Matching one document against another is a job for software.
Invoice against purchase order against contract. Expense claims against policy. Vendor onboarding against a checklist. We put that matching on software that runs on your systems and send your team only the cases that do not match.
If your job has become matching paper to paper…
You open the invoice, find the purchase order, check the contract, tick the box and click approve.
Nine times in ten the three agree. The tenth is why you are there.
Your judgement is needed on the odd mismatch. The matching itself is rule-checking, and that is what software is good at.
See what reaches your people.
One invented invoice checked line by line. The matching lines clear on their own; only the mismatches go to a person, and each leaves a record.
Invoice INV-2041 against its purchase order and contract
| Line | Invoice | Purchase order | Contract | Check |
|---|---|---|---|---|
| Consulting days | 12 x $800 | 12 x $800 | $800 a day | Cleared |
| Travel | $1,950 | not on order | capped at $1,500 | Exception · over cap |
| Licence fee | $4,200 | $4,200 | $3,900 | Exception · rate differs |
Sent to your team
What the 30 days look like.
A Proof shows you on your own data: one workflow, run for 30 days beside your current process, for a fixed price. Nothing you run today is switched off.
Pick the workflow.
We scope one workflow with you and agree in writing, on day 5, what it has to get right for you to keep it.
Test it on your own data.
Up to three candidate AI models and one leading hosted model do the same matching on your past invoices, orders and contracts, on your systems, which we can read but never change. If a simple rule does the job, we'll use a rule.
Take the evidence to your leadership.
You get a working workflow, a comparison you can rerun, and a pack showing how it meets the rules in one country or region.
You keep what we built either way.
The data, the rules, the tests and the documents stay yours. The exact terms are at the bottom of this page.
Straight answers.
- "We just want this automated. We don't want AI."
- We'll take that brief. If a simple rule does the job, we'll use a rule and tell you so. Matching a line item to a price is usually a rule. A model only comes in where the paper is messy, such as reading a scanned contract clause, and it is tested first on your own past documents.
- "Our invoices arrive as PDFs and paper."
- That is the normal case. We start with what you already hold: scanned or emailed invoices, the order system, the contract folder. If part of it exists only on paper, we tell you on the first call whether getting it readable fits inside 30 days.
- "Will my team push back?"
- They stay the ones who approve. They stop re-reading the lines that match and see only the exceptions, each with the reason. Most teams switch when they have seen it agree with them on their own past invoices.
- "Does it approve payments?"
- No. It reads your systems and never changes them. A person approves or rejects every exception, and the record shows who did.
Bring us the matching job nobody enjoys.
A 30-minute call and six questions. You get green, amber or red, and if it's red we say so and tell you why.
From $30K, fixed scope. Live in 30 days, or you don't pay the balance. 30% at kickoff, 70% only if the bar we agree on day 5 is hit. Terms are set out in each statement of work. You own the data, the rules, the tests and the documents; nothing is locked to us. Exact terms