Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Explore the Jev ecosystem.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Watch & learn
Video guides.
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
Experiments.
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.
The directory03 / 03 · Experiments
Find something worth exploring.Experiments
Every category, from games and tools to repositories and writeups, traced to a primary source.
Real-time research powered by
Same ideas.
Different paths.
This is the full registry, not just the featured picks. Figures like speed, cost, and stars are maker-reported or captured snapshots, not JevMade measurements.
33 experiments
Build thirteen Jev tools across twelve notebooks, from routing and scam checks to agent guards, vulnerability scans and evaluation gates.
SOURCE SCREENSHOTEXPAND ↗
An introduction to Jev and its unusual restriction: it can decide, but it can't write an answer.
SOURCE SCREENSHOTEXPAND ↗
AINews examines the tradeoff behind Jev: give up free-form answers to get fast decisions with probabilities.
SOURCE SCREENSHOTEXPAND ↗
Search for a flight with Jev choosing browser actions and a small language model filling in text only when needed.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Breaking: Browser Use + Jev = Ultrafast ⚡
Findings flights took 7s and cost only $0.0...
Developers discuss TypeSafe's claim that software needs an AI model for decisions, not another chatbot.
SOURCE SCREENSHOTEXPAND ↗
Gabriel Anhaia builds a TypeScript ticket router with Jev and unpacks the launch claims.
SOURCE SCREENSHOTEXPAND ↗
These field notes compare zero-shot Jev with an internal fine-tuned classifier and inspect the confidence scores.
SOURCE SCREENSHOTEXPAND ↗
from the source
“was pumped to get early access to @typesafe_ai's Jev, pointed it at an internal benchma...
Daniel White explains Jev and its typed-question API in a 34-second video.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Spent the evening making sense of this, so here's Jev in 34 seconds.
Super excited to...
Steve Krouse introduces TypeSafe Typewriter, a live demo that asks Jev sixteen questions about your text as you type.
SOURCE SCREENSHOTEXPAND ↗
from the source
“typesafe's jev is fun! live demo you can play with: https://t.co/ctnPF0w70r" / X”
Mizchi pits two Jev players against each other in gomoku and documents the match in Japanese.
SOURCE SCREENSHOTEXPAND ↗
The Neuron explains how Jev's structured, confidence-bearing decisions differ from chatbot responses and where they fit in workflows.
SOURCE SCREENSHOTEXPAND ↗
Anthony Maio makes the case for Jev as a software component, while questioning claims about a model that cannot hallucinate.
SOURCE SCREENSHOTEXPAND ↗
TypeSafe cofounder Diogo Almeida explains why he spent two years building a model that makes decisions instead of writing text.
SOURCE SCREENSHOTEXPAND ↗
from the source
“After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not l...
Mike Taylor gives Jev his writing to judge and considers what the same approach could do for agent reviews.
SOURCE SCREENSHOTEXPAND ↗
Agent Journal compares one holistic judge call with twelve Jev-derived features across three classification tasks.
SOURCE SCREENSHOTEXPAND ↗
A technical introduction to building software around Jev's choices, scores and yes-or-no answers.
SOURCE SCREENSHOTEXPAND ↗
The Register looks at TypeSafe's bid to build AI for software rather than conversation, with Doom as a launch demo.
SOURCE SCREENSHOTEXPAND ↗
An introduction to Jev's decision-only API, calibrated probabilities, response times and pricing.
SOURCE SCREENSHOTEXPAND ↗
A Japanese take on Jev's launch that asks how much of the same behavior a conventional language model can reproduce.
SOURCE SCREENSHOTEXPAND ↗
Mohammed Shehu walks through Jev's decision-making API and shows how to call it from Python.
SOURCE SCREENSHOTEXPAND ↗
Dorian Smiley reports exhausting $5 of free Jev credit only after processing 123 million tokens.
SOURCE SCREENSHOTEXPAND ↗
Nicolay explains how agents can use Jev’s typed answers and calibrated probabilities as branches around an LLM.
SOURCE SCREENSHOTEXPAND ↗
Josh Rosen rounds up the first two weeks of JevOps — decision-model calls showing up in telemetry, incident response, SRE agents, CI, and deploys — and argues DevOps is packed with exactly the small semantic judgments Jev is built for.
