So there are a few very specific tasks that LLMs are good at from the perspective of a software developer:

1. Certain kinds of analysis tasks can be done very quickly and efficiently with Copilot in agent mode. For instance, having it assess your existing code for adherence to stylistic standards where a violation isn't going to trigger a linting error.
2. Quick script writing is something it excels at. There are all kinds of circumstances where you might need an independent script, such as a database seed file. It's not part of the application itself, but it's a useful utility to have, and Copilot is good at writing them.
3. Scaffolding a new application. If you're creating something brand new and know which tools you want to use for it, but don't want to go through the hassle of setting everything up yourself, having Copilot do it can be a real time saver.

And that's... pretty much it. I've experimented with building applications with "prompt engineering," and to be blunt, I think the concept is fundamentally flawed. The problem is that once the application exceeds the LLM's context window size, which is necessarily small, you're going to see it make a lot more mistakes than it already does, because - just as an example - by the time you're having it write the frontend for a new API endpoint, it's already forgotten how that endpoint works.

As the application approaches production size in features and functions, the number of lines of code becomes an insurmountable bottleneck for Copilot. It simply can't maintain a comprehensive understanding of what's already there.