Skip to content

Jev AI

Public Jev playground and API site that answers typed Choice, Score and yes/no questions about pasted text in about 0.5 s.

Service

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

Jev AI at jev-ai.pro is a public web playground and API listed in yibie/awesome-jev. Users paste text and put typed Choice, Score and yes/no questions to the model for tasks such as ticket triage, moderation and review scoring, receiving a parsed answer with a confidence value in about half a second per decision.

It is a quick way to see how typed decisions behave without writing code. No README or source was available, and the site is a third party rather than TypeSafe, so it is unclear how requests are proxied, how keys are handled, or what the API terms are.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich category does this ticket or text belong to?(inferred)—
ScoreHow should this review be scored?(inferred)—
Yes / noDoes this text violate the moderation rule?(inferred)yes · no

How it works

  1. Paste text into the playground
  2. Define a Choice, Score or yes/no question
  3. Receive the parsed answer and confidence

Strengths

  • No-code way to try typed decisions
  • About 0.5 s per decision per the list

Caveats

  • Third-party site; not official
  • No documentation of data handling or API terms

At a glance

Type
Service
Runtime
web playground and API

Use cases and integrations

How curated lists describe it

  • Developer tooling: public Jev playground and API that puts typed `Choice`, `Score` and Yes/No questions to the model about pasted text - ticket triage, moderation, review scoring - and returns a parsed answer with a confidence value in about 0.5 s per decision.

    yibie/awesome-jev

Frequently asked questions

What is jev-ai.pro?

A third-party playground and API for asking Jev typed questions about pasted text.

Is it official?

No, it is not TypeSafe's site.

How fast is it?

About 0.5 s per decision, according to the list summary.

Related projects

  • Worked Jev examples for ticket triage and reranking, runnable through OpenRouter without an early-access key, with offline tests.

    ProjectprototypePython
  • Runnable Jev cookbooks, a plain-English guide and sixteen interactive simulations of how a typed decision model changes architecture.

    AppbetaPython
  • Research notes on Jev plus a live Cloudflare Worker playground that triages support messages by department, urgency and frustration.

    AppprototypeTypeScript
  • Korean course code for attaching Jev to Claude Code, Codex and OpenClaw: skills, hooks, routers and open-model comparisons.

    ProjectproductionJavaScript
  • Small Python demos of Jev: parallel Noul ticket checks with measured speedup, and a three-way Choice citation and claim checker.

    AppprototypePython
  • Two beginner Python apps using Jev: a message sorter and a support ticket router that send uncertain items to human review.

    ProjectprototypePython