devwithjev
— reading now— views
Submit a build

Jev-Powered Decision Loop

Varun reports using Jev, Jevcache, and Fable in a decision loop. Jev decisions took ~220–780ms versus 20–40s with Claude previously, and Fable was consulted on three low-confidence steps.

View on X cost~50× cheapertime~220–780ms Jev vs 20–40s claude before; 0ms replay; 7.2→5.3 min
VarunVarun@varun_mathur𝕏
noticed below cumulative impact of using Jev + Jevcache + Fable: - Per-decision: ~220–780ms Jev vs 20–40s claude before - Loop's decisions are ~50× cheaper; Fable was consulted only on the 3 low-confidence steps - jevcache: earlier identical-phrasing re-run showed cached (0ms replay) live.. repeat run was 26% faster (7.2→5.3 min)
Sep 20, 2026X postsView on X
An identical-phrasing rerun showed a cached 0ms replay. A repeat run took 5.3 minutes, down from 7.2 minutes.

Also filed under Agents & browsers

  • Building a Harness with Jev

    Building a Harness with Jev Learn all about Jev, a new System One model from TypeSafe AI, and how you can use it in your agent harness. Jev is up to 200x ...

  • How To Build A Harness With Jev | A LangChain x TypeSafe Conversation

    How To Build A Harness With Jev | A LangChain x TypeSafe Conversation Hear from Sydney Runkle, Product Manager, OSS at LangChain, Allie Laabs, Founding Developer Advocate at TypeSafe AI, and ...

  • Jev-kit for Claude Code

    Cadaverr’s Jev-kit integrates TypeSafe’s Jev model into Claude Code for tasks including tool-call guarding, sub-agent sizing, file search, and browser automation. Jev answers pick-one and yes/no questions in about 0.3s, according to the author.

  • Jev Browser Automation

    jev-browser takes a task and URL, then uses Jev to choose one action per step from the page’s clickable, typeable, and selectable elements. It scores whether the goal is met or the run is stuck.