Amazon Textract Insights is generally available: describe fields in natural language and extract results with confidence scores and page-level grounding from mixed packets of up to 3,000 pages
General LLMs extract documents fluently but give no source page or calibrated score. How Textract's approach adds both, for teams handling forms, claims or onboarding packets.
// Key points
- Fields are defined in a blueprint: a JSON Schema in which each field has a natural-language description and an inference type (read verbatim or inferred from content); public blueprints cover the W-2, Form 1040, passports and more.
- One asynchronous request takes a mixed file of up to 3,000 pages, splits it into sub-documents and matches each to a blueprint; every value carries a confidence score and page-level grounding, with no training.
- It supports PDF, PNG, JPEG and TIFF in English, French, German, Italian, Portuguese and Spanish, and is priced per page rather than per token with no minimum commitment.
Builder's takeSource plus confidence is what lets document automation scale: only then can you set a threshold for auto-accept versus human review. AI Cloud Drive's structured extraction should output in this shape whichever model it uses. Chinese isn't supported yet, so for China-facing work borrow the blueprint design rather than the service.