{"id":"cx-csat-small-sample-caution-note","audience":"managers","category":"support-work","technique":"verification","track":"support","level":"intermediate","title":"Write a CSAT note that does not over-read a tiny sample","free":false,"task":"Start with the line \"CSAT NOTE - week 45\" on its own. Write three lines starting \"Headline:\", \"Caution:\" and \"Action:\" for the weekly team note. A score from fewer than 30 responses is too few to compare. The headline must not claim any team improved or is better, and the Action must not suggest coaching or praise based on a too-small sample. Plain text, under 70 words.","materialLabel":"Your material (attached to your prompt automatically)","material":"WEEKLY CSAT (scale 1 to 5)\nThis week:\n- Team A: 4.8 from 5 responses\n- Team B: 4.3 from 120 responses\nLast week:\n- Team A: 4.1 from 60 responses\n- Team B: 4.3 from 110 responses\n\nNOTES\nA director asked in chat: 'Did Team A improve? Should we recognize them?' Team A handled about 140 tickets this week, but few customers filled in the survey (a response rate of about 4%). Team B's survey email was fixed on Monday, so its response rate is back to normal.","rules":[{"type":"plainText"},{"type":"maxWords","max":70}],"mistakes":[{"title":"Declaring Team A improved","why":"The AI sees 4.8 versus 4.1 and celebrates.","fix":"Say: \"Fewer than 30 responses is too few to compare.\"","checks":["r0","r1"]},{"title":"Recommending recognition","why":"The AI suggests praising Team A.","fix":"Say: \"No coaching or praise from a too-small sample.\"","checks":["r2"]},{"title":"Missing the sample sizes","why":"The AI reports scores without counts.","fix":"Say: \"Always include the response counts.\"","checks":["r0","r1"]},{"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":"Names the three lines","patterns":["headline:","caution:","action:"]},{"label":"States the minimum sample","patterns":["fewer than 30","30 responses","too few"]},{"label":"Rules out recognition or coaching","patterns":["no (praise|coaching|recognition)","don'?t (praise|coach|suggest)"]},{"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":"Name the three lines, state the minimum sample size and what the Action must not suggest.","rubricLabels":["The first line is exactly \"CSAT NOTE - week 45\". The line starting \"Headline:\" gives Team B at 4.3 from 120 responses (unchanged) and does not say Team A improved or is better","The line starting \"Caution:\" says Team A's 4.8 comes from only 5 responses, fewer than 30, so it can't be compared with last week's 4.1 from 60","The line starting \"Action:\" suggests collecting more responses (such as checking the survey) and does not suggest recognition or coaching for Team A"]}