Tenso

I built Tenso in the middle of my own job search, when I realized I was spending more time reshaping my resume for each posting than actually applying. Every job wants a slightly different version of you, and you almost never find out which version worked.

Tenso reads a job description and writes a resume tailored to it — and a cover letter if you want one — then follows what happens after you hit send: submitted, callback, phone screen, onsite, offer. The dashboard turns the whole search into something you can actually see — your response rate, which companies write back, and the feedback that comes in on the ones that don’t.

How it’s built — Tailoring an application is really several jobs of different difficulty, so Tenso routes each step to the cheapest model that can do it well: Haiku for the easy passes, Sonnet in the middle, Opus only where it earns the cost. Generation runs as a background pipeline so the page stays responsive while a job works, and a separate scorer rates fit in plain, deterministic Python — no model in the loop — so that number is one you can actually trust. FastAPI and Celery behind it, a Next.js front end, Postgres and Redis underneath.