Mini-Vibe Check: TypeSafe's Jev Judged Everything I’ve Written in 0.7 Seconds
Every Vibe Check article: Mike Taylor runs a writing corpus through TypeSafe's Jev and reports how it judged it.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
In this Mini-Vibe Check on Every, Mike Taylor runs TypeSafe's Jev over a corpus of his own writing. The title states the whole set was judged in 0.7 seconds, presenting Jev as a fast way to grade or characterise a body of text.
The article text was not fetched, so the specific questions and the reviewer's verdict are not summarised here. It is a useful first-hand account for writers, editors and content teams evaluating decision models for writing analysis or grading.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | Judgments of each written piece (rubric not known from sources)(inferred) | — |
How it works
- Gather a corpus of articles.
- Send each as state with typed questions to Jev.
- Compare the returned judgments across pieces.
Strengths
- Real-world review of Jev on writing analysis.
- Highlights speed over a large corpus.
Caveats
- Article not reviewed here; specifics unknown.
- A review piece, not reusable code.
At a glance
- Type
- Article
- Status
- discussion
- Has code
- no
- Has tests
- no
Use cases and integrations
How curated lists describe it
Every's Mike Taylor runs Jev over a writing corpus.
AnotiaWang/awesome-decision-models
Frequently asked questions
Who wrote it?
Mike Taylor, for Every's Vibe Check column.
What did Jev do?
It judged a corpus of his writing; the title says this took 0.7 seconds.
Does it include code to reproduce?
Not according to the listing.
Related projects
Analytics engine that rates published posts on pre-registered rubrics with Jev and tests ratings against real engagement.
ProjectbetaTypeScriptClaude Code plugin that logs your prompts locally and later has Jev score how well you prompt the coding agent over time.
PluginbetaTypeScriptChrome extension that grades readable page sections on ten rubric scores with Jev via Vercel AI Gateway and gives the page an A-E grade.
ProjectbetaTypeScriptNode tool that crosschecks a folder of Markdown notes for contradictions and repeats, and ranks notes by any question, using Jev.
ProjectbetaJavaScriptCLI and agent skill that checks every line of a document against every rule with Jev and outputs flags for an AI agent to fix.
Agent skillbetaTypeScriptDocument evaluation CLI and CI gate using Jev or OpenAI Decisions, with pre-registered validation and documented reliability limits.
CLIbetaPython