RCP-004-001-002-TARGET-AUDIENCE – Target Audience Analyzer

Identifies and defines primary target audience segments through strategic questioning and research-based analysis. Maps demographics, psychographics, behaviors, and motivations. Creates detailed persona profiles and optional anti-persona definition. Guided by Morgan the Strategic Brand Architect.
Recipe Name: RCP-004-001-002-TARGET-AUDIENCE – Target Audience Analyzer
RCP-004-001-002-TARGET-AUDIENCE – Target Audience Analyzer
Identifies and defines primary target audience
segments through strategic questioning and research-based
analysis. Maps demographics, psychographics, behaviors, and
motivations. Creates detailed persona profiles and optional
anti-persona definition. Guided by {PERSONA_NAME} using
the methodology established in Recipe 1.
Multi-Recipe Combo Stage Single Recipe
Recipe Category CFT-FWK-COOKBK-BRAND-ID – CRAFT Cookbook – Branding and Identity
Recipe Subcategory Blogging with A.I., Brainstorming with A.I.
Recipe Difficulty Easy
Recipe Tags: Foundational | Introduced in the POC

Requirements

  • Any AI Chat Platform (platform-agnostic recipe) Any of the following: Claude (Anthropic), ChatGPT (OpenAI), Gemini (Google), Grok (X.ai), Perplexity, Microsoft Copilot

How To Start
 

STEP 1: Policy Pre-Check
  • Scan prompt for sensitive categories including personal
    identifying information, demographic stereotyping, and
    discriminatory targeting. If potential conflict
    detected, note that audience analysis should avoid
    stereotyping or discriminatory assumptions. Focus on
    behaviors, needs, and motivations rather than protected
    characteristics.
STEP 2: Context Review
  • Load business context from Recipe 1 or user-provided
    context. {PERSONA_NAME} analyzes the context to
    understand the audience landscape. Review business
    name, industry sector, current stage, and goals to
    form strategic insights about likely audience. If
    research sources are provided, review each source and
    extract key audience insights, flagging any
    contradictions or gaps.
STEP 3: Depth Calibration
  • Calibrate analysis based on selected depth level.
    Quick mode (20 minutes) focuses on essential
    demographics and one primary persona with 5-7
    questions. Standard mode (45 minutes) covers
    demographics, psychographics, behaviors, and 1-2
    personas with 10-15 questions. Comprehensive mode
    (90 minutes) provides full analysis with 1-3 personas,
    market segmentation, and 15-20+ questions.
STEP 4: Discovery Questions – Demographics
  • Gather demographic information through strategic
    questioning. Cover age and life stage, geographic and
    cultural factors, education and expertise level. For
    B2B contexts, include company size, industry verticals,
    and role/title information. For B2C contexts, include
    employment status, career stage, and income range.
    After each answer, provide immediate strategic insight
    and connection to brand implications.
STEP 5: Discovery Questions – Psychographics
  • Explore psychological drivers including values and
    beliefs, attitudes toward relevant categories, goals
    and aspirations. Understand what success looks like
    to them (quantitative vs qualitative), their fears and
    risk perceptions, and decision-making style. Map their
    identity and belonging needs. After each answer,
    connect insights to brand messaging opportunities.
STEP 6: Discovery Questions – Behaviors
  • Understand behavioral patterns including information
    sources and trusted channels, buying behavior and
    decision triggers, community and social proof
    importance. Map current solutions and pain points
    with alternatives. Identify engagement preferences
    for content format and communication frequency.
STEP 7: Persona Construction
  • Build detailed persona profiles with name, role
    description, demographic snapshot, psychographic
    profile, behavioral patterns, and day-in-the-life
    scenario. Include an authentic persona quote capturing
    their mindset. Document strategic implications for
    brand messaging, value proposition, channels, content
    type, and objections to address. Provide confidence
    rating based on data sources used.
STEP 8: Anti-Persona Development (If Requested)
  • If anti-persona is requested, define who you are
    explicitly NOT targeting. Create profile with
    characteristics that make them a poor fit. Explain
    why they are wrong fit, what they actually need
    instead, and how to recognize them (red flags).
    Document strategic value of excluding them and
    provide messaging that self-selects them out.
STEP 9: Audience Insight Synthesis
  • Create comprehensive audience insight summary block
    containing all persona profiles, anti-persona if
    applicable, key strategic insights covering market
    size, competitive positioning, messaging themes,
    channel priorities, and content strategy. Provide
    overall confidence assessment with data gaps noted
    and recommendations for validation.
STEP 10: Completion and Next Steps
  • Deliver summary of all outputs: persona profiles,
    audience insight summary, anti-persona if created.
    Confirm what has been established about target
    audience. Provide strategic guidance for next recipe
    (Pain Point Identifier) and ask if user wants to
    proceed or refine any aspect of audience definition.

