devwithjevRoutes Review Tasks with Jev
Jev was tested on 32 real historical tasks. It identified 103/126 required reviewers, had 0/41 critical misses, and caught 7/7 escalation cases.
Pranay Suyash@pranaysuyash๐
Yesterday I posted the Jev routing experiment before I had API access. Got access later and ran it on 32 real historical tasks. Three-way comparison: Current council: 125/126 required reviewers, 0/41 critical misses, 1/7 escalation cases caught. Jev: 103/126 required reviewers, 0/41 critical misses, 7/7 escalation cases caught. Typed GPT-4.1-mini control, with the same state and the same 21 questi
The author ran the experiment after getting API access. For comparison, the current council identified 125/126 required reviewers, had 0/41 critical misses, and caught 1/7 escalation cases.
Also filed under Triage & routing
- Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using Jev AI. It is designed to speed up agent loops by routing decisions without relying on large generative LLMs at every step.
- Local Candidate Scoring with Jev
Bev performs local Jevfire-style candidate scoring using ternary models and a System One API. Its probabilities are candidate-relative.
- Team Agent Workspace for Routing and Model Selection
Agentconnect is a team agent workspace that uses Jev typed decisions for response routing and model selection.
- Desktop AI Assistant with Jev Plugin
PyGPT is a desktop AI assistant with a Jev plugin for typed classification, routing, verification, and scoring.