Jev founder on what comes after assistants: a decision layer
In a 36-minute talk, Diogo Almeida argues much of an agent's work needs decisions rather than generated answers, and describes Jev inserting a State, Decision, Action, Feedback layer between input and execution.
JEV founder Diogo Almeida spent 36 minutes explaining what comes after AI assistants. The question worth paying attention to: how much of your agent’s work actually needs a generated answer? Routing a task. Scoring an option. Choosing the next action. Those decisions sit inside almost every agent workflow. JEV’s approach puts a dedicated decision layer between the input and execution: State → Decision → Action → Feedback For me, that’s the interesting angle: how you build a system that can keep moving without asking a person to interpret every response. If you’re building agents, this is worth a spot in your watchlist. Watch the talk, then look at your own setup. Where are you generating paragraphs when you only need a decision?
This post quotes another post: “Jev screens 600 trade setups in 47 seconds for $0.07”