Small decisions. Interesting possibilities.Submit contentSubmit

How it uses Jev

When recommendations are enabled, Skillbox sends the task and a bounded set of candidate skill IDs and descriptions. Jev returns one Score answer per skill against a five-level relevance rubric (0 through 4); code validates the scores and filters/ranks recommendations.

What Jev decides

Illustrative skill relevance scoreExample answers · not a recorded Jev response · Source ↗
Question 1 · skill 0
YOUR APP
INSTRUCTION

Rate only candidate skill_0’s usefulness for the task, matching meaning and respecting the task context and skill limitations.

STATE

A user task and a representative candidate skill ID and description. The request has one score question per candidate, using the shared five-level relevance rubric.

JEV · SCORE
04

App workflow

  1. Search the skill catalog

    Retrieve candidate skills for the task and respect catalog bounds.

  2. Build the evaluation request

    Send task text and each candidate skill’s ID and description with a shared relevance rubric.

  3. Evaluate with the selected provider

    Call the configured provider, including TypeSafe when selected by the user.

  4. Validate and rank results

    Validate each bounded score and return only candidates meeting the relevance cutoff.

Why it is interesting

Task relevance is evaluated against a versioned skills catalog while provider choice and keys remain user-controlled. Low scores can be filtered instead of returning every catalog match.