RCP-000-000-046-AUDIENCE-MISCONCEPTION-MAPPER

{
“recipe_id”: “RCP-000-000-046”,
“recipe_name”: “Audience Misconception Mapper”,
“version”: “v2.00a-R”,
“schema_version”: “1.1”,
“schema_profile”: “user-recipe”,
“authored_by”: “Cat (P067, H073)”,
“source_of_truth”: “project/subprojects/SP10-recipe-build-out/phase3/recipe-46/RCP-046-SUPPLEMENTAL-CONTENT-v2_00a-R.txt”,
“audience_scope”: “AI EXECUTION GUIDANCE (NOT FOR HUMAN USERS)”,
“ai_to_ai_communication”: {
“purpose_and_positioning”: {
“type”: “prose”,
“body”: “The Audience Misconception Mapper helps users think through what misconceptions a specific audience might hold about a topic, and how to approach correcting them. The core design innovation is the user-as-expert pattern: the user provides real audience knowledge from actual interactions, and the AI structures that knowledge into an actionable framework while surfacing possibilities the user may not have considered. The key reframe from the original recipe (v2.00a) was replacing ‘audience research with psychological profiling’ framing with ‘audience thinking framework with user validation.’ The AI does not profile audiences — it helps users think more systematically about audiences they already know. This division of expertise produces better outcomes than AI-generated audience profiles, which would be fabricated.”
},
“capability_boundaries”: {
“type”: “prose”,
“body”: “The AI can suggest misconceptions an audience MIGHT hold based on general demographic patterns in training data. It can help users think through why certain beliefs might persist with their specific audience, provide communication principles (not scripts), and structure the user’s own observations into actionable frameworks. The AI cannot profile real audiences with psychological accuracy, know what specific channels an audience trusts, predict how receptive an audience will be to correction, generate effective messaging without the user’s input, measure or quantify audience beliefs, or identify ‘trusted messengers’ for a specific audience. The behavioral rules (especially RULES 1–4, 7, and 8) exist to prevent the AI from pretending otherwise. These boundaries are not limitations — they define the recipe’s honest operating zone.”
},
“user_as_expert_pattern”: {
“type”: “prose”,
“body”: “This is the recipe’s central behavioral mechanism and must be understood to execute correctly. Phase 1 captures four inputs: AUDIENCE (who), TOPIC (what), USER_OBSERVATIONS (what the user already knows from real interactions), and GOAL (what they want to do with the analysis). USER_OBSERVATIONS is the most valuable input — it represents real data from actual audience interactions. In Phase 2, the AI presents audience hypotheses (information environment, sticky factors, receptivity considerations) and explicitly asks the user to validate or correct. In Phase 3, the AI builds misconception mapping on CONFIRMED understanding only — never on unvalidated assumptions. Every audience claim uses hedged language (‘possibly because…’, ‘consider whether…’) and carries a verification check. If the user provides observations in Phase 1, those observations are addressed FIRST in Phase 3 before AI-suggested possibilities. The worst outcome is the user providing detailed audience knowledge and receiving generic output that ignores it.”
},
“goal_branching_design”: {
“type”: “prose”,
“body”: “Phase 4 branches based on the user’s GOAL selection from Phase 1 Question 4. This is the first goal-branched recipe in the Misconception Analysis series and requires careful execution. Content/marketing branch provides communication approach principles — messaging frameworks the user adapts to their brand voice. Sales/training branch provides objection preparation — how misconceptions manifest as objections and response principles. Product/onboarding branch provides experience design considerations — friction points and proactive correction approaches. Strategic understanding receives the full analytical framework without action-oriented narrowing. The AI must read the GOAL value before generating Phase 4 and produce ONLY the relevant branch plus the universal verification section. Generating all branches wastes the user’s time and dilutes the personalization value. Option E (‘Something else’) requires the AI to compose a custom Phase 4 section based on the user’s description.”
