Step 01
Persona
Step 02
Content
Step 03
Blueprint
Step 04
Experience
Phase 1: Inception

Persona Designer

Intentio interprets raw behavioral signals and environmental context to deduce a high-fidelity psychological twin in real-time.

Generate Signals with AI

Describe the user in your own words (e.g., "A luxury fashion enthusiast arriving from Instagram, carefully browsing new arrivals but hesitating on the price") and the AI will generate the corresponding JSON signals.

Liquid Persona Schema Overview

Identity & Environment

Deterministic signals: CRM data (loyalty), Environment (weather, local events), and geofencing.

Psychographics

AI-inferred archetype, current emotional state, and core values (e.g. compliance vs speed).

Behavioral

Navigation momentum, attention focus, and friction meter.

Journey

Funnel position (e.g. discovery vs evaluating) and routing recommendations (NBA).

Intent

What the user is actually trying to achieve in this session and any explicit constraints.

TypeScript Schema & Examples

1. Identity

Deterministic traits known about the user (e.g., from CRM mapping or IP enrichment).

// Schema
identity: {
  uid?: string;
  crm_data?: { loyalty_points: number; lifetime_value: string };
  segments?: string[];
}
environment: {
  weather?: string;
  local_events?: string[];
  geofence?: string;
}

// Example
"identity": {
  "uid": "user-lux-892",
  "crm_data": { "loyalty_points": 4500, "lifetime_value": "high" }
},
"environment": {
  "weather": "rainy",
  "local_events": ["Milan Fashion Week"],
  "geofence": "near-montenapoleone-store"
}

2. Psychographics

The psychological profile inferred from the user's behavior and context.

// Schema
psychographics: {
  archetype: string;
  emotional_state: string;
  core_values: string[];
  risk_profile: "low" | "medium" | "high";
}

// Example
"psychographics": {
  "archetype": "The Discerning Collector",
  "emotional_state": "indecisive",
  "core_values": ["exclusivity", "authenticity", "status"],
  "risk_profile": "high"
}

3. Behavioral

Pace and focus inferred from tracking events.

// Schema
behavioral: {
  momentum: "slow" | "steady" | "fast";
  friction_level: number; // 0.0 to 1.0
  engagement_depth: number; // 0.0 to 1.0
  attention_focus: string[];
}

// Example
"behavioral": {
  "momentum": "slow",
  "friction_level": 0.7,
  "engagement_depth": 0.92,
  "attention_focus": ["product-gallery", "price-details"]
}

4. Journey

Relationship phase and recommended next steps.

// Schema
journey: {
  stage: string;
  tenure: "new" | "returning" | "loyal" | "at-risk";
  next_best_actions: string[];
}

// Example
"journey": {
  "stage": "evaluation",
  "tenure": "returning",
  "next_best_actions": [
    "show scarcity nudge", 
    "offer styling consultation"
  ]
}

5. Intent

The immediate goal the user is trying to accomplish right now.

// Schema
intent: {
  primary_goal: string;
  constraints: string[];
  confidence_score: number; // 0.0 to 1.0
}

// Example
"intent": {
  "primary_goal": "evaluate the exclusivity and value of the limited edition Gucci bag",
  "constraints": ["must be limited edition", "high expectation of service"],
  "confidence_score": 0.88
}

1. Input Signals

Edit the JSON below or generate it using AI above. Press "Generate Persona" to call the Gemini 2.0 Agent.

2. Liquid Persona

The psychological model inferred from session behavioral signals.

Awaiting inference...