> ## Documentation Index > Fetch the complete documentation index at: https://docs.withgauge.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > For API and SDK launches, integration testing, and ongoing coding-agent checks, start with Gauge Agents: > - [Gauge Agents overview](https://docs.withgauge.com/agents/index.md) > - [Gauge Agents quickstart](https://docs.withgauge.com/agents/quickstart.md) > - [Create and inspect an eval](https://docs.withgauge.com/agents/guides/create-an-eval-and-run-an-experiment.md) > - [Agent Experience: diagnose integration failures](https://docs.withgauge.com/agents/concepts/agent-experience.md) > - [Agent Preference: measure product selection](https://docs.withgauge.com/agents/concepts/agent-preference.md) > - [GitHub PR checks](https://docs.withgauge.com/agents/guides/github-pr-checks.md) > For AI search visibility and AEO, start with [Gauge Chat](https://docs.withgauge.com/introduction/welcome.md). # Create prompts > Create prompts in bulk and queue them for sampling. A prompt whose text matches an existing prompt in the category (ignoring case and whitespace) is returned as `already_exists`, so retries are safe. If the new prompts exceed the plan's prompt limit, nothing is created and the response is 403 `limit_exceeded`. ## OpenAPI ````yaml chat/openapi.json POST /orgs/{org}/categories/{category}/prompts openapi: 3.1.0 info: title: Gauge Chat API version: '1.0' description: > The Gauge Chat API: manage tracked prompts and query AI visibility data. **Authentication:** `Authorization: Bearer ` using either a Gauge CLI login token (`gauge auth login`) or an organization API key. Login tokens are user-bound; every request is checked against your current organization memberships. API keys act as their organization (and, for an agency, its clients), and are scoped to read or read+write. `GET /me` describes the token in use. **Conventions:** camelCase JSON; typed opaque string IDs (`prm_…`, `top_…`); errors as `{"error": {"code", "message", "field"?}}`; list endpoints page with an opaque `cursor` and return `nextCursor`. contact: name: Gauge support email: support@withgauge.com servers: - url: https://app.withgauge.com/api/v1 description: Production security: - BearerAuth: [] tags: - name: Organizations description: The current credential, and the organizations and categories it reaches. - name: Topics description: Topics group tracked prompts within a category. - name: Prompts description: Tracked prompts, their topics, tracking type, and tags. - name: Tags description: Organization-wide labels for prompts. - name: Brands description: Brands Gauge tracks in a category, including competitors. - name: Query description: Aggregate AI visibility reports. - name: Answers description: Individual AI answers and the citations in them. paths: /orgs/{org}/categories/{category}/prompts: post: tags: - Prompts summary: Create prompts description: >- Create prompts in bulk and queue them for sampling. A prompt whose text matches an existing prompt in the category (ignoring case and whitespace) is returned as `already_exists`, so retries are safe. If the new prompts exceed the plan's prompt limit, nothing is created and the response is 403 `limit_exceeded`. operationId: createPrompts parameters: - in: path name: org schema: title: Org type: string required: true - in: path name: category schema: title: Category type: string required: true - in: query name: dryRun schema: default: false title: Dryrun type: boolean required: false requestBody: content: application/json: schema: $ref: '#/components/schemas/CreatePromptsIn' required: true responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/CreatePromptsOut' '201': description: Created content: application/json: schema: $ref: '#/components/schemas/CreatePromptsOut' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Not Found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Too Many Requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: CreatePromptsIn: properties: prompts: items: $ref: '#/components/schemas/PromptIn' maxItems: 500 minItems: 1 title: Prompts type: array required: - prompts title: CreatePromptsIn type: object CreatePromptsOut: properties: results: items: $ref: '#/components/schemas/CreateResult' title: Results type: array dryRun: title: Dryrun type: boolean remaining: anyOf: - type: integer - type: 'null' description: >- Prompts still allowed by the plan after this request; null if unlimited. title: Remaining required: - results - dryRun - remaining title: CreatePromptsOut type: object ErrorResponse: properties: error: $ref: '#/components/schemas/ErrorDetail' required: - error title: ErrorResponse type: object PromptIn: properties: text: maxLength: 500 minLength: 1 title: Text type: string topicId: title: Topicid type: string trackingType: default: visibility enum: - visibility - branded_own title: Trackingtype type: string tagIds: items: type: string title: Tagids type: array required: - text - topicId title: PromptIn type: object CreateResult: properties: index: title: Index type: integer status: enum: - created - already_exists - would_create title: Status type: string prompt: anyOf: - $ref: '#/components/schemas/PromptOut' - type: 'null' required: - index - status title: CreateResult type: object ErrorDetail: properties: code: title: Code type: string message: title: Message type: string field: anyOf: - type: string - type: 'null' title: Field required: - code - message title: ErrorDetail type: object PromptOut: properties: id: title: Id type: string text: title: Text type: string topicId: anyOf: - type: string - type: 'null' title: Topicid trackingType: title: Trackingtype type: string tagIds: items: type: string title: Tagids type: array createdAt: format: date-time title: Createdat type: string firstAnswerDay: anyOf: - format: date type: string - type: 'null' description: Pacific date of the prompt's first answer; null until sampled. title: Firstanswerday required: - id - text - topicId - trackingType - tagIds - createdAt - firstAnswerDay title: PromptOut type: object securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: gauge_sk_ description: >- An organization API key from **Settings → Integrations → API Keys**, or a Gauge CLI login token from `gauge auth login`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.