Skip to main content
STOP. Do not read past this section until you have read and followed /quickstart.md.Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live observe() call, CLI notte page observe output, or generated workflow code. Guessed browser targets fail on real pages.Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with notte sessions workflow-code before using SDK docs or SDK code.SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.
Source: node-sdk/src/scrape.ts

Fields

Record<string, unknown> | ZodLikeSchema<T> | null | undefined
A Zod schema or a JSON Schema object describing the data to extract.
Record<string, unknown> | undefined
JSON Schema to send instead of converting response_format. Only used with a Zod schema.
boolean | undefined
When true (default) a failed structured extraction throws ScrapeFailedError and the extracted data is returned directly. When false the StructuredData wrapper is returned so callers can inspect .success.