Skip to content

Case wall

Jev AI examples, page 24

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 Thiago Brezinski (@thiagobrez)

Apps

Thiago Brezinski @thiagobrez

CS

@thiagobrez posts a live TypeSafe Jev demo at AgentConf. The text does not describe what the demo does.

Live @typesafeai Jev demo at @AgentConf https://t.co/y3UpKP2e4z

Poster from Lomesh Dutta (@lomeshdutta)

Agents

Lomesh Dutta @lomeshdutta

EN

@lomeshdutta open-sourced a Skill Router built with Claude and TypeSafe Jev. They have about 90 Claude Code skills and use maybe five, so the router is meant to surface a skill Claude would not call on its own.

Just hacked a fun little project - Skill Router (Open source) using Claude and Jev @typesafeai Why? I have ~ 90 Claude Code skills installed and use maybe five.…

Quoted @CompleteSkeptic

Poster from Zhe (@iamzhe)

Agents

Zhe @iamzhe

EN

@iamzhe says minirouter/fusion is live: it classifies each request with TypeSafe Jev, then routes to a model matched to type and complexity. Codex lists their presets and routers in the model picker. They also fixed long prompts not caching automatically in Claude Code.

Small update for https://t.co/xXR4JLt377 today: 1. minirouter/fusion is live. It classifies each request with Jev by @typesafeai, then routes to a handpicked mo…

Poster from Arik Chakma (@imarikchakma)

Apps

Arik Chakma @imarikchakma

EN

@imarikchakma built a syntax highlighter with TypeSafe Jev that they say can highlight any language, including one they made up.

Built the ultimate syntax highlighter using @typesafeai Jev (i mean why not). It can highlight any language, even one that I made up.

Poster from kazuki🄽Notion (@kzkhykw)

Agents

kazuki🄽Notion @kzkhykw

JA

@kzkhykw used TypeSafe Jev to judge local Whisper transcripts and automate a Mac. Chrome pages use a browser harness; Slack and Notion are seen and operated through Mac accessibility. They say the implementation was done with Grok 4.6 only.

. @typesafeai のJevを使って、Local Whisperの文字起こしを都度判定して、Macbookのローカルコンピュータの操作を自動化して、あれこれするのやってみました! Chrome のページは Browser Harness、Slack やNotionは Mac の Accessibility で認…

Quoted @kzkhykw

Poster from Aditya A. (@iamAdityaAnjana)

Apps

Aditya A. @iamAdityaAnjana

EN

@iamAdityaAnjana used Jev to write C++ by giving it only the grammatically valid next tokens at each step and letting it pick one. They got a working fragment, and say it is slower and worse than a code model and is a novelty, not a recommended way to write code.

Ran a dumb experiment last night: used Jev by @typesafeai (a decision/classifier model, not a text-gen model) to write C++. At every step I gave it the finite s…

Poster from Peter Wang (@the_cyw)

Apps

Peter Wang @the_cyw

EN

@the_cyw says they are building egocentric training data for physical AI and that Jev QA’d 58,643 action labels in under 3 minutes for 90 cents.

Jev is insane. We are building egocentric training data for physical AI. Jev QA'd 58,643 action labels in under 3 minutes. 90 cents. A friction cost of the Clau…

Poster from Juris (@Juris_Savos)

Apps

Juris @Juris_Savos

EN

@Juris_Savos shows Jev playing Balatro. Each hand it sees the cards, jokers, and blind, then picks play or discard in about 200–500ms, and shops after the ante. They say a full run costs less than a cent.

Jev from @typesafeai plays @BalatroGame. Every hand it sees the cards, jokers, and blind, then picks play or discard in ~200–500ms. After the ante, it shops too…

Poster from Adrián Mato 🐙 (@adrianmg)

Apps

Adrián Mato 🐙 @adrianmg

EN

@adrianmg switches a game between manual and Jev-driven play at 2–3 calls per second at 60 FPS, with about 150ms average latency. They say the interesting part was turning the game into variables, actions, and criteria, such as whether to risk a powerup or protect the ball.

Had some fun taking Jev from @typesafeai for a spin, switching seamlessly between manual and AI-driven gameplay. It’s clocking 2–3 calls/sec at 60 FPS, with ~15…

Poster from Kaushik (@0xkaushik_k)

Agents

Kaushik @0xkaushik_k

EN

@0xkaushik_k built JevScope, which watches an agent and asks Jev whether each step is aligned, progress, repetition, or stuck, then plots that over time. They describe a coding agent stuck on a race condition where the curve shows it and no log line says “I’m stuck.” Code is said to be coming.

Got early access to @typesafeai Jev and spent a few hours building on it. The problem I keep hitting: agent traces tell you which tool ran, how long it took, wh…

Quoted @CompleteSkeptic

Poster from Bolha Dev (@BolhaDevs)

Notes

Bolha Dev @BolhaDevs

UND

@BolhaDevs posts about the Jev model (Jevons paradox) and TypeSafe’s RLCD, reinforcement learning for calibrated decisions, with a link. The text does not describe a build.

o modelo jev (paradoxo de jevons) com RLCD (reinforcement learning for calibrated decisions) da typesafe ai https://t.co/aGwtQkbJyj

Poster from Mnimiy (@Mnilax)

Agents

Mnimiy @Mnilax

EN

@Mnilax put Jev between GPT and themselves to kill drafts that broke their rules. Jev then stopped answering, and the agent treated silence as safer and sent nothing until a second agent unstuck it. They list branches for a quiet checker: pass it tagged unverified, hand the span to a big model, queue and retry, or wake a human if the action is irreversible.

it's f*cking insane Jev sat between GPT and me, killing every draft that broke my rules before i saw it. good setup. then Jev did not answer. the agent decided…

Quoted @Mnilax

Poster from Ekene Eze (@kenny_io)

Notes

Ekene Eze @kenny_io

EN

@kenny_io demos Thally creating a GitHub docs repo tied to the products it documents. They say they are now exploring how TypeSafe could make that workflow more efficient. The post does not say Jev is already wired in.

