What it is
An automated screening service for high-volume recruiting that eliminates unqualified applicants instantly using deterministic date math and hard dealbreaker gates, then provides EEOC-compliant rejection notices.
How it uses Jev
Jev makes the final disqualification decision on candidate state (tenure, visa, licenses) by answering a typed disqualifying question. The result is used to categorize candidates as DISQUALIFIED, ADVANCE, or MANUAL REVIEW.
Primitives:choice
Technique worth stealing
Asking the disqualifying question first to filter out 80% of unqualified resumes before full evaluation.
Try it
Clone repo, pip install -r requirements.txt, set TYPESAFE_API_KEY, run python gui/server.py, open http://localhost:8990.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.87
- Shows a System One patternyes0.63
- Handles uncertaintyno0.06
- Measuredno0.27
- Runnableunclear0.59
- Worth recommendingno0.23
- Model replicano0.15
- Problem scopescore on a 0–2 scale1.28
- About Jevyes0.89
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.