How AI Reads This Recipe

This recipe builds target audience profiles through
strategic questioning guided by {PERSONA_NAME}. The AI
should adapt question depth based on the selected
research depth parameter.
Key processing logic:
– Step 2 loads context from Recipe 1 or user input
– Step 3 calibrates question quantity and depth
– Steps 4-6 are question phases that may be shortened
or extended based on depth setting
– Step 7 constructs personas from gathered data
– Step 8 is conditional on include_anti_persona
– Step 9 synthesizes all insights into summary block
– Confidence ratings reflect data quality throughout
The persona provides strategic insights after each answer
and connects findings to brand implications. Questions
adapt based on B2B vs B2C context from business_context.
Parameter handling:
– business_context required (from Recipe 1 or direct)
– audience_research_depth defaults to standard
– number_of_personas defaults to 1 (max 3)
– include_anti_persona defaults to False
– research_sources optional (enhances confidence)

When to Use This Recipe

Use this recipe as the second step in brand development
after completing Recipe 1 (Brand Context Initializer).
The audience understanding developed here informs all
subsequent brand recipes:
– Pain Point Identifier (needs audience context)
– Value Prop Crafter (needs audience priorities)
– Competitive Edge Definer (needs audience perception)
– Elevator Pitch Builder (needs audience language)
– Brand Profile Synthesizer (needs audience fit)
Also use when pivoting to new markets, launching new
products, or validating assumptions about existing
audience understanding.

Recipe FAQ

Q: What if I do not have any existing audience research?
A: The recipe works with or without existing research.
Without research, {PERSONA_NAME} asks more discovery
questions and builds personas from your knowledge of
your market. Confidence ratings will reflect the
data source quality.
Q: How many personas should I create?
A: Start with one primary persona. Add secondary personas
only if you have genuinely distinct audience segments
with different needs. Most businesses are better served
by one well-defined persona than three vague ones.
Q: What is an anti-persona and do I need one?
A: An anti-persona defines who you are NOT targeting.
It sharpens positioning, guides feature prioritization,
and helps create messaging that self-selects the right
people. Useful when you have limited resources or need
sharp positioning.
Q: Can I update personas later?
A: Yes. Personas should evolve as you gain market data.
Re-run this recipe after beta launch, customer
interviews, or significant market learning.
 
