{"id":"cx-survey-questions-neutral-rewrite","audience":"customer-support","category":"support-work","technique":"tone","track":"support","level":"beginner","title":"Rewrite three leading survey questions neutrally","free":false,"task":"Rewrite the three survey questions so they are neutral and measure one thing each. Exactly 3 numbered lines, one question per line, each 12 words or fewer and ending with a question mark. Do not use the words amazing, great, don't you, or and. Plain text.","materialLabel":"Your material (attached to your prompt automatically)","material":"POST-CHAT SURVEY (current draft)\nQ1: \"How amazing was your support experience today?\" (measures: overall support)\nQ2: \"Don't you agree our team resolved your issue quickly?\" (measures: whether the issue was resolved)\nQ3: \"Was our support helpful and friendly?\" (measures: helpfulness only; friendliness is already measured elsewhere)\n\nNOTES FROM THE RESEARCH TEAM\n- Leading wording ('amazing', 'don't you agree') pushes people to answer positively.\n- A question that asks about two things at once (a 'double-barreled' question) can't be answered clearly.\n- Q1 should become a 1-to-5 rating question. Q2 should be a yes/no question about resolution only. Q3 should be a 1-to-5 question about helpfulness only.\n- Current average CSAT: 4.6, which the team suspects is inflated.","rules":[{"type":"numberedItems","count":3},{"type":"plainText"}],"mistakes":[{"title":"Keeping the leading words","why":"The AI softens but keeps 'great' or 'don't you agree'.","fix":"Say: \"Banned words: amazing, great, don't you, and.\"","checks":["r1"]},{"title":"Double-barreled Q3","why":"The AI keeps helpful and friendly in one question.","fix":"Say: \"Q3 measures helpfulness only.\"","checks":["r2"]},{"title":"Long or extra text","why":"The AI explains each rewrite.","fix":"Say: \"3 numbered lines, 12 words or fewer, each ending with ?.\"","checks":["r0"]},{"title":"Leaving the list shape open","why":"The AI picks its own number of items and its own layout.","fix":"Show the shape: \"exactly N numbered lines like: 1. Label: detail\".","checks":["numberedItems"]},{"title":"Getting markdown back","why":"AI adds bold and headings by default, which show up as stray symbols where this is pasted.","fix":"Say \"plain text, no bold, no headings, no asterisks\".","checks":["plainText"]}],"promptHints":[{"label":"Fixes the number of lines","patterns":["\\b\\d+\\b.{0,15}(lines|items|numbered)","numbered","exactly \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Names the banned words","patterns":["amazing","great","don.t you","banned","never use"]},{"label":"Asks for one thing per question","patterns":["one thing","single","only"]}],"hint":"Survey wording changes answers. Name the words to avoid, ask for one measure per question and fix the format.","rubricLabels":["The output has exactly 3 numbered lines, each ending with a question mark and 12 words or fewer","Q1 asks for an overall rating of the support experience and Q2 asks neutrally whether the issue was resolved, with no leading words such as amazing or don't you agree","Q3 asks about helpfulness only and does not include friendliness, and no question contains the word and"]}