RCP-000-000-041-COMPETITOR-DIFFERENTIATOR

{
“recipe_id”: “RCP-000-000-041”,
“recipe_name”: “Competitor Differentiator”,
“version”: “v3.00a”,
“schema_version”: “1.1”,
“schema_profile”: “user-recipe”,
“authored_by”: “Cat (P067, H071)”,
“source_of_truth”: “project/subprojects/SP10-recipe-build-out/phase3/recipe-41/RCP-041-SUPPLEMENTAL-CONTENT-v3_00a.txt”,
“audience_scope”: “AI EXECUTION GUIDANCE (NOT FOR HUMAN USERS)”,
“ai_to_ai_communication”: {
“purpose_and_positioning”: {
“type”: “prose”,
“body”: “This recipe is the capstone of the Niche Discovery series and the most complex consolidation in the CRAFT recipe library. It absorbed three separate competitive intelligence recipes (042, 043, 044) because with DR integration, the distinction between ‘landscape analysis,’ ‘content gap finding,’ and ‘customer voice mining’ becomes a distinction between DR prompt angles, not separate recipe workflows. The consolidation serves users better: instead of running four recipes with overlapping intake and redundant competitive research, they run ONE recipe that generates targeted DR prompts across all relevant angles and synthesizes everything into a unified differentiation strategy.”
},
“platform_access_problem”: {
“type”: “prose”,
“body”: “All four original recipes assumed the AI could access competitor websites, read their content, check SEO rankings, and browse customer reviews. The AI cannot do any of this. This is not a limitation to work around — it is the fundamental reason for the DR integration. Deep Research tools CAN access these sources and produce reports the AI can read. The AI must NEVER: describe a competitor’s website design quality without DR evidence, assess a competitor’s content strategy without DR evidence, quote or paraphrase customer reviews without DR evidence, estimate SEO rankings or keyword performance without DR evidence, or generate a comparison matrix with cells filled from general knowledge. Every cell in every comparison, every competitive assessment, every customer sentiment claim MUST trace back to a DR report or be flagged as ‘not covered in your research.'”
},
“dr_prompt_design”: {
“type”: “prose”,
“body”: “Competitive DR prompts must be SPECIFIC to produce actionable intelligence. Bad: ‘Research competitors in the meal planning market.’ Good: ‘Analyze the competitive positioning of Mealime, PlateJoy, and Eat This Much in the meal planning market targeting women over 40 with hormonal health concerns. For each competitor, identify: (1) their stated value proposition and target audience from their website and marketing, (2) their pricing tiers and what each includes, (3) their content strategy: blog topics, publishing frequency, social media presence, (4) customer reviews from App Store, Google Play, and Trustpilot: top 3 complaints and top 3 praises with representative quotes, (5) their apparent SEO strategy: what terms they rank for, what content types they produce. Cite sources for all data points.’ The AI must generate prompts at this level of specificity, naming the actual competitors from intake and requesting structured, source-cited output.”
},
“selecting_competitive_angles”: {
“type”: “prose”,
“body”: “The AI decides which DR prompt angles to recommend based on intake answers. The decision framework: Goal ‘landscape’ — always include landscape positioning, optional pricing/business model. Goal ‘content_seo’ — always include content/SEO strategy, optional landscape for context. Goal ‘customer_voice’ — always include customer reviews and sentiment, optional competitive weaknesses for context. Goal ‘differentiation’ or ‘all’ — include landscape + customer voice minimum, add content/SEO and pricing if user has enough competitors and scope. The AI should explain its angle selection reasoning when presenting prompts.”
},
“handling_uneven_dr_coverage”: {
“type”: “prose”,
“body”: “DR reports will inevitably cover some competitors better than others and some angles more thoroughly than others. The AI must: work with whatever coverage exists, be transparent about uneven coverage (‘Your research covered Competitor A thoroughly but only briefly mentioned Competitor C’), flag per-competitor intelligence confidence, never pad thin coverage with fabricated assessments to make the analysis look balanced, and note coverage gaps in the action plan as areas needing additional research. If one competitor has rich review data and another has none, the customer voice analysis should cover the data-rich competitor in depth and explicitly state what is missing for the others.”
},
“gap_analysis_structure”: {
“type”: “prose”,
“body”: “Phase 2 presents gaps across three dimensions. Not all dimensions will have DR data. POSITIONING GAPS: almost always possible if landscape DR was run — map competitors on relevant dimensions, identify white space, most reliable analysis. CONTENT/EXPERIENCE GAPS: only possible if DR covered content strategy — if not, skip and note the gap. CUSTOMER VOICE GAPS: only possible if DR covered reviews — if not, skip and note, if partially covered analyze what is available and flag missing competitors. The AI should never force all three sections if the data does not support them. Quality analysis of what the data covers beats thin analysis stretched across all dimensions.”
},
“differentiation_strategy_grounding”: {
“type”: “prose”,
“body”: “The Phase 3 differentiation strategy must pass TWO tests. Test 1 — Evidence test: Is the primary differentiator supported by DR evidence? Can the AI cite a report showing that competitors DON’T do this and customers DO want it? If not, it is a hypothesis, not a strategy. Test 2 — Authenticity test: Can the user actually deliver this? A differentiation strategy the user cannot execute is worse than useless. The AI should cross-reference the proposed differentiator against the user’s stated strengths and capabilities. If the evidence is strong but the user’s fit is questionable, present it honestly.”
},
“competitive_response_scripts”: {
“type”: “prose”,
“body”: “The ‘Why not [Competitor]?’ responses are among the most directly useful outputs. They must be: grounded in DR evidence (reference real competitor weaknesses, not invented ones), respectful (focus on your unique value, not competitor bashing), honest (do not claim advantages you do not have), and specific (not generic ‘we offer better service’ but ‘our customers get [specific thing] that [Competitor] does not offer, which addresses the [specific complaint] we saw in their reviews’).”
},
“series_capstone_positioning”: {
“type”: “prose”,
“body”: “Users who completed the full Niche Discovery series arrive at this recipe with: RCP-037 output (skills/passions alignment), RCP-038 DR files (niche evaluation research), RCP-039 DR files (gap identification research), RCP-040 output (target customer persona). The AI should leverage ALL available context. If the user brings prior DR files, extract competitive intelligence from them. The persona from RCP-040 can inform which competitive dimensions matter most to the target customer. The gap analysis from RCP-039 can confirm positioning opportunities. Users arriving without prior series context get the full value of this recipe alone — it is self-contained. The series context enriches but is not required.”
},
“common_user_patterns”: {
“type”: “prose_with_list”,
“preamble”: “Five common user behavior patterns the AI should be prepared for:”,
“list”: [
“Users who want to analyze 10+ competitors: Redirect to 3-5 most relevant. Comprehensive analysis of 5 beats surface-level analysis of 10. DR prompts become unfocused with too many targets.”,
“Users who expect the AI to browse competitor sites: Explain clearly that this is what the DR step provides. The Deep Research prompts will have the DR tool analyze those exact sites and produce reports the AI can work with.”,
“Users who bring only landscape data but want full differentiation: Work with what is available but note the gaps. The differentiation strategy is grounded in positioning data; adding customer voice research would strengthen the messaging pillars significantly.”,
“Users who want to skip straight to messaging: Redirect through the analysis. Effective messaging must be grounded in competitive reality — map the landscape first so messaging targets real gaps.”,
“Users whose competitors are very similar: This is the hardest scenario and the most valuable one. When competitors look alike, differentiation matters most. Focus on customer voice data for micro-level gaps, and experience/service model differences.”
],
“postamble”: “”
}
},
“lessons_learned”: []
}

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