All case studies
Document Intelligence/Logistics

Automating 22,000 logistics documents a month

A document-processing platform that reads invoices, delivery slips and customs declarations, including faxed and handwritten ones, validates them against the core logistics system, and routes only uncertain cases to human review.

of documents processed with no human touch
62%
of documents processed with no human touch
median time from receipt to booked
2 days → 35 min
median time from receipt to booked
field-level accuracy on a 2,000-document test set
96.2%
field-level accuracy on a 2,000-document test set

The challenge

A 16-person back-office team keyed carrier invoices, delivery slips and customs declarations into the company’s logistics system and SAP by hand. Volume had grown 35% in two years, and month-end closing regularly ran late.

Documents arrived by email, fax and paper scan, in Japanese and English, from more than 900 carriers and suppliers. Each used its own format, many carried hanko stamps and handwritten corrections, and an earlier OCR-template tool could not keep up.

Our approach

  1. 01

    Measure before building

    We sampled 5,000 real documents and labelled 2,000 of them. That gave us a test set before we wrote any product code, so every design decision could be measured.

  2. 02

    Confidence scoring on every field

    The system scores every field. High-confidence documents go straight to posting. Anything uncertain goes to a review queue with the doubtful fields highlighted.

  3. 03

    Validate against the business

    Extracted values are checked against orders, shipment records and carrier rate contracts. A plausible value that does not match the shipment record is still flagged.

What we built

Ingestion pipeline

Monitors shared mailboxes, the fax server and scanner folders, de-duplicates, splits multi-document PDFs and straightens scans.

Classification & extraction

Layout-aware parsing for Japanese tables, stamps and vertical text, plus LLM extraction into strict per-document-type schemas.

Validation engine

Business rules, three-way matching against orders and shipment records, and qualified-invoice registration number checks.

Review workspace

A web app where operators approve, correct or reject flagged fields. Every correction is fed back into the test set.

How it flows

  1. Email, fax & scans
  2. Classify
  3. Extract
  4. Validate vs core system
  5. Review queue
  6. SAP posting

How we measured it

Before release, every change runs against the 2,000-document test set. Accuracy is tracked per field, per document type and per source channel, with faxes tracked separately. Production corrections are sampled weekly and added back to the set.

Results

  • 62% of documents flow from inbox to SAP without anyone touching them.
  • Median processing time dropped from 2 days to 35 minutes.
  • The team absorbed a 20% volume increase without new hires; four people moved to carrier and billing inquiries.
  • Month-end closing now finishes on schedule.

Timeline

  1. Weeks 1–2

    Discovery

    Document sampling, process mapping, test-set labelling

  2. Weeks 3–5

    Prototype

    Extraction on the top 3 document types, accuracy baseline

  3. Weeks 6–13

    Build

    Validation engine, review app, core system and SAP integration

  4. Weeks 14–16

    Rollout

    Shadow mode, then staged go-live by document type

Contact

Have an AI product in mind?

Share what you would like to build, and we will help turn the idea into a production-ready product.

No technical specification required.

What happens next

  1. 1

    Share your idea

    Describe the problem, the users and the outcome you need.

  2. 2

    Discovery call

    We review your requirements together and clarify scope and constraints.

  3. 3

    Proposal

    You receive a clear scope, technical approach and delivery plan.