Case wall
Jev AI examples, page 5
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.
No posts match these filters.
@AIchen6666 released dsh-decide, a DeepSeek Harness plugin that calls decision models rather than chat models and returns a probability, an option or a score, with TypeSafe Jev among the providers.
这两天做了一个 DeepSeek Harness 插件:dsh-decide,用来接入决策模型(不是聊天模型),对给定状态做结构化判断,返回概率 / 选项 / 分数。 目前支持 TypeSafe Jev、基元律动 NeoHorse-Jev、OpenAI Decisions,以及本地 System One;并提供 `de…
@ericosiu runs recruiting outbound bots from Slack across five sourcing channels. After do-not-contact, title, and tenure checks, interested candidates get seven questions and Jev scores the answers. A daily funnel report lands in Slack; campaigns auto-pause above a 2% bounce rate.
Our talent bots run recruiting outbound 7 days a week from 5 sourcing channels (and any campaign that bounces over 2% pauses itself) I broke down how it works ↓…
@Bobo_hashtag introduces Flide, open-source inference infra that batches many Jev-style decision questions about one artifact in a single pass.
Flide is open-source inference infra built for Jev-style decision models. Your agent asks Jev 18 questions about one article. Most engines run 18 prompts. Flide…
@franzbruckhoff had a marketing agent use Treg’s Jev-powered social API to classify TikTok comments about nature sounds for sleep.
I asked my marketing agent working on social media observation to try Treg's new Jev-powered social-api to monitor what people are saying on TikTok about using…
@Max684229882063 introduces Euroscope, Jev-powered search and analysis over official European macro data. Ask about inflation, rates, wages or unemployment in any EU country and the official figure appears as you type. Free to use, open-source next week, at macro-search.vercel.app.
Introducing a small weekend project: Euroscope, Jev-powered fast search and analysis over official European macro data. Ask about inflation, rates, wages or une…
@teivah's RSS reader has 1,457 unread posts, so he built Barista. Tell it what you like to read, in plain English, with no fixed categories. Every day it emails only the posts worth your time. Part 1 is how it works: Postgres, embeddings, and Jev.
My RSS reader has 1,457 unread posts. So I built Barista ☕. Tell it what you like to read, in plain English (no fixed categories). Every day, it emails you only…
@maelcaldas put up a public spec at opensystemone.org to drive local System One implementations as calls spread across scripts, services and apps. He hopes @Cloudflare, @typesafeai and @OpenAI later converge on something structured, like Open Responses.
Ok, this is really important as we start spreading calls all over scripts, services and apps. I took some time to setup a public spec, so we can use to drive ou…
Quoted @maelcaldas
@ryanvogel built an X-signed-in app that ranks each reply's spamminess with Jev, then auto-mutes those accounts and removes the comments.
i built an app that you can sign in with you X account and every reply you get on a post it ranks the spamminess with Jev then it auto mutes those accounts and…
@brunocabado built Decision Lab and ran JEV against LLMs on support tickets he labeled himself. He writes that decision models answer classification questions with a probability per option instead of generated text. The linked page is titled "Decision models vs LLMs: JEV, measured on tickets".
Decision models like JEV answer classification questions with a probability per option instead of generated text. I wanted my own numbers before using them, so…
@michaelhrobersn shows a fall-detection demo for an AI eldercare camera: a rolling 20 seconds of frames, then Jev Image to judge how quickly someone went down, how they fell, and whether they are getting back up.
@typesafeai fall detection demo of an AI eldercare camera we’re working on. we keep a rolling 20 seconds of frames and use Jev's Image to figure out how quickly…
@waynesutton says that for a speedrun and YC27 application perk, Jev reviews uploaded email confirmations to see whether people are trying to game the system.
When I build new growth projects, I always build them so agents can automate tasks, with a human-in-the-loop process. For the speedrun and YC27 application perk…
Quoted @waynesutton
@helloiamvu built plain-English search over 12k+ stocks/ETFs by classifying facts from 49k SEC reports, joining financials and 22m prices, then using Jev to interpret the query.
