Runs inside Excel
modelflow
Auditable data extraction for Excel models
Any AI can pull numbers out of a PDF. The hard part comes later, when someone asks where a number in your model came from and you have to answer.
In short
- A person approves every value
- Every value links back to its source
- Every write goes into a journal
- Own servers, no AI provider
How it works
- 01
Map your model once
modelflow suggests fields like revenue, EBITDA and total assets from your own labels, and you confirm each one. The one-time mapping takes minutes and applies to every extraction after that.
- 02
Load your documents
Annual reports, scanned PDFs, Excel files, DATEV exports and XBRL filings, in any language. Your documents are not stored on our servers.
- 03
Review page by page
You see the proposed source pages with the fields taken from them highlighted directly on the page. You correct only what is wrong, and accepting every field on a page is a single button away.
- 04
Approve the write
modelflow writes only what you approved, asks before it touches a formula and records every change in the journal.
Straight to the product
Related service
Office integration & automationSomething similar on your desk?
Describe briefly what it is about. You get an honest assessment back.