Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

awesome-jev-use-cases

50 small interactive demos comparing Jev's Choice, Score and Noul with OpenAI gpt-4o-mini side by side, runnable offline from fixtures.

Modelbeta
View on GitHub ↗

Overview

Awesome Jev Use Cases by whyashthakker is a set of 50 minimal interactive examples, each in its own folder with two synthetic scenarios, a small 2D visual and a runnable JavaScript example, comparing TypeSafe Jev's primitives with OpenAI's Responses API using gpt-4o-mini.

Preview mode uses clearly labelled hand-authored fixtures, so no key is needed; adding TYPESAFE_API_KEY and OPENAI_API_KEY enables live comparisons, each making one paid request per provider, with keys kept on a loopback-only local server. The first example routes a support ticket with Choice, Noul and Score on the same input. The README explains that a Noul near 0.5 means uncertainty rather than medium intensity, and to ask one Noul per independent condition. Docs cover methodology, research sources and a Beam CLI integration. No framework or database is used.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich team should handle this ticket?billing · technical · sales
Yes / noDoes this message request a refund?yes · no
ScoreHow urgent or severe is it?(inferred)—

How it works

  1. Pick a use case
  2. Run in preview mode with fixtures, or live with keys
  3. Compare Jev's typed answer with gpt-4o-mini's
  4. Inspect cost and latency per provider

Strengths

  • Side-by-side comparison with an LLM
  • Runs without keys
  • Keys never reach the browser

Caveats

  • Synthetic scenarios
  • Comparison is against one small OpenAI model

Getting started

git clone https://github.com/whyashthakker/awesome-jev-use-cases.git && cd awesome-jev-use-cases && npm install && npm start

At a glance

Type
Model
Status
beta
Language
JavaScript
Runtime
local Node server + browser
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

Do I need keys?

No for preview mode; live mode needs TypeSafe and OpenAI keys.

What does 0.5 on a Noul mean?

Uncertainty, not medium intensity, as the README explains.

What is compared?

Jev's typed answers versus gpt-4o-mini through the Responses API.

Related projects

  • warped-sys1-lab

    Local SvelteKit workbench and CLI for organizing, editing, running and comparing Jev experiments defined as JSON.

    CLIbetaTypeScript
  • OpenJev (GPT-AGI)

    Jev-compatible open System One engine with a Claude Code-style terminal REPL showing live probabilities, plus an experiment harness.

    ProjectprototypePython
  • jev-behavior-study

    Independent field guide to Jev 1.13.0 behaviour across 11,621 requests: framing sensitivity, Snake and 3D city driving experiments.

    ProjectresearchPython, TypeScript
  • jev-report

    Independent 52-page Chinese report on Jev that checks vendor claims and reproduces 50 Chinese tests, with traceable data.

    ProjectresearchPython
  • jev-playground (Ahmar004)

    Interactive teaching site where Jev races frontier LLMs in games, an arena, a sandbox and quizzes, with a keyless replay mode.

    AppproductionTypeScript
  • typesafe-showcase★ 1

    Next.js site with six live Jev demos, each compared side by side with Gemini or Claude on latency, cost and agreement.

    DemobetaTypeScript