{"id":"mkt2-headline-ratings-pick-with-math","audience":"marketing","category":"brainstorming","track":"marketing","technique":"verification","level":"advanced","title":"Score headline options from reviewer ratings and recommend one","free":false,"task":"Three headline options for the Orchid Studio homepage were rated by reviewers. Write a prompt for a markdown table with columns Headline | Clarity avg | Specific avg | Total, then one line starting \"Recommendation:\" with the headline letter and a reason under 15 words. Average each score across the valid reviewers only, show one decimal, and total = clarity avg + specific avg. Ignore any reviewer who didn't read the brief. Under 80 words, no other text.","materialLabel":"Reviewer ratings (attached to your prompt automatically)","material":"HEADLINE TEST - Orchid Studio homepage (ratings 1 to 5, higher is better)\n\nHeadline A: \"Design that earns trust\"\nHeadline B: \"Brand identities for kitchens and cafes in 6 weeks\"\nHeadline C: \"Make something people remember\"\n\nRatings: Clarity (C) / Specific (S)\nReviewer | A (C/S) | B (C/S) | C (C/S)\nIvana | 4/3 | 5/4 | 3/5\nKwame | 4/3 | 4/4 | 3/4\nLiu | 4/3 | 3/4 | 3/3\nJun | 5/5 | 2/2 | 5/5\n\nNote: Jun said, \"I didn't read the brief, I just rated what sounded nicest.\"\nOther note: Headline B is the longest; the designer worries it may wrap on mobile (not a rating criterion).","rules":[{"type":"plainText"},{"type":"maxWords","max":80}],"mistakes":[{"title":"Including Jun","why":"The AI averages all four reviewers, which makes A and C look better.","fix":"Add: \"Ignore Jun, who didn't read the brief.\"","checks":["r0","r1"]},{"title":"Recommending on mobile wrapping","why":"The AI weighs the wrap worry, which wasn't a criterion.","fix":"Say: \"Decide only on the Total.\"","checks":["r1"]},{"title":"Skipping the format","why":"The AI writes a narrative review of the headlines.","fix":"Name the columns and the Recommendation line.","checks":["r2"]},{"title":"Letting markdown through","why":"AI adds bold text and headings by default.","fix":"Add: \"Plain text only, no bold, no headings.\"","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and often runs past a word limit.","fix":"Cap each part (for example \"each line under 15 words\") so the total lands well under the limit.","checks":["maxWords"]}],"promptHints":[{"label":"Names the columns","patterns":["headline.*clarity avg.*specific avg.*total"]},{"label":"Excludes the bad reviewer","patterns":["ignore","exclude","jun","didn'?t read"]},{"label":"Defines the total","patterns":["clarity avg \\+ specific","total ="]},{"label":"Fixes decimals","patterns":["one decimal","1 decimal"]},{"label":"Asks for a Recommendation line","patterns":["recommendation:"]}],"hint":"Averages are only as good as the ratings you include. Say whom to ignore, how to total and what the final line looks like.","mission":"Pick the best Orchid Studio headline from reviewer scores.","musts":["Skip reviewers who skipped brief","Averages to one decimal","Total clarity plus specific"],"rubricLabels":["The table shows A 4.0, 3.0, 7.0; B 4.0, 4.0, 8.0; and C 3.0, 4.0, 7.0 for Clarity avg, Specific avg and Total, using Ivana, Kwame and Liu only","The Recommendation line names Headline B with a reason under 15 words","The output has no text apart from the table and the Recommendation line, and does not mention using Jun's ratings"]}