AI is a confident first drafter and a terrible self editor. It won't tell you the output is mediocre. It'll hand it over like it's finished. Unless you make it look again. Try this after any output you're not thrilled with 👇 "Before I use this, critique it. What's generic? What could have been written about any business in this industry? Where did you make assumptions about my audience that I didn't give you? Score it out of 10 for how specific it is, and tell me what a 10 would require." Then, read the critique before you ask for a rewrite. Because the critique tells you what YOU left out. Nine times out of ten it says something like "I assumed your audience was time poor but you never told me who they are." That's not the AI failing, that's a gap in your brief. The next level: give it the criteria upfront. 👇 "You'll be judged on: specificity to my business, whether it sounds like me, and whether a reader would stop scrolling. Draft it, then score yourself against those three and revise once before showing me." Now it does two passes before you ever see it. Why this works ➡️ evaluating is a different task from generating and AI is much better at spotting a weak sentence than at avoiding writing one. Try it on something you've already generated this week and tell me what score it gave itself. 😄