For me it's the opposite. As long as I ask for small tasks, or error checking, it can help. But I'd rather think of the overall design myself because I tend to figure out corner cases or superlinear complexities much better. I develop better mental models than the NNs. That's somewhat of a relief.

Also the longer the conversation goes, the less effective it gets. (saturated context window?)

I don't think thats the opposite. I have an idea what I want and to some extent how I want it to be done. The design document starts with a brainstorming where I throw all my ideas at the agent and we iterate together.

> Also the longer the conversation goes, the less effective it gets. (saturated context window?)

Yes, this is exactly why I said the breakthrough came for me when I learned how to keep the context clean. That means multiple times in the process I ask the model to put the relevant parts of our discussion into an MD document, I may review and edit it and I reset the context with /clear. Then I have him read just the relevant things from MD docs and we continue.