{"id":"mkt2-weekly-report-two-sources-ceo","audience":"marketing","category":"summarizing","track":"marketing","technique":"verification","level":"advanced","title":"Write a four-line weekly report when two data sources disagree","free":false,"task":"You're writing the weekly marketing update for your CMO, Omar. Write a prompt for exactly four plain-text lines labeled \"Leads:\", \"Lead rate:\", \"Top win:\" and \"Ask:\", each under 20 words. Take lead counts from the CRM, which is the source of truth for leads, and visits from the web dashboard. The lead rate is CRM leads divided by dashboard visits, shown as a calculation to one decimal percent.","materialLabel":"Weekly numbers (attached to your prompt automatically)","material":"WEEKLY MARKETING NUMBERS - week ending Nov 6\n\nWeb dashboard (Nov 6): visits 24,300; leads captured 412 (counts form submissions, including duplicates and test entries).\nCRM (Nov 8, after dedupe): new leads 388.\nGap: 24 (duplicates and tests, per ops).\n\nHighlights\n- Webinar registrations: 310, up from 254 last week (+22%).\n- Paid social CPL: $41, down from $47.\n- The blog redesign went live Tuesday; too early to judge.\nRisks\n- Two team members out next week.\nRequests\n- Approve a $1,500 boost for the webinar promotion by Friday.\n- Hiring: the designer role is still open (not for this week's update).","rules":[{"type":"plainText"},{"type":"maxWords","max":80}],"mistakes":[{"title":"Using the dashboard's 412","why":"The AI takes the larger, more recent-looking number.","fix":"Say: \"Leads come from the CRM, the source of truth: 388.\"","checks":["r1"]},{"title":"Skipping the calculation","why":"The AI states a rate with no working.","fix":"Say: \"Show the calculation: leads / visits, one decimal.\"","checks":["r1"]},{"title":"Listing every request","why":"The AI includes hiring and risks.","fix":"Say: \"Ask: the single request with its deadline.\"","checks":["r2"]},{"title":"Missing labels","why":"The AI writes a narrative.","fix":"Name the four labels.","checks":["r0"]},{"title":"Letting markdown through","why":"AI adds bold text and headings by default.","fix":"Add: \"Plain text only, no bold, no headings.\"","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and often runs past a word limit.","fix":"Cap each part (for example \"each line under 15 words\") so the total lands well under the limit.","checks":["maxWords"]}],"promptHints":[{"label":"Names the four labels","patterns":["leads:.*lead rate:.*top win:.*ask:"]},{"label":"Uses the CRM for leads","patterns":["crm","source of truth"]},{"label":"Shows the calculation","patterns":["calculation","divided by","show the"]},{"label":"Limits the ask to one","patterns":["single","one request","one ask"]},{"label":"Caps length","patterns":["20 words","80 words"]}],"hint":"When two sources disagree, say which one wins and for what. Give the labels, the source rule, the calculation and a single ask.","mission":"Send CMO Omar a weekly update when data sources disagree.","musts":["Leads from CRM","Visits from dashboard","Show lead rate calculation"],"rubricLabels":["The output has exactly four lines starting Leads:, Lead rate:, Top win: and Ask:, each under 20 words","Leads uses 388 from the CRM (not 412), and Lead rate shows 388 / 24,300 = 1.6%","Top win names the webinar registrations (310, up 22%) or the lower paid social CPL, and Ask is the single request to approve the $1,500 webinar boost by Friday"]}