{"id":"cs-nps-by-segment-table-math","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"advanced","title":"Compute NPS by segment and name the weakest","free":false,"task":"Compute NPS for each segment with NPS = (promoters - detractors) / responses x 100. Output a table with the header row exactly \"Segment | Responses | NPS\" and three rows, each NPS shown with the working like \"(30 - 10) / 50 = 40\". Then a last line starting \"Lowest:\" naming one segment. Plain text, under 80 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"NPS SURVEY, Q3, by segment (promoters = 9-10, passives = 7-8, detractors = 0-6)\n\nEnterprise: 50 responses: 30 promoters, 10 passives, 10 detractors. Average score 8.4.\nMid-market: 50 responses: 20 promoters, 15 passives, 15 detractors. Average score 7.8.\nSmall business: 30 responses: 12 promoters, 6 passives, 12 detractors. Average score 7.1.\n\nAnalyst comment: 'Small business average 7.1 is basically fine, the weak one is Mid-market because its average is lower than Enterprise.'\n\nTotal responses: 130.\n\nSURVEY NOTES: The survey went out Sep 22 to 410 contacts and closed Oct 6 (a 32% response rate). Most Small business detractors mentioned slow support replies in free-text comments; Enterprise promoters praised the account team. The board deck last quarter reported a blended NPS of 18 across all segments. This readout is for the Customer Success director, who will use the lowest segment to decide where to add coaching time next quarter.","rules":[{"type":"plainText"},{"type":"maxWords","max":80}],"mistakes":[{"title":"Using averages","why":"The AI ranks by average score as the analyst did.","fix":"Say: \"Rank by NPS from the formula, not average scores.\"","checks":["r2"]},{"title":"Dividing by the wrong total","why":"The AI divides by 130 for every segment.","fix":"Say: \"Divide by that segment's own responses.\"","checks":["r1"]},{"title":"Wrong table","why":"The AI adds columns or text.","fix":"Give the exact header row and the Lowest line.","checks":["r0"]},{"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"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and usually runs long, so a vague \"keep it short\" lands well over the limit.","fix":"Cap each part instead of the total, for example \"each line under 15 words\".","checks":["maxWords"]}],"promptHints":[{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]},{"label":"Gives the formula","patterns":["promoters","detractors","responses"]},{"label":"Asks for working","patterns":["working","show","="]}],"hint":"NPS needs the formula, the correct denominator, and a rule to ignore averages.","rubricLabels":["The header row is exactly \"Segment | Responses | NPS\" with rows for Enterprise, Mid-market and Small business","The working shows Enterprise (30 - 10) / 50 = 40, Mid-market (20 - 15) / 50 = 10 and Small business (12 - 12) / 30 = 0","The last line starts with \"Lowest:\" and names Small business, not Mid-market"]}