{"id":"dat-cs-ticket-category-shares","audience":"customer-support","category":"data","technique":"grounding","title":"Work out ticket category shares after fixing mis-tags","free":false,"task":"Your support lead wants last week's ticket mix for the Monday standup. Write exactly 4 numbered lines, one per category, each as Category: count ÷ total = X%, then one unnumbered last line naming the top category. Apply the tagging notes, leave spam out of the total, plain text, under 60 words, nothing else.","materialLabel":"Helpdesk export and notes (attached to your prompt automatically)","material":"TICKETS BY CATEGORY - week of Nov 3 (Deskline export)\n\nCategory | Tickets\nBilling | 100\nShipping | 120\nLogin / account | 60\nOther | 120\nSpam | 25\nTotal | 425\n\nTagging notes (from Ray, QA):\n- 40 of the \"Other\" tickets were really billing questions (refund status). The auto-tagger missed the word \"refund.\" Count them as Billing.\n- Spam is auto-closed and should never count in our ticket mix.\n\nOther:\n- Shipping spiked Tuesday because of the carrier delay in the Midwest.\n- Login tickets should drop once the password reset fix ships next sprint.\n- Mo is out Friday; coverage is posted.","rules":[{"type":"numberedItems","count":4},{"type":"plainText"},{"type":"maxWords","max":60}],"mistakes":[{"title":"Trusting the auto-tags","why":"The AI uses the raw counts, so Billing looks smaller than Shipping.","fix":"Add: \"Move the 40 refund tickets from Other to Billing first.\"","checks":["r0","r2"]},{"title":"Counting spam","why":"The AI divides by 425, so every percent is off.","fix":"Add: \"Leave spam out. The total is 400.\"","checks":["r1"]},{"title":"Not showing the division","why":"Bare percents hide which total the AI used.","fix":"Add a line to copy: \"1. Shipping: 120 ÷ 400 = 30%\"","checks":["r1","numberedItems"]},{"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 standup doc.","fix":"Add: \"Plain text, no bold, headings or tables.\"","checks":["plainText"]}],"promptHints":[{"label":"Applies the tagging notes","patterns":["re-?tag","40","refund","notes?"]},{"label":"Leaves spam out","patterns":["spam","400"]},{"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":"The raw export has a tagging error and spam in it. Tell the AI about both and ask it to show each division.","rubricLabels":["Billing is 140 tickets at 35% (100 plus the 40 re-tagged from Other) and Other is 80 at 20%","Spam is left out, so every percent is out of 400 (not 425): Shipping 120 = 30%, Login 60 = 15%","The last line names Billing as the top category, with no intro or closing commentary"]}