Job Scout- Triage this tab hands the day's job listings to an AI model in one step. It copies every listing on screen as one compact batch — id, title, employer, pay, workplace and a trimmed description — with a prompt asking the model to sort each job into
strong(worth applying to this week),moderate(worth a second look) orskip, with one short reason. Paste the model's reply back into a box on the page and each job moves to the matching tab. About 150 listings fit in one paste. - The filters stay in code; only the judgment is delegated. The hard rules — pay floor, US-only, remote-first, disqualifying titles — cut thousands of listings to about 150, and they're the person's own, cheap and never guess. What a keyword score can't do is tell that a plain title over a description full of adoption and operating-model work beats an on-the-nose title at a staffing firm. That's the part worth sending to a model.
- The parser trusts nothing it didn't send. Each line of the reply must name a job id that was in the batch, so an invented id can't mark a real listing; it's counted as ignored and reported. The format is otherwise forgiving, because models drift from any format across 150 items.
- A person's own mark always wins. Marks from triage are recorded as machine-made, and a job the person already marked is left alone. The model's reason is stored with each mark, so later it's clear which marks were a model's guess and which were the person's judgment.
Revised 2026-09-25: now says what is being triaged — job listings to consider applying to.