Capture, OCR & indexing
How this is scored
How documents get in and become findable: scanning and email intake, OCR, classification and metadata extraction, and whether incoming e-invoices (XRechnung, ZUGFeRD) are read as structured data rather than as pictures.
0 — Not a document intake tool: files cannot be uploaded or captured into the product as documents.
3 — Upload, drag-and-drop or scan import with full-text OCR; email intake, document types and field extraction are basic or not described.
5 — Scanner or app capture and email intake, full-text OCR, and document types with metadata fields, some filled automatically (date, sender, amount or similar).
8 — AI- or rule-based classification and field extraction with a validation step, XRechnung and ZUGFeRD read as structured data, mailbox and Microsoft 365 intake, and duplicate detection documented.
10 — Capture is engineered and shown: classification and extraction trainable per document type, validation queues, e-invoice validation against the standard, intake channels listed with their limits, and where AI processing runs (location, model provider) stated.
The GoBD Auditor
The homepage states that generative AI capture extracts data from any document, including scanned images, forms and digital records, with an accounts-payable use case and a QuickBooks handover for invoices. That documents capture with automatic data extraction, but we found no public information on a validation step, on e-invoices such as XRechnung or ZUGFeRD being read as structured data, on intake channels and their limits, duplicate detection, or where the AI processing runs. That lands it above a basic scan import but short of a documented, validated capture chain. 1