},
“verification_threading”: {
“type”: “prose”,
“body”: “Every audience assumption the AI makes should come with a way for the user to check it against real audience data (RULE 10). In Phase 2, each hypothesis section ends with ‘Does this feel right for your audience? What would you adjust?’ In Phase 3, each misconception carries a ‘Check: Does this match what you’ve seen?’ prompt. In Phase 4, the universal verification section provides three validation approaches: quick check (test with 3-5 real audience members), optional DR research prompt (audience-specific search query), and A/B test recommendation (small-segment messaging test before full campaign). The verification prompts should be specific to the actual audience and topic — not generic templates. This threading ensures the user has multiple opportunities to validate AI output against reality throughout the workflow.”
},
“sensitive_topic_handling”: {
“type”: “prose”,
“body”: “RULE 11 requires explicit flagging when the topic involves sensitive beliefs — health, politics, religion, identity. This is particularly important for an audience-mapping recipe because misconception correction in sensitive domains intersects with deeply held belief systems. The flag should appear at the Phase 1 confirmation step (before analysis begins) with a recommendation for professional communication expertise beyond what AI can provide. The AI should not refuse to analyze sensitive topics — it should analyze them with appropriate framing and stronger verification emphasis. Misconception correction in sensitive domains carries higher stakes than general topics because the correction approach matters as much as the content. A factually correct correction delivered with the wrong framing can backfire and reinforce the misconception.”
},
“series_context”: {
“type”: “prose”,
“body”: “RCP-046 is the second recipe in the Misconception Analysis series (2 of 4). RCP-045 (Misconception Debunker) identifies misconceptions about a topic. RCP-046 maps misconceptions to specific audiences — who holds them, why, and how to approach correction per-audience. The logical progression is: identify (045) → audience-map (046) → [047] → [048]. Users who have run RCP-045 first will arrive with a list of identified misconceptions and want to understand which audiences hold which ones. Users running RCP-046 standalone will need to identify misconceptions as part of the audience-mapping process. The recipe handles both paths through Phase 1 intake — USER_OBSERVATIONS captures prior work if it exists, and ‘I’m exploring’ handles fresh starts.”
},
“common_user_patterns”: {
“type”: “prose_with_list”,
“preamble”: “Five common user behavior patterns the AI should be prepared for:”,
“list”: [
“Users coming from RCP-045: They have a list of misconceptions and want to map them to audiences. Phase 1 USER_OBSERVATIONS will be rich with prior analysis. The AI should acknowledge this existing work and build on it rather than starting fresh — ‘It looks like you’ve already identified several misconceptions. Let’s focus on which audiences hold each of these and how to approach them.'”,
“Users with vague audience definitions: ‘My customers’ or ‘people in my industry’ are too broad. RULE 7’s honesty principle applies but more importantly, the Phase 1 examples model the right specificity level. Help narrow: ‘Can you describe a specific type of customer — their role, how they find you, what they already believe about your space?'”,
“Users who want sample messaging: They will ask for specific language to use with their audience. RULE 8 prevents this — the AI provides messaging PRINCIPLES, not scripts. Redirect: ‘I can give you principles for how to frame corrections with this audience. You know their voice better than I do — what tone works in your existing communications with them?'”,
“Users with multiple audience segments: The recipe is designed for one audience at a time. If the user describes multiple segments, suggest running the recipe once per segment: ‘Each audience may hold different misconceptions for different reasons. Want to start with the segment that’s most important to your current goal?'”,
“Users in sensitive domains: Health misconceptions, political beliefs, religious practices, identity topics. RULE 11 applies. These users often have the strongest need for audience-specific correction approaches but also the highest risk of harm from poorly framed corrections. Emphasize professional communication expertise and verify more aggressively.”
],
“postamble”: “”
}
},
“lessons_learned”: []
}

Show/Hide accordion — “Extended Information for the AI” section (AI-to-AI execution guidance, failure modes, tone calibration, common mistakes)