Typesafe's Jev Decision Model Demos: 28 Use Cases and a $100k Job for $0.09
johnlindquist · x · 2026-10-01
Claire Vo and John Lindquist released two podcast episodes demoing Jev, a decision model from typesafe.ai.
- The 30-minute intro covers what Jev is, how it differs from general LLM usage, the 3 return types it supports, and a "$100k use case" that cost $0.09 to run.
- The follow-up shows roughly a dozen of Lindquist's 28 builds: multi-step routing, deduplicating messy data, model-vs-model blitz chess, and a real-time presentation coach.
A useful inspiration source for developers routing structured decisions through small models, with striking cost numbers.
More from coding & agent
- Azure AI kicks off series: why content extraction matters more as GenAI models get stronger — adnan_hashmi · 2026-10-01
- Power User Ranks Personal Agents — Muse Over Dots and Grok Bot — After 60+ Hours a Week in Agent Harnesses — brandon_galang · 2026-10-01
- Miles Brundage: Codex Ultra Fast burns budget in hours, widening the compute gap — Miles_Brundage · 2026-10-01
- All the Copyright Easter Eggs in That AI Music Video Came From Claude — technollama · 2026-10-01
- ChatGPT Wrote Lyrics, Suno Made Music, Claude Coded a 5,200-Frame Music Video — technollama · 2026-10-01
- New tool makes benchmarking across factory configs trivial, not just models — vikvang1 · 2026-10-01