Till reconciliation for restaurants

An hour of reconciliation per trading day, removed.

Sector : Hospitality — Two Brussels restaurants

The context

Every trading day, till reports have to be reconciled against the accounting summary: Z number, gross takings, VAT breakdown, and the split between cash, card and transfer payments.

The problem

An hour per trading day spent copying figures from one document into another. It adds nothing, and it is exactly the kind of task where a misaligned row goes unnoticed until the year-end accounts.

What was built

Two tools, deliberately different, because the two restaurants do not supply the same material. The first only has scanned thermal receipts: its PDFs are read by a vision model, and the extracted amounts feed three workbooks. The second has digital exports: everything is processed in the browser, so no accounting data ever leaves the machine.

What it changes

Re-entry disappears. Cells that already hold a value are never overwritten, and discrepancies are flagged rather than silently corrected — we remove the re-entry, not the vigilance.

How it works

The first tool is a Flask application: PDFs converted to 300 DPI images, read by Claude as OCR, results written to the workbooks with openpyxl. The second is a React application running entirely in the browser: XLSX exports read with exceljs, and surgical editing of the destination file — only the targeted cells are changed in the sheet XML, so formulas and formatting survive untouched.

What this could look like for you

The same reasoning applies wherever two systems ought to talk to each other and do not: till and accounts, rota and payroll, orders and stock. And the lesson is worth keeping: we pick the technology to match the material you supply. If your data is already digital, there is no reason to pay a model to read it again.