Sumarity
For controllers and finance teams

Close on the exceptions. Not the matching.

Sumarity matches the bank, customer receipts and supplier invoices across your systems, worded in English, German or French. Code ties out every figure, the Judgement Engine settles the easy calls, and your team gets an inbox of what's really open.

Bring one process See the track record

Code proves the numbers. People settle the doubts.

Bank reconciliation · run 2026-09 · v7 Example run
DateLineAmountDecided by
02.09STRIPE PAYOUT 0902Ties to 14 card sales, less fees1,284.50Code · tied
03.09RUECKLASTSCHRIFTReturned payment · 0.97 · reverses receipt R-1182−320.00Engine · proven
04.09GUTSCHRIFT M KELLER AGTiming match to INV-2207 · 0.91 · payer named450.00Engine · proven
05.09CHQ 004417Cheque number matches ledger, one to one−2,150.00Code · matched
08.09VIREMENT REF 88213Two customers paid 1,200.00 · no proof which1,200.00To a person
09.09INV-2214 ledger 1,540.00Keying error? · 0.73 · below the cutoff1,450.00To a person
Settled 4 To a person 2 Settled wrong 0
Illustrative lines in the style of our test months. Amber rows are the Judgement Engine's calls; each settles only above its cutoff and when its code check agrees.
What we'd run for you

Fewer items, and nothing missed

On nine months it had never seen, worded in English, German and French, the tuned workflow cut the team's inbox by two thirds and surfaced every real exception.

Controllers, shared services and treasury in growing companies

Bank and cash reconciliationTestedIs this receipt that invoice, paid days apart?Items for the team 236 → 73, false alarms 75 → 9, 108 of 108 exceptions surfaced. 0 settled wrong.
Customer cash applicationWhich invoices does this remittance pay?
Invoice and payment matchingA price change, or overbilling?
Financial reporting tie-outDoes it tie out, and is the variance explained?
Intercompany reconciliationWhich side has it wrong?

Sumarity for other work: Asset managers Accounting and tax firms Restaurants and hotels · everything

The number that matters most
0

wrong answers settled without a person, in every test we have run.

Models are sometimes wrong, ours included. The workflow is built so that a wrong answer has to pass a measured cutoff and a check in code before it can settle. So far, none has.

TestSettled wrong
Bank reconciliation, nine held-out monthsWording tuning never saw · 108 real exceptions, all surfaced0
The same months, three different judgement modelsJudgement Engine and two frontier models in the same seat0
Against a 1,154-line program an AI wrote for the jobThree unseen months · 36 of 36 exceptions0
Custody statements from a live fund42 real lines first seen after tuning0
UK pub VAT returns, a pub held out of tuning105 judgements · 15 of 15 problems reached the preparer0
Deliberately wrong picks at 100% confidenceFed to a changed check before it went live · 36 of 36 rejected0
Total0
How it works

Operations work is mostly rules. The rest is judgement.

Sumarity gives each part to whatever does it best: code for arithmetic, the Judgement Engine for lightning fast decisions, and people for what stays uncertain.

01

Describe

The expert writes a paragraph. Sumarity asks the questions that change the design, then writes the workflow.

Expert revisions
02

Validate

Numbers only from code, every doubt to a person, every path handled. What fails is repaired before anyone sees it.

43 errors → 0 in one repair
03

Review

Every step on a canvas in plain words, editable and versioned. What runs is what was reviewed.

draft → validated → published
04

Run

Code matches and ties out. The Judgement Engine decides, and learns when it cannot. People get an inbox.

2,112 lines in 4.5 s
05

Tune

Rulings become an answer key. Better questions are proposed, tested on data they haven't seen, and lets you decide.

77% → 97% on unseen lines
Every decision your team makes in the inbox goes back into step 5. It improves itself, with permission.
What the platform enforces

In this work, mistakes are expensive. So the rules aren't optional.

These aren't settings a busy team can switch off. The validator refuses a workflow that breaks them.

Left alone, AI invents a plausible number.The AI never writes an amount or a date. Code works out every figure.
It is sure, but not right.Nothing settles below the measured cutoff, or against a code check.
It fails quietly.Every unsure or unproven call must reach a person. Every path is handled.
It changes when its vendor updates it.The process changes only when an admin publishes a new version.
It can't show its work.Every call is on record: what it saw, how sure, which version, who reviewed it.
It answers questions it wasn't asked.Each judgement is one narrow question with a fixed set of answers.
It doesn't learn from your team.Your rulings tune its questions and cutoffs, tested first on data they haven't seen.
One person can approve their own work.Separation of duties and sign-off are enforced, not written in a policy.
Industries and use cases

Wherever the work is mostly arithmetic, with judgement calls in between.

Every one of these has the same shape. Code does the matching and the sums, the Judgement Engine answers one narrow question per item, and whatever stays uncertain goes to a person.

Codematches, ties out, works out every figureJudgementone narrow question, measuredA personwhatever stays uncertain

Finance and accounting

Controllers, shared services, treasury

Matching and tying out, where most lines are easy and the rest need someone who knows the business.

