{"id":"cs-decision-maker-map-quoted-evidence","audience":"sales","category":"support-work","technique":"grounding","track":"support","level":"advanced","title":"Map who decides on a deal, with a short exact quote for each","free":false,"task":"Build a plain-text table with the header row exactly \"Name | Role | Evidence\" and one row per person in the order given. Role is one of Decider, Influencer, Blocker, Process or Unknown. Evidence is an exact quote of 8 words or fewer copied from the thread in quotation marks, or \"none\" if the person never wrote anything. Do not infer roles from job titles. Plain text.","materialLabel":"Your material (attached to your prompt automatically)","material":"ROLE DEFINITIONS: Decider = signs or approves the spend. Influencer = recommends for it. Blocker = states a condition or objection. Process = handles paperwork or steps, no stance. Unknown = nothing in the thread shows a role.\n\nPEOPLE (order): Mara Quinn (CFO), Leo Park (IT director), Sunil Rao (head of operations), Dee Wells (procurement), Rob Hale (legal, cc'd)\n\nTHREAD (Nov 3-5, Delmar Print, deal $80,000)\nSunil: \"I love it and my team wants it. Mara signs everything over $50k, so this one is hers.\"\nLeo: \"I won't approve anything without SSO groups. That's non-negotiable.\"\nMara: \"Send me the three-year cost by Friday and I'll sign.\"\nDee: \"Send the redlines to me and I'll route them.\"\n(Rob Hale is copied on every message and has not replied.)\n\nSunil's title is \"head of operations\" and he runs the day-to-day product.","rules":[{"type":"plainText"},{"type":"maxWords","max":120}],"mistakes":[{"title":"Inferring from titles","why":"The AI makes Sunil the Decider because he runs operations.","fix":"Say: \"Do not infer roles from job titles; use only the thread.\"","checks":["r1"]},{"title":"Paraphrasing evidence","why":"The AI summarizes instead of quoting.","fix":"Say: \"Evidence is an exact quote of 8 words or fewer.\"","checks":["r2"]},{"title":"Guessing for Rob","why":"The AI assigns legal a role.","fix":"Say: \"If a person wrote nothing, the role is Unknown and evidence is none.\"","checks":["r1","r2"]},{"title":"Getting markdown back","why":"AI adds bold and headings by default, which show up as stray symbols where this is pasted.","fix":"Say \"plain text, no bold, no headings, no asterisks\".","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"The AI runs long and cannot count its own words.","fix":"Cap each part (\"each line under 12 words\") and add \"under N words in total\".","checks":["maxWords"]},{"title":"Leaving a requirement unstated","why":"The AI follows its own defaults unless the prompt spells this out.","fix":"State it plainly in your prompt: the header row is exactly 'Name | Role | Evidence' with five rows in the order Mara, Leo, Sunil, Dee, Rob.","checks":["r0"]}],"promptHints":[{"label":"Gives the header","patterns":["name \\|","header"]},{"label":"Lists the five roles","patterns":["decider","influencer","blocker","process","unknown"]},{"label":"Requires exact quotes","patterns":["exact quote","verbatim","quotation"]},{"label":"Bans title inference","patterns":["job title","do not infer","don't infer"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]},{"label":"Sets a word cap","patterns":["\\d+\\s*words","under \\d+","word"]}],"hint":"Deal maps go wrong when AI trusts titles. Define roles, require an exact quote and set a fallback for silence.","mission":"Work out who decides on this deal, with proof.","musts":["Exact quotes, 8 words max","Roles not from titles","Silent people get none"],"rubricLabels":["The header row is exactly \"Name | Role | Evidence\" with five rows in the order Mara, Leo, Sunil, Dee, Rob","The roles are Mara Decider, Leo Blocker, Sunil Influencer, Dee Process and Rob Unknown (Sunil is not the Decider despite his title)","Each evidence entry is an exact quote of 8 words or fewer from the thread in quotation marks, and Rob's evidence is none"]}