devwithjevClassifies Banking Support Messages
Adil Mouja tested Jev, TypeSafe AI’s new classifier model, on 100 real banking support messages across 77 intents in a zero-shot setup, achieving 82% accuracy.
adil.eth@AdilMouja𝕏
I tested Jev, @typesafeai's new classifier model, on 100 real banking support messages (77 intents, zero-shot): → 82% accuracy → 91.9% accuracy on the 74% of tickets where it was ≥90% confident → 329 ms median latency → $0.009 total Code: https://t.co/HtEjw82e7o https://t.co/zGGiGNGdJa
On the 74% of tickets where the model was at least 90% confident, accuracy was 91.9%. The post links to the code.
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.