A proposed primitive that pairs model calls with a Jev decision loop

Josh Rosen @JoshARosenOriginally posted 2026.09.23

Open original on X

I predict we're going to get a new AI primitive somewhere between a model call and an agent loop that makes LLMs much more accountable. Think invoke() or responses.create(), but paired with a fast decision model like Jev. You pass in the prompt/messages, typed questions, thresholds for those answers, and max iterations. The reasoning model loops until the decision model says the answers meet the thresholds. Basically the smallest possible agent loop packaged into a single invocation.