User shares rebuilding an agent stack on the TypeSafe Jev decision model for flight search, paper classification, and email triage, with setup steps.
this is literally f**king insane i just rebuilt my agent stack on a $0.042/M decision model @typesafeai Jev. Browser Use found flights in 7s. Hassan classified 1,018 papers. Riley triaged 500 emails. $0.0039. $0.08. $0.035. zero generation. here is how you set it up: install
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.
