The Unofficial Jev AI Handbook
Jev doesn't write. It decides.
Jev is a judgment-only AI model from TypeSafe AI — no paragraphs, no chat, just fast yes/no answers, choices, and scores. This handbook explains the paradigm and shows how to pair Jev with LLMs to make AI pipelines dramatically cheaper. Early Access launched September 15, 2026.
What is judgment-only AI?
Generative models produce text. Jev produces decisions. You send structured input; Jev returns a verdict — and nothing else.
Yes / No
Binary judgments: is this review spam? Does this lead fit our ICP? Does this email need a human reply today?
Choice
Pick one of N labels: route a ticket to billing, support, or sales; bucket content by topic or risk level.
Score
Numeric ratings: score a YouTube video idea, rank candidate leads, grade retrieval quality from an AI memory store.
Built to pair with LLMs
Jev is the cheap front filter; GPT-class models handle only what passes. Reported savings: up to hundreds of times cheaper.
Start here
Your entry point: the core guides
API key from console.typesafe.ai, your first curl call, and the official Python/TypeScript SDKs.
System One, the three primitives, state design, calibration, models & pricing, and the API reference.
Five field-tested classification patterns: moderation, lead scoring, email triage, sentiment, and data filtering.
When a judgment model beats a generative one, when it does not, and why the two together cost less than either alone.
Pipeline blueprints: speculative fan-out, confidence gating, cascade routing, and the Jev→LLM front filter.
Noul, RLCD, jaggedness, calibration — every term in the paradigm, defined in one line with links deeper.
Try the paradigm
Feed a state, pick a primitive, get a typed verdict — simulated locally in your browser. No API key, no network, no cost.
Simulated in your browser — not a live Jev call
Request
yes/no → probability 0–1
Response
Fill in a state and instructions, then run the judgment.
Noul returns a probability · Choice returns probabilities + confidence · Score returns legend + probabilities + confidence
This is the *shape* of a real Jev exchange. The real thing needs an API key from console.typesafe.ai — walkthrough in Getting Started.
Latest from the handbook
Every page is version-stamped and sourced — see the Sources section at the bottom of each guide.
Jev API Reference: Endpoint, Request Body & Response Shapes
The System One endpoint reference: POST api.typesafe.ai/v1/systemone, the state/model/questions body, per-primitive request and response shapes, 429 handling, and SDK installation.
Confidence & Calibration: When to Trust the Number
Jev returns probability (Noul) and probability + confidence (Choice/Score). What each field means, what calibration is, and how to design confidence gates that fall back to humans or LLMs.
Models & Pricing: jev-1.13.0, Costs, Limits & Honest Benchmarks
The Jev model card: jev-1.13.0 / jev-latest / jev-preview, $0.042 per million input tokens with free output, 64k context, rate limits, latency — plus the accuracy caveats nobody should skip.
State Design: State Is Not a Prompt
Jev's state field is a case file for an expert, not a chat prompt. Filter in code first, name fields so questions can point at them, and keep irrelevant detail out — it measurably degrades accuracy.
What Is a System One Model? Jev vs LLMs, Precisely
System One is the model category TypeSafe AI claims Jev opens: fast, calibrated, judgment-only. The four concrete differences from LLMs, the RLCD training method, and the "not just a classifier" debate.
Explore the handbook
Guides, use cases, and recipes — organized by what you are trying to do.
Guides
Core concepts: what Jev is, how to get access, and how it compares to LLMs.
Concepts
The mental models: System One, the three primitives, state design, calibration, models & pricing, and the API reference.
Use Cases
Where a judgment-only model fits: moderation, scoring, triage, and filtering patterns.
Recipes
Reusable pipeline patterns for combining Jev with generative LLMs.
Frequently asked
A few common questions. Full list on the FAQ page.