Docs
OfficialJev Guides & Articles
System One — docs.typesafe.ai
The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
- Format
- Docs
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
This is one of several Jev listings for the same project. The canonical entry is System One — iamaamir.
Highlights
- System One returns decisions, not replies, code, or explanations.
- Three primitives cover the decision space: Choice, Score, and Noul.
- Confidence travels with each answer so code can act, confirm, or escalate.
- Callable through the official SDKs or POST /v1/systemone.
Quickstart
python
from typesafe_sdk import Choice, Noul, Score, TypeSafeClient
client = TypeSafeClient()
response = client.system_one(
state="I was charged twice for the same order and I want my money back.",
questions={
"team": Choice(instructions="Which team should handle this ticket?",
criteria={"billing": None, "technical": None, "account": None}),
"frustration": Score(instructions="How frustrated is this customer?",
criteria=["calm", "frustrated", "very frustrated"]),
"refund": Noul(instructions="Does this message request a refund?"),
},
)Watch out
Calibration is measured across many predictions and does not guarantee that any single answer is correct.
Questions about this entry
Short answers drawn from the linked project or page.
No. It returns decisions rather than replies, code, or explanations, so it handles the classification, routing, and scoring calls a text model would otherwise be asked to make while generation stays with an LLM.
Choice, Score, and Noul cover the decision space: pick one of up to 255 options, rate against 2 to 10 ordered levels, or get one calibrated yes probability. Confidence travels with Choice and Score answers so code can act, confirm, or escalate.
Through one of TypeSafe's client SDKs or POST /v1/systemone. The model field selects which model handles the request, and the docs examples use jev-latest, which is also the SDK default.
Daniel Kahneman's Thinking, Fast and Slow: System 1 is fast and intuitive, while System 2 is slower and more deliberate. Here the emphasis is on fast, focused judgments rather than deliberate generation.
Calibration is measured across groups of predictions and means probabilities reflect uncertainty. It does not guarantee that any single answer is correct, so keep a review path for the individual cases that matter.
No. It does not write replies, produce code, or generate explanations of its reasoning. It returns typed values and probabilities, and the possible answers are defined by the primitives you supply.
Answers include the typed decision plus a confidence value, so code can decide when to act and when to escalate to a person or a reasoning model.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: How the agent stack moved in Jev's first three days
YouTube: Diogo Almeida tells swyx what System One is, why RLHF failed his automation goal, and why AI should eventually disappear.
X: The 10-step roadmap, summarised
X: Giving your agents a decision brain
More Jev resources like this
A public guide to orchestrating coding agents with TypeSafe Jev and Herdr: Jev routes tasks and scores risk, coordinator code owns policy and thresholds, Herdr runs workspaces, and agents execute bounded tasks.
Jev Guides & Articles#community#catalog-import#logicrw
Community
sherajdev/jev-researchTypeScript
sherajdev/jev-researchTypeScriptGuidance on how Jev fits coding agents: it is not a drop-in agent model, so the page routes readers to routing, rubric scoring, and truth checks instead.
Jev Guides & ArticlesDocs#official#docs#coding-agent
Official
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Jev Guides & ArticlesDocs#official#docs#api
Official
The canonical introduction: Jev is TypeSafe's flagship model and the first System One model. Send state and typed questions, get structured answers your code can use directly.
Jev Guides & ArticlesDocs#docs#official#primitives
Official
A community field guide to TypeSafe's Jev with one documented support-ticket call, runnable JavaScript and Python starters, a JSON directory, and links to independent evaluations.
Jev Guides & Articles#community#awesome-list#sdk
Community
AbdelStark/awesome-typesafe-jevHTML
AbdelStark/awesome-typesafe-jevHTMLThe Jev Day release post: Jev 1.14.0 under jev-preview plus three danger-zone features — composable images on both models, the box question type on 1.14 only, and opt-in 262k context.
Jev Guides & ArticlesArticle#official#release#vision
Official
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.