One of the popular requests since launching @thallyio is a demo of how it works. So here it is! Thally can create a new docs repository on your GitHub account,…

Quoted @kenny_io

Poster from Yuntian Deng (@yuntiandeng)

Training

Yuntian Deng @yuntiandeng

EN

@yuntiandeng describes ProgramAsWeights: small neural programs for fuzzy judgments, compiled from English descriptions, combined with code for control flow. One example joins 30 programs and a decision tree into a course-website helper that looks like a chatbot but runs locally, including a question such as which specialist should receive the query.

I increasingly think future software will combine code for control flow with small neural programs for "fuzzy" judgments. That's what I've been exploring with P…

Quoted @CompleteSkeptic

Poster from Norbert Bodziony 🇵🇱 (@norbertbodziony)

Apps

Norbert Bodziony 🇵🇱 @norbertbodziony

EN

@norbertbodziony built a moderation guard on TypeSafe Jev and links a live demo at guard-jev.vercel.app. They call it fast and accurate; the post does not include a measured score.

i have created moderation guard based on typesafe's jev its fast and accurate live demo you can: https://t.co/FquTJtWCzq https://t.co/PyNNZGu0iW

Poster from Parth (@mittalparth_)

Apps

Parth @mittalparth_

EN

@mittalparth_ shows TypeSafe Jev playing Chrome Dino. They report about 280ms average response, 116M tokens spent, $4.65 cost, and decisions to jump, run, or duck with a confidence score from a snapshot of the runner. A repo link is in the post.

@typesafeai jev playing chrome dino! the model is incredibly fast! - avg response time: ~280ms - spent 116M tokens - cost? just $4.65. - the input here is a sna…

Quoted @thread

Poster from Daniel White (@dwhitedesign)

Guides

Daniel White @dwhitedesign

EN

@dwhitedesign posts a 34-second explainer made after spending an evening making sense of Jev, and says they want to build with TypeSafe.

Spent the evening making sense of this, so here's Jev in 34 seconds. Super excited to build some incredible things with @typesafeai what a time to be alive... h…

Poster from Melvin Vivas (@melvindvivas)

Guides

Melvin Vivas @melvindvivas

EN

@melvindvivas lists 9 use cases they thought of for Jev. The post text itself does not enumerate them.

9 Use Cases I thought of for Jev Hope you find it useful

Poster from Prakshal Jain (@prakshaljain_)

Apps

Prakshal Jain @prakshaljain_

EN

@prakshaljain_ describes Yappy from MitosisLabs, a Mac agent that fills job applications, taxes, and forms, sped up with Jev. Their comparison versus a competitor is 1m 54s versus 13m 14s, 22 versus 104 LLM calls, and about $0.24 versus $4.24.

Jev by @typesafeai turns your  Mac into an AI agent... what this means for You ? - Jev, a new model from a ChatGPT co-inventor, can operate computer tools in r…

Poster from amit (@legitamit)

Apps

amit @legitamit

EN

@legitamit used Jev to make an audience of 100 personalities at 1v100.fun. Each blob has its own personality and makes a Jev call whenever you talk, to decide if it is bored. They say a round costs under $0.01.

I used Jev to make an audience of 100 personalities to yap to. Each blob has its own personality and makes its own Jev call every time you talk to decide if it’…

Quoted @thread

Poster from SamG (@SamGCoder)

Apps

SamG @SamGCoder

EN

@SamGCoder tests TypeSafe as the decision layer for an AI game companion. It reads the player’s message and game context and returns an action, destination, and confidence. Game code moves the character; dialogue is prewritten.

Testing @typesafeai Testing TypeSafe as the decision layer for an AI game companion. It reads the player’s message and game context, then returns an action, des…

Poster from Sam Enoka (@maybe_im_sam)

Apps

Sam Enoka @maybe_im_sam

EN

@maybe_im_sam wired TypeSafe into a three.js action game as an AI co-op partner. It reads game state and chooses when the bot should engage, regroup, survive, or escape. They say the demo was about an hour of work and about 10 minutes of playtesting cost about $0.02.

Woke up with early access to @typesafeai and was super excited to try. Got a demo cooking before work this morning where typesafe drives an AI co-op partner in…

Poster from Jon Kraayenbrink (@kraayenJon)

Apps

Jon Kraayenbrink @kraayenJon

EN

@kraayenJon says Jev checked a website for 35 tells of AI slop in 243ms for $0.00015, including purple gradients, emoji headers, the word “seamlessly,” fake testimonials, and bento grids. The free tool is at madewithjev.com/free-tools/ai-slop-detector.

jev is INSANE. in 243 ms it checked a website for 35 tells of ai slop. purple gradients. emoji headers. "seamlessly". fake testimonials. bento grids. the works.…

Quoted @CompleteSkeptic

Poster from Ashutosh Mathore (@ashutoshftw)

Agents

Ashutosh Mathore @ashutoshftw

EN

@ashutoshftw built a semantic circuit breaker so agents that try different actions from the same wrong assumption still get stopped. In one stuck run they report 12 model calls down to 4 and 19.9K tokens down to 5.1K.

Jev unlocked a new way to stop AI agents from spinning. Agents do not always repeat the same action. Sometimes they try different things based on the same wrong…

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