User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev TypeScript Starter
A TypeScript starter for Jev called through the Vercel AI Gateway with the AI SDK. It wraps evaluate calls in an askJev helper and ships a support-ticket triage example using choice, score and boolean questions.
- Stars
- 0
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- 1leetadmin
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- Vercel AI Gateway
- Capabilities
- Requires API key
Highlights
- Typed questions table: choice with probabilities for classification and routing, score for rubrics, boolean for checks.
- Limits noted in the README: 64k tokens per request, 32k for state plus the longest question, no streaming.
- Calls go through the Vercel AI Gateway, so the key is AI_GATEWAY_API_KEY, not a TypeSafe key.
- src/jev.ts is a thin wrapper around the AI SDK's experimental_evaluate; a triage example uses all three question types.
- npm run triage runs it; a quoted argument replaces the default invoice question.
Quickstart
bash
npm install
cp .env.example .env
npm run triageWatch out
README and GitHub metadata reviewed 2026-10-17; the digest truncates the usage example. The repository declares no license, and the wrapper depends on the AI SDK's experimental evaluate API, which the README warns may change between releases.
Questions about this entry
Short answers drawn from the linked project or page.
A TypeScript starter for Jev, TypeSafe AI's System One decision model, called through the Vercel AI Gateway with the AI SDK. It wraps evaluate calls in an askJev helper and ships a support-ticket triage example.
It runs three typed questions over a ticket: a choice among departments, a score over ordered levels, and boolean checks. npm run triage runs it, and a quoted argument replaces the default invoice question.
Requires Node 22.9 or newer. npm install, copy .env.example to .env and paste an AI Gateway API key, which is read from AI_GATEWAY_API_KEY, then npm run triage. Get a key in the Vercel dashboard under AI Gateway API Keys.
The README notes 64k tokens per request, 32k for state plus the longest question, no streaming, and pricing of about 0.04 USD per 1M input tokens with output free.
The wrapper depends on the AI SDK's experimental_evaluate API, which the README warns may change between releases. It also notes the AI SDK names yes/no questions boolean while TypeSafe's own API calls them noul.
No. Calls go through the Vercel AI Gateway, so the starter expects an AI Gateway key with access to the Jev model rather than a TypeSafe key; the key is read from AI_GATEWAY_API_KEY.
A single-author repository created on 2026-10-04 and last pushed on 2026-10-09, with 0 stars and no license declared. It reads as a learning starter around the AI SDK rather than a maintained product.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev lands on the Vercel AI Gateway
X: Vercel ships the AI SDK provider for Jev
YouTube: Greg Isenberg and Ryan Vogel on the businesses Jev unlocks, and a path in through the Vercel AI Gateway.
More Jev resources like this
Vercel Labs example that routes three forms by context with Jev and AI SDK: Jev's team choice is accepted when its confidence is at least 95%, otherwise openai/gpt-6-luna-fast independently evaluates the submission and its choice becomes final.
Jev Demos & Experiments#community#catalog-import#logicrw
Three TypeScript demos built on one pattern for students: Jev answers a typed question with a probability, your code decides what to do, and Claude works only where it is needed. Demos cover Jira triage, pre-flight checks and PR routing.
Jev Demos & Experiments#community#github#demo
Community
soyjorgepilo/jev-demoTypeScript
soyjorgepilo/jev-demoTypeScriptA learning lab for decision models: TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls, while Claude handles the hard cases. It ships an interactive site, a benchmark, calibration tests and docs.
Jev Demos & Experiments#community#github#benchmark
A Next.js workbench for evaluating AI ticket triage with TypeSafe AI: classify, route and score support tickets through structured schemas, then inspect outputs, latency, token use and estimated cost in a three-column view.
Jev Demos & Experiments#community#github#typescript
Community
netflix2023/jevTypeScript
netflix2023/jevTypeScriptA pilot build of the Parking Operations Decision Layer PRD: the support desk, agent guard and shared decision layer send each item to Jev as typed questions in one call, then rules and a confidence gate route it to AUTO, REVIEW, HUMAN or BLOCKED with an audit log.
Jev Demos & Experiments#community#github#typescript
A Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.