Skip to content
Keshav Raj
A robot filling job applications with a fact-check magnifier and a policy gate.
AI DISTRICT4 ATS
SHIPPED Policy-gated applications with numeric fact-checks of generated text.I OWNED Sole authorOUTCOME 4 ATS

Job-search agent

Keshav RajSole author · 2026 · In useContact meResume PDF

Context

This is a job-search agent I wrote as the sole author for a designer's job hunt. It is in use, and it runs locally.

The problem

A job hunt needs discovery, fit scoring and applications at volume. Done carelessly, that produces fabricated claims and spammy behaviour, which hurts the applicant.

What I did

  1. I built the pipeline: discovery, fit scoring, resolving each posting to its real application system, referral lookup, a tailored application package, a policy gate, then submit or send to review.

  2. I wrote the resolver for four applicant tracking systems: Greenhouse, Lever, Ashby and Workable.

  3. Generated text goes through a numeric fact-check. Numbers in a draft are checked, and a failed check falls back to a template.

  4. I added score calibration using Wilson intervals, ghost-job detection and liveness checks, rate limits and a full submission audit record.

Key decision

The key decision was a strict policy gate between generation and submission, with fact-checks that fall back to templates. The cost is fewer fully automatic submissions. The gain is that nothing invented gets sent.

I judged that trade-off worth it because a wrong claim on an application is hard to take back.

Result

It resolves postings across 4 ATS vendors and is in use. I do not report applications sent, interviews or offers, since that is the applicant's personal data.

What I learned

I would again keep the checks in code, not in the prompt. I would add outcome tracking early, with the applicant's consent, so calibration can be judged against real responses.

Stack

  • Next.js
  • TypeScript
  • Prisma
  • PostgreSQL
  • Playwright
  • Claude API
  • MCP
Play the world →