Available · 2 projects · Q4 2026Independent practice · Montreal

Invoices and documents · Quebec SMBs

Are your invoices and purchase orders still keyed in by hand?

Every document that arrives as a PDF, a photo or an email attachment ends up being read and re-typed by someone. AI can now read these documents reliably: it extracts the fields, checks them against your rules and sends them into your software. Your team only handles the exceptions.

Gabriel Nadon, independent consultant in Montreal. You talk to the person who builds it.

The documents we process
  • Supplier invoices: number, date, amounts, taxes, product lines.
  • Purchase orders and delivery slips, matched against each other.
  • Supplier price lists, in PDF, Excel or CSV, each in a different format.
  • Forms, timesheets and job-site documents.

The signs

Someone on your payroll is copying out what’s already written.

Document data entry doesn’t appear on any financial statement. It hides in payroll, in billing delays and in errors discovered too late.

  • Invoices pile up at month-end, and accounting scrambles to catch up.
  • Every supplier sends a different format; no off-the-shelf tool reads them all.
  • A data entry error on a price or a quantity costs more than the data entry itself.
  • Delivery slips are never matched against orders.
  • You tried OCR software: it read the text, but didn’t understand the document.

How it works

OCR reads the characters. AI understands the document. Rules check it. A person settles the exceptions.

A document goes through four steps: it is captured (email, shared folder, scan), read and structured by AI, checked against rules specific to your business — known supplier, totals that add up, matching order — then entered into your system. Anything that fails the checks lands in a review queue, with the reason.

  • Tested on your real documents

    Before any commitment, we run a sample of your invoices through and measure what comes out correctly.

  • Checks, not blind trust

    A total that doesn’t add up, an unknown supplier, an unusual price: the document is held back and flagged.

  • Connected to your software

    QuickBooks, Acomba, Sage, your ERP or Excel — through import, API or export, depending on what the software allows.

How it works, in five steps

  1. Document inventory

    Which documents, how many per month, from how many suppliers, and where they need to end up.

  2. Test on a sample

    Around fifty real documents go through the system. We see exactly what is reliable and what isn’t.

  3. Validation rules

    Together we write the checks that matter: thresholds, matching, approved suppliers.

  4. Software connection

    Validated data is entered automatically; exceptions land in a queue that’s simple to work through.

  5. Exception follow-up

    We look at what falls into exceptions and improve the rules until the queue becomes marginal.

Real results

An independent grocery store received price lists from all its suppliers, each in its own format, and re-typed them into its point-of-sale system: close to $56,000 a year. The system now reads those lists, compares about 37,000 prices each cycle and prepares the update — without replacing the POS, and the team approves before it’s applied. Read the full case study →

Pricing

Sample test included in the first sprint: from $4,500, fixed scope, 2 to 3 weeks for one document type. On top of that come per-use processing fees, estimated on your real volumes before building. Calculate what data entry costs you →

Questions I often get

What’s the difference between OCR and AI processing?

OCR turns an image into text. AI understands that text: it knows a number is a pre-tax total, a line is a product, a document is a credit note. That’s what makes it possible to read different formats without a template per supplier.

What accuracy can we expect?

It depends on your documents: scan quality, variety of formats, handwriting. That’s why we start with a test on your real documents, and why rules hold back anything doubtful instead of entering it.

Does it work with QuickBooks, Acomba or Sage?

Yes, depending on the access the software offers: API, file import or structured export. We confirm the integration path during the review, before any commitment.

What about handwritten or poorly scanned documents?

They are read when possible, and sent for review when the reading isn’t reliable enough. The goal isn’t zero human involvement, it’s zero pointless data entry.

Our documents contain personal information. Is that a problem?

Not if it’s governed: we choose providers and settings compatible with your obligations (Quebec’s Law 25), limit access and keep only what’s necessary.

Free review

How many documents does your team re-type every month?

Tell me which ones and roughly how many. I’ll reply within 24 hours with what can be automated and an honest idea of the effort.

Or book your 20 minutes now

Reply within 24 hours. Or book 20 minutes directly.