Documents and AI extraction
Every upload is classified by document type and its key fields extracted. The extraction speeds the applicant up without ever taking authorship of their answers away from them.
How extraction is applied
- Extracted values are presented to the applicant as proposals to review and accept, not as silent autofill. The applicant remains the author of their own answers.
- Extraction output is schema-checked before it is allowed anywhere near the form.
- The required-document checklist gates approval. Optional documents are collected but do not block.
- An analyst can request a specific missing document, which reopens the relevant part of the form for the applicant.
- Uploads are size- and type-checked, and malware-scanned where that is enabled for your deployment.
Typical checklist
The exact checklist is part of your intake configuration. A typical corporate intake looks like this.
Required documents block approval until they are present. Optional documents are collected for the file but never hold up a decision.
Requesting a missing document
From the Documents tab, an analyst can request anything missing with one click. The request reopens the relevant part of the form for the applicant, who is emailed and told exactly what is needed. The rest of their application stays as they left it.
This moves the application to Needs info. See Onboarding lifecycle and The compliance dashboard.