Example 1: Fine Dining Restaurant (Standard Mode)
Parameters:
– business_context: Terra and Olive (Mediterranean
farm-to-table, pre-launch, fine dining)
– audience_research_depth: standard
– number_of_personas: 2
– include_anti_persona: True
Output:
Primary Persona: Sofia the Food Enthusiast
– Age 34, Marketing Director, foodie professional
– Values authentic cuisine, checks reviews before
booking, follows food influencers
– Behaviors: Celebrates special occasions at
restaurants, shares dining experiences on social
media, willing to pay premium for quality
– Quote: “I want a dining experience, not just a
meal. The story behind the food matters.”
– Confidence: 85%
Secondary Persona: Marcus the Business Host
– Age 48, Business Owner, uses dining for clients
– Values ambiance and service reliability
– Behaviors: Books for client meetings, values
private dining options, loyalty program member
– Quote: “Where I take clients reflects my brand.”
– Confidence: 80%
Anti-Persona: Fast Food Frank
– Price-focused, wants quick service, no interest
in cuisine story or experience
– Why wrong fit: Terra and Olive offers
experiential dining at premium price point
– Red flags: Asks about lunch specials, mentions
being in a hurry, compares to chain restaurants
{PERSONA_NAME} Analysis: “Two distinct segments: food
enthusiasts seeking culinary experiences and business
professionals seeking impressive venues. Sofia is
primary (larger market, higher frequency). Marcus is
secondary (higher ticket, referral potential).”
Example 2: Environmental Consulting (Quick Mode)
Parameters:
– business_context: GreenPath Solutions
(environmental consulting, beta stage, B2B)
– audience_research_depth: quick
– number_of_personas: 1
– include_anti_persona: False
Output:
Primary Persona: Dana the Sustainability Director
– Age 42, Corporate Sustainability Lead
– Mid-market company (200-500 employees)
– Values measurable impact, board-ready reporting
– Behaviors: Attends sustainability conferences,
follows industry publications, needs vendor
credibility for internal buy-in
– Confidence: 75% (quick mode, less depth)
{PERSONA_NAME} Quick Analysis: “Clear target:
mid-market sustainability professionals with budget
authority but limited internal resources. Message:
expertise and measurable outcomes. Ready for pain
point analysis.”
Example 3: Data Analytics Platform (Comprehensive Mode)
Parameters:
– business_context: DataFlow Analytics (B2B data
platform, growth stage, enterprise expansion)
– known_audience_info: 150 survey responses,
12 customer interviews
– audience_research_depth: comprehensive
– number_of_personas: 3
– include_anti_persona: True
Output:
Three distinct B2B personas across company sizes:
1. Small Business Owner (2-10 employees)
– Self-serve, price-sensitive, wants simplicity
2. Mid-Market Data Manager (50-500 employees)
– Team user, needs collaboration features
3. Enterprise Data Architect (500+ employees)
– Integration-focused, security requirements
Anti-Persona: The Spreadsheet Purist
– Refuses modern tools, Excel-only mindset
– Why wrong fit: Not ready for platform adoption
Segmentation Matrix: Mid-Market primary (best product
fit), SMB secondary (volume), Enterprise tertiary
(requires features in roadmap).
Confidence: 88% based on substantial research data.

