Replaying 3,300 Real Production Decisions to Test Small Model Jev

mikegiannulis · x · 2026-09-18

The company's product uses AI to help people write books. They replayed 3,300 real production decisions through Jev from @typesafeai, covering tasks like finding sources, routing messages, and catching "I already sent you that."

These are boring tasks, but the ones customers notice immediately when they break — exactly where small model value should be tested.

Related event: TypeSafe Launches Jev, a Decision-Only Model That Never Writes a Word(44 posts)→

Original post →

More from coding & agent

coding & agent channel →