Question 1

What is DAN?

Accepted Answer

DAN stands for Data Automation Ninja. It is an AI document extraction SaaS that turns PDFs, scans, invoices, receipts, contracts, resumes, ID cards, bank statements, and official documents into structured data.

Question 2

Is DAN just OCR?

Accepted Answer

No. OCR reads text from a document. DAN extracts structured fields, adds confidence scores, supports human verification, and exports clean JSON or Excel.

Question 3

Can I choose my own fields?

Accepted Answer

Yes. You can define your own fields before extraction. DAN extracts the data you ask for instead of forcing you into a fixed schema.

Question 4

Can DAN handle scanned or handwritten documents?

Accepted Answer

Yes. DAN supports scanned documents and handwritten documents using vision models, text models, and fallback processing.

Question 5

Can developers use the API?

Accepted Answer

Yes. Developers can generate API keys, send documents through the REST API, receive structured JSON, and use webhooks to push extracted data to downstream systems.

Question 6

Does DAN work for medical or healthcare documents?

Accepted Answer

No. DAN is built for general business documents. Medical records, prescriptions, and patient data carry HIPAA and other privacy requirements that DAN is not designed to meet. Use a healthcare-specific compliant tool for those.