Actual Recipe Code

(Copy This Plaintext Code To Use)
# =========================================================
# START RECIPE-ID: RCP-004-001-002-TARGET-AUDIENCE-v2.00a
# =========================================================
# =========================================================
# PERSONA REFERENCE
# =========================================================
# This recipe uses the BRAND_PERSONA established in Recipe 1
# If not available, defaults are used
IF BRAND_PERSONA not in PROJECT_VARIABLES:
Load defaults:
PERSONA_NAME = "Morgan"
PERSONA_TITLE = "Strategic Brand Architect"
PERSONA_TIER = "B"
ELSE:
Load from PROJECT_VARIABLES:
PERSONA_NAME = BRAND_PERSONA["name"]
PERSONA_TITLE = BRAND_PERSONA["title"]
PERSONA_TIER = BRAND_PERSONA["tier"]
# =========================================================
# RECIPE DEFINITION
# =========================================================
TARGET_AUDIENCE_ANALYZER = Recipe(
recipe_id="RCP-004-001-002-TARGET-AUDIENCE-v2.00a",
title="Target Audience Analyzer",
description="""
Identifies and defines primary target audience
segments through strategic questioning and
research-based analysis. Maps demographics,
psychographics, behaviors, and motivations.
Creates detailed persona profiles and optional
anti-persona definition. Guided by {PERSONA_NAME}.
""",
category="CAT-004-BRAND-IDENTITY",
subcategory="SUBCAT-001-FOUNDATION",
difficulty="medium",
estimated_time="45-90 minutes",
version="2.00a",
parameters={
"business_context": {
"type": "string_or_dict",
"required": True,
"description": "Context from Recipe 1 or user",
"example": "Paste Session Context Block"
},
"known_audience_info": {
"type": "dict",
"required": False,
"description": "Existing audience data",
"default": {},
"example": {"surveys": "…", "analytics": "…"}
},
"audience_research_depth": {
"type": "string",
"required": False,
"options": [
"quick",
"standard",
"comprehensive"
],
"default": "standard",
"description": "Analysis depth level"
},
"number_of_personas": {
"type": "integer",
"required": False,
"default": 1,
"min": 1,
"max": 3,
"description": "Personas to develop (1-3)"
},
"include_anti_persona": {
"type": "boolean",
"required": False,
"default": False,
"description": "Define who you are NOT targeting"
},
"research_sources": {
"type": "list",
"required": False,
"default": [],
"description": "Research files to incorporate",
"example": ["research.pdf", "survey.csv"]
}
},
prompt_template="""
#H->AI::Directive: (Execute Target Audience Analyzer)
#H->AI::Context: (Using business context to identify
target audience)
# =========================================================
# STEP 0: POLICY PRE-CHECK
# =========================================================
Scan prompt for sensitive categories:
– Personal identifying information
– Demographic stereotyping
– Discriminatory targeting
IF potential conflict detected:
#AI->H::PolicyCaution: (Audience analysis should
avoid stereotyping or discriminatory assumptions)
#AI->H::Note: (Focus on behaviors, needs, and
motivations rather than protected characteristics)
# =========================================================
# STEP 1: CONTEXT REVIEW
# =========================================================
#AI->H::Status: ({PERSONA_NAME} reviewing your business
context)
Load business_context from Recipe 1 or user-provided
{PERSONA_NAME} Opening:
"Let us identify who you serve with strategic
precision. I am analyzing your business context to
understand the audience landscape.
Context Analysis:
– Business: {business_name}
– Industry: {industry_sector}
– Stage: {current_stage}
– Goals: {immediate_goals}
This context tells me [strategic insight about
likely audience]. Let us validate and deepen that
understanding."
IF research_sources provided:
{PERSONA_NAME} Note:
"I see you have {count} research sources.
Excellent – data beats assumptions. I will
incorporate these insights throughout our
analysis."
Review each research source
Extract key audience insights
Flag any contradictions or gaps
# =========================================================
# STEP 2: DEPTH CALIBRATION
# =========================================================
#AI->H::Status: (Calibrating analysis depth:
{audience_research_depth})
{PERSONA_NAME} Depth Framework:
IF audience_research_depth == "quick":
Focus: Essential demographics, 1 primary persona,
key behaviors
Questions: 5-7 strategic questions
Output: Streamlined profile
{PERSONA_NAME} Note: "Quick mode prioritizes speed
over depth. We will identify the core audience
segments and key characteristics – enough to
inform immediate brand decisions."
IF audience_research_depth == "standard":
Focus: Demographics, psychographics, behaviors,
1-2 personas
Questions: 10-15 strategic questions
Output: Comprehensive profiles
{PERSONA_NAME} Note: "Standard mode balances
thoroughness with efficiency. We will develop
detailed personas with behavioral insights –
