> ## Documentation Index > Fetch the complete documentation index at: https://developers.scrunch.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Prompt > Creates a new prompt with variants for the specified platforms. Requires the `configure` scope. **Behavior:** - `stage` is optional. If omitted, the journey stage is auto-classified against your brand's active stages using an LLM. - If `stage` is provided, it must match one of your brand's active stages (case-sensitive display name). An unknown value returns `400`. An explicit stage is treated as a manual assertion and won't be overwritten by later re-classification. - Creates variants for each specified platform. - Reactivates an archived prompt if a duplicate exists. - Dispatches collection events to begin tracking. ## OpenAPI ````yaml /api-reference/openapi.json post /{brand_id}/prompts openapi: 3.1.0 info: title: Scrunch Data API version: 0.1.0 servers: - url: https://api.scrunchai.com/v1 security: [] paths: /{brand_id}/prompts: post: summary: Create Prompt description: >- Creates a new prompt with variants for the specified platforms. Requires the `configure` scope. **Behavior:** - `stage` is optional. If omitted, the journey stage is auto-classified against your brand's active stages using an LLM. - If `stage` is provided, it must match one of your brand's active stages (case-sensitive display name). An unknown value returns `400`. An explicit stage is treated as a manual assertion and won't be overwritten by later re-classification. - Creates variants for each specified platform. - Reactivates an archived prompt if a duplicate exists. - Dispatches collection events to begin tracking. operationId: createPrompt parameters: - name: brand_id in: path required: true schema: type: integer description: The unique identifier for the brand title: Brand Id description: The unique identifier for the brand requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/APIPromptInputModel' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PromptListing' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: - configure components: schemas: APIPromptInputModel: properties: text: type: string title: Text description: The prompt text to track across AI platforms persona_id: anyOf: - type: integer - type: 'null' title: Persona Id description: >- Optional persona ID to associate with this prompt for segmented analysis stage: anyOf: - type: string - type: 'null' title: Stage description: >- The customer journey stage this prompt represents. Must match one of your brand's active stages (case-sensitive display name); custom stage names are accepted. Omit to auto-classify against the brand's stage definitions. **Default stage sets:** - **Intent (v1)** — `Advice`, `Awareness`, `Evaluation`, `Comparison`, `Other` - **Funnel (v2)** — `Awareness`, `Consideration`, `Conversion`, `Loyalty`, `Other` Unknown stage names return `400 Bad Request`. An explicit stage is treated as a manual selection and won't be reclassified later. tags: items: type: string type: array title: Tags description: Custom tags for categorizing and filtering prompts default: [] key_topics: items: type: string type: array title: Key Topics description: Key topics to associate with this prompt from the brand's topic list default: [] language: anyOf: - type: string - type: 'null' title: Language description: >- Lowercase ISO 639-1 code of the language the prompt text is written in (e.g. `pt`, `ja`, `es`). Case-insensitive; uppercase input is normalized. Invalid codes return `422 Unprocessable Entity`. If omitted, the language is auto-detected from the prompt text, falling back to the brand's default language. platforms: items: type: string enum: - chatgpt - claude - google_ai_overviews - perplexity - meta - google_ai_mode - google_gemini - copilot - grok type: array title: Platforms description: >- AI platforms to track this prompt on. If empty, defaults to all supported platforms. **Supported platforms:** - `chatgpt` - OpenAI ChatGPT - `claude` - Anthropic Claude - `google_ai_overviews` - Google AI Overviews (Search) - `perplexity` - Perplexity AI - `meta` - Meta AI - `google_ai_mode` - Google AI Mode - `google_gemini` - Google Gemini - `copilot` - Microsoft Copilot default: [] type: object required: - text title: APIPromptInputModel description: Input model for creating a new prompt to track AI visibility. PromptListing: properties: id: type: integer title: Id description: Unique identifier for the prompt text: type: string title: Text description: The prompt text being tracked stage: type: string title: Stage description: >- The customer journey stage this prompt represents. Returned as the display name of the brand's active stage — one of the brand's default set (`Advice`, `Awareness`, `Evaluation`, `Comparison`, `Other` for intent brands; `Awareness`, `Consideration`, `Conversion`, `Loyalty`, `Other` for funnel brands) or a custom stage name. persona_id: anyOf: - type: integer - type: 'null' title: Persona Id description: ID of the associated persona, if any platforms: items: type: string enum: - chatgpt - claude - google_ai_overviews - perplexity - meta - google_ai_mode - google_gemini - copilot - grok type: array title: Platforms description: AI platforms this prompt is tracked on tags: items: type: string type: array title: Tags description: Custom tags assigned to this prompt topics: items: type: string type: array title: Topics description: Auto-detected or assigned topics for this prompt created_at: type: string format: date-time title: Created At description: Timestamp when the prompt was created type: object required: - id - text - stage - persona_id - platforms - tags - topics - created_at title: PromptListing description: >- Represents a prompt being tracked for AI visibility, including its configuration and metadata. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: HTTPBearer: type: http scheme: bearer ````