{"id":"pro-mgr-survey-report-exec","audience":"managers","category":"summarizing","technique":"grounding","title":"Shrink a customer survey report into 3 bullets for your VP","free":false,"task":"Your VP, Carla, asked for the headline from the 300-word quarterly customer survey report before her budget meeting. She wants at most 3 bullets under 60 words in total, plain text, with the one thing she must decide in the first bullet. The report has an erratum at the bottom, so use the corrected number, and skip how the survey was run. Write a prompt that gets you exactly that.","materialLabel":"The survey report (attached to your prompt automatically)","material":"Q3 Customer Survey - Summary Report\nPrepared by Insights team, Fernway Home Services\n\nMethod: 1,240 customers surveyed by email Sept 2-20. Response rate 18%. Margin of error about 4 points. Weighted by region. Thanks to the summer interns for coding open answers.\n\nKey results:\n- Net Promoter Score: 47 (Q2: 44)\n- Satisfaction with technicians: 88% (flat)\n- Satisfaction with booking: 61% (Q2: 72%). Biggest drop this year.\n- Top complaint in open answers: the new online booking form \"logs me out\" and \"loses my time slot\" (mentioned by 212 people).\n- Customers who booked by phone were much happier (79%) than online (54%).\n\nRecommendation: The Insights team recommends funding the booking-form fix proposed by the web vendor ($18,000, about 6 weeks) this quarter. Without approval by Oct 31, the vendor slot moves to January.\n\nOther notes: we tested a new survey tool and it worked well. Next survey in December. Regional breakdown in the appendix.\n\nERRATUM (added Oct 8): The NPS above was miscalculated. The correct Q3 NPS is 41, down from 44 in Q2, not up.","rules":[{"type":"maxBullets","max":3},{"type":"maxWords","max":60},{"type":"plainText"}],"mistakes":[{"title":"Burying the decision","why":"The AI follows the report's order, so the funding ask lands at the end.","fix":"Add: \"First bullet: the decision Carla must make and the deadline.\"","checks":["r0"]},{"title":"Missing the erratum","why":"The wrong NPS appears first and in bold-looking spots; the fix is at the bottom.","fix":"Add: \"Use the corrected NPS from the erratum.\"","checks":["r1"]},{"title":"Keeping the method details","why":"The AI thinks response rates make a summary look rigorous, but Carla doesn't need them.","fix":"Add: \"Skip how the survey was run. Keep the booking drop.\"","checks":["r2"]},{"title":"Not limiting the bullets","why":"The AI gives one bullet per finding, with bold headings.","fix":"Be exact: \"At most 3 bullets, plain text.\"","checks":["maxBullets","plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for \"under 60 words\" and it often lands well over.","fix":"Cap each part instead: \"each line under 14 words.\"","checks":["maxWords"]}],"promptHints":[{"label":"Limits the bullets","patterns":["\\b(3|three)\\b.{0,15}bullet","bullet.{0,20}\\b(3|three)\\b"]},{"label":"Says who it's for","patterns":["carla","\\bvp\\b","executive","exec"]},{"label":"Puts the decision first","patterns":["decision","approv","first bullet","lead with"]},{"label":"Uses the correction","patterns":["erratum","correct","41"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)"]}],"hint":"An executive reads the first line and decides. Tell the AI what goes first, how short it must be, and that the report corrects itself at the bottom.","rubricLabels":["The first bullet is the decision Carla must make: approve the $18,000 booking-form fix by Oct 31 (or the vendor slot moves to January)","If NPS is mentioned, it uses the corrected figure (41, down from 44), never 47 or 'up'","Includes the booking satisfaction drop (61%, down from 72%), and leaves out survey method details (response rate, margin of error, survey tool, interns)"]}