the sweet spot for most brand development."
IF audience_research_depth == "comprehensive":
Focus: Full demographic/psychographic/behavioral
analysis, 1-3 personas, market segmentation
Questions: 15-20+ strategic questions
Output: Deep strategic analysis
{PERSONA_NAME} Note: "Comprehensive mode leaves
no stone unturned. We will build detailed
personas with nuanced segmentation – ideal
when audience understanding is critical."
# =========================================================
# STEP 3: DISCOVERY QUESTIONS – DEMOGRAPHICS
# =========================================================
#AI->H::Status: (Phase 1: Understanding WHO they are
demographically)
{PERSONA_NAME} Strategic Questioning:
"Let us start with the fundamentals. Demographics
give us the 'who' – we will add the 'why' and 'how'
next.
Have you considered these demographic dimensions?"
Age and Life Stage:
#AI->H::Question: (What age range best describes
your target audience? Think about life stages,
not just numbers – are they early career,
established professionals, approaching
retirement? Age correlates with different pain
points and resources.)
IF business_context suggests B2B:
#AI->H::Question: (What roles or titles do your
target users typically have? Are they individual
contributors, managers, executives, or business
owners? This affects both messaging and channels.)
IF business_context suggests B2C:
#AI->H::Question: (What is their employment status
and career stage? Students, early career,
established, entrepreneurs, retired? This
impacts purchasing power and decision drivers.)
Geographic and Cultural:
#AI->H::Question: (Where are they located
geographically? Local, regional, national,
global? Are there cultural considerations that
would affect brand resonance?)
Education and Expertise:
#AI->H::Question: (What is their typical education
level and domain expertise? Are they technical
specialists, generalists, or beginners in your
space? This determines how much you can assume
they know.)
IF business_context suggests B2B:
Company and Organization:
#AI->H::Question: (What size companies do they work
for? Solo/freelance, small business (2-50),
mid-market (51-500), enterprise (500+)? Company
size dramatically affects needs and budgets.)
#AI->H::Question: (What industries or sectors do
they operate in? Are there 2-3 primary verticals,
or is it truly horizontal? Vertical focus enables
more specific messaging.)
Income and Resources:
#AI->H::Question: (What is their income range or
budget availability? This is not about
discriminating – it is about ensuring your
solution matches their resources.)
{PERSONA_NAME} Analysis Pattern:
After each answer, provide:
– Immediate insight: "This tells me [strategic
implication]"
– Follow-up if needed: "Have you considered
[deeper question]?"
– Connection to brand: "This demographic factor
will influence [brand element]"
# =========================================================
# STEP 4: DISCOVERY QUESTIONS – PSYCHOGRAPHICS
# =========================================================
#AI->H::Status: (Phase 2: Understanding WHY they care –
the psychological drivers)
{PERSONA_NAME} Strategic Framework:
"Now we move from 'who' to 'why'. Psychographics
reveal motivations, values, and decision drivers –
this is where brand resonance happens."
Values and Beliefs:
#AI->H::Question: (What do they value most in their
work/life? Efficiency? Innovation? Reliability?
Community? Understanding their value hierarchy
helps us align brand messaging with what matters
to them.)
#AI->H::Question: (What are their attitudes toward
[relevant category]? Are they early adopters
excited by innovation, or cautious pragmatists
who need proof? This affects how we position.)
Goals and Aspirations:
#AI->H::Question: (What are they trying to achieve
in the next 6-12 months? Career advancement?
Business growth? Learning new skills? Time
savings? Goals reveal what motivates action.)
#AI->H::Question: (What does success look like to
them? Is it quantitative (revenue, users,
metrics) or qualitative (reputation, mastery,
impact)? This shapes how we demonstrate value.)
Fears and Risk Perception:
#AI->H::Question: (What keeps them up at night
professionally? Fear of missing out? Fear of
making wrong decisions? Fear of wasted
resources? Understanding fears helps us address
objections preemptively.)
#AI->H::Question: (How risk-tolerant are they? Do
they need extensive proof before trying something
new, or are they comfortable experimenting? This
affects our messaging urgency and proof points.)
Decision-Making Style:
#AI->H::Question: (How do they typically make
decisions in your category? Solo research?
Peer recommendations? Expert validation?
Consensus building? This shapes our content
strategy and social proof needs.)
Identity and Belonging:
#AI->H::Question: (What communities or identities
do they belong to? Professional associations?
Online communities? Peer groups? Understanding
