Career-Ops: AI Job Search System That Scored 740+ Applications and Landed the Job

By Prahlad Menon 1 min read

Companies use AI to filter candidates. Now candidates have AI to filter companies.

Career-Ops is an open-source system that turns Claude Code (or any AI coding CLI) into a full job search pipeline. The creator used it to evaluate 740+ job listings, generate 100+ tailored CVs, and land a Head of Applied AI role.

Now it’s open source with 69K+ GitHub stars.

Repo: github.com/santifer/career-ops

What It Does

Paste a job URL into your terminal. Career-Ops:

  1. Evaluates the offer into a structured A-H report with a 1-5 score
  2. Generates a tailored CV — ATS-optimized PDF customized for that specific job
  3. Tracks the application in a single source of truth
  4. Drafts follow-up emails and cover letters (never sends — you decide)

Works with Claude Code, Codex, OpenCode, Antigravity CLI, Qwen, Kimi, and GitHub Copilot.

The A-H Evaluation System

Every job gets a comprehensive breakdown:

BlockContents
ARole summary
BCV match analysis
CLevel strategy
DCompensation research
EPersonalization angles
FInterview prep (STAR+R stories)
GPosting legitimacy check (flags ghost jobs/scams)
HOnly drafted for 4.5+ scores — the “apply now” signal

The score isn’t a keyword match. The AI reasons about your CV vs the job description holistically across five dimensions.

Important: The system strongly recommends against applying to anything below 4.0/5. This is a filter, not spray-and-pray.

Installation

One Command

npx @santifer/career-ops init

This clones the repo and installs dependencies. Then:

cd career-ops
claude  # or codex / qwen / opencode / agy / grok

On first launch, it walks you through setup via conversation — your CV, profile, target roles. No manual config editing required.

Manual Setup

git clone https://github.com/santifer/career-ops.git
cd career-ops && npm install
npx playwright install chromium  # for PDF generation

# Validate
npm run doctor

# Configure
cp config/profile.example.yml config/profile.yml
cp templates/portals.example.yml portals.yml

# Add your CV as cv.md

Features

Auto-Pipeline

Paste a URL → full evaluation + PDF + tracker entry.

Portal Scanner

100+ companies pre-configured:

  • Anthropic, OpenAI, ElevenLabs
  • Retool, n8n, Stripe
  • Custom queries across Ashby, Greenhouse, Lever, Wellfound

Batch Processing

Evaluate 10+ offers in parallel with headless CLI workers (claude -p / opencode run).

Interview Story Bank

Accumulates STAR+Reflection stories across evaluations. After a few dozen evaluations, you have 5-10 master stories that answer any behavioral question.

Negotiation Scripts

  • Salary negotiation frameworks
  • Geographic discount pushback
  • Competing offer leverage

ATS PDF Generation

  • Keyword-injected CVs
  • Space Grotesk + DM Sans design
  • Playwright rendering

Cover Letter Generator

  • Research-backed with keyword mirroring
  • Four interactive angle prompts (why/problems/approach/tone)
  • Draft-in-chat approval gate
  • A4 PDF output

Dashboard TUI

Terminal UI (built with Go + Bubble Tea) to browse, filter, and sort your pipeline.

Company Research

The deep mode surfaces:

  • AI strategy
  • Recent moves
  • Engineering culture
  • The angle your profile should take

Contact Discovery

The contacto mode identifies hiring managers, recruiters, or team peers worth reaching out to — drafts ≤300-character LinkedIn messages tuned to each contact type.

Interview Suite

  • Time-blocked prep plans
  • Practice sessions with feedback
  • Post-interview debriefs
  • Company red-flag detector

Pattern Analysis

  • Rejection patterns
  • Per-ATS-channel advance rates
  • Repost/ghost-job detection
  • Lifetime funnel stats

The Philosophy

“Applications get you in the queue; research gets you a conversation.”

Career-Ops is human-in-the-loop by design. The AI evaluates and recommends. You decide and act. The system never submits an application — you always have the final call.

The first evaluations won’t be great. The system doesn’t know you yet. Feed it context:

  • Your CV
  • Your career story
  • Your proof points
  • Your preferences
  • What you’re good at
  • What you want to avoid

Think of it as onboarding a new recruiter: the first week they need to learn about you, then they become invaluable.

Running on a Budget

Multiple options:

Plugin System

Opt-in integrations (disabled by default):

  • Gmail
  • Notion
  • Apify
  • Community registry

See docs/PLUGINS.md.

Real Results

The “HIRED.md” file in the repo tracks everyone who landed a job using the system. Every count is a public story you can audit — and they all started mid-search like you.

Featured in:

  • Wired — “The AI tool revolutionizing how we search for jobs”
  • Business Insider — “How I built a tool to filter job listings and landed Head of AI”

The CareerOps Manifesto

Career-Ops is the first reference implementation of the CareerOps Manifesto. If it says what you believe, your signature becomes a commit.

Mode Commands

If your CLI supports slash commands:

/career-ops scan      # Scan company portals
/career-ops evaluate  # Evaluate a job listing
/career-ops pdf       # Generate tailored CV
/career-ops tracker   # View pipeline status
/career-ops cover     # Generate cover letter
/career-ops deep      # Deep company research
/career-ops contacto  # Find the right person to contact

Or just ask in plain language: “Run the career-ops scan mode”

Why This Works

  1. It’s a filter, not a firehose — Helps you find the few offers worth your time
  2. Tailored, not templated — Every CV is customized to the specific JD
  3. Research-first — Company deep dives before applications
  4. Human-in-the-loop — AI recommends, you decide
  5. Single source of truth — No more spreadsheet chaos

Links: