Personas

Personas are the core of Mavera’s intelligence layer. They inject specialized audience knowledge into every AI interaction — shaping language, values, decision-making patterns, and behavioral tendencies to reflect how real demographics think and respond. Instead of getting generic AI outputs, you get responses filtered through the lens of a specific audience: a Gen Z consumer, a B2B enterprise buyer, a health-conscious millennial, or any custom segment you define.

Personas work across all Mavera products: Responses API, Focus Groups, and Speak. Create a persona once, reuse it everywhere.

Why Personas Matter

Traditional AI gives you one generic perspective. Mavera personas let you hear from the audience that actually matters to your business. Each persona encodes:

Demographics — age, location, income level, education
Psychographics — values, motivations, lifestyle preferences
Behavioral patterns — buying habits, media consumption, decision triggers
Communication style — language register, cultural references, tone

Persona Types

Pre-built Personas

50+ ready-to-use personas across generational, professional, lifestyle, industry, and expert categories. Battle-tested and immediately available.

Custom Personas

Define your exact target audience with three creation pipelines: North Star (simple), Intermediate (guided), and Advanced (full control).

Pre-built Categories

Mavera provides 50+ pre-built personas organized into five categories. Each persona is a rich behavioral model, not just a label.

Generational

Personas based on generational cohorts, each with distinct values, media habits, and purchasing behavior.

Persona	Key Traits
Gen Z Consumer (18–26)	Digital native, values authenticity, social responsibility, short-form content
Gen Z Professional (22–26)	Career-driven, purpose-seeking, hybrid-work preference
Millennial Consumer (27–42)	Experience-seeking, brand-loyal, subscription-friendly
Millennial Parent (30–42)	Safety-conscious, research-heavy, values convenience
Gen X Consumer (43–58)	Quality-focused, skeptical of trends, values reliability
Gen X Professional (43–58)	Leadership-oriented, pragmatic, prefers proven solutions
Baby Boomer (59–77)	Brand-loyal, values customer service, prefers established channels
Silent Generation (78+)	Trust-driven, values simplicity, prefers personal interaction

Professional

Personas representing different roles in business decision-making.

Persona	Key Traits
B2B Decision Maker	ROI-focused, risk-averse, multi-stakeholder consensus builder
Startup Founder	Growth-obsessed, resourceful, values speed over perfection
Enterprise CTO	Security-first, integration-aware, long evaluation cycles
Marketing Director	Brand-conscious, data-driven, campaign-focused
Product Manager	User-centric, prioritization-driven, roadmap-focused
Small Business Owner	Budget-conscious, wears many hats, values simplicity

Lifestyle

Personas defined by lifestyle choices and consumption patterns.

Persona	Key Traits
Health-Conscious Consumer	Reads labels, organic preference, fitness-oriented
Eco-Warrior	Sustainability-first, willing to pay premium, activist mindset
Budget Shopper	Price-comparison driven, coupon-savvy, values per-dollar
Luxury Consumer	Experience-driven, brand-prestige seeking, quality over quantity
Digital Nomad	Location-independent, minimalist, values flexibility
Urban Professional	Convenience-driven, time-scarce, delivery-dependent

Industry

Personas with deep domain knowledge in specific industries.

Persona	Key Traits
Healthcare Professional	Evidence-based, HIPAA-aware, patient-outcome focused
Finance Expert	Risk-adjusted thinking, regulatory-aware, data-driven
Tech Enthusiast	Early adopter, spec-driven, community-influenced
Education Professional	Pedagogy-focused, accessibility-aware, outcomes-driven
Real Estate Agent	Market-timing aware, relationship-driven, local expertise

Expert

Personas that reason like domain specialists. Useful for strategic analysis and review.

Persona	Key Traits
Market Analyst	Quantitative, trend-spotting, competitive-landscape aware
Brand Strategist	Positioning-focused, narrative-driven, consumer-insight oriented
UX Researcher	User-empathy driven, usability-focused, evidence-based
Growth Marketer	Funnel-optimizing, experiment-driven, metrics-obsessed
Content Strategist	Audience-first, channel-aware, narrative-arc thinking

Listing Personas

Retrieve all available personas (pre-built and custom) for your workspace.

import requests

response = requests.get(
    "https://app.mavera.io/api/v1/personas",
    headers={"Authorization": "Bearer mvra_live_your_key_here"}
)

personas = response.json()["data"]
for persona in personas:
    print(f"{persona['name']} ({persona['category']})")
    print(f"  ID: {persona['id']}")
    print(f"  Custom: {persona['is_custom']}")
    print(f"  {persona['description'][:100]}...")

const response = await fetch("https://app.mavera.io/api/v1/personas", {
  headers: { Authorization: "Bearer mvra_live_your_key_here" },
});

const { data: personas } = await response.json();
personas.forEach((persona) => {
  console.log(`${persona.name} (${persona.category})`);
  console.log(`  ID: ${persona.id}`);
  console.log(`  Custom: ${persona.is_custom}`);
});

curl https://app.mavera.io/api/v1/personas \
  -H "Authorization: Bearer mvra_live_your_key_here"

Filtering by Category

response = requests.get(
    "https://app.mavera.io/api/v1/personas",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    params={"category": "Generational"}
)