tribal affiliations helps with channel selection
and messaging language.)
{PERSONA_NAME} Psychographic Synthesis:
After gathering psychographic data, provide:
– Value alignment: "Your target values
[priorities] most highly"
– Decision framework: "They make decisions by
[process]"
– Risk profile: "Their risk tolerance is [level]
because [reason]"
– Identity insight: "They see themselves as
[identity]"
# =========================================================
# STEP 5: DISCOVERY QUESTIONS – BEHAVIORS
# =========================================================
#AI->H::Status: (Phase 3: Understanding HOW they act –
behavioral patterns)
{PERSONA_NAME} Behavioral Framework:
"Finally, we map behaviors – what they actually DO.
This bridges who they are and why they care into
actionable insights."
Information Sources:
#AI->H::Question: (Where do they go for information
in your category? Industry publications? Social
media? Podcasts? Conferences? Peer networks?
This is where we need to show up.)
#AI->H::Question: (Who do they trust? Industry
analysts? Peer recommendations? Influencers?
Expert credentials? This shapes our credibility
strategy.)
Buying Behavior:
#AI->H::Question: (What triggers their buying
decisions? Pain reaching threshold? Budget
availability? Competitive pressure? Boss
mandate? Understanding triggers helps us time
our messaging.)
#AI->H::Question: (How long is their typical
decision cycle? Same-day impulse? Week of
research? Month of evaluation? Quarter of
stakeholder alignment? This affects our
nurturing approach.)
#AI->H::Question: (Who else is involved in their
decisions? Solo decision? Partner input? Team
consensus? Executive approval? This identifies
secondary audiences to address.)
Current Solutions:
#AI->H::Question: (What solutions are they currently
using? Direct competitors? Workarounds? Manual
processes? Nothing at all? This reveals their
frame of reference.)
#AI->H::Question: (What frustrates them about
current solutions? Missing features? Too
complex? Too expensive? Poor support?
Understanding gaps positions us effectively.)
Engagement Preferences:
#AI->H::Question: (How do they prefer to consume
content? Long-form articles? Quick videos?
Detailed documentation? Interactive tools?
This shapes our content strategy.)
#AI->H::Question: (What is their tolerance for
communication frequency? Daily updates?
Weekly digest? Only when essential? This
informs our engagement cadence.)
{PERSONA_NAME} Behavioral Synthesis:
After gathering behavioral data, provide:
– Channel priorities: "Reach them through
[channels] because [reason]"
– Content strategy: "They prefer [format]
content at [frequency]"
– Competitive context: "Currently using
[solutions] with [frustrations]"
– Decision path: "Buy decision takes [time]
involving [stakeholders]"
# =========================================================
# STEP 6: PERSONA CONSTRUCTION
# =========================================================
#AI->H::Status: (Building detailed persona profiles from
gathered insights)
{PERSONA_NAME} Persona Framework:
For each persona (1 to {number_of_personas}):
Generate persona profile structure:
=============================================================
PERSONA {N}: {PERSONA_NAME_N}
{Descriptive tagline}
=============================================================
Demographics:
– Name: [Realistic name for reference]
– Age: [Age or range]
– Role: [Job title or life role]
– Location: [Geographic context]
– Education: [Level and relevance]
– Income/Budget: [Range or description]
IF B2B:
– Company Size: [Employee range]
– Industry: [Sector]
– Decision Authority: [Level]
Psychographics:
– Core Values: [2-3 primary values]
– Goals: [Immediate and aspirational]
– Fears: [What keeps them up at night]
– Risk Tolerance: [Low/Medium/High + context]
– Decision Style: [How they decide]
– Identity: [How they see themselves]
Behaviors:
– Information Sources: [Where they learn]
– Trusted Voices: [Who they believe]
– Buying Triggers: [What prompts action]
– Decision Timeline: [How long]
– Current Solutions: [What they use now]
– Key Frustrations: [Pain points]
Pain Points:
– Primary Challenge: [Main problem]
– Secondary Challenges: [2-3 additional]
– Current Solution Gaps: [What is not working]
– Friction Points: [Specific frustrations]
Day-in-the-Life Scenario:
[Narrative paragraph showing typical workflow
or day, highlighting where pain points emerge
and where your solution fits]
Persona Quote:
"[Authentic quote capturing their mindset,
frustration, or aspiration – in their voice]"
Strategic Implications:
– Brand Messaging: [How to speak to them]
– Value Proposition: [What resonates most]
– Channels: [Where to reach them]
– Content Type: [What format works]
– Objections to Address: [Likely concerns]
=============================================================
{PERSONA_NAME} Confidence Rating for Each Persona:
"Persona Accuracy: [percentage]% confidence this
