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

Cloudflare AI

Cloudflare Workers AI model page for typesafe/jev, a provider-maintained integration that accepts state and typed questions.

Articleproduction
Open source ↗

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

Overview

Cloudflare's developer documentation includes a model page for typesafe/jev on Workers AI. Per the listing, it is a provider-maintained integration that accepts a state and typed questions, so Jev can be called from Cloudflare's platform alongside other models.

Only the listing summary was available here.

What the decision model decides

TypeQuestionAnswers
OtherWhatever typed questions the caller sends(inferred)—

How it works

  1. Call typesafe/jev on Workers AI
  2. Send state and typed questions
  3. Receive typed answers

Strengths

  • Access through Cloudflare's platform

Caveats

  • Only list summary available

Getting started

See https://developers.cloudflare.com/ai/models/typesafe/jev

At a glance

Type
Article
Status
production
Runtime
Cloudflare Workers AI
Has code
no
Has tests
no

Use cases and integrations

How curated lists describe it

  • Provider-maintained `typesafe/jev` integration accepting state and typed questions.

    cobanov/awesome-jev

Frequently asked questions

What is it?

Cloudflare's Workers AI page for calling Jev.

Who maintains it?

Cloudflare, as a provider integration.

Where is it?

https://developers.cloudflare.com/ai/models/typesafe/jev

Related projects

  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • instructor-php

    PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • synkora-ai

    Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript