Job Risk Analyzer
TypeScript CLI and REST API that asks Jev to rate an occupation's AI layoff risk, trajectory and need for human accountability.
Overview
Job Risk Analyzer is a TypeScript and Node CLI and REST API that evaluates an occupation's exposure to AI-driven layoffs. Given a job title and optional description, it sends three independent questions to Jev in one request: a five-level layoff-risk Score normalised to 0 to 1, a future trajectory with confidence, and the probability that the role needs human accountability. Application code derives an overall resilience score.
It works immediately without credentials: if JEV_API_KEY is unset, it logs a warning and returns deterministic, occupation-aware mock data in the same validated shape as a live response. A responsive web page calls the API, and the Fastify server deploys to Vercel without extra configuration. It is a small demo of combining typed judgments into a derived metric; the outputs are model opinions, not labour-market forecasts.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | How exposed is this occupation to AI-driven layoffs? | — |
| Choice | What is the likely future trajectory of this occupation? | — |
| Yes / no | Does this role require human accountability? | — |
How it works
- Enter an occupation title and optional description
- Send three questions to Jev in one request (or use mock data)
- Normalise answers and derive a resilience score
- Display in CLI table, web page or JSON API
Strengths
- Works without a key using typed mock data
- Single request for all questions
- Deploys to Vercel easily
Caveats
- Outputs are model judgments, not forecasts
- Demo project
- Live mode needs a Jev key
Getting started
npm install, export JEV_API_KEY (optional), then npm run cli -- --title "Data Entry Clerk" or npm run server.At a glance
- Type
- CLI
- Status
- prototype
- Language
- TypeScript
- Runtime
- Node CLI and Fastify API
- Has code
- yes
Use cases and integrations
How curated lists describe it
Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Layoff risk, future trajectory and whether human accountability is needed for an occupation.
Can I run it without a key?
Yes, it falls back to deterministic mock data.
Is the score a reliable forecast?
No, it reflects model judgments and should be read as a demo.
Related projects
Resume 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.
ServiceprototypeTypeScriptCV review app where Jev makes traceable document-level judgments on clarity, contribution and results, optionally against a job posting.
ProjectprototypePythonCombines Jev judgments on row text with a tabular foundation model like TabPFN to predict outcomes from few labels.
LibraryprototypePythonLocal CV screening workbench that asks Jev fixed typed questions per CV and scores them with editable, free-to-rerun policy arithmetic.
ProjectprototypeResume-to-JD screening study (Chinese) with 5 Noul gates, 4 Score dimensions and a routing Choice per request, hardened over three versions.
Projectresearch