Diagnose marketing copy (roast / review)
diagnose_marketing_copyReview marketing copy line by line to see which of nine reader questions it answers, where it falls short, and the main persuasion gap.
Instructions
Review, critique or roast any piece of marketing copy, whether it's an ad, a landing page, an email, a sales page, a social post or a script, and find out why it might not persuade. Before you call it, read the copy and label each line with the one reader question it mainly answers, quoting the words exactly. Those labels go in the moves array. You get back which of the nine questions the copy answers for its goal, which it answers weakly and which it skips, along with the biggest gap and what readers do when it is missing. It also checks the order, whether the answers agree with each other, and the craft, pointing to the exact words that read as machine-written, like em dashes, "it's not X, it's Y" lines and sentences that all run the same length. Then it checks the opening line and suggests techniques from the catalog to fill the gap. Use it before you show anyone a draft you wrote, and whenever someone asks "is this good?", "roast this", "what's wrong with this copy?" or "how do I make it better?"
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| copy | Yes | The full copy, exactly as written. | |
| goal | Yes | What the copy has to get the reader to do. Use purchase when they should buy now, signup for an opt-in, a trial, a demo or a lead form, click when the whole job is the click (most ads and links), and engagement for nurture emails, newsletters and social posts that should be read, answered or followed. | |
| brief | No | The brief, if you have it: the brand, product, offer, audience and proof. With it, the opening line gets the swap test, which asks whether a competitor could send it unchanged. | |
| moves | Yes | Your line-by-line labels. Quote each persuasive line exactly and name the one reader question it mainly answers. Skip lines that are pure filler. | |
| format | Yes | The kind of copy it is: ad, landing_page, sales_letter for long-form sales copy, email, email_subject, social_post, video_script or headline. | |
| category | No | The industry, if you want to compare against what brands in that category usually do. There is enough data for apparel, automotive, b2b_saas, beauty_skincare, business_coaching, consumer_tech, dtc_food_bev, dtc_health, fitness_health, home_goods, info_product, investing, marketing_education, otc_pharma, personal_care, personal_development, supplements, weight_loss. Any other category still works, just without the comparison. | |
| headline | No | The headline or opening line, if it isn't the first line of the copy. | |
| awareness_level | No | How much the reader already knows, on Eugene Schwartz's scale. Use unaware if they don't know they have the problem, problem_aware if they feel it, solution_aware if they know solutions exist, product_aware if they know you, and most_aware if they're ready and only need the offer. | |
| persuasion_mode | No | How hard the copy is allowed to push. Balanced is the default, persuasive and sustainable over time. Equity protects long-term trust, so it rules out fear, hype and hard-sell moves. Aggressive is for short-term direct response and allows fear, threat and hard scarcity. In every mode, the claims stay true. | balanced |