Documents and AI
How the AI reads your documents, and when to trust it
What it extracts, what the confidence level means and who has the final word.
When a document arrives in a case it does not just sit there as a file: it is read, and the fields you asked for are extracted. Invoice number, amount, due date, company name. That is what later lets you search for "every invoice over €5,000" instead of opening fifty PDFs.
What the confidence level means
It is not a quality score for the document: it is how sure the system is that it read that specific field correctly. The same document can have the amount at high confidence and the date at low, because the date was handwritten in a margin.
| Confidence | What it usually means | What to do |
|---|---|---|
| High | Printed field, sharp, where it was expected | A glance is enough |
| Medium | It was read, but the format or position was unusual | Check it before confirming |
| Low | Shaky photo, rotated document, handwritten or struck-through field | Review it fully; sometimes it is worth asking for a better copy |
Watch out
Low confidence does not mean the value is wrong: it means the system is not committing. Confirming it without looking is exactly the use it should not get.
What to do when it reads something wrong
- 1
Correct the field by hand
It is immediate, and the record shows the final value came from you.
- 2
See whether the document can be improved
A photo with shadow or backlight reads badly. Asking for a retake costs less than correcting twelve fields.
- 3
If it repeats with the same document type, say so
A one-off failure on a bad photo is not the same as a pattern with a specific form, and the second can be tuned.
What it does NOT do
- It does not decide whether a document is valid: you or your process do.
- It does not reject documents based on their content.
- It does not modify the original file, which is kept exactly as it arrived.
- It does not read in SmartCheck: there, documents are sealed as-is, uninterpreted.
Frequently asked questions
›How long does reading a document take?
Seconds. If it takes much longer it is not thinking: something has failed and it is worth reloading.
›Does reading a document consume credits?
Yes, automatic reading is one of the actions that consumes credits. Correcting a field by hand does not.
›Can I ask for fields that are not in the document?
You can ask for them as data for the person to fill in. If they are not on the page, reading does not invent them: it leaves them empty.
›Does it read documents in other languages?
Yes. What affects reading most is image quality, not language.
›What if the document has several pages or several invoices?
All of them are read. When one document contains several occurrences of the same group of fields, each is extracted separately.
A real case
The situation
An accountancy receives 300 invoices a month and needs the number, date and net amount from each.
What you do
- Defines those three fields on the process request
- Reviews only the ones flagged medium or low confidence
- Confirms the rest in bulk
What you get
About 30 get reviewed by hand instead of 300, and the ones reviewed are exactly the ones that needed it.
The situation
Everything read is approved without looking.
What you do
- Reviews whatever the AI flags as uncertain
What you get
The work shifts from keying to checking.
The situation
A high-confidence figure turns out to be wrong.
What you do
- Corrects the figure and records it
What you get
The indicator guides and the last word stays human.
The situation
One document type always reads badly.
What you do
- Checks whether the format matches what is expected
What you get
The problem is tackled at source.
The situation
A hundred invoices a month are keyed by hand.
What you do
- Lets them be read and reviews the uncertain ones
What you get
Time goes on checking rather than copying.
The situation
The reading is distrusted and everything is checked.
What you do
- Filters by confidence and starts at the bottom
What you get
Review concentrates where the risk is.
This article answers
- how does the AI read documents
- what is the confidence level of an extracted field
- the AI misread a field what do I do
- automatic data extraction from invoices
- OCR for scanned documents