Exactly, I agree. I have been working on a ux harness that creates a deep product model with personas, user journeys, etc as well as designs. Originally I was hoping it that it could work just some skills and a data export format. It was burning 300M tokens just to get nowhere.

Now I have this DAG with something like 40 specialized subagents. It's sort of a monstrosity, but it works much better for 100x fewer tokens. I've found that basically every single judgment call (which is characteristic of ux) really wants an agent solely focused on it with plenty of concrete examples.