SOURCE SCREENSHOTEXPAND ↗
Does Jev hold up outside demos? Glean's team benchmarked it on four workloads they run in production and published the wins next to the losses — routing came out ahead of their LLM router, reranking did not beat their search stack.
SOURCE SCREENSHOTEXPAND ↗
The weekly How I AI digest leads with Claire Vo spending a week inside Jev: nine cents to make sense of two years of ChatPRD pull requests, about four dollars for 200,000 classifications, and a working answer to which tasks still deserve a frontier model.
SOURCE SCREENSHOTEXPAND ↗
Claire Vo opens the hood on her week in Jev: nine cents to classify two years of ChatPRD pull requests, her Claude and Codex sessions sorted in minutes, and a real-time voice app where the quote API, not the decision model, was the slowest part.
SOURCE SCREENSHOTEXPAND ↗
A red-team of Jev 1.13 got it to approve harmful tool calls 70.1% of the time under direct misuse and 43.5% under indirect injection. The fix has a nice shape: Jev re-judges its own tool calls before they run, and both attack rates roughly halve.
SOURCE SCREENSHOTEXPAND ↗
Mr. Buzzoni maps an agent’s small decisions to Jev, sends uncertain cases to Kimi K3, and keeps irreversible actions with people.
SOURCE SCREENSHOTEXPAND ↗
The New Stack reports on OpenAI’s Luna-based answer to Jev: an API that picks predefined answers instead of writing prose.
SOURCE SCREENSHOTEXPAND ↗
The New Stack follows Jev’s launch, Vercel’s early adoption figures, and a developer who asks the text-only model to recognize drawings.
SOURCE SCREENSHOTEXPAND ↗
Vercel charts Jev’s first day on AI Gateway, reporting use by nearly 13% of paid teams within 24 hours.
SOURCE SCREENSHOTEXPAND ↗
Vercel announces Jev on AI Gateway and shows how its AI SDK turns a support case into typed decisions.
SOURCE SCREENSHOTEXPAND ↗
A short concept thread proposes converting learner and model language into numerical features using Jev, then fitting a tabular model to learner outcomes.
SOURCE SCREENSHOTEXPAND ↗
Jev, briefly
A decision model, not a chatbot.
A chat model generates text token by token and hopes you parse it. Jev never generates a word. Your code sends the state of the world plus typed questions; Jev returns every answer in one parallel pass — typed values with calibrated probabilities and a confidence score your code can trust. About 70–500 ms end to end, $0.042 per million input tokens, output free. Trained with what TypeSafe calls Reinforcement Learning for Calibrated Decisions.
choice Pick one of these.
You define the options. Jev returns the chosen option, a probability for every option, and a confidence. The workhorse of routing, agents, and games — the answer space is always legal, so there is nothing to parse and nothing to hallucinate.
score Rate this on a rubric.
You describe ordered levels — say trivial / normal / critical. Jev returns the level, the probability of each, and a confidence. Scores turn fuzzy judgment (“how severe is this log line?”) into a number-free decision your code can branch on.
noul Is this statement true?
You assert a statement; Jev returns the probability that it is true — a noul. Moderation, verification, guardrails, “does this diff actually fix the bug?”: one question, one calibrated probability.
Official material lives at typesafe.ai and docs.typesafe.ai. JevMade is an independent community registry — not affiliated with or endorsed by TypeSafe AI.
Recurring lessons
Patterns that keep showing up.
One decision per tick
Games, drones, trading bots, and browser agents all converge on the same loop: serialize the state, ask one decisive question, act, repeat. Jev’s latency makes the loop feel instant — the model lives inside the control loop, not outside it.
Confidence as a gate
The answer says what; the confidence says whether to act. The most reliable entries threshold on confidence to route edge cases to a slower model or a human — automation with an honest escape hatch.
Shrink the choice space in code
Makers rarely ask Jev to pick from everything. Local tactics prune 225 gomoku moves to ~40; DOM filters turn a page into an element table; code narrows options, Jev judges within them.
Jev judges, LLMs talk
A recurring split: Jev makes every decision cheaply and instantly, and a small LLM is only invoked when a human-facing string must actually be written. Decision and generation are separate budgets.
Made something with Jev?
Send the link — repo, live demo, post, or video — plus a line on what it does and which primitives it uses. Every entry is verified against its primary source before it ships.
Submit your experimentSign in first so we can reply to you. Submissions are reviewed, not published automatically.