Expense claim audit
Reads expense claims, receipts, the expense policy. Produces approved, queried or rejected claims. Code works out every figure, the Judgement Engine answers the narrow questions, and whatever stays uncertain goes to a person.
Narrow questions, each with a check behind it.
Whether each claim fits policy; receipt matches the claim
Proven by code: receipt amount and date. Code proves the answer from the data itself: totals tie, a match is exact, the quote is on the document. Most of these judgements settle without a person.
Cross-checked: policy. A second source has to agree: a register, a contract, a list. When it does the judgement settles; when it doesn't, a person decides.
| Reads | Expense claims, receipts, the expense policy |
| Produces | Approved, queried or rejected claims |
| Who signs | A person on your team, with every figure traced to its document and every call on record |
| Process | Screening, audit and compliance |
| Industry | Finance and accounting |
Every line, decided where it's safest.
An example run. Each stage lights up as a line is decided there; pick a stage to see its lines.
| Ref | Item | Value | Decided by |
|---|---|---|---|
| EXP-410 | Taxi, client visitReceipt amount and date match the claim | 42.50 | Code · matched |
| EXP-411 | Dinner, 4 peopleWithin the per-head limit · 0.93 · guests named | 312.00 | Engine · proven |
| EXP-412 | Hotel, 2 nights ZurichWithin the city rate | 460.00 | Code · within policy |
| EXP-413 | Train ticket, first classPolicy allows second class unless approved · 0.66 | 128.00 | To a person |
| EXP-414 | Software subscriptionPersonal or business? Receipt names a private address | 19.90 | To a person |
|
Settled 3
To a person 2
Settled wrong 0
| |||
Your volumes in. Your hours out.
In our tests, between 24% and 42% of items still went to a person after tuning. Set your own share; a pilot measures it on your data.
Start from what's closest.
Screening, audit and compliance in other work
Supplier bank-detail change verification
Whether a change request is genuine
BankingSanctions screening alert review
True match or false positive
BankingAML transaction monitoring alert triage
Suspicious or explained
More for finance
What buyers ask
What happens when Sumarity isn't sure?
Nothing settles below the cutoff, or when the check disagrees. The item goes to a person in the inbox with what the engine saw, its best answer and the runner-up. The person's ruling is kept and tunes the next run.
How are its judgements checked?
Code proves the answer from the data itself: totals tie, a match is exact, the quote is on the document. Most of these judgements settle without a person.
Can we change it to fit how we work?
Yes. Start from this workflow and describe your differences in plain words. The design assistant revises it, the validator checks it, your expert reviews it on the canvas, and your admin publishes it.
Does it read our files as they are?
Yes: spreadsheets and CSV in any layout, PDFs, bank formats and e-mail attachments. Sumarity suggests how each column maps, proves the mapping on a sample and remembers it once a person confirms it.
Where does our data go?
Sumarity runs in Zurich. Your data, backups and logs are stored in Switzerland.
How does it get better?
Your team's rulings become an answer key. Better questions and cutoffs are proposed, tested on data they haven't seen, and published only when your admin approves. It improves itself, with permission.
Start from this workflow. Run it on your data.
A pilot runs alongside your own process for a few weeks, at our cost, and ends in a line-by-line comparison.