Real-Time Payment Transaction Classification

Frankiedigiac compared Typesafe AI’s JEV with Claude Haiku 4.5 on the same payment transactions, using eight concurrent threads to evaluate each stream. The author reported that JEV was noticeably faster and felt well-suited to real-time classification.

View on X timenoticeably faster

Frankiedigiac@frankiedigiac𝕏

@typesafeai 's JEV is actually pretty neat. I compared it against claude-haiku-4.5 on the same payment transactions, with 8 concurrent threads evaluating each stream. JEV was noticeably faster and feels well-suited for real-time classification. Accuracy is always debatable for any model, but infra can be built around confidence scores. AI slop -> https://t.co/E8EbJqRdXD

Sep 17, 2026X postsView on X

The author noted that accuracy is debatable for any model and suggested building infrastructure around confidence scores.

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.