What people are shipping with Jev.

3 days ago ... With TypeSafe it just picks the class (actually probabilities across ... Using Jev I'd decompose the prompt into a bunch of smaller questions, then I ...

Using Jev from @typesafeai in this side quest to help with intelligence and deciding when to escalate to the user. Very cool stuff. Jev with an inexpensive paid model via @vercel's

It's super fun to play with @typesafeai 's #Jev with the #SREGym team. It's crazily fast and unlocks a lot of new capabilities for SRE use cases. A simple integration already leads

There's so much clutter on so much websites. 2-3 distraction can be enough overload the working memory and then you forget why you went to the site to begin with. This free exten

2 days ago ... TypeSafe's Jev is a new class of AI model, a System One Model, that returns typed decisions with calibrated probabilities instead of text, running 40-200x ...

Found the perfect use case for @typesafeai Jev: instant compaction in 2026. Why is compaction still a summarization prompt? Jev scores every tool call and drops what’s irrelevant—m

Ok let's go 😃 Using Jev to find reviews of our apps from the last year to create a review database I will share the results when it finishes https://t.co/PPWhOBA98O https://t.co/h

@fernandoeeu_dev @typesafeai A gente tinha isso determinístico antes. Mas errava muito. Aí a gente aumentou o limite do determinístico pra trazer uns 20 itens e o jev tá decidindo

instead of generating text, jev from @typesafeai generates structured output this makes it great for classification tasks like model routing, tool selection/search, and guardrails

Switched a big chunk of matching, routing tasks to Jev by @typesafeai Crashed my bill by 87% I was already using DSV4F btw Crazy times we're living in

Jev from @typesafeai cannot write sentences but is great at deciding and classifying This makes it a direct alternative to LLM-as-a-judge setups. Jev returns a choice between pr

Jev from @typesafeai is 11x faster, but a bit more expensive than gpt 5 nano. Tested it on an email classification task for @TripNoted. At this cost the price difference isn't m

There's a new AI model that outputs decisions instead of text. You feed @typesafeai's 'Jev' a set of typed questions, and it hands back a decision (a pick, a score, a yes or no) w

La rapidité pour les recherches web en intégrant jev de @typesafeai est incroyable 🚀 Quelques secondes pour des dizaines de recherches sur @okazfr. Et ce n'est que le début... ht

jev unlocked better browser use - pull in a LLM when you need it, but otherwise 10x speed by just using jev to classify pages and important elements

@ThisisMarkT @typesafeai Yes, as a filter or reranker rather than the generator: retrieve wide, ask Jev per chunk "does this answer the question", keep only the high-probability on

@barckcode Hay ya decenas de enrutadores de modelos con Jev. Es un caso de uso bastante claro. https://t.co/1GcFAm02v6

I am going to build for companies who have lot of candidates to evaluate based on resume I am using the coolest model JEV by @typesafeai to analyse all of them and find the rig

What about using Jev to attach the only tool schema necessary for the task based on prompt classification? might this solve the MCP overhead problem?

I think @typesafeai Jev has solved a much bigger AI problem than it first appears: LLMs shouldn’t have to think about everything. A huge amount of “reasoning” is actually classif