ブログ — ガイドと開発ノート

Jev を使った開発に関する製品アップデート、開発ノート、実践ガイド。型付きの質問と、コードで分岐できる構造化された回答について解説します。

Open-source projects built on Jev

Hands-on guides to six independent GitHub projects: what each does, how to install it, and how to call Jev with a JevStation API key. We are not affiliated with any of them.

jev-seo

Live SEO audit from one homepage URL: 52 checks, Core Web Vitals and Jev page questions, exported as PDF, XLSX and Markdown.

jev-ultrafast

A browser agent that picks its next click or keystroke with one Jev call over a numbered element table.

jev-review

AI code review for a Git diff or a whole codebase, with risk, severity and routing steps and a local dashboard.

semdecide

Grep for meaning: a CLI that turns typed Jev answers into exit codes for shell scripts and CI.

jev-router

Per-turn model routing for Claude Code and Codex: Jev picks a fast, balanced or strong tier and fails open.

winnow

A Rust parser-combinator library, paired here with Jev: winnow parses the structure, Jev judges the meaning.

These repositories belong to their authors and are unrelated to JevStation.

Cloudflare Clef Tested: Context Cap, Tokens, Cost

We called Clef and Clef-flash on Workers AI ~70 times: at launch they read only ~2,048 state tokens; a 10-07 retest found the cap gone. Costs per call.

2026年10月4日

JevStation

Jev のユースケース：System One モデルが下せる 12 の判断

Jev に何ができるのか。チケットのトリアージからツール呼び出しのガードまで、エージェントやパイプラインで Jev が下す 12 の判断を、質問セットと無料のツールページ付きで紹介します。

2026年9月28日

JevStation

Jev Benchmarks: Every Independent Test So Far

Is Jev accurate? Every independent Jev test to date, from an AI-control pilot to GLiNER and routing tests, with sample sizes, caveats and vendor claims apart.

2026年9月28日

JevStation

Jev as a Judge: What One Yes/No Question Catches

Can a text-free model judge LLM output? One Jev question ranks backdoored code at AUROC 0.976 for ~$0.04 per 1,000 checks. Where it holds, where it breaks.

2026年9月27日

JevStation

Jev Alternatives: Clef, GLiNER and LLMs Compared

Five ways to get typed decisions from text: Clef, structured-output LLMs, GLiNER, your own classifier and Jev. Measured accuracy, cost and where each wins.

2026年9月27日

JevStation

fast-jev-compaction: Claude Code Context Compaction

fast-jev-compaction is a Claude Code plugin that drops stale tool calls with Jev instead of summarising them. How it works, install steps, and what it keeps.

2026年9月20日

JevStation

System One モデルとは何か、そして何ではないのか

System One モデルは生成テキストではなく、型付きの判断とキャリブレーションされた確率を返します。その意味、RLCD と RLHF の違い、そして独立した検証がまだ乏しい点を解説します。

2026年9月20日

JevStation

What One Jev Evaluation Costs, Measured

We made 11 real Jev calls across every state size and question count, fitted the token model and measured the cost: $0.000012 to $0.000377 per evaluation.

2026年9月20日

JevStation