Repo · Documents & research

Document Classification

Sort text documents into categories.

Open github.com ↗

From the repository

JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.

blazing-fastdocument-classifierjevprompt-injection-detectiontypesafe-ai

How builders describe it

JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.

Local-first Vite/Express app that files root-folder documents into configured category folders using TypeSafe Jev (via Vercel AI Gateway) for category, confidentiality, prompt-injection risk, and subject choices.

Local-first app that extracts document text on the machine and files it into configured category folders using typed Jev decisions for category, confidentiality, prompt-injection risk and subject, with a per-run audit that previews and undoes every move.

The decision Jev makes

Assign a topic, choose a document category, or answer whether a passage supports a citation.

Where it fits

Sorting, labelling and checking documents is classic decision work: topic labels for papers, categories for files, and whether a source actually supports a claim. All 45 documents & research projects →

Related projects