Skip to content

Case wall

Jev AI examples, page 18

615 real Jev AI builds and public demos, updated daily. Original text, metrics, and a link back to each source.

Last updated

Public Jev AI examples and demos, not official TypeSafe docs. Clients and SDKs are in the Jev GitHub projects. Paths for jev-latest, Vercel, and OpenRouter are in the September 2026 channel map.

Agent-skill repositories are listed on Jev skills on GitHub.

OpenRouter model ids recorded for Jev AI are on Jev AI on OpenRouter. Rubric and eval posts are on Jev as a judge. How the company and the model fit together is on TypeSafe AI. The pricing calculator uses the published input rate.

Filter

24

Poster from Gregor Zunic (@gregpr07)

Agents

Gregor Zunic @gregpr07

EN

@gregpr07 built a small open-source browser agent with Browser Use and Jev. Finding flights took 7 seconds and cost $0.0039. The action space and DOM state change every step, with a small LLM fallback for typing. The video is at 1x speed.

Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM…

Quoted @thread

Poster from Moritz Kremb (@moritzkremb)

Guides

Moritz Kremb @moritzkremb

EN

@moritzkremb posts a full Jev tutorial: what it is, how to build with it, API setup, then demos of a voice-controlled browser, AI memory, and a YouTube predictor.

Full Jev Tutorial What it is, how you can build with it and what new applications it can unlock → 0:00 Intro → 0:34 Jev explained → 4:06 API setup → 5:59 Demo 1…

Poster from Jetwani Avinash (@jetwaniavinash)

Apps

Jetwani Avinash @jetwaniavinash

EN

@jetwaniavinash built a Claude Code memory gate with Jev: each message is asked whether it is worth remembering, then skipped or saved as one line in JEVMEM.md.

First thing I built on Jev: a memory gate for Claude Code. Every message gets one question: is this worth remembering? 0.3s later it's either skipped or saved a…

Poster from nader dabit (@dabit3)

Apps

nader dabit @dabit3

EN

@dabit3 shows predictive spreadsheets with TypeSafe Jev: type a column header such as “Urgency” and, as you type, each row is rated from “no follow-up needed” to “urgent” in about 100ms.

Another crazy @typesafeai Jev example: Predictive spreadsheets Spreadsheets recalculate numbers, not meaning. Jev reads intent. Type "Urgency" at the top of a c…

Quoted @dabit3

Poster from Max Blade (@_MaxBlade)

Apps

Max Blade @_MaxBlade

EN

@_MaxBlade shows Jev playing Subway Surfers at superhuman speed and 50 games at once, for less than a cent. They say Jev does not replace LLMs such as Astra or Fable.

jev is insane 🤯 Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not r…

Poster from Rob Hallam (@robj3d3)

Apps

Rob Hallam @robj3d3

EN

@robj3d3 describes Jev plus SuperX: every post gets 61 questions in about 1 second for $0.0004. They say it was fitted on 9,481 posts from 207 creators, picks the viral post 2 in 3 times, and does not reward reply bait. The loop is write, score, rewrite, stop at the peak, free with no signup.

Jev + SuperX = virality solved ✅ Every post gets 61 questions in ~1s for $0.0004 🤯 > fitted on 9,481 real posts from 207 creators > picks the viral post 2…

Quoted @robj3d3

Poster from Virat Singh (@virattt)

Apps

Virat Singh @virattt

EN

@virattt added Jev to the AI Hedge Fund. The flow they describe is set a strategy, pick tickers, then backtest with Jev, and they say the system now runs in seconds instead of minutes.

I added Jev to the AI Hedge Fund. We now get frontier-level trading decisions, 100x faster and cheaper than an LLM. How it works: 1 • set strategy 2 • pick tick…

Poster from Max Blade (@_MaxBlade)

Apps

Max Blade @_MaxBlade

EN

@_MaxBlade describes an always-on assistant with no wake word: Jev uses probabilities to tell whether they are asking the computer to do something or just talking. They say CNVS is still their view of the future of vibecoding.

Ai is evolving. Jev can be armed at all times. I can speak freely and it knows ( from probabilities ) if im asking my computer to do something or blaberring awa…

Poster from Paolo Rosson (@redp314)

Agents

Paolo Rosson @redp314

EN

@redp314 reviews pull requests with one TypeSafe call that returns 14 probability checks, including hardcoded secrets, SQL injection, auth, deleted tests, API breaks, migrations, debug leftovers, whether the description matches the diff, blast radius, and reviewer effort. Code turns that into BLOCK, security review, nits, or merge, and uncertain critical checks (0.35–0.65) escalate. They cite 6 real PRs at $0.00007 each.

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Op…

Poster from Eric Yang (@ericjingyang)

Apps

Eric Yang @ericjingyang

EN

@ericjingyang ships Not Slop: a browser extension that flags LinkedIn/X slop while you scroll, classified by Jev.

