01
Where this one gets misread
The label covers parsing, extraction and question-answering. They have different failure modes and different evidence requirements, so being sold document AI does not tell you which of the three you are buying.
Glossary
What is document AI?
Document AI is software that applies machine learning or generative models to documents, whether to parse them, pull out values or answer questions from them.
Updated 21 Aug 2026
02
Questions to ask
Ask for a worked example on your own material, and the evidence needed to reproduce it.
- Which of those three is this, primarily?
- What is measured for each part?
- Where is the human step?
- What happens with an unsupported format?
03
How Marella uses the term
We use “Document AI” only where a product mechanism or an evaluation method backs it up, and we say when the behaviour depends on how a deployment is configured.
- Backed by a product mechanism or an evaluation method
- Deployment differences flagged
What this page does not prove
- B1A definition is not a claim about how the product performs.
- B2Vendor implementations vary.
- B3Test the term against a representative workflow.
Related pages
Test the claim on your documents
Pick a real piece of work, agree what a good answer looks like, then go through the results together.