Jev Vercel

Vercel's agent framework with Jev wired into its experimental evaluate path, so the scoring step of an agent returns typed decisions rather than prose the surrounding code has to parse.

Vercel's official AI SDK for Python, in public beta: streaming models, agent tool loops, hooks for human approval and structured output, with provider IDs routing through AI Gateway by default. The SDK's evaluation operation and Gateway examples carry Jev as a decision and evaluation provider.

A Next.js dashboard and daily Vercel cron that scores public job postings against one resume with Jev through the Vercel AI Gateway, then applies through a Grok Bot webhook that fills ATS forms and writes status back.

Yury Selivanov's 2 October 2026 post on the Python AI SDK: experimental evaluate() calls typesafe-ai/jev through an AI Gateway key.

Vercel's changelog for typesafe-ai/jev on AI Gateway, with AI SDK 7 experimental_evaluate and a support-ticket routing example.

An intraday trading bot for the Nifty 50: Jev ranks names every 15 seconds through the Vercel AI Gateway, and code sizes positions, stops, and flatten times.

Vercel's Pranit reports benchmarking the fx auto-mode safety classifier with Jev: about 5 to 18 times faster and more accurate than GPT-5.6 Luna.

A small demo app that fetches a URL, turns the page into clean Markdown, and asks Jev ten bounded Choice questions about what a first-time visitor is likely to understand.

An unofficial, dependency-free Go SDK for Jev's System One API with direct TypeSafe and Vercel AI Gateway providers, an interactive CLI, and an installable agent skill that covers request and retry semantics.

A Pi plugin that has Jev pick one model and one reasoning-effort level from a configured list at the start of a session, then keeps both pinned for the rest of it.

A filesystem-first framework for durable AI agents whose auto model router defaults to Jev through Vercel AI Gateway and whose evaluate helper asks typed Choice, Score, and Boolean questions inside tools.

A hosted and self-hostable pull-request reviewer where Jev answers a Clean Code question set for each changed file and Luna writes the review from those answers; also exposed as a stateless Streamable HTTP MCP server.

A Chinese and English lateral-thinking puzzle site hosted by Jev: Choice questions classify player questions and check proposed solutions against required facts, while code enforces confidence thresholds before a puzzle is marked solved.

An experimental TypeScript gate that asks Jev one wake, not-yet, or unrelated Choice before resuming a sleeping agent's LLM, while code handles timers, user messages, skip limits, errors, and timeouts.

A Next.js playground that benchmarks Jev against GPT-5.6 Luna, Claude Haiku 4.5, Gemini 3.5 Flash Lite, and GPT-6 Astra in tic-tac-toe and Connect Four, giving every model the same legal-move Choice options through the Vercel AI Gateway.

WXT Chrome extension that grades readable page sections with Jev through Vercel AI Gateway, giving each section ten rubric scores and each page an inspectable A-E grade.

Generative UI framework with an experimental Jev composer that selects components and layout from application-supplied candidates through Vercel AI Gateway, rendering catalog-constrained JSON specs.

Vercel Labs' terminal CLI for the AI SDK: its `ai evaluate` command answers named Boolean, Choice, and Score questions, with Jev as the default evaluation model and one unchanged input shared across all questions.

A local, read-only Gmail triage app that sorts mail into five trays with Jev: each message becomes one experimental_evaluate call answering tray, urgency, and human-written questions, and 1,000 emails sort in about a minute for around 3 cents.

A multiplayer demo workflow builder for Jev built with Liveblocks: wire Jev and LLM steps together, call the workflow through a REST API, and preview test runs with shared state and cursors.

@ai-sdk/typesafe-ai adds an evaluation model to the Vercel AI SDK: one experimental_evaluate call sends a state with choice, score, and boolean questions and returns typed answers, probabilities, confidence, and usage.

TypeSafe's announcement that Jev is available on the Vercel AI Gateway, linking the model page with the Jev API, pricing, and playground.

Guillermo Rauch says the fx auto-mode safety reviewer, currently on GPT Luna, is up to 18x faster at p95 and more accurate with Jev, and that Jev is coming to Vercel AI Gateway.

Vercel CTO Malte Ubl reports that Jev beat an existing classifier eval previously run on Gemini 2.5 Flash Lite, saturating the eval on quality and running 6x faster.

End-to-end guide to a ticket-routing workflow with confidence thresholds, zero-data-retention options, and mock-based tests that need no network call.

AI Gateway's evaluation modality: call Jev as `typesafe-ai/jev` through the AI SDK's experimental_evaluate API, with structured answers instead of free-form text.

Model card for `typesafe-ai/jev`: evaluation type, $0.042 per 1M input tokens, zero output token charge, and a hosted playground.