This was basically my realization as well. We are trying to get LLMs to write software the way humans do it, but they have a different set of strength and weaknesses. Structuring tooling around what LLMs actually do well seems like an obvious thing to do. I wrote about this in some detail here:

https://yogthos.net/posts/2026-02-25-ai-at-scale.html

My experimentation with Verblets also concluded plain functions are the most logical harness for LLMs.