I've been using Claude for about 3 months now. What I've learned is that you have to learn how Claude "thinks" about your project, meaning what kinds of mistakes he makes. They're pretty consistent. As you uncover each new kind, compile a list of things to remind him of each time. For my own project, some of my reminder items to give him each chat (sometimes multiple times in the chat) include: "maintain a single source of truth", "avoid duplication", "stick to our established architecture instead of building new architecture". I always make sure he has an up-to-date file tree to look at. I remind him to ask me if there's a particular file he needs to see for reference instead of making up something new. I also say to make the changes specific to just what needs to be changed, rather than building in stuff and "anticipating" problems that aren't even here yet. Stuff like that. By the way, Project Knowledge is a very useful feature. Just don't expect Claude to ever look at it after your first statement/question. That's when he looks at what's there.