Decision models: a probability instead of a paragraph

Most LLM calls inside an agent aren't asking for writing. Which tool next? Is this relevant? How urgent is this ticket? Closed questions dressed up as text generation.

Jev, released by TypeSafe on 15 September 2026, answers only those. Microsoft, OpenAI, Perplexity and dozens of open models have followed. It's a category now.

TypeSafe calls them System One models, after Kahneman: System 1 is the fast gut call, System 2 the slow, deliberate work. LLMs are System 2. Decision models are System 1.

A smart if statement

An LLM writes text for a person to read. A decision model doesn't write. You give it an input, a few questions, and the answers each question is allowed to have. It picks from your answers and says how sure it is. A smart if statement.

Three kinds of question, plus an experimental fourth for images:

The model answers. Your code decides what to do with each answer:

How that differs from asking an LLM for JSON:

• Many questions, one call. They run in parallel against the same input. One more question barely adds latency, and no question can contaminate another.
• It only knows what you send. If a question leans on your rules, the rules go into the question, and they have to fit: up to 32k tokens per question.
• You pay for input only. There is no output to speak of.
• The probabilities are the API. You threshold, rank, route and escalate on them.
• Two kinds of sure. Every answer has a probability. Pick-one and scale answers also carry a confidence: how far ahead the winner is. "Scam" at 54% with "careless seller" right behind it is the cue to ask before acting.

What it is not:

• Not a writer. You can't drop Jev into Claude Code as "the model".
• Not a calculator. Counting, arithmetic and dates are documented failure modes. Do the maths in code, ask the model only the semantic part.
• Not a deep reasoner. Indirection and double negatives degrade it. It answers what you wrote, not what you meant.
• Not immune to its input. Adversarial text inside the input can steer it, much like prompt injection.

An LLM writes, a decision model decides, code acts.

Framing is the product

Decision models reward question design far more than LLMs do. In one public phishing benchmark of 2,000 emails, a single question, "is this phishing?", got Jev to 63% and Haiku 4.5 to 81%. With the question split into five atomic parts and combined in code, Jev reached 95% and Haiku 93%, a gap too small to call. The decomposition closed the gap, and Jev did it at a twelfth to a twenty-seventh of the cost. A two-line regex reached 92%, which tells you how much of the work was in choosing the questions.

A vague question packs several judgments into one word, and the model has to guess how you weigh them. Switch between one question and five:

The playbook:

• One judgment per question. If you catch yourself explaining what you meant after a wrong answer, that explanation was the missing half of the question.
• Combine in code. Ask about market size, feasibility and differentiation separately and weight them in code. When priorities change, you change a number, not a prompt.
• Give it a way out. Add "none of these" or "can't tell" to a pick-one. A yes/no has no "doesn't apply", so define what counts as no.
• Several can apply? One yes/no per label. There is no multi-select.
• Ask in English. The content can be in any language. The questions should stay in English: translated questions cost Jev up to 13 points on one Spanish benchmark, English questions over Spanish text cost nothing measurable.

Confidence is a design material

When every judgment comes with a calibrated probability, "how sure is the system?" stops being a vibe and becomes a value you design with.

The usual shape has three bands: above a high line, act. In the middle, suggest and let the user confirm. Below a floor, hand it to a person or a larger model. Where the lines go is a product decision: the cost of a wrong action against the cost of interrupting someone.

Drag the top line down and more receipts file themselves, but the wrongly filed ones land there too, where nobody checks. Drag it up and you're safe, but tapping to confirm more often.

The same shape at scale: a decision model first, the uncertain tail to an LLM or a person. One build on Made with Jev classified 100 fraud emails with Jev in 1.42 seconds, sent the 31 below 95% confidence to a larger model, and got 96 right for about seven cents. The author's own figures, with no published code.

