{"id":"res-mgr-deck-claims-vs-survey","audience":"managers","category":"fact-checking","technique":"verification","title":"Check your team deck's claims against the engagement survey","free":false,"task":"You drafted 5 slide headlines about your team's engagement survey and want to check them before the all-hands. You want exactly 5 numbered lines, one per headline, each labeled Supported, Overstated, or Not in survey, with the survey figure after any Overstated label. Use only the survey results, plain text, and nothing else.","materialLabel":"Your survey results and draft headlines (attached to your prompt automatically)","material":"TEAM ENGAGEMENT SURVEY - Customer Operations (Fall 2026)\nResponses: 38 of 45 team members\n- \"I would recommend this team as a great place to work\": 71% agree (Spring 2026: 64%)\n- \"I have the tools I need to do my job\": 52% agree (Spring: 55%)\n- \"My manager gives me useful feedback\": 84% agree (Spring: 82%)\n- \"I see myself here in a year\": 63% agree (Spring: 63%)\n- \"Workload is manageable\": 41% agree (Spring: 48%)\n\n-----\nMY DRAFT SLIDE HEADLINES\n1. \"Recommend-as-a-workplace score jumped 7 points since spring\"\n2. \"Nearly everyone has the tools they need\"\n3. \"Feedback from managers rated highly by 84% of the team\"\n4. \"Retention intent is climbing\"\n5. \"Team morale is the best in the company\"","rules":[{"type":"numberedItems","count":5},{"type":"plainText"}],"mistakes":[{"title":"Asking if the slides are good","why":"The AI gives presentation tips and rewrites headlines instead of checking them.","fix":"Say: \"Label each headline against the survey only.\"","checks":["r2"]},{"title":"No fixed labels","why":"The AI hedges with 'mostly accurate' and 'could be clearer', which you can't act on.","fix":"Give them: \"Supported, Overstated, or Not in survey.\"","checks":["r1","r2"]},{"title":"Missing a flat trend","why":"\"Climbing\" sounds fine unless you compare to the spring number, which the AI may not do.","fix":"Add: \"Compare to spring numbers when a headline claims a change.\"","checks":["r1","r0"]},{"title":"Not saying how many","why":"The AI decides the length itself and usually returns more lines, one per headline than you can use.","fix":"Be exact: \"exactly 5 numbered lines, one per headline.\"","checks":["numberedItems"]},{"title":"Getting markdown back","why":"AI defaults to bold labels and headings, which show up as stray symbols in your speaker notes.","fix":"Ask for \"plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Gives exact labels","patterns":["supported","overstated","not in (the )?survey","label"]},{"label":"Names the source","patterns":["only.{0,30}survey","survey.{0,20}(only|source|truth)"]},{"label":"Checks trend claims","patterns":["spring","compare","change"]},{"label":"Says exactly how many","patterns":["\\b(5|five)\\b.{0,25}(line|headline)","exactly \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"Slide headlines love to round up. Give the AI labels that separate 'true', 'stretched' and 'not in the data', and make the survey the only judge.","rubricLabels":["Labels headlines 1 and 3 Supported (71% vs 64% is 7 points; 84% feedback)","Labels 2 Overstated with 52% (not 'nearly everyone') and 4 Overstated with 63% unchanged from spring, and labels 5 Not in survey (the survey has no company comparison)","Outputs only the 5 labeled lines using Supported, Overstated or Not in survey: no intro, no rewritten headlines, no advice on presenting"]}