Bank and cash reconciliationIs this receipt that invoice, paid days apart?
Customer cash applicationWhich invoices does this remittance pay?
Invoice and payment matchingA price change, or overbilling?
Financial reporting tie-outDoes it tie out, and is the variance explained?

Accounting and tax services

Outsourced bookkeepers, tax preparers, practices

Many clients, the same process each period, and a filing at the end that has to be right.

VAT return preparationWhat was this purchase used for, and is any VAT reclaimable?
Bookkeeping and account codingWhich account does this belong to?
Expense and policy reviewWithin policy?
Client queries and chasingHas the client's answer settled the question?

Risk and compliance

Compliance, financial crime, onboarding teams

High-volume alerts where most are noise, every decision needs a record, and the real ones must never be missed.

Sanctions and screening alertsThe same party, or a namesake?
Transaction monitoringWorth escalating?
Vendor and client onboardingComplete and consistent?
Periodic KYC reviewHas anything material changed?

Fund and investment operations

Administrators, depositaries, asset managers

Statements in every custodian's layout, against your own book, with breaks that have to be explained and chased.

Custody and position reconciliationA redemption, a fee, or a transfer of subscription cash?
Trade and corporate action breaksTiming, or a real error?
Fee and expense checksIn line with the agreement?
Price and valuation reviewIs this move plausible?
The library

A workflow for every process. In every industry.

Standard workflows, each tested against an answer key before it's published. Start from the closest one and describe how yours differs.

Finance and accounting

18 workflows

Accounting, tax and Treuhand firms

8 workflows

Banking and payments

11 workflows

Wealth, asset management and fund administration

9 workflows

Insurance

8 workflows

Healthcare

7 workflows

Manufacturing and supply chain

7 workflows

Retail, hospitality and consumer

6 workflows

Logistics and transport

4 workflows

Energy and utilities

4 workflows

Telecoms

3 workflows

Real estate

4 workflows

Public sector

4 workflows

Legal and compliance

3 workflows

HR and payroll

4 workflows
By processReconciliation and matching Payables, receivables and payments Filings, returns and reporting Documents, onboarding and KYC Claims, disputes and exceptions Screening, audit and compliance Close and accounting Billing and revenue assurance
Browse the library
Track record

Three processes, three domains. Every figure from a run.

Each workflow was authored through the product from an expert's description, then scored against a known answer.

Tested against the alternatives

Why not just hand it to an AI? We tried that too.

Same brief, same data, same scoring. These are the three things a capable team would try instead.

Give a frontier model the whole job

Each model got the brief and both exports and returned the finished reconciliation, five times on each of two data sets.

SumarityOpus 5.5GPT-6 Sol
Exceptions (of 108)10810895
Same result, 10 runs10/1010/102/10
2,112-line account4.5 s262 s–
Record per lineYesNoNo
Past about 6,000 lines the job no longer fits in one reply.
Ask an AI to write the code

Opus wrote a careful 1,154-line program from the same brief and sample files. Both then ran on three months worded in ways neither had seen.

SumarityAI-written code
Exceptions (of 36)3636
Settled wrongly00
Judgement items to people314
False alarms314
The program's rules were written from the sample's wording. Nothing in it learns from a review.
Put a frontier model in the judgement seat

The same workflow and checks, with only the judgement model swapped. 180 decisions with known answers.

EngineOpus 5.5GPT-6 Sol
Answered right100%99%100%
Median per call0.21 s1.76 s1.47 s
Per 1,000 callsIncluded$4.67$1.36
Settled wrong000
The checks keep any model safe. What changes is the bill and the wait.

Reasoning, audit trails and human approval are now common. Checks in code, measured confidence and tested changes are not.

Checked, not just explained

Every call declares how it is checked. What code can't check, people audit by sample, and every doubt goes to a person.

Confidence measured

Cutoffs come from backtests against your team's rulings, not from what a model says about itself.

Changes tested first

Each improvement runs on data it hasn't seen, and against deliberately wrong answers, before an admin can publish it.

Start with a pilot

Bring one process. Run it alongside yours.

A few weeks in parallel on your own data, at our cost, then a line-by-line comparison: what it settled, what it sent to people, what it caught, and the time it took.

Bank and cash reconciliationInvoice and payment matchingFee and expense checks
Contact us sumarity.ai
  1. 01
    Start from a tuned template, or describe itA paragraph from the person who runs the process today.
  2. 02
    Review the workflow with usOn the canvas, step by step, in plain words.
  3. 03
    Run it in parallelYour process stays the process of record.
  4. 04
    Your rulings tune its callsEvery inbox decision joins the answer key.
  5. 05
    Compare, line by lineThen decide, on your own evidence.
Contact us

Tell us about the process. We'll come back to you.

A few details are enough to start. We'll reply to arrange a conversation with the person who runs the process today.

  • We reply to set up a first call.
  • We look at the process with your expert, and say whether it fits.
  • If it does, we scope a pilot run alongside yours.

We use these details only to reply to you.