What cheap, calibrated judgments make practical:

• Generative UI that can't invent controls. The model picks from the components the interface already has.
• Flows that branch on meaning. The next question is a pick-one, not a hand-written if/else tree. Low confidence triggers a clarifying question.
• Agent steps you can show and audit. Every step is a typed decision with a probability you can display, log and explain.
• A judgment per keystroke. At around $0.00004 per decision, you can afford one per row, per frame or per keypress.

One firm line: for consequential decisions about people (credit, employment, housing, health, legal), a decision model is decision support with meaningful human review, never the sole decider. Microsoft says so in its own docs, and in the EU these are the uses the AI Act's high-risk obligations cover, from 2 December 2027 after the Digital Omnibus deferral.

Against Haiku 5.5 and GPT-6 Luna

Small, fast LLMs classify too. Artificial Analysis ran both kinds on the same tasks in its Decision Index, published 13 October 2026.

On safety and tool choice, decision models match or beat the LLMs at a tenth of the latency. On knowledge the LLMs win by a wide margin, and decision models are overconfident there. Trust the probabilities on classification and routing, not on trivia.

What people build with them

The community catalogue Made with Jev lists 855 builds. The authors' own figures, grouped by the job the model does:

The EU question

This is where the options narrow. Jev itself has no documented EU endpoint. For EU processing today, the practical choice is Microsoft-Decision-1 on Foundry, or open weights you host yourself.

For comparison, Claude Haiku 5.5 in the EU means Bedrock EU regions or Google Cloud's EU multi-region endpoint.

Language matters less than you'd expect. On a reading benchmark covering 122 languages, Jev scored 97% in English and a median of 91% across the rest. On a French suite, no model lost more than about a point against English. The rule that does matter: keep the questions in English even when the content isn't. Translating them into Spanish cost Jev 13 points on toxicity detection. Finnish is unmeasured, so test it.

For the engineers

Three things whoever runs the model will want to know. Everyone else can skip ahead.

{
  "model": "jev-1.13",
  "state": "Help! My payouts have been failing for 3 days.",
  "questions": {
    "team": {
      "type": "choice",
      "instructions": "Which team should handle this ticket?",
      "criteria": { "billing": "Payments, refunds", "technical": "Bugs, outages" }
    },
    "urgent": { "type": "noul", "instructions": "Does the customer need a reply today?" }
  }
}

{
  "model": "jev-1.13.0",
  "answers": {
    "team": {
      "type": "choice",
      "choice": "billing",
      "probabilities": { "billing": 0.91, "technical": 0.09 },
      "confidence": 0.82
    },
    "urgent": { "type": "noul", "noul": 0.95 }
  }
}

The short version

Decision models don't replace LLMs. They replace the part of your LLM usage that was never really generation: the closed questions that decide what happens next. That part gets faster, cheaper and, most usefully, honest about its own uncertainty.

An LLM writes, a decision model decides, code acts.

Intentface is an agentic experience company. If you want to find the closed decisions hiding in your product and design what happens at each confidence level, get in touch.

Sources

• TypeSafe docs: primitives, confidence, System One API, known limitations
• Introducing Microsoft-Decision-1 and Foundry deployment docs
• OpenAI Decisions guide and data residency
• Vercel AI SDK: Decisions
• Artificial Analysis Decision Index v1.0
• Jev Decision Index: scores quoted from v0.3.2, the index is at 0.4.1 at the time of writing
• Evaluating and Benchmarking the System One Model Jev: Belebele, 122 language varieties
• DecisionBench: the same questions in French and English, five models
• Galtea: Does an AI judge need to speak your customer's language?: Spanish and Catalan, and the effect of translating the questions
• haiku-decides: Haiku 5.5 vs Jev vs OpenAI Decisions
• Phishing shadow eval and its repo: one question against five, Jev and Haiku 4.5
• Fraud email triage build by Hassan (@nutlope), archived copy
• OpenRouter in-region routing
• Made with Jev: community builds and their published figures
• Verda: GPU pricing