Blog — Guides and Engineering Notes
Product updates, engineering notes and practical guides on building with Jev, typed questions and structured answers your code can branch on.
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.
Latest posts
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.
JevStationJev Use Cases: 12 System One Model Decisions
What can Jev do? Twelve decisions it makes in an agent or pipeline, from ticket triage to tool-call guards, each with its question set and a free tool page.
JevStationJev 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.
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.
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.
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.
JevStation
What Is a System One Model? Jev, Explained
A System One model like Jev returns typed decisions with calibrated probabilities instead of text. How it works, how RLCD differs from RLHF, and its limits.
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.
JevStation
Building a Harness with Jev
An agent loop is only as fast as its slowest decision. Where Jev, the System One model from TypeSafe, fits: model routing, action gating, escalation.
JevStation
Designing Jev Questions: Choice, Score and Noul
The three Jev question types, Choice, Score and Noul, set what your code can branch on. How to write atomic questions, sharpen rubrics and gate on confidence.
JevStation