FutureSmart Document Intelligence in Structured Document Extraction

FutureSmart Document Intelligence returned an honest null for the absent field. The structured data row shows the loyalty cell empty while sibling fields are filled, and the document details output carries only document-level fields; the source text has no loyalty or member mention.

FutureSmart Document Intelligence extracted the same field correctly across three differently laid-out documents. The baseline receipt, the invoice, and the stacked receipt all returned the right identifiers and amounts; the tax field format varied, and the invoice was labeled as an invoice while the other two were receipts.

FutureSmart Document Intelligence passed this plain-field extraction case. The output and the document overview both returned the receipt number as RHS-70234, and the receipt text shows a different nearby identifier.

FutureSmart Document Intelligence derived the missing fuel cost for this invoice. The invoice shows 450 miles and £0.18 per mile, and the product returned 81 in both the JSON output and the overview card.

FutureSmart Document Intelligence passed this definition-driven extraction case. It returned the consignment reference, not the more prominent invoice number, and the field definition named the consignment reference and excluded the invoice number.

FutureSmart Document Intelligence passed this repeated-set case. It returned three line items with the right descriptions, quantities, unit prices, and amounts in the right rows; item code was requested but missing from every record.

FutureSmart Document Intelligence passed this non-member scenario. It kept the five genuine rows, omitted the Total row, showed the same five items on screen, and treated the 1,982.00 GBP total as document-level information.

FutureSmart Document Intelligence kept one array across the page break. The invoice splits across two pages, and the output keeps ten entries in order with item 6 followed by item 7 and no missing or repeated member.

FutureSmart Document Intelligence passed this empty-set extraction case. It returned damage_exceptions as an empty array, and the document says no damage or exceptions were reported; the overview card omits that field.

FutureSmart Document Intelligence passes this clean-scan OCR check. The image-only twin has no text layer, and the digital and scanned runs match on every graded field.

FutureSmart Document Intelligence handled the mixed-page document successfully. It returned all five requested values exactly, including the two that existed only on the scanned page, and the three digital-page values matched unchanged.

FutureSmart Document Intelligence aggregated across the three named invoices and returned the exact sum, £10,327.64. The Coppergate invoice's £1,982.00 total matched its line items, and the answer itemized the three document totals without any document missing or extra value added.

FutureSmart Document Intelligence passes this cross-document filter task. It returned Meridian Retail Group invoice MRG-INV-20481 at £6,591.24. The run covered 17 documents, and a later 20-document totals table still shows that Blackwood invoice was the only record above £2,500.

FutureSmart Document Intelligence passed this scenario. It gave the IFSC code and then said it came from reading the document directly, not from a separate extracted metadata field.

FutureSmart Document Intelligence did not let the corrected value reach the stored record. The overview and document view showed plain-text fields with no edit control, and the stored receipt number stayed RHS-70234 while RHS-99999 never appeared.

FutureSmart Document Intelligence did not keep corrected data downstream. The export path existed, but it carried only the original extraction, and the receipt row in the downloaded CSV still held RHS-70234.

FutureSmart Document Intelligence fails this repair task. It could not add a new line item or find a delete option, and the read-back stayed at the same ten Blackwood items.

FutureSmart Document Intelligence returned an honest null for the absent field. The structured data row shows the loyalty cell empty while sibling fields are filled, and the document details output carries only document-level fields; the source text has no loyalty or member mention.

FutureSmart Document Intelligence failed to trace the subtotal to its document location. The subtotal was on page 2, but the saved result had no location field, the chat only named a chunk, and the magnifier highlighted text in the extracted-text panel rather than a returned pointer.