Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

grokbot-jev-jobs

Daily job-search pipeline that triages and scores public postings against a resume with Jev, then applies via a Grok Bot webhook.

Serviceprototype
View on GitHub ↗

Overview

grokbot-jev-jobs scores public job postings against one resume using Jev through Vercel AI Gateway. A daily Vercel cron ingests public feeds, Jev triages titles, the app fetches full ATS descriptions, and Jev scores each plausible posting, storing results in Neon. A dashboard Apply button webhooks a Grok Bot agent, Resume Rudy, to fill ATS forms and write status back.

The README distinguishes two Jev uses: the app's title triage and full-text scoring, and a sparse page-brain inside the apply agent that scans for knock-out questions before a heavy ATS fill. It cites Jev at roughly half a second per call and $0.042 per million input tokens, cheap enough to read every plausible posting daily. Personal data lives in a git-ignored profile directory and environment variables, never in code.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this job title plausibly a match worth reading?(inferred)yes · no
ScoreHow well does this posting match the resume?(inferred)—
Yes / noDoes this application page contain a knock-out question?(inferred)yes · no

How it works

  1. Ingest public postings on a daily cron
  2. Jev triages titles, then scores full descriptions
  3. Show ranked matches in a dashboard
  4. Apply triggers Grok Bot, which checks knock-outs with Jev before filling forms

Strengths

  • Cheap enough to score every plausible posting daily
  • Separates triage from detailed scoring
  • Personal data kept out of code

Caveats

  • Built for one person's resume and setup
  • Automated applications need care

Getting started

Deploy to Vercel with AI Gateway and Neon configured; see the README for environment variables and profile setup.

At a glance

Type
Service
Status
prototype
Language
TypeScript
Runtime
Vercel serverless + cron
Has code
yes

Use cases and integrations

How curated lists describe it

  • Job search: a daily Vercel cron that scores public job postings against one resume with Jev through the Vercel AI Gateway, so only the plausible matches surface.

    yibie/awesome-jev

  • Scores public job postings against my resume using TypeSafe.

    wh000wh000/awesome-jev-live

Frequently asked questions

What does Jev score?

How well each job posting matches the resume, after a title triage.

Does it apply automatically?

Applying is triggered from the dashboard and handled by a Grok Bot agent.

How is Jev accessed?

Through Vercel AI Gateway.

Related projects

  • jevsume

    Resume review app and MCP server where a Cloudflare Worker asks Jev typed questions and composes a JevScore, generally or per job.

    AppbetaTypeScript
  • jev-resume-analyzer

    CV review app where Jev makes traceable document-level judgments on clarity, contribution and results, optionally against a job posting.

    ProjectprototypePython
  • typesafe-jev CV screener

    Local CV screening workbench that asks Jev fixed typed questions per CV and scores them with editable, free-to-rerun policy arithmetic.

    Projectprototype
  • jev-resume-screening

    Resume-to-JD screening study (Chinese) with 5 Noul gates, 4 Score dimensions and a routing Choice per request, hardened over three versions.

    Projectresearch
  • hiresignal

    Small demo that scores resumes for first-pass fit and interview recommendation with TypeSafe Jev.

    Demoprototype
  • jev-resume-match

    Next.js resume review app where Jev returns typed scores for overall fit, individual criteria and each experience bullet.

    AppprototypeTypeScript