human (subject to per-channel handoff behavior).
        items:
          type: array
          items:
            type: object
            properties:
              name:
                type: string
                description: The topic name.
              description:
                description: >-
                  Guidance the AI uses when deciding whether a session matches
                  this topic, or null. Conditions stated here are applied as
                  strict rules.
                type:
                  - string
                  - 'null'
            required:
              - name
              - description
            additionalProperties: false
          description: The same topics, each with its description.
      required:
        - topics
        - items
      additionalProperties: false
    ErrorDto:
      type: object
      properties:
        statusCode:
          type: integer
        message:
          type: string
        error:
          type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT

````

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