{"id":"cx-quarterly-readout-method-change","audience":"customer-support","category":"support-work","technique":"verification","track":"support","level":"advanced","title":"Write a five-line quarterly readout that flags a changed survey method","free":false,"task":"Write a quarterly support readout for the CEO, Dana, in exactly five lines starting \"Volume:\", \"CSAT:\", \"First reply:\", \"Top issue:\" and \"Ask:\". Show before and after numbers with the change. If a metric is not comparable, say so and do not compare it. Plain text, under 90 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"SUPPORT QUARTERLY DATA, Q2 vs Q3\nTicket volume: 4,200 (Q2), 4,620 (Q3).\nAverage first reply: 3h 20m (Q2), 2h 50m (Q3).\nCSAT: 4.4 (Q2), 4.1 (Q3). NOTE: on Aug 1 the survey changed from an email survey (about 12% response) to an in-app survey (about 31% response, different wording). The team believes the scores are not comparable.\nTop issue in Q3: Login problems, 1,300 of 4,620 tickets (28%).\nAsk from the support director: approval to extend chat hours from 6 PM to 10 PM, cost $48,000 per year, to cut the login backlog.\n\nDraft from the analyst: 'CSAT fell 0.3, a clear quality problem.'\nThe CEO reads on her phone and wants numbers without extra explanations.","rules":[{"type":"plainText"},{"type":"maxWords","max":90}],"mistakes":[{"title":"Comparing CSAT directly","why":"The numbers look comparable and the analyst's draft says CSAT fell.","fix":"Say: \"CSAT is not comparable: the survey method changed Aug 1.\"","checks":["r2"]},{"title":"Missing the ask details","why":"The AI writes 'we need more hours'.","fix":"Say: \"Ask: extend chat hours to 10 PM, $48,000 per year.\"","checks":["r2"]},{"title":"Wrong arithmetic","why":"The AI misstates the change.","fix":"Say: \"Show before to after and the change for volume and first reply.\"","checks":["r1"]},{"title":"Free-form summary","why":"The AI writes paragraphs.","fix":"Name the five labels.","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","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":"Names the labels","patterns":["volume:","csat:","first reply:","top issue:","ask:"]},{"label":"Flags not comparable","patterns":["not comparable","method","changed"]}],"hint":"A readout must flag metrics that changed definition. Name the lines, the numbers and the not-comparable rule.","rubricLabels":["The output is exactly five lines starting Volume:, CSAT:, First reply:, Top issue: and Ask:","Volume shows 4,200 to 4,620 (+420) and First reply shows 3h 20m to 2h 50m (30 minutes faster)","CSAT says it is not comparable because the survey changed on Aug 1 and does not say CSAT fell 0.3, while Top issue gives login problems 1,300 of 4,620 (28%) and Ask gives extending chat hours to 10 PM for $48,000 per year"]}