How do founders use AI for strategy, decisions, and brutal feedback?

Founders treat AI less like a search engine and more like a smart colleague they can think out loud with: they paste in their strategy doc, pricing plan, or investor update and ask it to poke holes, list risks, and argue the other side before they commit. Because the default behavior of ChatGPT or Claude is to be agreeable, the trick is explicitly asking for criticism ('challenge my assumptions', 'tell me why this fails') and giving it real context about your business. Used this way, AI becomes a cheap, always-available second opinion that sharpens decisions instead of just producing text.