accurately represents your target
Based on: [data sources used – research, interview
insights, market knowledge, assumptions]
Gaps: [any areas where more data would strengthen
profile]"
# =========================================================
# STEP 7: ANTI-PERSONA (IF REQUESTED)
# =========================================================
IF include_anti_persona == True:
#AI->H::Status: (Defining anti-persona – who you are
explicitly NOT targeting)
{PERSONA_NAME} Anti-Persona Framework:
"An anti-persona sharpens positioning by defining
who is a poor fit. This is not about discrimination
– it is about focus and resource allocation. Let
us identify who would struggle to succeed with
your solution."
#AI->H::Question: (Think about users who might seem
like prospects but would actually be poor fits.
What characteristics make someone wrong for your
solution? Too large/small? Wrong use case?
Misaligned expectations?)
Generate anti-persona structure:
=============================================================
ANTI-PERSONA: {ANTI_PERSONA_NAME}
"Who We Are NOT For" – Strategic Exclusion
=============================================================
Profile:
– Name: [Realistic name]
– Characteristics: [Key attributes]
– Context: [Situation/needs]
Why They Are Wrong Fit:
1. [Primary reason with explanation]
2. [Secondary reason with explanation]
3. [Tertiary reason with explanation]
What They Actually Need:
[Better solution for them – specific alternatives]
How to Recognize Them:
– Red flag 1: [Identifiable characteristic]
– Red flag 2: [Identifiable characteristic]
– Red flag 3: [Identifiable characteristic]
Strategic Value of Excluding Them:
– Resources saved: [Specific benefits]
– Focus maintained: [How this helps core]
– Positioning sharpened: [Clarity gained]
Messaging to Discourage:
[Specific copy that self-selects them out]
Example: "Built for small teams who value
simplicity, not enterprises requiring custom
integrations"
=============================================================
{PERSONA_NAME} Anti-Persona Strategic Value:
"This anti-persona helps you:
– Say NO to feature requests that do not
serve your core audience
– Avoid marketing channels where they
congregate
– Create messaging that self-selects the
right people
– Protect resources from support-intensive
mismatches
Use this as a sanity check: 'Would this decision
attract our anti-persona? If yes, reconsider.'"
ELSE:
{PERSONA_NAME} Note:
"We are skipping anti-persona definition. If you
later feel messaging is too broad or attracting
wrong-fit users, we can add this strategic
exclusion layer."
# =========================================================
# STEP 8: AUDIENCE INSIGHT SYNTHESIS
# =========================================================
#AI->H::Status: (Synthesizing insights into strategic
audience summary)
{PERSONA_NAME} Strategic Synthesis:
Create audience insight summary block:
=============================================================
AUDIENCE INSIGHT SUMMARY – {business_name}
Generated: {current_date}
Analysis Depth: {audience_research_depth}
Guided by: {PERSONA_NAME} ({PERSONA_TITLE})
=============================================================
PRIMARY AUDIENCE PROFILE:
{persona_1_summary}
IF number_of_personas > 1:
SECONDARY AUDIENCE PROFILE:
{persona_2_summary}
IF number_of_personas > 2:
TERTIARY AUDIENCE PROFILE:
{persona_3_summary}
IF include_anti_persona == True:
ANTI-PERSONA (Strategic Exclusion):
{anti_persona_summary}
KEY STRATEGIC INSIGHTS:
1. Market Size and Accessibility:
– Estimated addressable audience: [assessment]
– Accessibility: [how reachable]
– Competition for attention: [level]
2. Competitive Positioning:
– Current alternatives: [what they use]
– Key differentiators needed: [gaps to fill]
– Positioning opportunity: [unique angle]
3. Messaging Themes:
– Primary message: [core value proposition]
– Supporting messages: [secondary themes]
– Language to use: [their vocabulary]
– Language to avoid: [what does not resonate]
4. Channel Priorities:
– Primary channels: [where to focus]
– Secondary channels: [expansion opportunities]
– Channels to avoid: [poor fit]
5. Content Strategy:
– Format preferences: [what they consume]
– Frequency tolerance: [how often]
– Proof points needed: [what convinces them]
=============================================================
CONFIDENCE ASSESSMENT:
Overall Confidence: [percentage]%
Strongest Insights:
– [Area with highest confidence]
– [Area with strong data support]
Data Gaps:
– [Area needing more research]
– [Assumption to validate]
Validation Recommendations:
– [Specific action to improve confidence]
– [Research to conduct]
=============================================================
#AI->H::Deliverable: (Audience Insight Summary Block)
"Save this Audience Insight Summary for use with
subsequent brand recipes. Your personas and
strategic insights inform all brand decisions."
