Case wall
Jev AI examples, page 10
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.

@honnibal ran Jev with Ellf on data from Opus few-shot classifiers; Jev agreed with Opus on 95% of the inputs.
Very impressed with @typesafeai Jev. We've been working on a user project that was built with a lot of few-shot classifiers powered by Opus. I used Ellf to run…
@ClementWalter uses Jev (@typesafeai) to label and triage email in real time on mermoz.xyz, including smart threads without a fixed class set.
using jev @typesafeai for labelling and triaging email real time is SO efficient omg the nice thing with such decision model is that they don't need a fixed set…

@Hydra_Swarm shares Hydra with JEV (@typesafeai) after one month; links hydraswarm.io.
By popular request. Hydra with JEV @typesafeai after 1 month. https://hydraswarm.io
@mikeclarke argues Jev as a precondition unlocks proactive agents beyond cron and external triggers.
proactive agents only work two ways today (tell me if i'm missing something): 1. scheduled cron 2. external trigger using jev as a precondition for (1) and (2)…

@andrewingram uses TypeSafe Jev to auto-tag Sudoku puzzles by rule or constraint from puzzle data and the description. Fog of war is their favorite.
Been using @typesafeai Jev to somewhat successfully auto-tag Sudoku Puzzles by rule/constraint based on puzzle data and description. Fog of war is my fav so fin…
@GenkitFramework ships Genkit Go 1.14 with decision-model support for fast classification and routing (preview), plus HITL tools and budgets.
Genkit Go 1.14 is out! - Typed human-in-the-loop tools - Improved model recovery from tool errors - New usage budgets and context compression - Decision model s…

@ikkistan benchmarks guest-photo moderation for Candids on UnsafeBench: Cloudflare clef-flash, TypeSafe Jev, Claude Haiku 5.5, and Amazon Rekognition.
I’m building Candids, an app for wedding and party guests add photos to one shared album from their phones. Guest uploads need moderation, so I benchmarked four…

@baboonzero uses Jev, TypeSafe's System 1 model, to decide where a teaching explanation starts, ends, and stands alone, in a Super IC write-up.
I have more than a hundred hours of recorded teaching. Finding useful two-minute clips means deciding where an explanation starts, where it ends and whether it…

@MiguelriosEN open-sources Pi-vision: TypeSafe Jev analyzes images/video/docs while a Pi agent orchestrates, cutting frontier-token spend.
A few weeks ago, we built a new harness, AgentRun, which turns repetitive steps into workflows and code using Jev. This week we're open-sourcing its best featur…
@samsaffron: with Jev or any decision model configured in term-llm, ag results get smart reranking (PR #1267).
If you have @typesafeai Jev or any decision model configured in term-llm, you will get smart reranking of ag results starting today: https://github.com/SamSaffr…
@tonysimons ships Verdict: a second AI on Grok Bot that uses TypeSafe Jev to rank X posts and drafts against your criteria.
🚨 I gave my Grok Bot a SECOND AI. Its job? Judge my shit. 😂 📢 Meet Verdict: Grok Bot + Jev, the decision model from @typesafeai, run by @CompleteSkeptic, who he…
@lotusfracture demos multi-object detection using Jev loops with feedback.
multi-object detection using Jev loops with feedback
@josefrichter demos genUI "app in the app" using Jev and Mercury for quick organic UI inside existing apps.
Some more #genUI experiments. This is sort of an "app in the app". Using #Jev and #Mercury for very quick "organic UI" within existing apps. The idea is that th…
@ikkistan: Jev, Haiku, and clef-flash reach AUROC 0.86 to 0.87 on unsafe images, Rekognition 0.70, at 4 to 18 cents per 1,000 images versus $1.
Jev, Haiku and clef-flash rank unsafe images about equally well (AUROC 0.86 to 0.87, Rekognition 0.70) at 4 to 18 cents per 1,000 images vs $1. Code, per-image…

@Xavidop built a Kubernetes software factory: Gemini and Genkit build each stage, and Jev gates ship, rework, or ask a human.
I built a software factory on Kubernetes 🏭 Feature request in, tested and reviewed Go module out. Gemini (@googleaidevs) builds each stage as a @GenkitFramework…
@luv_agarwal_ cut agent browser test runs by 90-95% with a Jev-driven YAML step runner (ck-browser).
we made our agent browser test runs faster by 90-95% using Jev previously: an agent would navigate through the page using chrome-devtools-axi. the way that work…
@KevinMagnan has a decision model like Jev pick the retake winners from the transcript while editing TikToks.
Been editing my TikToks this way since January. What I've learned and built along the way: - Have a decision model like @typesafeai Jev pick the retake winners…
Quoted @petergyang
@abgregs built a Claude Code skill router plugin: each skill scored with a Jev Noul before the model sees the prompt.
My experiment building a skill router plugin for Claude Code with Jev: https://abgregs.github.io/jev-skill-router/ How it Works Before the model sees your promp…
Quoted @CompleteSkeptic
@Shah1337L says Jev now plays Snow Bros with an LLM and a local controller. In that minute, levels 61–62 were cleared, 63 was reached, and no lives were lost.
I used to play Snow Bros on my PC in Karachi. Now Jev plays it with an LLM + local controller. This minute: levels 61–62 cleared, 63 reached, zero lives lost. C…
@Su1eyman11 tries reasoning plus inverse kinematics with no learned motion policy: Jev as System 1, Astra as fallback, IK for motion, fruit into a tray.
How far can we get with reasoning + inverse kinematics, without a learned motion policy? I built this small experiment with Jev as System 1 and Astra as the fal…
@localixai explains decision models (Jev from TypeSafe) and shows where they built them into a pet project.
Decision models (Jev from TypeSafe) are a relatively new class of models: they don't write text, they make decisions. I built them into my pet project in a few…

@instantricecook runs 66 Where's Waldo scenes across decision models; Jev 1.14 is quickest, with a public Waldo bench site.
I wanted to see how well decision models are at... Finding Waldo. After 66 scenes, here are the results: - @liquidai d1-ultra found the most Waldos - @typesafea…

@ajitomatix tests TypeSafe Jev 1.14 experimental image support on SOS Draw, comparing text, image, and hybrid against a handcrafted stroke-to-text pipeline.
When @typesafeai AI released #Jev 1.14 with experimental image support, I had to test it on SOS Draw! Can @typesafeai recognize a player's raw canvas drawing be…
@gcai: GC AI Engineering built 38 projects in 12 hours with TypeSafe Jev while @ChrisDzoba tried to break it.
GC AI Engineering built 38 projects in 12 hours with TypeSafe's Jev, a classification model. Director of Engineering @ChrisDzoba spent the day trying to break i…