Small decisions. Interesting possibilities.Submit a project / videoSubmit

Jev Kit

A set of Jev-powered tools for Claude Code, including guarded tool calls, document classification, search, browser control, and review.

Added to Jevfast

How it uses Jev

Jev Kit includes several Jev-backed agent tools. In its document classifier, it sends up to 6,000 characters of page text to a first Choice over document families, then a second Choice over members of the chosen family with that earlier decision in state. The Python classifier reads the returned choice and confidence, applies its gates, and can request human review.

What Jev decides

Document family decisionExample answers · not a recorded Jev response · Source ↗
Question 1 · family
YOUR APP
INSTRUCTION

Choose the kind of document this page is, or the escape option when none fits.

STATE

The current document page text, truncated to 6,000 characters; taxonomy entries supply the candidate families.

JEV · CHOICE
  1. letter
  2. financial_document
  3. technical_record
  4. form
  5. not_in_this_list
Specific document typeExample answers · not a recorded Jev response · Source ↗
Question 1 · member
YOUR APP
INSTRUCTION

Choose a specific document type within the decided family, or the escape option.

STATE

The same page text plus already_decided, which states the selected family and its definition; the member choices come from that family.

JEV · CHOICE
  1. covering_letter
  2. chasing_letter
  3. not_in_this_list

App workflow

  1. Read a page

    Take text from the document page and load the caller-supplied taxonomy.

  2. Choose a family

    Ask Jev for a document family and check the choice and confidence against the configured gate.

  3. Choose a member

    For a supported family, ask a second Jev Choice with the first decision in state, then check the narrower answer and its confidence.

  4. Return a label or review signal

    Return the taxonomy label when supported; otherwise report an unmatched or low-confidence result for review.

Why it is interesting

Its two-stage document taxonomy keeps choices focused. Both stages include a not-in-this-list option, so a page outside the taxonomy need not be forced into a wrong class. The code treats low confidence as a review signal rather than a final label.