{"id":"res-mgr-vendor-pitch-vs-case-study","audience":"managers","category":"fact-checking","technique":"verification","title":"Check a vendor's sales claims against its own case study","free":false,"task":"A scheduling software vendor emailed you big claims and attached a case study. You want exactly 4 numbered lines, one per claim in the email, each labeled Backed, Stretched, or Not in case study, with the case study's actual figure after any Stretched label. Judge only by the case study, in plain text with nothing else.","materialLabel":"The vendor's email and its case study (attached to your prompt automatically)","material":"EMAIL from Brent Hollis, ShiftWise sales:\n\"Great chatting! As promised, here's what ShiftWise does for teams like yours:\n1. Cuts scheduling time by 60%\n2. Reduces overtime costs by a third\n3. Trusted by over 500 retail chains\n4. Dunmore Grocers store managers rated it 4.6 out of 5\nCase study attached. Let's talk Thursday!\"\n\n-----\nCASE STUDY - Dunmore Grocers (12 stores, 640 employees), published by ShiftWise, 2025\nBefore ShiftWise, store managers spent about 6 hours a week building schedules. After 4 months, that dropped to about 3.5 hours, a 42% reduction.\nOvertime hours fell from an average of 210 per week across all stores to 140, a drop of one third.\nDunmore's store managers rated ShiftWise 4.6 out of 5 on average.\n\"It took a few weeks to get used to, but now I can't imagine going back,\" said one store manager.\nResults reflect Dunmore's rollout and may vary by company.","rules":[{"type":"numberedItems","count":4},{"type":"plainText"}],"mistakes":[{"title":"Asking if it's a good product","why":"The AI evaluates the software in general instead of checking each claim against the evidence.","fix":"Say: \"Label each claim against the case study only.\"","checks":["r2"]},{"title":"No fixed labels","why":"The AI hedges with 'roughly accurate', so you can't tell a stretched number from a solid one.","fix":"Give them: \"Backed, Stretched, or Not in case study.\"","checks":["r0","r1"]},{"title":"Not asking for the real figure","why":"Without the case study's number, you can't push back on Thursday's call.","fix":"Add: \"After Stretched, give the case study's figure.\"","checks":["r0"]},{"title":"Not saying how many","why":"The AI decides the length itself and usually returns more lines, one per claim than you can use.","fix":"Be exact: \"exactly 4 numbered lines, one per claim.\"","checks":["numberedItems"]},{"title":"Getting markdown back","why":"AI defaults to bold labels and headings, which show up as stray symbols in your notes for the call.","fix":"Ask for \"plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Gives exact labels","patterns":["backed","stretched","not in (the )?case study","label"]},{"label":"Names the source","patterns":["only.{0,30}case study","case study.{0,20}(only|source|truth)","against the case study"]},{"label":"Asks for the real figure","patterns":["actual (figure|number)","case study('s)? (figure|number)","real number"]},{"label":"Says exactly how many","patterns":["\\b(4|four)\\b.{0,25}(line|claim)","exactly \\d+"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"Sales emails round up their own evidence. Give the AI labels for 'true', 'stretched' and 'unsupported', and ask for the real number when it's stretched.","rubricLabels":["Labels claim 1 Stretched with the case study's 42% (about 6 to 3.5 hours), not 60%","Labels claims 2 and 4 Backed (overtime fell by a third; 4.6 out of 5), and claim 3 (500 retail chains) Not in case study","Outputs only the 4 labeled lines using Backed, Stretched or Not in case study: no intro, no buying advice, no questions to ask the vendor"]}