# Automated invoice and receipt extraction

> A document AI pipeline that reads invoices and receipts, validates the data and posts it to accounting software for review.

Source: https://www.mapleorbitsol.com/work/invoice-data-extraction

- Service: AI / ML (https://www.mapleorbitsol.com/services/ai-ml.md)
- Client: An outsourced accounting firm processing thousands of documents a month
- Industry: Accounting services
- Region: Europe
- Duration: 10 weeks
- Team: 2 AI engineers, 1 back-end engineer

## The challenge

Staff keyed invoice data by hand during month-end close, which meant overtime, late reports and typing errors.

## How we approached it

1. **Document study:** Sampled 2,000 documents across suppliers, languages and formats.
2. **Extraction:** LLM extraction with schema-validated output, plus rules for totals, VAT and duplicates.
3. **Review queue:** Low-confidence fields routed to a simple review screen instead of the whole document.
4. **Integration:** Approved entries posted straight to the accounting system via its API.

## Results

- **80%** of documents processed with no manual edits
- **3 days** faster month-end close
- **−90%** data entry hours

## Tech stack

Python, Google Gemini, Pydantic, FastAPI, PostgreSQL, Celery, Docker