Case study 04
Invoice Extraction Pipeline
An extraction pipeline replacing hours of daily retyping, with a confidence threshold that routes anything uncertain to a person.
- Sector
- Distribution
- Year
- 2026
- Service
- AI Automation
PDF → structured data · human review
The problem
A staff member spent most of each morning opening supplier invoice PDFs and retyping line items, quantities and rates into a spreadsheet. High volume, entirely mechanical, and error-prone in exactly the way that produces disputes with suppliers three weeks later.
What we built
Invoices land in a watched inbox, get parsed to structured line items, and are written straight through when extraction confidence is high. Anything below the threshold — a scanned copy, an unusual layout, a smudged total — goes to a review queue where one click confirms or corrects it. Accuracy is logged per supplier, and drift raises an alert rather than quietly corrupting a quarter of data.
Under the hood
- inbox:watch
- pdf:split
- ocr:extract
- schema:validate
- confidence:gate
- review:queue
- commit:ledger
- confidence_threshold=0.92
- totals_must_reconcile
- duplicate_invoice_hash
- supplier_drift_alert
- POST /ingest
- GET /review/pending
- POST /review/:id/confirm
Built as
AI AutomationOther engagements