devwithjev
reading now views
Submit a build

Jev-Powered O*NET Job Classifier

Mark Jaquith uses Jev for IRS O*NET job classification across 1,016 possibilities. The query “I scoop scoops and sprinkle sprinkles” returned 35-3023.00 Fast Food and Counter Workers.

Mark JaquithMark Jaquith@markjaquith𝕏
IRS O*NET job classification using Jev (1,016 possibilities) Query: "I scoop scoops and sprinkle sprinkles" Result: 35-3023.00 Fast Food and Counter Workers https://t.co/SSXUqQwNo3
Sep 17, 2026X postsView on X

Also filed under Triage & routing

  • Jev is HERE. How to use it

    Jev is HERE. How to use it In this episode, I talk with Ryan Vogel about Jev, a new type of AI built for classification. Ryan shows how Jev takes an input plus ...

  • Jev-Powered Agent Runtime for JarvisCore

    Muyukani Kizito says JarvisCore uses Jev in its agent runtime for RAG classification and ranking, model routing, subagent routing, and agent decisions.

  • Jev Benchmarks for Review Pipelines

    Niels Bantilan benchmarked Jev against a “System 2” approach for customer support, code review, and legal contract review. He reports Jev was up to x2.6 faster and at least x10 cheaper, with no loss in quality.

  • Classifies Issues with Jev

    Mike Hostetler demonstrates using Jev with ReqLLM and makes a real API call to classify an issue.