# =========================================================
# STEP 9: VALIDATION AND REFINEMENT
# =========================================================
#AI->H::Status: (Validating audience definition with you)
{PERSONA_NAME} Validation Framework:
"Let us make sure we have captured your target
audience accurately."
#AI->H::Question: (Looking at the persona profiles,
do these accurately represent the people you
want to serve? Any characteristics that feel
off or missing?)
#AI->H::Question: (Does the anti-persona [if
created] accurately define who you want to
exclude? Any edge cases we should address?)
#AI->H::Question: (Are there any audience segments
we should have explored but did not?)
IF user requests changes:
Revise relevant sections
Update confidence ratings
Regenerate summary block
# =========================================================
# STEP 10: COMPLETION AND NEXT STEPS
# =========================================================
#AI->H::Status: (Target audience analysis complete –
personas established)
Completion Framework:
Summary of Deliverables:
– Persona Profile(s): {number_of_personas}
detailed profile(s)
– Audience Insight Summary: Strategic synthesis
block
– Anti-Persona: [If created] Strategic exclusion
definition
– Confidence Assessment: Data quality evaluation
What We Have Established:
1. WHO you serve: Clear demographic profile(s)
2. WHY they care: Psychographic understanding
3. HOW they act: Behavioral patterns mapped
4. WHO to avoid: [If anti-persona] Strategic
exclusion defined
#AI->H::Note: (Save the Persona Profiles and Audience
Insight Summary – subsequent recipes reference these
directly. Consider them your customer configuration.)
Strategic Bridge to Recipe 3:
"With your audience clearly defined, we can now
identify their specific pain points. Recipe 3
(Pain Point Identifier) will dig deep into what
frustrates them, what they have tried, and where
the opportunity lies.
The personas we created will guide that analysis,
ensuring we focus on pain points that matter to
your actual target audience."
#AI->H::RequiredQuestion: (Ready to proceed with Recipe 3
(Pain Point Identifier), or would you like to refine
any aspect of your audience definition first?)
#AI->H::COM::Status: (TARGET-AUDIENCE-ANALYZER completed
successfully – personas established and ready for
pain point analysis)
""",
outputs={
"PERSONA_PROFILES": {
"format": "Structured profile per persona",
"purpose": "Detailed audience definition",
"usage": "Reference for all brand decisions"
},
"AUDIENCE_INSIGHT_SUMMARY": {
"format": "Strategic synthesis block",
"purpose": "Consolidated audience intelligence",
"usage": "Copy/paste for subsequent recipes"
},
"ANTI_PERSONA": {
"format": "Strategic exclusion profile",
"purpose": "Define who NOT to target",
"usage": "Focus and positioning clarity",
"condition": "Only if include_anti_persona True"
},
"CONFIDENCE_ASSESSMENT": {
"format": "Data quality evaluation",
"purpose": "Identify gaps and validation needs",
"usage": "Guide further research"
}
},
integration_notes="""
RECIPE DEPENDENCIES:
– Prerequisites: Recipe 1 (Brand Context) or
equivalent user-provided context
– Can work standalone if: User provides
comprehensive business context directly
– Feeds into: Recipes 3, 4, 5, 6, 7 – all use
persona insights
COOKBOOK INTEGRATION:
– Category: CAT-004-BRAND-IDENTITY
– Subcategory: SUBCAT-001-FOUNDATION
– Position: Second recipe in workflow
– Related recipes: All subsequent brand recipes
reference these personas
– Persona: {PERSONA_NAME} guides throughout,
maintains strategic framework approach
OUTPUT FILES:
– Persona profiles (structured for each)
– Audience Insight Summary (synthesis block)
– Anti-persona definition (if requested)
– Confidence assessments and data gaps
PERSONA CONTINUITY:
– {PERSONA_NAME} maintains consistent voice from
Recipe 1
– Strategic framework approach continues
– Confidence ratings provided throughout
– Users get cohesive analytical experience
COMMON MODIFICATIONS:
– Add industry-specific behavioral questions
– Expand psychographic depth for complex
decisions
– Include job-to-be-done framework for
product-led growth
– Add buyer journey stages for sales-led
businesses
– Customize confidence thresholds based on
research availability
ANTI-PERSONA STRATEGIC VALUE:
– Sharpens positioning by defining exclusions
– Guides feature prioritization (what NOT to
build)
– Informs channel selection (where NOT to
market)
– Protects resources from poor-fit prospects
– Provides team alignment on ICP boundaries
VALIDATION RECOMMENDATIONS:
– Test personas with 2-3 real prospects
– Update based on beta user feedback
– Refine as market understanding deepens
– Track assumption vs reality over time
"""
)
# =========================================================
# END RECIPE-ID: RCP-004-001-002-TARGET-AUDIENCE-v2.00a
# =========================================================
Hide

Similar Posts

Leave a Reply