What is Jev?
Jev is the first System One Model released by TypeSafe AI — a new class of frontier models built specifically for fast, structured decisions that software can use directly. Unlike traditional LLMs optimized for chat and text generation, Jev is designed from the ground up for automation: it takes unstructured program state as input and returns typed, calibrated probabilistic decisions as output.
"Think of Jev as a frontier-intelligence function call: unstructured state in, typed probabilistic decisions out." — Diogo Almeida, Founder, TypeSafe AI
The Core Innovation: System One vs. System Two
Inspired by Daniel Kahneman's Thinking, Fast and Slow, TypeSafe distinguishes between:
| Aspect | Traditional LLMs (System Two) | Jev (System One) |
|---|---|---|
| Training | RLHF / RLVR (human preferences) | RLCD — Reinforcement Learning for Calibrated Decisions |
| Optimization Target | Human-preferred chat responses | Calibrated decisions with epistemically honest probabilities |
| Input | Sequential messages (chat) | Structured program state |
| Output | Strings (text, code, hallucinations) | Type-safe structured values (Choice, Score, Boolean) |
| Sampling | Sequential (token-by-token) | Parallel (all outputs in one query) |
| Speed | 3–329 seconds | 70–500ms (40–200x faster) |
| Cost | $0.20–$10/M input tokens; output ~5x more | $0.042/M input tokens; output FREE |
| Hallucination | Inherent risk | Mathematically impossible (schema-guaranteed) |
| Confidence | Overconfident, inconsistent | Calibrated — higher c higher accuracy |
Why Jev Changes Everything
1. Zero Hallucination, Guaranteed Type Safety
Jev cannot hallucinate a format or emit an invalid type. The output schema is defined in advance — every answer conforms to your declared types. This is "table stakes for automation" — a hallucinated tool call is inconvenient in a chatbot, but a deal-breaker in production systems with latency guarantees or deep dependency chains.
2. Calibrated Probabilities, Not Guesses
Every Jev output includes calibrated confidence scores. If Jev says 95% confidence, it's right 95% of the time. Traditional LLMs are notoriously overconfident and inconsistent — they can't tell you when they're in the 5% failure case, making them unreliable for automation.
3. Parallel Sampling = Insane Speed
Jev evaluates all declared questions in a single parallel pass instead of autoregressive token generation. This enables:
- 70–500ms end-to-end latency (vs. seconds for LLMs)
- Real-time AI in UX-critical paths
- Map-reduce over petabytes of data
- 10+ queries/second in game loops (see the Doom demo)
4. Economics That Enable New Use Cases
- Input tokens: $0.042/M ($42 per billion)
- Output tokens: FREE (too cheap to meter)
- 193.6x faster, 444.6x cheaper on workflow evaluations vs. frontier LLMs
This follows the Jevons Paradox (namesake William Stanley Jevons): every order-of-magnitude drop in intelligence cost unlocks orders of magnitude more use cases.
Ideal Use Cases for Jev
Jev shines where you need structured decisions at speed and scale:
| Category | Examples |
|---|---|
| Smart Routing / Classification | Support ticket triage, intent classification, spam detection |
| Risk Scoring & Guardrails | Fraud scoring, content moderation, jailbreak detection, refund approval |
| Agent Control Loops | Choose next tool, decide continue/retry/stop, subagent selection |
| Real-Time Applications | Game AI (Doom bot), browser agents, live recommendations |
| Data Processing at Scale | Extract fields from millions of documents, feature engineering |
| Verification & Evaluation | Score LLM outputs, verify reasoning traces, enforce policies |
Reference: TypeSafe AI Official Announcement
📖 Primary Source: Introducing System One Models & Jev — TypeSafe AI Blog
Published September 15, 2026 by Diogo Almeida (founder, former OpenAI). The post includes:
- Side-by-side demos comparing Jev vs. GPT-5.6 Terra
- Workflow evaluations showing Pareto-frontier performance
- Technical deep-dive on RLCD training methodology
- Hallucination/type-safety guarantees
- Fun demos: Doom bot and Wikiracing agent
- FAQ addressing "Is Jev just a smaller LLM?" and "How is this possible?"
