{"id":"dat-cs-handle-time-outage-calls","audience":"customer-support","category":"data","technique":"context","title":"Average handle times after removing outage calls","free":false,"task":"Your handle time target is 12 minutes or less. Calls over 120 minutes were from Tuesday's system outage and don't count. Write exactly 3 numbered lines, one per agent, each as Agent: (counted calls added) ÷ count = X min, then OK or OVER, then one unnumbered last line: Coach: [agents OVER]. Plain text, under 70 words.","materialLabel":"Call log sample (attached to your prompt automatically)","material":"HANDLE TIME SAMPLE - 5 calls per agent, week of Nov 3 (minutes)\n\nJo Park: 8, 12, 10, 150, 10\nMax Ruiz: 9, 11, 13, 7, 10\nRae Kim: 14, 16, 15, 135, 15\n\nNotes:\n- Tuesday 2-5 pm: billing system outage; calls stayed open while agents waited on hold with IT.\n- Rae handles most of the Spanish-language queue; those calls run longer on average.\n- QA scores for all three were above 90%.\n- Dashboard average: Jo 38 min, Max 10 min, Rae 39 min (includes outage calls).\n- Team lead asked for this before Friday's 1:1s.\n- New knowledge base article on refunds went live Monday.\n- Handle time includes after-call notes.\n- Shared with the team in the usual folder.","rules":[{"type":"numberedItems","count":3},{"type":"plainText"},{"type":"maxWords","max":70}],"mistakes":[{"title":"Not mentioning the outage","why":"The AI averages in the 150- and 135-minute calls, like the dashboard.","fix":"Add: \"Calls over 120 minutes were outage calls. Leave them out.\"","checks":["r0","r1"]},{"title":"Not giving the target","why":"The AI can't mark OK or OVER.","fix":"Add: \"Target: 12 minutes or less.\"","checks":["r2"]},{"title":"Not asking to see the work","why":"Agents will want to see which calls counted.","fix":"Add a line to copy: \"1. Jo: (8 + 12 + 10 + 10) ÷ 4 = 10 min OK\"","checks":["numberedItems","r0"]},{"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 14 words.\"","checks":["maxWords"]},{"title":"Forgetting where it goes","why":"AI loves markdown tables and bold, which show up as clutter in 1:1 notes.","fix":"Add: \"Plain text, no bold, headings or tables.\"","checks":["plainText"]}],"promptHints":[{"label":"Removes outage calls","patterns":["outage","120","leave out|exclude|drop"]},{"label":"Gives the target","patterns":["12 min","target"]},{"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":"Two calls are outliers with a known cause. Tell the AI to remove them and give it the target.","rubricLabels":["Jo leaves out the 150: (8 + 12 + 10 + 10) ÷ 4 = 10 min OK","Max is 50 ÷ 5 = 10 min OK and Rae leaves out the 135: (14 + 16 + 15 + 15) ÷ 4 = 15 min OVER","The last line names only Rae, with nothing before the first numbered line"]}