5 AI Coding Mistakes That Waste Hours (and the Prompts That Fix Them)

You paste code into ChatGPT. You get an answer. It looks right. You ship it. Two hours later, it breaks. I've made every AI coding mistake in the book. Here are the five that cost me the most time — and the exact prompts I use now to avoid them. Mistake 1: Asking for a Solution Without Explaining the Constraint What happens: You say "write a function that sorts users by name." The AI gives you a perfectly valid sort — that loads 50,000 records into memory. The fix prompt: I need a function that sorts users by name . Constraints : - Dataset : ~ 50 k records , PostgreSQL backend - Must use database - level sorting ( no in - memory ) - Return paginated results ( 20 per page ) - Must work with the existing User model ( id , name , email , created_at ) Show me the query and the controller method . Why it works: Constraints turn "write me a sort" into "write me this sort." The AI can't over-engineer or under-engineer when boundaries are explicit. Mistake 2: Accepting the First Output Without