Sure. This is an internal web app that uses react on the front end and rails on the back end. Typical examples I see LLM success with are writing and writing up routes/controllers/models, writing specs for those, abstracting components, writing front-end vitest/storybook entries. A typical request (filenames and such redacted) is like: "We recently added <link to model>. We refactored our approach for <goal> to <link to different model file>. We need to refactor <A> to be like <B> in these ways. Do that, then update the spec to match the pattern in <file Y>. Run rspec and rubocop when done, and address any issues". I then either wait or go do something else, then review the code and either ask for follow up, or fix minor issues. Sometimes it follows the wrong pattern and I ask it to adjust, or simply git checkout -- and say try again you did Y wrong.
Roughly speaking that is how I think through my work, and when I get to the point of actually writing the code having most of the plan (context) in my head, I simply copy that context to the LLM then go to do something else. I only do this if I believe the LLM can do it effectively, so some tasks I do not ask for help at all on (IMHO this is important).
I also have it help with scripts, especially script that munge and summarize data. I know SQL very very well, but find it still a bit faster to prompt the LLM if it has the schema on hand.
Do you find ^ helpful? i.e does that match how you prompt and if not, in what ways does it differ? If it does, in what ways do you get different results and at what step?