Best GitHub Repositories to Get Started
🏠 Official TypeSafe AI Organization
| Repo | Description |
|---|---|
| typesafe-ai/system-one-adapter-python | Official Python wrapper to constrain LLMs to System One structured outputs |
| typesafe-ai/typesafe-ai.github.io | TypeSafe AI website & docs source |
🚀 Community Quickstarts & Playgrounds
| Repo | Description | Best For |
|---|---|---|
| codaaiteam/jev-ai | Quickstart & FAQ — 30-second intro, free browser playground at jevtypesafeai.com | Beginners, immediate hands-on |
| codaaiteam/jev-typesafe-ai | Developer notes & examples — Practical patterns, live playground running real /v1/systemone calls | Developers building integrations |
| TypeSafeAI/typesafe-playground | Interactive playground — Edit classification experiments, A/B inputs, routing, extraction, code-policy decisions, games | Experimentation, learning by doing |
🔧 Integrations & Tooling
| Repo | Description |
|---|---|
| Vercel AI SDK | Official Jev support via experimental_evaluate API (AI SDK 7.0.105+) — model: 'typesafe-ai/jev' |
| awesome-jev | Curated list of Jev tools, integrations, examples (community-maintained) |
| jev-mcp | Model Context Protocol server for Jev |
Quick Start: Your First Jev Call (TypeScript)
pnpm add ai@latest
import { experimental_evaluate as evaluate } from 'ai';
const result = await evaluate({
model: 'typesafe-ai/jev',
state: 'The support agent issued a full refund to the customer.',
questions: {
refunded: {
type: 'boolean',
instructions: 'Was a refund issued?',
},
priority: {
type: 'choice',
options: ['low', 'medium', 'high', 'critical'],
instructions: 'What is the urgency level?',
},
riskScore: {
type: 'score',
rubric: ['safe', 'review', 'block'],
instructions: 'Risk level of this action',
},
},
providerOptions: {
gateway: { zeroDataRetention: true },
},
});
console.log(result.answers.refunded); // { value: true, probability: 0.99 }
console.log(result.answers.priority); // { value: 'high', probability: 0.92 }
console.log(result.answers.riskScore); // { value: 'review', probability: 0.78 }
// Calibrated confidence metadata
console.log(result.providerMetadata?.typesafe?.confidence);
What's Next for Jev?
TypeSafe AI is still in early access — they're actively onboarding developers from the waitlist. Key areas to watch:
- Expanded cardinality support (currently up to 255 options per Choice)
- Multi-modal inputs (images, structured logs, traces)
- Fine-tuning / customization for domain-specific workflows
- Lower latency tiers for ultra-real-time use cases
- Open benchmarks and community evaluation standards
Final Thoughts
Jev represents a fundamental shift in how we integrate AI into software:
Old way: Prompt an LLM → Parse text → Validate → Hope it doesn't hallucinate → Retry on failure
Jev way: Define typed questions → Call Jev → Get calibrated, type-safe decisions instantly → Branch with confidence
If you're building AI-powered workflows, agents, real-time apps, or data pipelines — Jev is worth a serious look. The economics and latency finally make "AI as a reliable function call" viable.
Resources
- 📖 Official Blog: typesafe.ai/blog/introducing-system-one-models-and-jev
- 🎮 Free Playground: jevtypesafeai.com (no waitlist)
- 📚 Docs: docs.typesafe.ai
- 📊 Workflow Evals: evals.typesafe.ai
- 💬 Community: TypeSafe AI on LinkedIn | X/Twitter
Have you tried Jev? Building something with System One Models? Share your experience in the comments or reach out on X.
discussion
Comments on Jev: The First System One Model — A New Paradigm for AI-Powered Automation
loading comments...