The author shares experimenting with TypeSafe's Jev inside Plai for intent classification, arguing it needs a decision rather than text generation, and outlines a prompt→Jev→intent→orchestration→Path flow that could extend to retrieval, ranking, filtering, and clarification.
Experimenting with TypeSafe's Jev inside Plai. Intent classification doesn't need text generation. It needs a decision. prompt → Jev → intent → orchestration → Path This could extend to retrieval, ranking, filtering, and clarification. Different AI, different job!
Gregor Zunic showcases an open-source browser agent combining Browser Use and Jev, finding flights in 7 seconds for $0.0039, using a new action space per step, DOM state space, and small LLM fallback for typing.
Scott Williams predicts custom Jev-style models (parallel constrained decoding) will make existing company agent systems more token efficient, creating millionaires.
The user praises the JEV model for its extremely fast reproduction of each movement and command, believing bots will become smarter as a result.
