Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

I built a deterministic, quote-verified ATS resume scanner & job aggregator so AI stops hallucinating fake skills

Description and use

Built a deterministic, quote‑verified ATS resume scanner that eliminates random scoring and hallucinated skills, delivering consistent and verifiable scores.

Problem

AI resume scanners produce random scores and hallucinate skills, causing unreliable assessments and candidate rejection.

Outcome

Consistent ATS scores with 55% weight on quote‑verified hard skills, 15% measurable impact, 15% soft skills, 15% structural completeness, eliminating hallucinations and score variance.

Workflow

  • Extract job description skills
  • Parse resume into sentences
  • Verify each hard skill by matching an exact sentence quote
  • Extract measurable metrics via regex/NLP
  • Check soft skills and role markers
  • Validate structural completeness (contact, links, headers, word count)
  • Calculate weighted ATS score from verified components

Evidence

Random Score Generation: Because LLMs are probabilistic (temperature > 0), submitting the exact same resume twice often yields 62% first and 84% a minute later.

Source

Skill Hallucinations: When asked to tailor a resume or cover letter, standard LLM wrappers cheerfully invent experience with technologies the candidate has never touched—leading to instant rejection during the first 5 minutes of a technical screen.

Source

55% — Quote-Verified Hard Skills (resumeQuoteEvidence): A skill from the job description is only counted as matched if the parser extracts the exact sentence from the resume as proof.

Source

Here is the core deterministic scoring and quote-extraction logic from our engine: ...

Source

  • Record date: 2026-11-02T04:44:02.178Z