jev-resume-analyzer
CV review app where Jev makes traceable document-level judgments on clarity, contribution and results, optionally against a job posting.
Overview
JEV Resume Analyzer reviews a CV with structured judgments from Jev, optionally against a job posting. You upload a PDF or DOCX, check the extracted text, and get a report where every assessment shows the exact question, criteria, answer and probability distribution. Document-level questions cover work clarity, personal contribution, interpretability, outputs and results, scope and summary specificity, and two job-alignment questions assess evidence of relevant responsibilities and qualifications.
Answers use four outcomes (present, absent, not applicable, unable to assess), so a missing summary is not a defect and 'unable to assess' is not a zero. Explanations are predefined rubric text, never generated advice. The design deliberately avoids an overall rating until calibrated, hiring predictions, ATS scores, truthfulness verdicts and rewrites. It is a localhost demo with no accounts or stored CV text, one Jev request per analysis, and a React plus FastAPI stack with backend and frontend test suites.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Does the CV show clear personal contribution? | present · absent · not_applicable · unable_to_assess |
| Choice | Does the CV evidence the posting's responsibilities and qualifications? | present · absent · not_applicable · unable_to_assess |
How it works
- Upload a CV and optionally a job posting
- Extract and review the text
- Send one batched Jev request
- Show each finding with question, criteria and probabilities
Strengths
- Fully traceable findings
- Explicit 'unable to assess' outcome
- No generated advice or hiring predictions
- Extensive tests
Caveats
- CV text is sent to TypeSafe
- No overall score yet
- Localhost demo only
Getting started
In backend: set TYPESAFE_API_KEY in .env, uv sync, uv run uvicorn app.main:app --port 8017; in frontend: npm ci && npm run dev.At a glance
- Type
- Project
- Status
- prototype
- Language
- Python
- Runtime
- FastAPI backend with React frontend
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Whether each CV quality criterion is present, absent, not applicable or cannot be assessed.
Does it predict hiring outcomes?
No. It deliberately avoids hiring predictions and ATS scores.
Is CV data stored?
No database or local storage; text is sent to TypeSafe for analysis.
Related projects
Resume review app and MCP server where a Cloudflare Worker asks Jev typed questions and composes a JevScore, generally or per job.
AppbetaTypeScriptNext.js resume review app where Jev returns typed scores for overall fit, individual criteria and each experience bullet.
AppprototypeTypeScriptAgent skill where Jev scores a task prompt's clarity, the agent refines it up to three times until it reaches 80/100, then builds.
ProjectbetaJavaScriptClaude Code plugin that logs your prompts locally and later has Jev score how well you prompt the coding agent over time.
PluginbetaTypeScriptChrome extension that grades readable page sections on ten rubric scores with Jev via Vercel AI Gateway and gives the page an A-E grade.
ProjectbetaTypeScriptCLI and agent skill that checks every line of a document against every rule with Jev and outputs flags for an AI agent to fix.
Agent skillbetaTypeScript