Curated by AY Automate
What people are building with Jev
1,305 public builds, tests, repos and guides from X, LinkedIn and GitHub in the first days after TypeSafe launched Jev on September 15, 2026, sorted by use case. Numbers are each poster's own claims. We include the tests where Jev fell short.
Diogo Almeida@CompleteSkepticAfter co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I've spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Sort byEvery build is scored by Jev itself: specificity, real build, verifiable, hype, exaggeration.
Kev 0.5B open Jev-like model on Qwen
Jared Palmer@jaredpalmerKev-0.5B: A tiny open source Jev-like decision model with a TypeSafe-compatible API based on Qwen2.5-0.5B that you can train and run on a MacBook Pro. Model card and weights are available on GitHub
Limits and counterpoints
Jev score 89Memory relevance check: faster but 27% costlier
Benchmarked Jev with a fallback model against GPT-5.6 Luna on deciding which passages support a question. Same accuracy and faster, but the fallback route cost more.
708ms vs 5,690ms median, 78 of 81 correct (poster's figure)
Classifying 1,018 research papers for eight cents
Hassan@nutlopeI used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on The summaries cost $3.99 on @togethercompute. The classifications cost $0.08 on @typesafeai. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the
Trading bot placing on-chain orders every 300ms
Jarrod Watts@jarrodwattsI 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 place the orders on Kuru's on-chain order book in every 300ms block. Demo link →
Games and simulations
Jev score 83Jev directing cars at city junctions
In a browser city scene, Jev decides which waiting car goes next at each junction from JSON state. Collision avoidance still uses plain rules and behavior is chaotic.
About 350 ms per request, about $0.001 per minute of traffic (poster's figure)
Tools and demos
Jev score 83Dubium returns true or false percentages
A small app answers typed or spoken questions with a probability using Jev, aimed at showing the model's uncertainty rather than replacing search.
Evals and judging
Jev score 80Local Jev stand in benchmarked across several models
GitHub Next@GitHubNextNot everyone on the team has access to Jev yet. Spent a morning cobbling together a poor man's Jev on top of omlx for local use. Benchmarked and eval'ed a variety of models including diffusiongemma and a variety of autoregressive models (Qwen MoE, Gemma 4 MoE, and Gemma 4 e4b/e2b.) Benchmark report is in the repo. This is 100% promptcoding but hey the evals look okay, speeds are pretty good on local machine (m5 max 64gb), and the LocalJev server exposes an API that can be used with the normal Jev API wrapper libraries.
Rubik's cube solved with Jev using beginner method
Paolo Rosson@redp314I got a rubik's cube to solve itself with @typesafeai 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!
Full Jev tutorial with three demos
Moritz Kremb@moritzkrembFull 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: Voice-controlled browser → 11:33 Demo 2: AI memory → 17:27 Demo 3: YouTube predictor
Research and analysis
Jev score 86Research feed that scores sources with Jev
An optional step scores source summaries against a task, reordering a reading list and exporting a Markdown brief. The author says it has not made the vault faster or proven better research.
Evals and judging
Jev score 83Ad-tech predictions against GPT-5.6 Sol
Benchmarked Jev on four synthetic ad outcomes. Few-shot quality was similar, zero-shot quality was mixed, and the poster says the results are synthetic.
64x lower cost, 5.4x lower latency (poster's figure)
will-it-hitA live LinkedIn draft scorer. One call asks eight Score questions (hook, specificity, emotion, clarity, repostability, authority, algorithm fit, expected engagement) and one Choice question for post type. A separate LLM writes rewrites, and Jev scores each rewrite again so you see both numbers.
Built by AY Automate
Browser agent finds flights in 7 seconds
Gregor Zunic@gregpr07Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓
PostgreSQL extension for natural language row search
Zachi@iam_zachiI think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1s for $0.0009. Second run: 6ms from cache.
Evals and judging
Jev score 90JevRerank plugin for LlamaIndex
Wiktor Byrka built a reranker on Jev and tested it on BEIR nfcorpus with MiniLM retrieving the top 10 and Jev reranking to the top 5. He cautions the first stage retriever is weak.
nDCG@5 0.340 to 0.396 at about $0.0003 per query (poster's figure)
Scoring 384 news stories for brands in 25 seconds
Elvis@elvissunJev is INSANE. 🤯 in 24.9 seconds it read 384 news from this morning and told 15 brands which stories to hop onto today, for $0.19. Claude Opus 5, running on the same feed at the same time, got through 4/384 and cost $0.77. per headline that is ~390x cheaper, and the answer comes back before you finish reading the headline yourself. there's going to be so many ways for JEV to help you find trending stories, find journalists covering it, and get press coverage. everything in the video open-sourced here: (in the demo/ folder, together with 30+ skills to turn your agent into a PR team)
Fraud email triage routing uncertain cases to Kimi
Hassan@nutlopeJev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.0
Jev reviews pull requests with 14 typed checks
Paolo Rosson@redp314got 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 Opus 5 paste a diff → ONE call to @typesafeai → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort… code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed
Tools and demos
Jev score 73Open source Mac pointer companion driven by Jev
Milind S@milindlabsAaaaaand this is now open-source here: A tiny AI pointer companion for your Mac driven by JEV or Gemini Live - Bring your own keys - Local OmniParser running on CoreML - Jev drives the pointer - Ctrl + K to type a task Voice mode next if people want it!
Live BS meter for a political debate
Chetaslua@chetaslua🚨 I gave the Trump vs Kamala debate a live BS meter using Jev every sentence, both candidates, 5 yes/no questions each 1,191 Jev calls / 1.18M tokens / 415 ms median total cost : $0.0497 same questions for both, clips picked by one fixed rule, not a fact-check
Not sure how to use Jev in your product?
Jev is priced at $0.042 per million input tokens with free output. Show me the routing, triage and scoring steps in your product and I will tell you which ones are worth moving off a large model.
FAQ
Before you build with Jev
What it is, what people have really shipped, and how far to trust the numbers on this page.
01What is Jev?
Jev is TypeSafe's System One model. It does not write text. You send it a state and typed questions, and it returns a choice, a yes/no probability or a score, each with a probability and a confidence value.
02What have people built with Jev?
Since the September 15, 2026 launch, public posts show browser agents, email and ticket triage, real-time game and drone control, trading loops with confidence gates, evaluation scorers and research labeling. This page lists them by category.
03Are the numbers on this page verified?
No. Every figure is the poster's own claim, marked as such. AY Automate has not rerun these projects. For our own test, see the independent Jev benchmark on our blog.
04Has AY Automate used Jev for client work?
Not yet. We index what the community is building and test where Jev fits. If you have a routing, triage or scoring workflow you want to pilot, book a call.
05How do I get my build listed?
Post it publicly on X or LinkedIn, then send us the link through the contact page. We list builds that show what was built and how it performed, including the ones where it did not work.