JevMade hello@JevMade.com
← Back to guides

JevMade field notes / Reported project survey

WTF is Jev, and 9 things people are building

Matt Van Horn surveys early Jev projects across browser control, context pruning, safety review, model routing, retrieval, games, email, document evaluation, and local clones, while preserving contrary benchmark and calibration evidence.

Original by Matt Van HornGetting startedX postOriginal published Source reviewed

Before you dive in

What you’ll find in the original

  1. A recurring architecture keeps a large model for planning or writing while Jev chooses browser actions, routes models, filters retrieval results, or reviews proposed tool calls.
  2. Typed output prevents invalid labels but not wrong valid labels; the post highlights one test where Jev found six of seven planted defects while Fable found seven.
  3. Early headline figures varied substantially by workload: the post contrasts a reported 200× claim with a separate 25× test and treats maker-reported costs and latencies as claims rather than universal rates.
Worth knowing

This is a secondary survey assembled from launch-week posts. Most figures are reports by project authors, not measurements reproduced by Van Horn, and several featured projects have fuller primary sources elsewhere.