What Is Jev? TypeSafe AI's Decision Model Explained
Learn how TypeSafe AI's Jev model returns typed choices, probabilities and scores through the Jev API, and where it fits in AI agent workflows.
Jev is TypeSafe AI's System One AI model for structured decisions. Instead of generating open-ended text, the Jev model evaluates shared state against bounded questions and returns typed choices, probabilities and scores through the Jev API. Software can use those answers directly without first parsing a generated paragraph.
TypeSafe AI calls this model family System One Models. The design goal is fast judgment inside software, where a bounded answer is more useful than generated prose.
This guide is about the Jev AI model released by TypeSafe AI. It is not about the unrelated medical abbreviation JEV, which is commonly used for Japanese encephalitis virus. AutoJev is an independent integration platform and is not affiliated with TypeSafe AI.
What is Jev AI?
Jev AI behaves more like an intelligent decision function than a chatbot. An application supplies context plus explicit questions such as “Which queue should receive this ticket?”, “Does this action require approval?” or “How risky is this deployment?” Jev returns an answer constrained to the options or scale supplied by the application.
That narrower interface makes Jev useful at high-frequency decision points where open-ended text would need extra parsing, validation and error handling. It does not mean every Jev judgment is correct; it means the output shape and available answers are bounded before the call.
Who created Jev?
TypeSafe AI created Jev and introduced it as its first public System One model. TypeSafe AI provides the underlying decision model and native protocol; AutoJev packages Jev for agent workflows through a hosted MCP server, authenticated REST endpoints, portable Skills and an online playground.
For primary product information, use the TypeSafe introduction to Jev and System One documentation. AutoJev focuses on practical integration patterns rather than representing the model vendor.
How the Jev model works
A Jev request separates two ideas:
- State contains the facts, evidence, or content being evaluated.
- Questions contain the judgments Jev should make about that state.
AutoJev supports the three Jev question types used by TypeSafe workflows and the configured Decisions API:
- Choice selects one option from a set of named criteria.
- Noul returns a probability for a yes-or-unknown judgment.
- Score places the state on a rubric defined by the caller.
Several questions can evaluate the same state in one request. A tool-call review can ask for an action verdict, a risk score, and a human-confirmation probability together.
How do you use the Jev API?
The Jev API accepts a model identifier, shared state and one or more named questions. Each question declares a choice, noul or score output instead of asking the model to generate prose. The response returns bounded answers plus the probabilities and confidence signals an application can use in its own action policy.
AutoJev exposes this protocol at /api/v1/decisions and keeps the upstream provider credential on the server. Authenticated clients send an AutoJev access key, while the public Ask Jev experience lets visitors try a simplified bounded question without configuring a key.
Read the complete Jev API guide for the request shape, cURL example, response handling and authentication. Use the Jev model guide for deeper coverage of Choice, Noul and Score, or open the Jev playground to inspect a request interactively.
Jev compared with a generative LLM
Jev and a generative language model solve different parts of an agent workflow.
| Need | Jev | Generative LLM |
|---|---|---|
| Pick from known actions | Strong fit | Possible, but requires output parsing and validation |
| Return calibrated probabilities | Native response | Depends on prompting and provider behavior |
| Write code or prose | Not supported | Strong fit |
| Explain a complex plan | Not supported | Strong fit |
| Route, classify, score, or gate | Primary use case | Often slower and more expensive for repeated decisions |
A practical agent stack uses a generative model to plan and create, then calls Jev at bounded decision points. The Jev answer does not replace deterministic checks, permissions, budgets, or human approval.
Good Jev use cases
Jev works best when the possible actions are known before the request:
- Route a task to one of several AI models.
- Classify a support request or operational event.
- Score release, compliance, or tool-call risk.
- Decide whether research evidence is sufficient.
- Check whether an agent task is complete.
- Estimate whether a human needs to review the next action.
- Choose whether a workflow should proceed, pause, split, or stop.
When not to use Jev
Do not use Jev when the task requires it to write an answer, generate code, create tool arguments, inspect files, or explain its reasoning in prose. Those jobs belong to a generative model or deterministic application logic.
Typed output prevents invalid response shapes, but it does not guarantee that every decision is semantically correct. Test important decisions against your own data, keep irreversible actions behind normal approval boundaries, and combine model judgments with deterministic policy checks.
How AutoJev uses Jev
AutoJev turns the Jev decision model into an operational layer for AI agents:
- A remote Jev MCP server exposes typed tools to MCP clients.
- REST presets define stable input contracts for common decisions.
- Portable Skills teach agents when to call each decision tool.
- Deterministic guidance maps model outputs to workflow actions.
- Bearer authentication keeps the upstream provider key on the server.
- The AutoJev Playground lets you test requests without writing a client.
AutoJev does not replace Jev and does not hide the underlying decision model. It packages Jev for agent workflows that need repeatable inputs, discoverable tools, and explicit action policies.
Jev AI questions people ask
Is Jev a chatbot?
No. Jev does not produce open-ended chat responses. It evaluates the state and questions supplied by software, then returns typed decisions and probabilities.
Is Jev a replacement for an LLM?
Not for generation. A generative LLM remains the better tool for writing, coding, planning and explanation. Jev can complement that model by handling classification, routing, scoring and verification steps.
Can Jev make a wrong decision?
Yes. A typed response guarantees a valid interface, not a correct judgment. Production systems should calibrate thresholds on their own data, preserve deterministic validation and escalate uncertain or high-impact decisions.
Explore the Jev topic cluster
- TypeSafe Jev guide explains the model's official identity, primitives, access paths and limitations.
- Jev AI for agents explains the agent architecture and practical decision patterns.
- Jev API guide covers authentication, request schemas, cURL and response handling.
- Jev ecosystem guide explains OpenJev, NanoJev, jev-router and Awesome Jev projects.
- Jev model guide covers state, Choice, Noul, Score and response handling.
- Jev MCP server shows how to connect Codex, Claude Code, Cursor and other MCP clients.
- Jev Skills explains the umbrella router and five focused AutoJev workflow Skills.
- Jev online playground lets you inspect real request and response shapes.
Official Jev resources
- TypeSafe System One documentation
- TypeSafe introduction to Jev
- Jev on OpenRouter
- Jev on Cloudflare Workers AI
Continue with the AutoJev integration guide or configure the Jev MCP server.
Jev in practice
Put Jev to work routing Codex, Claude Code and your other agents.
AutoJev is a free, open-source desktop gateway. Its intelligent selection asks Jev which model fits each request — using routing metadata only, never your conversation.