Documents and receipts

Receipts that include an invoice number keep their receipt classification. When the fast model is uncertain about a document’s type, a larger model checks it. Long invoices and receipts can use source-backed headers without hitting unused reference-candidate limits; uncertain financial facts still need review.

Invoice and receipt fields can be parsed before you choose a contract. If OCR cannot confirm a PDF’s readable text, its parsed fields remain available for review and recording stays blocked. Complete, verified documents still need the ordinary contract, ownership and recording checks.

Give your agent an invoice or receipt as a PDF or as text. It reads the document, tells you what it found, and records the bill or the payment you made, but only if you have allowed it to, and only for a vendor you already have an agreement with. Invoices you send to customers are not recorded this way yet. Anything it is unsure about comes back to you with the reason, so you decide.

Bills and payments recorded from a file link back to it. Files keep the names you gave them, and PDFs now open in Safari. Scanned pages are read and sorted but never booked automatically; only PDFs with selectable text can be recorded.