devwithjevJev Grades AI Assistant Work
JH Trader uses Jev with Muse to review AI assistant Sarah’s work before he sees it.
Okay so we also built something else. So we are using @Muse & @typesafeai Jev together now. I’m using Jev to grade my AI assistant Sarah on her own work before I ever see it.
So (Jev by Typesafe) will act as the judge.
Every caption draft gets scored against my actual writing voice: my hooks, my outro style, my banned words, all of it.
And It's bigger than captions. Before she states a fact, the judge checks it against her own records, it caught a wrong number tonight before I saw it.
Before she acts on a vague instruction, the judge decides: act, or ask me first. A checklist that never
Jev scores caption drafts against his writing voice, including his hooks, outro style, and banned words. It also checks facts against Sarah’s records and decides whether she should act on vague instructions or ask first.
Also filed under Content & growth
- Grades Meta Ads Across Nine Dimensions
Ajay Ponna Venkatesh used Jev, a classifier model from TypeSafe AI, to evaluate Meta ads from eight beauty brands across nine dimensions.
- Crowd Check Simulates Post Reception
Crowd Check lets users test a post or tweet on 10,000 AI readers before the real internet sees it. It shows how the readers react, including whether they like, repost, follow, or block the author.