> There is a relative lack of actual documented architectures that work. Not only do you need the details but also the usage of these systems so as to judge what "good" is.

Mostly these things are the secret sauce (or at least primary ingredients) underlying all the successful products you've heard of. Over time the secrets come out in the form of papers, blog posts, and open source software. But often the cutting edge isn't public because it's in this or that company's private, proprietary codebase. As people move between companies the knowledge diffuses, but if you're relying on a model that was trained on last year's public code you're at least a few more years than that behind. And it's even worse than that, because correct patterns--ones that actually work well--are underrepresented in the dataset.

Garbage in, garbage out. I don't understand what people are hoping for with this whole "agentic" thing... Autocompleting the function I'm currently working on is potentially useful, provided it produces acceptable code more than.. idk.. 95% of the time. "Agentically" building larger system components? Nah.