devwithjevScores Leads and Selects Outbound Messages
Efe Berke Çolaker plugged JEV into Getlead to evaluate 462 leads, score ICP fit and buying signals, and select a hook, angle, CTA, and winning message for each.
Efe Berke Çolaker@Efe_berke_c𝕏
JEV is INSANE. I plugged it into Getlead and gave it 462 leads. In 47 seconds, it made 7,068 decisions: scored every lead's ICP fit, read the buying signal, and picked the best hook, angle and CTA for each person. Then it chose the winning message out of 4. Per lead. 190 leads never got an email. Wrong fit, bad data, no buying power. All for just $0.06. This is how outbound should work: judge firs
The run made 7,068 decisions. It withheld email from 190 leads due to poor fit, bad data, or lack of buying power.
Also filed under Triage & routing
- Jev-Assisted Codex Model and Effort Routing
The project provides Jev-assisted model and reasoning-effort routing for local Codex Desktop and CLI.
- Plain-English Gmail Filter Judge
The project uses Jev (TypeSafe) to judge Gmail filters written in plain English.
- Framework-Agnostic Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using TypeSafe’s Jev decision model to speed up agent loops.
- MCP Tool Router with Jev and MCTS
Harness-router is a lightweight tool router that uses Jev for fast tool selection and Monte Carlo Tree Search for harder multi-step decisions. It uses MCP as the tool interface and falls back when routing is uncertain.