Job Search Studio

Job Search Studio didn't start as a technical idea — it started with something I watched happen to people. I watched a wave of AI-driven layoffs hit experienced developers, the ones who knew their companies' systems, customers, and quirks better than any onboarding doc ever could, and I wanted to build something useful for the people on the receiving end of those decisions rather than just write about it from the sidelines.

What I built automates the parts of a job search that don't need a human: discovering new listings against a candidate's stated requirements, ranking them by fit, and tracking every application through to an outcome. It's built on NestJS with a full CQRS command/query split on the backend and an Angular front end, with a multi-provider AI router doing the requirement-matching and prioritization work — the same router pattern I'd already proven out building Prompt Workbench, reused here rather than reinvented.

It shipped as a complete, defect-hardened SaaS app — discovery, ranking, resume/cover-letter generation, and application tracking all working end to end — after a dedicated defect-remediation and UX-compliance pass. If you're an employer reading this: before you lay off the people holding your institutional knowledge in favor of a model that doesn't have it, price out what it actually costs to rebuild that knowledge from scratch. In my experience that number is usually bigger than whatever the slide promised, and it doesn't show up until year two.

flowchart TD
    Discover["Discover listings"] --> Rank["Rank by fit\n(AI Router)"]
    Rank --> Generate["Generate resume\n+ cover letter"]
    Generate --> Track["Track application"]
    Track --> Outcome["Outcome"]