{"id":"cx-nps-verbatims-group-reason-table","audience":"analysts","category":"support-work","technique":"format","track":"support","level":"intermediate","title":"Group six NPS responses by score band and main reason","free":false,"task":"Output a table with the header \"ID | Group | Reason\" and six rows, then a last line \"Detractors: N#, N#\". Group comes from the score: 0 to 6 Detractor, 7 to 8 Passive, 9 to 10 Promoter. Reason is the main topic of the comment, praise or complaint, and is exactly one of Speed, Billing, Product, Knowledge base, Agent or None. If the comment has both praise and a complaint, use the complaint. Plain text, under 70 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"NPS RESPONSES (post-ticket survey)\nN1 | score 10 | \"Fast replies, solved in one go.\"\nN2 | score 6 | \"Waited two days for an answer.\"\nN3 | score 8 | \"Fine, nothing special.\"\nN4 | score 3 | \"Got charged twice and nobody told me why.\"\nN5 | score 9 | \"The agent was lovely but the app is slow.\"\nN6 | score 7 | \"Okay, though the help article was out of date.\"\n\nNOTES\nSpeed = how quickly we replied or solved. Product = the app itself. Knowledge base = the help articles. Agent = the person's behavior. Billing = charges and invoices.","rules":[{"type":"plainText"},{"type":"maxWords","max":70}],"mistakes":[{"title":"Judging group by comment tone","why":"The AI calls N2 Passive because the comment is mild.","fix":"Say: \"Group comes only from the score.\"","checks":["r1"]},{"title":"Using the praise for mixed comments","why":"The AI picks Agent for N5.","fix":"Say: \"When there is a complaint, use the complaint.\"","checks":["r2"]},{"title":"Inventing reasons","why":"The AI uses labels outside the list.","fix":"List the six allowed reasons.","checks":["r2","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":"Gives the header","patterns":["id \\| group \\| reason"]},{"label":"Lists the score bands","patterns":["0 to 6","9 to 10","detractor"]},{"label":"Resolves mixed comments","patterns":["complaint","praise and"]},{"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+"]}],"hint":"Give the header, the score bands, the allowed reasons and the rule for mixed comments.","rubricLabels":["The first row is \"ID | Group | Reason\" followed by rows N1 to N6","Groups: N1 Promoter, N2 Detractor, N3 Passive, N4 Detractor, N5 Promoter, N6 Passive","Reasons: N1 Speed, N2 Speed, N3 None, N4 Billing, N5 Product, N6 Knowledge base, and the last line is \"Detractors: N2, N4\""]}