← All case studies
Live implementationContract Intelligence

Handwritten contracts turned into live data, so no renewal or obligation slips.

Enterprise supplier · Delivered · name withheld

Everyhandwritten contract read and storedReported
Linkedpurchase orders checked against contract termsReported
Alertedexpiries flagged in timeReported
01
The problem

An enterprise supplier's customer agreements were signed on paper, often with handwritten terms.

£What it was costing them

Missed renewals, unfulfilled obligations and orders priced against the wrong terms.

Read more

Nobody could easily see what had been agreed, which orders were still owed or when a contract expired.

02
The existing workflow

How the work was done, and where it broke.

It starts with

A batch of signed forms or contracts is uploaded: typed, scanned or photographed, up to 30 PDFs at a time.

What goes in

Bank detail change forms (two German layouts, 38 and 9 fields), with typed, scanned and handwritten entries and tick boxes.

Done by hand today

Reading each form, retyping every field and checking bank details digit by digit.

✕

Critical terms and prices lived in filing cabinets.

✕

Teams couldn't see what had been agreed with each customer.

✕

Orders owed under a contract were tracked by memory.

✕

Expiries and renewals were noticed too late.

03
The solution

People review the source of every extracted term before it becomes the record.

1Read once

Typed and handwritten fields extracted by AI, with source review.

2Built a live record

Terms, prices and obligations stored as data, not scans.

3Linked to orders

Purchase orders checked against what the contract says must be delivered.

4Set the alerts

Renewals and expiries flagged so the team and customer hear in time.

☺
Where a person decides

A reviewer sees the page with a box on every field. Only flagged values need attention. Press J for the next issue, then confirm or correct, and approve the export.

04
Architecture

From input to outcome.

1

Inputs

  • Scanned, typed and handwritten PDFs
  • Bulk upload, up to 30 at once
2

Ingestion

  • Pages rendered to images
  • Cloud OCR and text extraction OCR: forms, tables, tick boxes
  • Cache by file fingerprint, each PDF read once
3

AI layer

  • A large language model on a managed cloud AI service reads cropped field images independently
4

Rules

  • IBAN checksum and OCR-confusion repair
  • BIC, postcode, date and email checks
  • Cross-field consensus rules
5

Human review

  • Page view with a box per field
  • Only flagged values need a decision
6

Outcome

  • Approved CSV or Excel export
  • Per-document run record
05
Integrations

Works with the systems already in place.

⇄

Export to CSV or Excel for the customer's core system import

⇄

Production integration to the target system to be scoped

06
Business value

What changed for the business.

Every contract ingestedReported

Each handwritten contract read and stored as live data.

Obligations visibleReported

The team sees what was agreed with each customer.

Orders matched to termsReported

Purchase orders checked against the contract they fall under.

Nothing slipsReported

Expiries flagged and customers told in good time.

07
The evidence

Shown on real work.

Read once, tracked for the life of the contract. The same contract data lets order intake price orders against the right terms and lets a sales assistant answer questions about them.
About the evidence

Qualitative outcomes; no volume or time figures are cleared for sharing.

How we label results

Have a process like this?

Tell us about it. The first discovery call is free.