BTW Studio
← All work

Invoices into validated data.

Upload an invoice and get structured fields. Every number is re-computed in code and reviewed next to the line it was read from.

Open the demo ↗Read the code

In plain words

You upload an invoice and get its fields as data: vendor, dates, amounts, line items. Before you see them, code re-does the arithmetic. Anything that does not add up is marked with the reason, next to the line of the document it was read from.

How it works

  1. Upload a PDF or paste text

    A sample invoice opens by default, one where the lines do not add up.

  2. See what was read and what failed

    Every field has a status: ok, missing or inconsistent, with the reason in plain words.

  3. Fix it and export

    Editing a value re-runs the checks at once. The checked result is copied as JSON.

The problem

Whatever reads a document can be wrong in a way that looks fine: a dropped line, a swapped digit, a total taken from the wrong row.

What we built

Extraction and checking are separate. After the fields are read, code verifies the arithmetic: quantity times price, line items against the subtotal, subtotal plus tax against the total. Anything that fails is marked with a plain reason, and a person fixes it on a review screen that re-checks as they type.

How we know it works

Sample invoices, three layouts, two currencies8
Fields read correctly on the samples64 of 64
Deliberately broken invoices caught2 of 2
Automated tests34

The samples and the rules were written together, so this is a regression check, not a benchmark. Known limits are listed in the repository.

Built with
TypeScript, Express, PDF text extraction
Model
Optional; a rule-based reader runs by default
Output
JSON, after a human review step
Good fit for
Accounting intake, logistics paperwork, back office

Under the hood

  1. PDFText layer, lines rebuilt from positions
  2. ReadRules by default; a model is optional
  3. CheckArithmetic, dates and sources, in code
  4. ReviewA person fixes what is flagged
  5. JSONExported after the review

Scanned pages without a text layer are rejected; there is no OCR. The model path is tested against a stubbed endpoint and has not been run on a live provider yet.

Decisions and why

Reading and checking are separate

Arithmetic does not depend on the reader behaving, so the same checks run on rules and on a model.

Rules first, model optional

The default reader is deterministic and needs no key, so the demo is free and repeatable.

A person stays in the loop

A wrong vendor name can still add up. The review screen exists for what arithmetic cannot catch.

Limits are written down

Whole-number prices, wrapped descriptions and scanned pages are listed in the repository as known gaps.