> ## Documentation Index > Fetch the complete documentation index at: https://crevio.co/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create task > Creates a new AI task. Use trigger_type to schedule it: `immediate` runs once right away, `cron` runs on a cron expression, `interval` runs every N seconds, `once` runs at a specific scheduled_at, `event` runs in response to account events. For recurring tasks (`cron`/`interval`), add an optional `condition_script` — a cheap JavaScript gate that runs before each fire (no LLM, no credits) and skips the run unless its last expression is truthy, so the agent only wakes when there's work to do. ## OpenAPI ````yaml /developer/api-reference/openapi.json post /tasks openapi: 3.1.1 info: title: Crevio API V1 version: 1.0.0 description: > API for the Crevio creator platform — a multi-tenant SaaS for digital product sales. Uses snake_case keys following Stripe conventions. All resource IDs are string IDs (e.g., "prod_abc123"). Authentication is a bearer token: `Authorization: Bearer $CREVIO_API_KEY`. List endpoints are cursor-paginated with `limit` and `starting_after`. Writes accept an `Idempotency-Key` header and are safe to retry. Every response carries IETF RateLimit headers (`RateLimit`, `RateLimit-Policy`) so a client can self-throttle, and `Retry-After` on a 429. The quota is 600 requests per minute per credential. The API is versioned in the URL path (`/v1`). Nothing is removed without in-band warning: a deprecated operation is marked `"deprecated": true` here and serves `Deprecation` (RFC 9745), `Sunset` (RFC 8594) and `Link; rel="deprecation"` headers for at least six months before it stops answering. See https://crevio.co/docs/developer/guides/versioning. contact: email: support@crevio.co name: Crevio Support url: https://crevio.co/docs license: name: Apache 2.0 url: http://www.apache.org/licenses/LICENSE-2.0.html termsOfService: https://crevio.co/legal/terms-of-service servers: - url: https://api.crevio.co/v1 description: Production security: - ApiKey: [] tags: - name: Account description: Current account information - name: Bots description: >- Named bot identities (persona, skills, toolsets) chats and tasks can run as - name: Analytics description: Account-wide business analytics - name: BlogCategories description: Blog post categories - name: BlogPosts description: Blog content management - name: Broadcasts description: One-to-many email sending - name: CheckoutLinks description: Shareable checkout links - name: CheckoutConfiguration description: Account-wide checkout settings - name: Checkouts description: Checkout session management - name: Customers description: Customer relationship management - name: Discounts description: Discount code management - name: Experiences description: Digital experiences (courses, communities, downloads) - name: Files description: File uploads and external media management - name: FormSubmissions description: Form submission management - name: FormationDocuments description: Documents generated for a formation - name: Formations description: Whitelabel business formation via doola Partner API - name: Forms description: Hosted forms that capture leads and submissions - name: Invoices description: Invoice creation, payment, and lifecycle management - name: LegalPages description: Terms, privacy and refund pages for the storefront - name: Me description: Current user profile - name: OrderItems description: Order line items - name: Orders description: Order history and details - name: PriceVariants description: Product pricing tiers - name: Products description: Digital product catalog - name: Refunds description: Refund management - name: Reviews description: Product reviews - name: Socials description: Social media management (accounts, posts, media). - name: Subscriptions description: Subscription lifecycle management (cancel, pause, resume) - name: Tags description: Customer tags - name: TaskRuns description: Individual execution records for AI tasks. - name: Tasks description: >- AI tasks — scheduled or event-triggered agentic work (cron, interval, once, immediate, event). - name: WebhookEndpoints description: Webhook endpoint management - name: WebhookEvents description: Webhook event delivery history - name: Leads description: Find, verify and enrich business leads (Hunter.io-backed). - name: Ads description: >- Paid advertising — campaigns, ad groups, ads, audiences, targeting, leads, conversions, and reports across Meta, Google, TikTok, LinkedIn, Pinterest, and X. - name: Domains description: Custom web domains for your sites. - name: Web description: >- Web search & scraping (search, read, map, crawl, extract, research), backed by Firecrawl. - name: Skills description: >- AI skills marketplace — search the catalog and install or uninstall skills for your account's agent. - name: Schedules description: Reusable availability schedules that back event types. - name: EventTypes x-displayName: Event Types description: Bookable services customers can schedule time on. - name: Bookings description: Reservations made against event types. - name: Connections description: Third-party app connections (connect, list, execute) - name: Approvals description: Human-in-the-loop approvals for gated actions - name: Logs description: Account activity log - name: Access description: Per-user access checks for gated resources - name: ApiKeys description: API key management - name: Audio description: AI audio generation - name: Calls description: Outbound phone calls placed by the account's agent - name: Chapters description: Course chapters - name: Deployments description: Site deployments and