jev-dev

同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ(affectus + Vercel AI Gateway)

How it uses Jev

同じ user の発言を TypeSafe の jev と LLM の両方に判定させ、判定結果のズレと速度差を1画面で見せるデモ。判定は affectus の感情状態として別々に蓄積され、2つの状態が会話を重ねるにつれて分岐していく様子をプルチックの輪で見られる。さらに、分岐したそれぞれの感情状態で同じ発言への返答を生成するので、判定の差が2つの返答の違いとして読める。

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-dev

Browse all
jev-model-router project preview
Agent tooling
Jev (TypeSafe) model router on the Vercel AI Gateway
jevpolicy project preview
Demos & playgrounds
JevPolicy is an open-source TypeScript decision runtime that turns probabilistic judgments from Jev, accessed through Vercel AI Gateway, into versioned, deterministic, replayable, observable application decisions.
flue-jev-demo project preview
Demos & playgrounds
Flue agent routing with TypeSafe Jev through Cloudflare AI Gateway
jev-trip project preview
Demos & playgrounds
Two Minds, One Trip. https://jev-trip.vercel.app/
pi-jev-router project preview
Agent tooling
Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway
jevplayground project preview
Browser & computer use
Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway
laya-server (1Panel-dev) project preview
A self-hosted API and web interface for Laya’s structured decision models, compatible with the TypeSafe Jev API format.
Hosted typesafe-ai/jev for AI SDK evaluate calls, no TypeSafe waitlist required.
typesafe-ai-benchmark project preview
Benchmarks & research
This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.