- Finance / AccountingIndustry
- Finance & payments companyClient
- Automation & OptimizationCategory
- Fast to valueTime to impact
The challenge
- Bank reconciliation (reconciliação bancária) is a manual, error-prone grind: matching hundreds of statement lines to ledger entries, then chasing down the handful that do not line up.
AI-assisted matching of bank transactions against the ledger.
A reconciliation assistant that matches bank statement lines to ledger entries automatically and surfaces the exceptions that need a human.
What we built
- 01Automatically match statement transactions to ledger entries.
- 02Flag exceptions and mismatches for review instead of burying them.
- 03Keep a clear, auditable record of how each match was made.
How it works
What it can do
Automated matching
Matches statement lines to ledger entries at scale.
Exception flagging
Surfaces only what needs human attention.
Audit trail
Transparent record of every reconciliation decision.
Who stays in the loop
The call the system deliberately does not take, and what the person is given to take it with.
A reconciliation assistant that matches bank statement lines to ledger entries automatically and surfaces the exceptions that need a human
The finance team
Decidesevery exception the matcher could not close
Seesthe unmatched lines with the candidates considered, and the audit trail behind the matches that did close
The payoff
What is different once it is running. No invented numbers: these are the changes the work was built to make.
Hundreds of statement lines reconcile themselves, and the only thing that reaches a human is the handful that genuinely don’t match.
The bulk of matching happens automatically.
Only real exceptions need a person.
Every match leaves an auditable trail.
Built with
The layers this runs on, from what comes in to what it plugs into.
- Model layer
- ML matching
- LLM
- What people use
- Web
Common questions
The same answers as above, written out.
A reconciliation assistant that matches bank statement lines to ledger entries automatically and surfaces the exceptions that need a human.
Bank reconciliation (reconciliação bancária) is a manual, error-prone grind: matching hundreds of statement lines to ledger entries, then chasing down the handful that do not line up.
Import the bank statement and the ledger. The engine matches lines automatically. Only true exceptions are flagged for review.
The finance team decides every exception the matcher could not close. They see the unmatched lines with the candidates considered, and the audit trail behind the matches that did close.
Model layer: ML matching, LLM. What people use: Web.
The bulk of matching happens automatically. Only real exceptions need a person. Every match leaves an auditable trail.
Where this fits
The practice it belongs to, how an engagement like it runs, and what we have written about the subject.
Data AnnotationData Labeling: The Overlooked Bottleneck in AI and Machine Learning
Model architectures often get the spotlight, but real-world performance in AI depends heavily on data labeling quality. Learn why annotation workflows, human-in-the-loop systems, and synthetic data strategies are what make an ML model hold up in production.
Frederico VicenteSep 20259 min read
Business & OperationsHow to spot an AI use case worth doing
The six prerequisites that decide whether an AI use case is worth building, with a scoring rubric, two worked examples, and the red flags that say walk away.
Miguel Vicente JrJun 202611 min read
Business & OperationsSoon, talking to a human will cost extra
The first layer of AI isn't taking our jobs, it's quietly putting humans behind a paywall. Why talking to a person is becoming a premium service.
Miguel Vicente JrJun 20267 min read
Other projects in this line.
Bring us the problem nobody has cracked yet.
We are a small team of senior specialists. We pick the right model and the right layer, and we build the least machinery that does the job. You get a call with an engineer, not a sales deck.