{"id":"res-np-gala-press-release-tally","audience":"nonprofit","category":"fact-checking","technique":"verification","title":"Check a gala press release against the final event tally","free":false,"task":"Your board chair drafted a press release about last week's gala, and the final tally from the finance team just came in. You want one numbered line per stat in the release, under 60 words total, labeled Matches, Wrong, or Not in tally, with the tally's figure after any Wrong label. Use only the final tally, plain text, nothing else.","materialLabel":"The final gala tally and the press release stats (attached to your prompt automatically)","material":"FINAL GALA TALLY - Harvest Moon Gala 2026 (Finance, Nov 4)\nAttendees: 318\nGross raised: $214,600\nEvent costs: $41,300\nNet raised: $173,300\nLive auction: $62,000\nPaddle raise (scholarship fund): $48,500\nNew donors: 57\n\nPreliminary count on gala night (for reference): gross $226,000, attendees 340.\n\n-----\nPRESS RELEASE DRAFT - stats used\n1. \"More than 300 guests attended.\"\n2. \"The evening raised $226,000.\"\n3. \"The paddle raise brought in $48,500 for scholarships.\"\n4. \"We welcomed 75 new donors.\"\n5. \"It was our most successful gala in 20 years.\"","rules":[{"type":"maxWords","max":60},{"type":"plainText"}],"mistakes":[{"title":"Using gala-night numbers","why":"The preliminary count is in the tally as a reference, so the AI may treat it as valid.","fix":"Say: \"Use only the final Nov 4 figures.\"","checks":["r0"]},{"title":"Calling history claims wrong","why":"The tally doesn't cover past galas, so 'most successful' can't be checked here.","fix":"Add: \"If the tally doesn't cover it, label it Not in tally.\"","checks":["r1"]},{"title":"Getting a new release","why":"The AI rewrites the release instead of showing what to fix.","fix":"Say: \"Label only, no rewrite.\"","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 10-20% over.","fix":"Cap each line: \"each line under 10 words.\"","checks":["maxWords"]},{"title":"Getting markdown back","why":"AI defaults to bold labels and headings, which show up as stray symbols in an email to your board chair.","fix":"Ask for \"plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Gives exact labels","patterns":["matches","not in (the )?tally","label"]},{"label":"Uses the final figures","patterns":["final","nov(ember)?\\.? 4","not (the )?preliminary"]},{"label":"Asks for the tally's figure","patterns":["tally('s)? figure","correct (number|figure)","give the"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","one (short )?sentence","word (limit|count)"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"Event-night numbers often change once the books close. Tell the AI which tally is final and give it labels, including one for claims it can't check.","rubricLabels":["Labels stat 2 Wrong (final gross is $214,600; $226,000 was the preliminary count) and stat 4 Wrong (57 new donors)","Labels stats 1 and 3 Matches, and stat 5 (most successful in 20 years) Not in tally","Outputs only the numbered labeled lines: no intro, no rewritten release, no PR advice"]}