Live Chat Churn Preventer

Mahir built Churn Preventer, a tool that watches live support chats and sends each customer message to TypeSafe’s Jev with 11 questions. It uses the responses to guide how the support conversation should proceed.

View on X

Mahir@mahirb22𝕏

Jev is crazy. I built Churn Preventer - a tool that watches a live support chat. Each customer message goes to TypeSafe's Jev with 11 questions: how angry, what do they want, is it time to pitch? Angry: help them out, maybe offer them a discount. Irritated: no selling, just answer straight. Calm: continue the conversation, pitch an upsell. Happy: thank them, mention the next tier lightly. Whole ch

Sep 18, 2026X postsView on X

For angry customers, it recommends helping them and possibly offering a discount. For irritated customers, it recommends answering directly without selling; for calm customers, pitching an upsell; and for happy customers, thanking them and lightly mentioning the next tier.

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.