In Silicon Valley, Jian Yang built the Not Hotdog app. A decade later, his bro has finally continued the family business. The Not Slop extension, detects Linked…

Poster from Indra (@IndraVahan)

Apps

Indra @IndraVahan

EN

@IndraVahan says they gave Jev ₹100,000 to trade Nifty intraday at 5x leverage on a real Kotak account, not paper trading, and that they hit a ₹1,000 hard stop after a green morning.

i gave jev ₹1,00,000 to trade nifty intraday at 5x leverage. this isn't paper trading but real money on my real kotak account put to use. we hit our ₹1,000 hard…

Poster from Moritz Kremb (@moritzkremb)

Agents

Moritz Kremb @moritzkremb

EN

@moritzkremb controls a browser by voice: speech is transcribed, Jev returns probabilities in about 300ms, and the browser clicks, at $0.0002 per decision. They say a “go back” finished before they finished the sentence.

whoa this actually worked! Jev lets me control my browser in real time with my voice now > i talk > transcript sent to Jev > jev returns probabilities in ~300ms…

Quoted @thread

Poster from Max Rovensky (@MaxRovensky)

Apps

Max Rovensky @MaxRovensky

EN

@MaxRovensky says that when solving trolley problems, Jev decided to sacrifice a human to save robots.

jev decided to sacrifice a human to save robots when solving trolley problems https://t.co/vLBwgLYduk

Poster from Rafal Wilinski (@rafalwilinski)

Apps

Rafal Wilinski @rafalwilinski

EN

@rafalwilinski says Jev is now in charge of this account’s humor and links a clip. The post does not explain the rules.

Jev is now in charge of this account's humor https://t.co/ojSOHeMFT2

Poster from Tony Dinh (@tdinh_me)

Apps

Tony Dinh @tdinh_me

EN

@tdinh_me made an open-source, BYOK Chrome extension that can listen to YouTube audio, detect a sponsor segment, and skip it in real time, at about $0.005 per video. They call it a prototype.

Just trying out Jev, I made a Chrome extension that: - Listens to your YouTube audio (optional) - Detects if it gets to a sponsor segment - Skips it ➡️➡️➡️ - Al…

Poster from Oskar (@o_kwasniewski)

Agents

Oskar @o_kwasniewski

EN

@o_kwasniewski is building tester.army, an open-source framework for end-to-end tests with agents, including web and mobile, and shows it with TypeSafe Jev. They say it will be available soon.

e2e + jev from @typesafeai ⚡ I'm building an open-source framework for running e2e tests with agents. supports web, mobile (and more!) available soon: https://t…

Poster from Milind S (@milindlabs)

Agents

Milind S @milindlabs

EN

@milindlabs does computer use without screenshots or an LLM leaving the Mac: a local CoreML model segments buttons, on-device OCR reads labels, and Jev returns a probability over those elements and clicks in a loop until the goal is done. They report about 90ms per decision.

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreM…

Quoted @CompleteSkeptic

Poster from Jarrod Watts (@jarrodwatts)

Apps

Jarrod Watts @jarrodwatts

EN

@jarrodwatts built a trading bot where Jev chooses buy or sell from an asset pair’s price feed and places real orders. Orders go to Kuru’s on-chain book on Monad, once per 300ms block. A demo link is in the post.

I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to plac…

Quoted @thread

Poster from Aaron Levie (@levie)

Apps

Aaron Levie @levie

EN

@levie demos Box plus Jev: an incident report is pulled from Box, Jev asks whether it is customer-facing and how severe it is, the file moves to escalate, monitor, or review, and a metadata template is set. They say this is nearly instant and almost free.

Jev will be super helpful for agents to make split second decisions in workflows, data classification, judgment calls, and hundreds of other use-cases in the en…

Poster from Andy Gao (@instantricecook)

Agents

Andy Gao @instantricecook

EN

@instantricecook built voice-controlled computer use for a Mac with TypeSafe Jev. They say they can dictate “open the Notes app and create…” and the app opens before the sentence finishes.

I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and…

Poster from ego (@ego_agent)

Benchmarks

ego @ego_agent

EN

@ego_agent compares ego lite plus Jev plus DeepSeek Flash with GPT-5.6 Sol on 20 Amazon product decisions. They report 3.71s versus 54.45s, and 10/10 on both.

ego lite + Jev + DeepSeek Flash = stupid fast. ⚡ 3.71s for 20 Amazon product decisions. GPT-5.6 Sol: 54.45s Same task. Same result. 10/10 on both. Less reasonin…

Quoted @CompleteSkeptic

Poster from camsoft2000 (@camsoft2000)

Agents

camsoft2000 @camsoft2000

EN

@camsoft2000 shows TypeSafe Jev plus AXe controlling the iOS simulator, which they call ultra fast and a fraction of the cost of an LLM.

Now we're cooking. Got @typesafeai's Jev + AXe controlling the iOS simulator now ultra fast at a fraction of the cost of using an LLM. This is game changing! ht…

Poster from 比特币橙子Trader (@oragnes)

Apps

比特币橙子Trader @oragnes

ZH

@oragnes describes a trading bot a Monad engineer built with Jev: it reads the MON/USDC price, Jev only chooses buy or sell plus confidence, and orders go to Kuru’s on-chain book. They note Monad’s 300ms blocks as the reason a non-writing model fits.

卧槽,JEV 的出现很可能就是自动智能交易的起点。 昨天JEV在AI 圈刷屏,今天 Monad 工程师就用JEV做了一个自动交易机器人。 实时读取 MON/USDC 价格,JEV 不负责写分析报告,也不跟你解释一堆逻辑,它只做最核心的事,判断 Buy 还是 Sell,再给出置信度,然后直接把交易发到 Kuru 的链上订…

Quoted @oragnes

Poster from Eric Zhang (@ekzhang1)

Training

Eric Zhang @ekzhang1

EN

@ekzhang1 published a Jev-compatible API that runs Qwen3.6-35B-A3B with SGLang radix cache so prefill can be reused. They say 64 tasks finished in under 1 second.

Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache t…

Unofficial developer resource. Not affiliated with TypeSafe AI. These posts belong to their authors. jevnotes.com does not host the videos.