The short version
A System One model is a class of AI model built to make fast, structured decisions that software can use directly. That is TypeSafe AI’s own wording, and TypeSafe coined the term.
You hand the model some content and a set of typed questions. It hands back answers that match those types, plus a probability for every possible answer. It does not write a reply, produce code, or explain itself. The docs put it plainly: System One models “do not write replies, produce code, or generate explanations of their reasoning.”
Where the name comes from
Daniel Kahneman’s Thinking, Fast and Slow splits human thought in two. System 1 is fast and intuitive. You see a face and know it is angry before you could say why. System 2 is slow and deliberate. You multiply 17 by 24 on paper.
TypeSafe’s launch post borrows that split, contrasting “fast, intuitive System 1 thinking and slow, deliberate System 2 reasoning.” The claim is about the shape of the task, not about what happens inside the model. Sorting a support ticket into one of five queues is a System 1 task for a person. Writing the reply is not.
Kahneman was describing people. Nobody has shown that a model trained on these tasks works the way human intuition works, and the Thinking, Fast and Slow entry keeps that distinction clear.
What comes back
Three things, depending on the question type. A typed answer: the option you defined, a number on the scale you defined, or a probability. A full probability distribution over the options you gave. And, for two of the three question types, a confidence value between 0 and 1.
Confidence is not a second opinion from the model. TypeSafe describes it as “a statistic computed from the probability distribution the answer already gives you.” A tight distribution means high confidence. A flat one means the model is guessing. Your code decides what to do about it, which is the whole point of confidence gating.
The three primitives
Every question you ask is one of three shapes.
Choice picks one option from a list you define and returns the winner, a probability for each option, and a confidence value. It takes up to 255 options.
Score places the content on an ordered scale you define. It needs at least 2 levels and takes at most 10. The returned score is the probability-weighted mean of the level numbers, so it can land between levels: (0 x 0.0) + (1 x 0.70) + (2 x 0.30) gives 1.30.
Noul asks a yes/no question and returns a single number from 0 to 1, the probability that the answer is yes. It returns no separate confidence value, because the probability already is one. The docs do not explain where the name came from.
The Choice, Score and Noul guide works through a full example of each.
Why they cannot hallucinate free text
A System One model never generates prose, so there is no sentence in which it can invent a citation, a policy number, or a customer name. The output space is the set of options you wrote down. That is a real property.
It is also a narrow one. The model can still be wrong. It can pick the wrong option with high confidence, or return a probability that does not match how often it is actually right. TypeSafe publishes a per-version page of known weaknesses it calls jaggedness, and the jaggedness guide lists the ones that bite hardest: Jev 1.13 reads questions literally, is weak at arithmetic and counting, “reads dates as text, not as ordered quantities,” and by default treats everything in the input as data rather than as potentially hostile. Losing free-text hallucination does not buy you correctness.
How they differ from LLMs and reasoning models
An LLM predicts the next token, then the next, conditioned on everything before it. Ask it to classify something and it still runs a generation loop to produce the word “billing.” A reasoning model does more of that loop, spending extra tokens on intermediate steps before it answers.
A System One model skips the loop. TypeSafe says Jev “generates all outputs in a single query” rather than one token at a time. Its architecture is unpublished, so how that is done is a guess for now. See how Jev is built for what is known and what is not.
The practical differences: an LLM returns a string you have to parse and validate, a System One model returns a typed value you can branch on. An LLM gives you a token log-probability if you dig for one, a System One model gives you a calibrated distribution as the primary output. The side-by-side comparison covers cost, latency and failure modes.
Where they fit in a stack
Inside the code, not around it. TypeSafe’s own framing is that the model “does not generate code or choose its own next action.” You keep the control flow, the thresholds and every side effect. The model answers narrow questions about state you assembled.
A typical shape: a System One model decides which queue a ticket belongs in and how urgent it is, your code applies the routing rules, and an LLM writes the customer-facing reply once the decision is made. The two model types are not competing for the same slot. Confidence-gated actions and LLM guardrails are two of the places this pattern shows up most often.
Jev, and what comes after it
Jev is the first and, as of 18 September 2026, only System One model on the market. TypeSafe announced it on 15 September 2026 alongside a $40M seed round led by DCVC. Access is a closed managed API in early access off a waitlist, and the weights are not released. Jev explained covers the specifics, and the examples directory tracks what people have built with it.
Whether a second vendor ships one is open. The pieces are not exotic: a small model, a training objective that rewards calibrated probabilities, and an API that returns types. Several open reproductions appeared within days of the launch. What none of them have is TypeSafe’s training method, RLCD, which has no published paper or dataset.
FAQ
Is a System One model an LLM?
Not in the usual sense. It takes text input and makes judgments about it, but it does not generate text. TypeSafe has not published Jev’s architecture, so whether a transformer language model sits underneath is unknown. Treat “System One model” as a description of the interface and the training target rather than the internals.
Can a System One model hallucinate?
It cannot invent free text, because it never writes any. Its answers are always members of the option set you defined. It can still choose wrong, and it can return a probability that does not match its real accuracy. TypeSafe documents nine known weakness areas for Jev 1.13, including arithmetic, counting and date comparison.
Do I still need an LLM?
Usually yes. A System One model decides; it cannot draft an email, write code, or summarise a document. The common pattern is a System One model making the routing and gating decisions inside your code, with an LLM handling any text a human will actually read.
What does calibrated mean here?
A model is calibrated when its stated probabilities match reality: of all the answers it gives at 80% confidence, roughly 80% should turn out correct. That property is what lets your code set a numeric threshold and trust it. TypeSafe has not published a calibration error figure for Jev.
Who else sells a System One model?
Nobody, as of 18 September 2026. TypeSafe coined the category name and shipped the only product in it. Open-source reproductions such as openjev and open-jev appeared within days, but they are community projects built on other models, not vendor products with their own training method.