What it does
A 15-page packet comes back as four documents, including two adjacent Treasury auction results that share a category. In the maker's 40-document pilot, every classification was right and seven of eight packets split exactly.
Apps & data pipelines
DocJev
Point DocJev at a PDF and a list of categories you wrote in plain English, and Jev names the category or marks where each new document starts.
Bookmark: DocJev
Keep this in your collection.
Leave a noteWhat would you try with this?
: DocJev
Only you can see your notes.
Recording unavailable. Open the experiment ↗
How you can use it
You can sort multi-page office files into categories or split combined packets into separate files. Start by listing the kinds of documents you handle, writing plain descriptions for each type. Gather a few scanned files or presentations to see how well your rules sort them.
A developer can set up the Python tool on their computer. They will need a TypeSafe service access code to run the categorization checks. When the tool is unsure about a page division or label, it flags that spot so a person can review it.