build logs - name: Email description: Inboxes, threads, messages, drafts and delivery events - name: Email Suppressions description: Addresses no send path will deliver to - name: EventSessions description: Scheduled sessions of an event experience - name: EventSources description: Third-party event sources that trigger tasks - name: Events description: Events an account can subscribe to - name: ForumPosts description: Posts inside a forum experience - name: Images description: AI image generation, editing and stock search - name: Jobs description: Long-running asynchronous jobs - name: Lessons description: Lessons inside a course chapter - name: LinkItems description: Links inside a link-in-bio experience - name: Phone Consents description: Recorded consent to place calls to a number - name: Phone Numbers description: Phone numbers provisioned for the account - name: Phone Suppressions description: Do-not-call entries - name: Sites description: AI-built sites — storefronts and web apps - name: Status description: API and account status - name: Topics description: Discussion topics inside a forum experience - name: Usage description: Credit usage and transaction history - name: Users description: Users of the account - name: Video description: AI video generation - name: Secrets description: Account-level environment variables shared across the account's sites externalDocs: description: Crevio developer documentation url: https://crevio.co/docs/developer paths: /tasks: post: tags: - Tasks summary: Create task description: >- Creates a new AI task. Use trigger_type to schedule it: `immediate` runs once right away, `cron` runs on a cron expression, `interval` runs every N seconds, `once` runs at a specific scheduled_at, `event` runs in response to account events. For recurring tasks (`cron`/`interval`), add an optional `condition_script` — a cheap JavaScript gate that runs before each fire (no LLM, no credits) and skips the run unless its last expression is truthy, so the agent only wakes when there's work to do. operationId: createTask parameters: - $ref: '#/components/parameters/IdempotencyKey' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AiTaskRequest' responses: '201': description: Task created content: application/json: schema: $ref: '#/components/schemas/AiTask' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '422': $ref: '#/components/responses/UnprocessableEntity' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' security: - ApiKey: [] x-codeSamples: - lang: typescript label: Typescript (SDK) source: |- import { Crevio } from "@crevio/sdk"; const crevio = new Crevio({ apiKey: process.env["CREVIO_API_KEY"] ?? "", }); async function run() { const result = await crevio.tasks.create({}); console.log(result); } run(); components: parameters: IdempotencyKey: name: Idempotency-Key in: header required: false description: >- Makes this write safe to retry: a repeat with the same key replays the first response instead of creating a second resource. Scoped to the account, remembered for 24 hours; reusing a key with a different payload is an error. schema: type: string maxLength: 255 example: 1f7a4c2e-3b19-4a6d-9f0c-2ac81b5d7e33 schemas: AiTaskRequest: type: object properties: name: type: string description: type: - string - 'null' prompt: type: string trigger_type: type: string enum: - immediate - cron - interval - once - event cron_expression: type: - string - 'null' interval_seconds: type: - integer - 'null' scheduled_at: type: - string - 'null' format: date-time timezone: type: string model_id: type: - string - 'null' agent: type: string enum: - business - engineering description: >- Which agent runs the task. Use `engineering` for pure code/build work on a site; defaults to `business`. condition_script: type: - string - 'null' description: >- Cheap pre-run gate for recurring tasks (`cron`/`interval`). Plain JavaScript run in a sandboxed isolate against the same `crevioApi.*` connector as the execute tool, BEFORE each scheduled run — no LLM, no credits. The task only runs when the script's last expression (or explicit `return`) is truthy; it skips on `false`/`null`. **Default to setting this whenever the task is "act only when X"** (new/unfulfilled/failed records, a threshold crossed, an unread inbox, a metric at zero) — without it the agent wakes and spends credits on every tick even when there's nothing to do. Only omit it for tasks that genuinely should run every tick (e.g. a scheduled report the user always wants). End with a boolean, e.g. `const r = await crevioApi.listOrders({ status: 'succeeded' }); r.data.some(o => o.fulfillment_status !== 'fulfilled')`. Errors fail open (the task runs). Ignored for non-recurring triggers. pre_run_script: type: - string - 'null' approval_mode: type: string enum: - autonomous - supervised - read_only expires_at: type: - string - 'null' format: date-time active: type: boolean visibility: type: string enum: - account - personal delivery_methods: type: array items: type: string enum: - notification - email - telegram - discord - slack depends_on_task_ids: type: array items: type: string event_conditions: type: - object - 'null' site_id: type: string description: >- Site this task works on (`site_...