{"id":"cs-time-to-value-average-with-outlier","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"intermediate","title":"Report average time to value with and without a delayed customer","free":false,"task":"Report time to first value for the six customers in exactly three lines starting \"All customers:\", \"Without Dune:\" and \"Fastest:\". Show the average as a sum and division, like \"90 / 6 = 15 days\". Dune was delayed by the customer's own IT freeze. Fastest names every customer tied for the fewest days. Plain text, under 70 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"TIME TO FIRST VALUE (days from kickoff to first report built), Q3 cohort\nAlder Foods: 12\nBirch Labs: 9\nCedar Co: 15\nDune Works: 30 (the customer's IT team froze changes for 3 weeks)\nElm Partners: 9\nFir Logistics: 15\n\nTarget: 14 days or fewer.\nBoard slide draft: 'Average time to value is 12 days.' (This excludes Dune without saying so.)\nThe VP wants both numbers, clearly labeled, so nobody assumes the outlier was hidden.\n\nBACKGROUND: Time to first value is measured from the kickoff call to the first report a customer builds on their own data. Last quarter's average was 18 days. Dune Works' IT team froze all changes for three weeks after kickoff, which delayed their first report by about 15 days. The board will see this number next week, and the CS director prefers that we show the real average alongside the one without the delayed customer.","rules":[{"type":"plainText"},{"type":"maxWords","max":70}],"mistakes":[{"title":"Hiding the outlier","why":"The board draft quietly uses 12 days.","fix":"Say: \"Show both averages with labels.\"","checks":["r1"]},{"title":"Naming one fastest","why":"Two customers tie at 9 days and the AI names only one.","fix":"Say: \"Name every customer tied for fewest days.\"","checks":["r2"]},{"title":"No working","why":"The AI gives only the averages.","fix":"Say: \"Show the sum and division.\"","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":"Names the labels","patterns":["all customers:","without dune:","fastest:"]},{"label":"Asks for sums","patterns":["sum","division","/ 6"]}],"hint":"Outliers change averages. Ask for both versions with working, and for ties to be listed.","rubricLabels":["The output is exactly three lines starting All customers:, Without Dune: and Fastest:","All customers shows the sum 12 + 9 + 15 + 30 + 9 + 15 = 90 and 90 / 6 = 15 days, and Without Dune shows 60 / 5 = 12 days","Fastest names both Birch Labs and Elm Partners at 9 days"]}