Another cracked search I built with @mostlyrightmd. I extracted and classified facts from 49k SEC reports, embedded text, joined financials and 22m prices, then…
@sardine says Jev caught 27 of 29 fraudulent transactions in a September fraud ring, the most of any approach they tested, and that Jev is now a node in Sardine Flow.
We ran Jev, TypeSafe AI's new System One model, on a fraud ring that hit one of our customers in September. Jev caught 27 of the ring's 29 fraudulent transactio…
@ClementHu666 introduces EasyHire AI, a recruiting agent powered by Jev: one line scores 1,286 candidates from 30+ sources in 60 seconds. Jev scores each profile with evidence and flags the unsure ones.
Introducing EasyHire AI @easyhireai: a Jev @typesafeai powered recruiting agent 1-line brief → 1,286 scored candidates from 30+ sources in 60s. No more week-lon…
@lambda1666 shipped Sketch Sprint: a 2-minute drawing game where Jev guesses your doodle live from image input, with a 55% AI line to beat and friend challenge links on Cloudflare.
Made a drawing game where Jev guesses your doodle live while you draw ✏️ Beat the AI's 55% line to score. 2 min, or challenge a friend with a link. https://sket…
@nolansym shows a "Jev JSON Render" pattern: English in, UI out. It picks prepared fields and never writes new copy, and the preview can be edited after it composes. Built with AI SDK v7 and the shadcn registry.
New AI Pattern - Jev JSON Render 🤝 English in, UI out. ✅ Picks prepared fields, never writes new copy ✅ Edit the preview after it composes built with: @aisdk v7…
@nicky_sap says Trivy files new findings as Linear tickets, and a Jev classifier on the @cvedotnow feed decides whether a CVE touches their stack. If it does, an agent opens a fix branch and auto-merges when review is green.
How we're handling the deluge of CVEs: Trivy triages new findings into Linear tickets, and we stream the @cvedotnow feed into a Jev classifier that decides in n…
@noahsark769 had @typesafeai Jev look at and categorize all ads for the top 680 brands on @replohq's industry landscape list. About 67% of these brands have some ads with customer quotes, and of those brands about 4–10% of the ads they're running have customer quotes.
dove deep into this to figure out how many of the top brands are doing this type of ad. I had @typesafeai Jev look at and categorize all ads for the top 680 bra…
@_sarant turned a personal Google-to-Excel job script into a realtime Convex website anyone can use, made with Convex, Firecrawl, Jev, and coss-ui.
I used to find jobs with a tiny script I wrote that searched Google and pulled out the exact results I wanted, and manually wrote to an excel sheet. So I turned…
@schwentker shows a TypeSafe Jev experiment where a store catalog API talks a shopping agent out of a $149 sale: return risk 2/2 at 100% confidence, and no human in the loop.
Continuing experiments w/ @typesafeai Jev. Imagine software that can tell another piece of software "don't buy this" & attach a confidence score. A store's cata…
@willcraigz built Jarvis to run voice commands on his Mac, and the repo is now public. He wrote about where Jev helps, what still needs an LLM, and what went wrong. The GitHub link and install instructions are in the article.
I built Jarvis to run voice commands on my Mac, and the repo is now public. I wrote about where Jev helps, what still needs an LLM, and what went wrong. GitHub…
@rawkode built a Linux / GPUI Gmail client that uses TypeSafe Jev to detect phishing and spam and to suggest which labels mail should get.
I've built a Linux / GPUI Gmail client with @typesafeai Jev integration for detecting phishing, spam, and it even tries to determine which of your labels it sho…
@robomotionio says they built an Automated QA Test Suite app with Jev in three prompts. It runs tests with Jev and RPA, surfaces flaky tests, and decides whether a release should ship or hold.
We built an Automated QA Test Suite app with Jev. In just 3 prompts. The result is a fully functional QA app that: ✅ Imports test cases from spreadsheets …
@rperry_ says an Agent SDK bot that lets Jev make decisions beat a Level 9 CPU in Smash Melee after 13 training games, rising from Level 1.
Yesterday I tried Jev for the first time and already today my Agent SDK bot with Jev making its decisions beat a Level 9 CPU in Smash Melee! It only took 13 gam…