`); its repo is mounted as the run's workspace. Defaults to the account's default working site. AiTask: type: object properties: id: type: string object: type: string name: type: string description: type: - string - 'null' prompt: type: string trigger_type: type: string enum: - immediate - cron - interval - once - event cron_expression: type: - string - 'null' interval_seconds: type: - integer - 'null' scheduled_at: type: - string - 'null' format: date-time event_conditions: type: - object - 'null' condition_script: type: - string - 'null' pre_run_script: type: - string - 'null' timezone: type: string delivery_methods: type: array items: type: string enum: - notification - email - telegram - discord - slack approval_mode: type: string enum: - autonomous - supervised - read_only model_id: type: - string - 'null' agent: type: string enum: - business - engineering visibility: type: string enum: - account - personal active: type: boolean expires_at: type: - string - 'null' format: date-time next_run_at: type: - string - 'null' format: date-time last_run_at: type: - string - 'null' format: date-time total_runs_count: type: integer consecutive_failure_count: type: integer total_credits_consumed: type: integer created_at: type: string format: date-time updated_at: type: string format: date-time depends_on: type: array items: type: string site_id: type: - string - 'null' required: - id - object - name - description - prompt - trigger_type - cron_expression - interval_seconds - scheduled_at - event_conditions - condition_script - pre_run_script - timezone - delivery_methods - approval_mode - model_id - agent - visibility - active - expires_at - next_run_at - last_run_at - total_runs_count - consecutive_failure_count - total_credits_consumed - created_at - updated_at - depends_on - site_id Error: type: object properties: error: type: object properties: type: type: string enum: - api_error - invalid_request_error - validation_error code: type: string message: type: string param: type: string errors: type: object required: - type - message required: - error responses: BadRequest: description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: invalid_request_error code: bad_request message: The request was malformed or contained invalid parameters headers: RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' Request-Id: $ref: '#/components/headers/RequestId' Deprecation: $ref: '#/components/headers/Deprecation' Sunset: $ref: '#/components/headers/Sunset' Link: $ref: '#/components/headers/DeprecationLink' Unauthorized: description: Authentication required content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: invalid_request_error code: authentication_required message: You did not provide an API key. headers: RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' Request-Id: $ref: '#/components/headers/RequestId' Deprecation: $ref: '#/components/headers/Deprecation' Sunset: $ref: '#/components/headers/Sunset' Link: $ref: '#/components/headers/DeprecationLink' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: invalid_request_error code: forbidden message: You do not have permission to perform this action headers: RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' Request-Id: $ref: '#/components/headers/RequestId' Deprecation: $ref: '#/components/headers/Deprecation' Sunset: $ref: '#/components/headers/Sunset' Link: $ref: '#/components/headers/DeprecationLink' UnprocessableEntity: description: Validation error content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: validation_error code: validation_failed message: Email is required errors: email: - can't be blank headers: RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' Request-Id: $ref: '#/components/headers/RequestId' Deprecation: $ref: '#/components/headers/Deprecation' Sunset: $ref: '#/components/headers/Sunset' Link: $ref: '#/components/headers/DeprecationLink' TooManyRequests: description: >- Rate limit exceeded — 600 requests per minute per credential. Retry after the number of seconds in `Retry-After`. headers: Retry-After: $ref: '#/components/headers/RetryAfter' RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: invalid_request_error code: rate_limit_exceeded message: Too many requests. Please retry later. InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' example: error: type: api_error code: internal_error message: An unexpected error occurred headers: RateLimit: $ref: '#/components/headers/RateLimit' RateLimit-Policy: $ref: '#/components/headers/RateLimitPolicy' Request-Id: $ref: '#/components/headers/RequestId' Deprecation: $ref: '#/components/headers/Deprecation' Sunset: $ref: '#/components/headers/Sunset' Link: $ref: '#/components/headers/DeprecationLink' headers: RateLimit: description: >- Remaining quota for the current window, as an IETF structured field: `"default";r=;t=`. schema: type: string examples: - '"default";r=596;t=11' RateLimitPolicy: description: >- The quota this credential is subject to: `"default";q=;w=`. schema: type: string examples: - '"default";q=600;w=60' RequestId: description: Unique id for this request. Quote it when reporting a problem. schema: type: string examples: - 8fe045fe-cb8a-4407-a44d-5df60385e522 Deprecation: description: >- Present only on a deprecated operation. Structured-field date (RFC 9745) — `@` followed by the Unix timestamp at which the operation became deprecated. schema: type: string examples: - '@1775001600' Sunset: description: >- Present only on a deprecated operation. HTTP-date (RFC 8594) after which the operation stops responding. Always at least six months after `Deprecation`. schema: type: string examples: - Thu, 01 Oct 2026 00:00:00 GMT DeprecationLink: description: >- Present only on a deprecated operation. `; rel="deprecation"` pointing at the migration notes. schema: type: string examples: - >- ; rel="deprecation" RetryAfter: description: Seconds to wait before retrying. schema: type: integer examples: - 11 securitySchemes: ApiKey: type: apiKey in: header name: Authorization description: 'API key in the format: Bearer {api_token}' ````