[iamben]

A couple of things that really helped me (Claude is my choice for coding):

- add to your global settings a few lines that say something like "don't write any code until you fully understand my requirements, ask questions until you are completely clear", this mostly stops it just going ahead and writing best guess just the first time. And then,

- when it looks it's going off the rails, cut your loses straight away and ask it to write a prompt for another chat. Tell it to cover everything it knows about what you're working on and what you want to do. Paste that into the new chat and get it to ask if it needs clarification (and then if needed, paste between the two chats). The new chat often solves the problem the other one was stuck on first time.

Hope they help - coding with AI has made me enjoy the process once again. I'm actually completely silly projects I've always wanted to do because I can get past the blockers so much more easily.

[gndk]

I'm having good results with similar stuff, but not sure about the best approach. What exactly do you mean by "your global settings"? Do you have a global CLAUDE.md file? Or do you do this via the UserPromptSubmit hook and return an additionalContext? I use this hook to constantly reinforce some things, like "be concise. use context7." It even works to put "ultrathink" in there to always have it in thinking mode. But I wonder if these constant reminders are overdoing it.

[iamben]

Hey, fwiw I'm almost certainly not using Claude in the best possible way - I have a 'pro' (as in the ~$20 a month plan) and I just prompt. But in the 'Settings' section there's a bit that says: "What personal preferences should Claude consider in responses?" - I add stuff in there.

[gndk]

Ah thats interesting. I only use Claude Code right now and don't have anything in that section you mention. Wonder how/when its applied and if it is also applied to CC...

[fuzzzerd]

With Claude code you can have a personal, project (shared) and project local set of memory files.

I would put the bits about clarifying questions in your personal (machine level) claude.MD file so it applies across projects.

[johnisgood]

I use claude.ai too and it is fine for me, even though I do the copy-pasting, or uploading.