Rules for the clear cases. AI only for judgment calls.
Reviewing every transaction by hand is slow, and a pure AI reviewer is hard to trust. I designed a hybrid: 13 coded rules handle the clear cases, and AI answers only two yes/no judgment questions.
Languages
Tools & platforms
AI & LLM
Skills
checks: 13 coded rules + 2 AI judgments
real transactions tested
flagged for human review
The thinking behind it
- 01 · What I noticed
Accountants need to explain every flag, so a black-box AI reviewer would never be trusted.
- 02 · What I decided
Use coded rules for everything they can catch, and ask AI only narrow yes/no questions that are logged.
- 03 · What I delivered
A review list a human can trust, validated on 1,016 real transactions.
Old system vs new system
- Export transactions
- Review every line by hand
- Note anything odd
- Ask the client
- Repeat next period
- Pull the period's transactions
- 13 coded rules run
- AI answers 2 yes/no checks
- Human reviews flagged items only
Watch it run
Click through the four steps. In step 3, click any box to see what it does.
Making AI auditable.
An accountant has to explain every flag. So AI never decides alone: deterministic rules handle everything they can, and AI answers narrow yes/no questions that are logged per transaction. Testing on real data caught a date-handling bug that would have flagged 58% of transactions before it ever reached a reviewer.
Why it's built this way
Deterministic first
Anything a rule can catch is caught by a rule: predictable and explainable.
AI as yes/no, not free text
Narrow questions are easy to log, check and compare.
Validate on real volume
Tested on 1,016 real transactions before anyone relied on it.
Have a similar mess? Tell me the step you hate.