{"id":"search-mgr-research-findings-confidence","audience":"managers","category":"ai-search","track":"research","technique":"verification","title":"Label a deep-research report's findings by confidence","free":false,"task":"A deep-research tool gave you 4 findings about compressed work weeks before your team vote. Label each High, Medium or Low using your rules: High = 2 or more sources from 2024 or later; Medium = exactly 1 source from 2024 or later; Low = only older sources or a source paid for by a vendor. Write exactly 4 numbered lines, each with the label and the source count and years that justify it. Plain text, under 100 words.","materialLabel":"The deep-research findings and their sources (attached to your prompt automatically)","material":"DEEP-RESEARCH REPORT: \"Do 4x10 schedules work for support teams?\"\n\nFinding 1: Teams on 4x10 schedules report higher job satisfaction.\nSources: Okafor & Lin, Journal of Work Studies (2025); State Labor Office survey (2024).\n\nFinding 2: First-response times stay the same or improve.\nSources: ShiftPro case study (2025) - ShiftPro sells scheduling software and paid for the study.\n\nFinding 3: Burnout drops in the first year.\nSources: Hartley Institute report (2019); Pearce, HR Quarterly (2021).\n\nFinding 4: Sick days fall by about 10%.\nSources: Vance et al., Occupational Health Review (2024).\n\nReport summary (written by the tool): \"Strong evidence supports moving to a 4x10 schedule across all four areas.\"\n\nTeam context: 11 support agents, current hours 8-5 Mon-Fri, vote on Nov 18.","rules":[{"type":"numberedItems","count":4},{"type":"maxWords","max":100},{"type":"plainText"}],"mistakes":[{"title":"Trusting the report's summary","why":"The AI repeats \"strong evidence\" because the report says so.","fix":"Say: \"Label each finding yourself using my rules, not the report's summary.\"","checks":["r2"]},{"title":"Not giving your rules","why":"The AI judges confidence by gut feel, so a vendor-paid study can rate High.","fix":"Add: \"High = 2+ sources from 2024 on; Medium = 1; Low = older or vendor-paid.\"","checks":["r0","r1"]},{"title":"Labels with no proof","why":"The AI gives a label but not the count and years, so you can't check it.","fix":"Add: \"Each line shows the source count and years.\"","checks":["r2"]},{"title":"Long or formatted output","why":"AI writes a section per finding with bold headings.","fix":"Add: \"Exactly 4 numbered lines, each under 20 words, plain text.\"","checks":["numberedItems","maxWords","plainText"]}],"promptHints":[{"label":"Gives your confidence rules","patterns":["high\\s*=","2 or more|2\\+|two or more","2024"]},{"label":"Flags vendor-paid sources","patterns":["vendor","paid","sponsor"]},{"label":"Asks for the proof on each line","patterns":["source count","years","how many sources"]},{"label":"Sets the shape","patterns":["\\b(4|four)\\b.{0,20}lines","exactly","numbered"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown"]}],"hint":"Research tools grade their own homework generously. Give the AI your confidence rules and make it show the count and years on every line.","rubricLabels":["Finding 1 is labeled High (2 sources, 2024 and 2025) and Finding 4 is labeled Medium (1 source, 2024)","Finding 2 is labeled Low because the only source was paid for by a vendor (ShiftPro), and Finding 3 is labeled Low because its sources are from 2019 and 2021","Every line gives the source count and the years behind its label, and the reply does not repeat the report's claim of strong evidence across all four areas"]}