{"id":"dat-cs-csat-minimum-responses","audience":"customer-support","category":"data","technique":"context","title":"Rank agent CSAT while flagging tiny samples","free":false,"task":"You're posting October CSAT by agent. Your team rule: under 20 survey responses is \"not enough data,\" with no score. CSAT = positive ÷ responses. Write exactly 4 numbered lines in export order, each as Name: positive ÷ responses = X% (or not enough data), then one unnumbered last line: Top: [agent with enough data]. Plain text, under 60 words.","materialLabel":"Survey export (attached to your prompt automatically)","material":"CSAT SURVEYS - October (per agent)\n\nAgent | Responses | Positive (4-5 stars)\nAna Reyes | 50 | 45\nBo Lindqvist | 40 | 38\nCy Okoro | 10 | 9\nDee Marsh | 60 | 51\n\nNotes:\n- Cy joined Oct 20 and only worked 8 shifts.\n- One of Dee's negative surveys was about shipping, not her reply. Survey tool can't exclude it.\n- Survey goes out 24 hours after a ticket closes.\n- Ana asked to be on the escalations queue next month.\n- CSAT survey is one question: \"How satisfied were you with your support experience?\"\n- Ratings of 4 or 5 count as positive; 1 to 3 do not.\n- Bo mostly handles billing tickets, which tend to be quick.\n- Monthly CSAT post goes in the team channel every first Monday.\n- Ana and Dee both mentored new hires this month.","rules":[{"type":"numberedItems","count":4},{"type":"plainText"},{"type":"maxWords","max":60}],"mistakes":[{"title":"Not giving the minimum","why":"The AI scores Cy at 90% from 10 surveys.","fix":"Add: \"Under 20 responses = not enough data.\"","checks":["r0"]},{"title":"Not asking to see the work","why":"Agents will ask how their number was figured.","fix":"Add a line to copy: \"1. Ana Reyes: 45 ÷ 50 = 90%\"","checks":["numberedItems","r1"]},{"title":"Leaving the ending open","why":"The AI adds coaching advice for each agent.","fix":"Add: \"Then one line: Top: [agent]. Nothing else.\"","checks":["r2"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total word limit and it often lands over it.","fix":"Cap each line: \"each line under 10 words.\"","checks":["maxWords"]},{"title":"Forgetting where it goes","why":"AI loves markdown tables and bold, which show up as clutter in a team channel.","fix":"Add: \"Plain text, no bold, headings or tables.\"","checks":["plainText"]}],"promptHints":[{"label":"Gives the minimum","patterns":["20","not enough data","minimum|sample"]},{"label":"Defines CSAT","patterns":["positive","÷|divided|out of"]},{"label":"Asks to show the math","patterns":["show (the |your )?(math|work)","x \\$|\\bx\\b.{0,10}=","calculation","step"]},{"label":"Sets a word limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no (headings|tables)"]}],"hint":"A tiny sample can look like a great score. Tell the AI your minimum and show it the line shape.","rubricLabels":["Cy Okoro is marked not enough data (10 responses), with no 90% score","Ana is 45 ÷ 50 = 90%, Bo is 38 ÷ 40 = 95% and Dee is 51 ÷ 60 = 85%","The last line names Bo Lindqvist as top, with no intro or coaching notes"]}