Intent-Based Predictive Launcher

The launcher uses Jev to interpret intent, putting the newest PDF first when the user types “the pdf I just downloaded.” The author reports full confidence on every keystroke.

View on X timeAbout 100 ms

hityyhz@hityyhz𝕏

Also been playing with @typesafeai Jev. Insane. A pile of apps suddenly become possible. What a time to be a builder. Sharing experiments here. First one: Keystroke oracle / predictive launcher A normal launcher ranks by aliases, fuzzy match, and habit. Jev reads intent. Type “the pdf I just downloaded” and the newest PDF is already the top hit. Full confidence on every keystroke. About 100 ms.

Sep 18, 2026X postsView on X

The author describes it as their first experiment with Jev. They contrast it with launchers that rank results by aliases, fuzzy match, and habit.

Also filed under Tools & apps

TypeSafe Jev Decision-Model Client
It provides a shared TypeSafe Jev decision-model client for the dsh ecosystem, with strict response validation, keychain-first key resolution, and typed fail-open errors. It is Jev-optional by design.
Jev Reviews Changed Code
The Claude Code plugin uses Jev (TypeSafe AI) to assess changed code at the end of a turn and, when needed, propose a code review using Open Code Review rules.
Alerts on Company Data-Use Changes
TOS Watch sends an email when a company changes what it does with your data. It combines Open Terms Archive history, a Jev classifier, a static site, and a Cloudflare Worker.
OpenAI API-to-Jev Gateway
jev-gateway turns any OpenAI API backend into a gateway compatible with Jev.