Skip to content
AI Bookkeeper

Buyer's checklist

How to compare AI bookkeeping software

Every tool in this category demos well, because a demo shows extraction and extraction is the part that works. Here is what to ask about instead — the questions are useful whether or not you end up here.

Use this on everyone

If you are early in evaluating, run this checklist against every vendor including us. A tool that answers these well is a good tool regardless of whose logo is on it.

Why we publish it

These are the five questions this product was designed around, which is why we are comfortable publishing them as the test.

What to ask any vendor, the weak answer, and what to look for
Ask aboutThe weak answerWhat to look for
ConfidenceOne score per documentA score on every field
Provenance'You can open the document'Click a value, see the exact region
The gateAuto-post above a thresholdA human sees every document
Audit trailA log you can editAppend-only, corrections as new entries
IsolationOne pool with filtersEach client its own organization

Run these against every vendor you are evaluating, this one included.

1. Is confidence reported per field or per document?

A document-level score is close to useless: if a bill scores 94%, you still do not know which field is the shaky one, so you check all of them and the automation saved you less than it looked like.

Ask to see a document where the tool was unsure about exactly one value, and watch where that shows up.

2. Can you get from a value back to the page it came from?

Not 'can you open the source document' — every tool can do that. Can you click a total and have the exact region it was read from highlighted?

Without it, verifying a field means finding it yourself, which is the work you were automating.

3. Where is the human gate, and can it be turned off?

Some tools auto-post above a confidence threshold. That demos brilliantly and it is the setting that produces the entry nobody remembers approving.

Ask whether the gate is a default or a guarantee.

4. Can the audit trail be edited?

If entries can be changed or deleted, the log's value as evidence is gone — including for the entries nobody touched, because a reader cannot tell which those are.

Ask what happens to the old value when someone corrects a mistake.

5. How are clients kept apart?

For a firm this is the one that matters. A filter over a shared pool and a genuine per-client boundary look identical in a demo and behave very differently when a staff member changes clients or leaves.

Ask what a user sees if the filter fails.