--- title: Jev from TypeSafe AI description: Jev is TypeSafe AI's System One model for fast, typed decisions. It evaluates supplied context and returns choices, scores, and probabilities that applications can use to classify requests, route tasks, and assess proposed actions without generating prose. url: "https://vercel.com/kb/jev-from-typesafe-ai" published: 2026-09-22 last_updated: 2026-09-22 install_vercel_plugin: npx plugins add vercel/vercel-plugin --- # Jev from TypeSafe AI Jev is TypeSafe AI's System One model for fast, typed decisions. It evaluates supplied context and returns choices, scores, and probabilities that applications can use to classify requests, route tasks, and assess proposed actions without generating prose. ## Build with Jev - [How to classify, route, and score with Jev and AI SDK](/kb/guide/typesafe-jev-and-ai-sdk): Use Jev from TypeSafe AI with AI SDK's experimental \`evaluate\` API to classify, route, score, and verify inside your application. Jev returns typed choices, scores, and boolean probabilities through AI Gateway. - [Moderate product reviews with Jev, TanStack AI, and AI Gateway](/kb/guide/moderate-product-reviews-jev-tanstack-ai): Moderate product reviews for an e-commerce storefront with Jev from TypeSafe AI and TanStack AI's \`decide()\` function. The \`@tanstack/ai-vercel-gateway\` adapter returns typed choices, scores, and boolean probabilities through Vercel AI Gateway, so your code can publish clear reviews and hold flagged ones. - [Route form submissions with Jev and AI SDK](/kb/guide/jev-ai-sdk-form-router): Route form submissions to the right team with the Jev x AI SDK Form Router template. Jev routes clear cases and a fallback model decides uncertain ones. - [How to automatically approve tool calls in eve with Jev](/kb/guide/auto-approve-tool-calls-eve-jev): Use Jev to review tool calls in eve, allow routine actions, and request human approval when needed. Configure the policy and test its failure paths. ## Learn more about Jev - [What is Jev, TypeSafe AI's System One model?](https://vercel.com/i/what-is-jev): Jev is TypeSafe AI's System One model, built to return typed decisions with probabilities from supplied state and questions. - [7 practical Jev use cases for AI applications](https://vercel.com/i/jev-use-cases): Explore seven Jev use cases, including form routing, ticket prioritization, tool approvals, document classification, and response evaluation. - [6 ways to integrate Jev into your application](https://vercel.com/i/jev-integrations): Explore six ways to integrate Jev, including AI SDK, TanStack AI, Cloudflare, LangChain, eve, and TypeSafe's SDKs and HTTP API. - [When should you use Jev instead of a chat model?](https://vercel.com/i/when-to-use-jev): Choose Jev for bounded decisions, code for fixed rules, and a generative model for prose. Compare workload fit and plan an evaluation. - [Where does Jev fit in an AI agent loop?](https://vercel.com/i/jev-agent-control): Place Jev in an AI agent loop for bounded decisions, while application code controls tool permissions, execution, and state updates. - [How should you use Jev's probabilities to set decision thresholds?](https://vercel.com/i/jev-probabilities-and-thresholds): Interpret Jev's probabilities, confidence, and scores, then test decision thresholds against the cost of mistakes in your application. - [What is OpenAI's Decisions API?](https://vercel.com/i/what-is-openai-decisions-api): Learn how OpenAI's Decisions API uses predefined answers for application decisions and how it differs from Structured Outputs. - [TypeSafe AI Jev vs. GPT-6 Astra: When should you use each?](https://vercel.com/i/jev-vs-gpt-6-astra): Compare TypeSafe AI Jev and GPT-6 Astra for classification, structured outputs, and agent workflows, with a shared AI SDK example. - [OpenAI Decisions API vs. Jev: How do they compare?](https://vercel.com/i/openai-decisions-api-vs-jev): Compare input support and answer types, including the role of Jev's probabilities in application routing rules. - [TypeSafe AI's Jev vs. Perplexity's Decisions API](https://vercel.com/i/jev-vs-perplexity): Compare Jev and Perplexity\'s Decisions API by input support, answer types, deployment options, and the work required to switch providers. - [Jev vs. Laya vs. Liquid d1: Which decision model should you use?](https://vercel.com/i/jev-vs-laya-vs-liquid-d1): Compare Jev, Laya, and Liquid d1 by API compatibility, deployment options, and probability handling, with a product-catalog example through AI Gateway. - [Using Jev in TanStack Start with TanStack AI](https://vercel.com/i/using-jev-in-tanstack-start-with-tanstack-ai): Use Jev in TanStack Start through TanStack AI's Vercel Gateway adapter. Build a typed decision endpoint and compare the AI SDK integration. ## Explore other topics in the Vercel Knowledge Base - [Python](/kb/python): Build, deploy, and scale Python on Vercel. Run FastAPI, Flask, Django, or any ASGI or WSGI app on Vercel Functions with zero configuration, and find guides on background jobs, storage, AI workloads, containers, and migrating from other platforms. - [Enterprise Apps and Agents](/kb/enterprise): Explore how enterprises develop, deploy, and govern internal apps and AI agents. Learn about citizen development, shadow AI, access controls, and agent auditing, with practical guidance for turning employee-built tools into supported business applications. - [Vercel Sandbox](/kb/vercel-sandbox): The compute primitive designed to safely run untrusted or user-generated code on Vercel. - [FDE Field Notes](/kb/fde): Insights from our work with customers. Explore the patterns, diagnostics, and recommendations Vercel’s Forward Deployed Engineers use in production.