jev-resume-disqualifier
Resume knockout tool: deterministic date math and hard gates first, then a Jev decision gate, producing disqualify or advance verdicts.
Overview
Jev Resume Disqualifier is pitched as an automated knockout engine for high-volume recruiting. A batch of resumes passes three layers: non-overlapping calendar date math that computes true tenure without double-counting overlaps; deterministic hard gates for visa status, minimum role tenure and state licences; and a Jev decision gateway for the remaining judgment. Output is a table of disqualified versus advance verdicts, templated rejection notices and a CSV or JSON audit.
Recruiters paste a job description or pick a role template, and the engine extracts dealbreakers. The README argues that LLM screeners cannot do date math, are slow and costly, and can invent vague rejection reasons that create legal risk, and it claims sub-25 ms Jev decisions and elimination of 80% of unqualified applicants. These are the project's marketing claims; the 25 ms figure is well below latencies other projects report for the hosted API. Automated rejection in hiring carries legal and fairness risks that the README's compliance claims do not remove.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this resume fail a disqualifying requirement?(inferred) | yes · no |
| Choice | Should this candidate be disqualified or advanced? | DISQUALIFIED · ADVANCE |
How it works
- Set dealbreakers from a job description or template
- Compute tenure with deterministic date math
- Apply hard knockout gates
- Ask Jev for remaining judgments
- Produce verdicts, notices and an audit file
Strengths
- Date math and hard rules handled in code
- Audit export of decisions
Caveats
- Latency and accuracy figures are unverified marketing claims
- Automated rejections carry legal and fairness risk
- Unclear how candidates can contest decisions
At a glance
- Type
- Project
- Status
- prototype
- Runtime
- Web service
- Has code
- yes
Use cases and integrations
How curated lists describe it
Recruiting: knocks a resume out of a pipeline in under 25 ms by asking Jev the disqualifying question first, so only survivors reach a full evaluation.
yibie/awesome-jevJev Resume Disqualifier: Sub-25ms automated resume knockout engine powered by TypeSafe Jev System One decision intelligence. Eliminates 80% of unqualified applicants with deterministic date math & EEOC-safe rejection notices.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Whether a resume should be disqualified or advanced after deterministic gates.
Who handles date calculations?
Code, not the model.
Are the speed claims verified?
No. The sub-25 ms figure is the project's own claim.
Related projects
Resume screening where an LLM writes the questions once per job and Jev answers them for every resume, quoting the evidence line.
ProjectproductionTypeScriptResume-fit platform where Jev scores six factual dimensions and returns KILL, FIX or SHIP before Claude adapts a resume.
ProjectprototypeTypeScriptClaude Code job-application tool that finds roles, fills forms in Chrome, reads every answer back and sends only those you approve.
ProjectbetaTypeScriptFour Java tools on one kernel that ask Jev whether something was delivered as required, with deterministic gates keeping the final say.
ProjectbetaJavaResume review app and MCP server where a Cloudflare Worker asks Jev typed questions and composes a JevScore, generally or per job.
AppbetaTypeScriptDaily job-search pipeline that triages and scores public postings against a resume with Jev, then applies via a Grok Bot webhook.
ServiceprototypeTypeScript