Gemini Nano
238 of 240 invoices, extracted free
A builder tested new browser AI tools on 240 real client invoices. The files were scans, phone photos, and Word exports. He ran the test on a $600 laptop with no special graphics card. An on-device model in Chrome read each invoice in chunks through a small extension. The job was to return vendor, line items, subtotal, tax, and total as clean data for the accounts system. The tool had to fail loudly on a page it could not read.
How it wentThe local model extracted 238 of 240 invoices cleanly. Two badly rotated phone photos failed, and the same two had broken his old cloud flow. Cost was $0 per invoice, against about 1.1 cents per invoice all-in for the cloud flow. His rule: under 200 documents a month, cloud is fine. From 200 to 2,000, local first with cloud fallback works best.
Try it · based on the source's workflow
Extract vendor, line_items[], subtotal, tax, and total from each invoice document as structured data for [accounting system]. If a page is unreadable or a field is missing, flag it loudly instead of guessing. Work document by document and report the cost and failure count at the end.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.
238 of 240 invoices, extracted free — from The SmallOffice Brief, a daily brief of real AI cases for small businesses: https://smalloffice.space/case-238-of-240-invoices-extracted-free