Persona Response Object

{
  "id": "persona_abc123",
  "name": "Gen Z Consumer",
  "category": "Generational",
  "description": "Digital native aged 18-26 who values authenticity, social responsibility, and personalized experiences.",
  "is_custom": false,
  "is_expert": false,
  "created_at": "2024-01-15T10:30:00Z"
}

Using Personas

In the Responses API

Pass persona_id to shape AI responses through the persona’s lens.

from openai import OpenAI

client = OpenAI(
    api_key="mvra_live_your_key_here",
    base_url="https://app.mavera.io/api/v1",
)

response = client.responses.create(
    model="mavera-1",
    input=[
        {"role": "user", "content": "What makes a brand authentic?"}
    ],
    extra_body={"persona_id": "gen_z_consumer"},
)

print(response.output[0].content[0].text)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "mvra_live_your_key_here",
  baseURL: "https://app.mavera.io/api/v1",
});

const response = await client.responses.create({
  model: "mavera-1",
  input: [
    { role: "user", content: "What makes a brand authentic?" },
  ],
  persona_id: "gen_z_consumer",
});

console.log(response.output[0].content[0].text);

In Focus Groups

Supply multiple persona_ids to simulate diverse audience panels.

response = requests.post(
    "https://app.mavera.io/api/v1/focus-groups",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    json={
        "name": "Brand Perception Study",
        "sample_size": 50,
        "persona_ids": [
            "gen_z_consumer",
            "millennial_professional",
            "gen_x_parent",
            "luxury_consumer"
        ],
        "questions": [
            {
                "question": "How likely are you to recommend this brand?",
                "type": "NPS",
                "order": 1
            }
        ],
        "workspace_id": "your_workspace_id"
    }
)

In Speak (Video)

Attach a persona to video-generation requests for audience-specific delivery.

response = requests.post(
    "https://app.mavera.io/api/v1/speak",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    json={
        "text": "Introducing our new sustainable product line...",
        "persona_id": "eco_warrior",
        "workspace_id": "your_workspace_id"
    }
)

Creating Custom Personas

When pre-built personas don’t match your exact target audience, create a custom one. Mavera offers three creation pipelines with increasing levels of control.

North Star (Simplest)

Provide a name and description — AI generates the complete behavioral profile.

response = requests.post(
    "https://app.mavera.io/api/v1/personas",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    json={
        "pipeline_type": "NORTH_STAR",
        "name": "Sustainable Fashion Buyer",
        "description": "Eco-conscious millennial interested in sustainable fashion, shops primarily online, values transparency in supply chains",
        "workspace_id": "your_workspace_id"
    }
)

persona = response.json()
print(f"Created persona: {persona['id']}")

const response = await fetch("https://app.mavera.io/api/v1/personas", {
  method: "POST",
  headers: {
    Authorization: "Bearer mvra_live_your_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    pipeline_type: "NORTH_STAR",
    name: "Sustainable Fashion Buyer",
    description: "Eco-conscious millennial interested in sustainable fashion, shops primarily online, values transparency in supply chains",
    workspace_id: "your_workspace_id",
  }),
});

const persona = await response.json();
console.log(`Created persona: ${persona.id}`);

Include specific details in the description for better results. “Eco-conscious millennial who shops online and values supply chain transparency” produces a richer persona than “someone who likes sustainability.”

Intermediate (Guided)

A 3-step process with explicit goals, pain points, and buying stage.

response = requests.post(
    "https://app.mavera.io/api/v1/personas",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    json={
        "pipeline_type": "INTERMEDIATE",
        "name": "Enterprise IT Buyer",
        "persona_type": "B2B",
        "buying_stage": "SOLUTION_AWARE",
        "decision_role": "ECONOMIC_BUYER",
        "goals": ["Reduce IT costs by 20%", "Improve security posture", "Consolidate vendors"],
        "pains": ["Budget constraints", "Integration complexity", "Compliance requirements"],
        "workspace_id": "your_workspace_id"
    }
)

const response = await fetch("https://app.mavera.io/api/v1/personas", {
  method: "POST",
  headers: {
    Authorization: "Bearer mvra_live_your_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    pipeline_type: "INTERMEDIATE",
    name: "Enterprise IT Buyer",
    persona_type: "B2B",
    buying_stage: "SOLUTION_AWARE",
    decision_role: "ECONOMIC_BUYER",
    goals: ["Reduce IT costs by 20%", "Improve security posture", "Consolidate vendors"],
    pains: ["Budget constraints", "Integration complexity", "Compliance requirements"],
    workspace_id: "your_workspace_id",
  }),
});

Buying stage options: UNAWARE, PROBLEM_AWARE, SOLUTION_AWARE, PRODUCT_AWARE, DECISION Decision role options: ECONOMIC_BUYER, CHAMPION, TECHNICAL_BUYER, END_USER, GATEKEEPER

Advanced (Full Control)

Complete customization with psychographics, tech stack, channels, and triggers.

response = requests.post(
    "https://app.mavera.io/api/v1/personas",
    headers={"Authorization": "Bearer mvra_live_your_key_here"},
    json={
        "pipeline_type": "ADVANCED",
        "name": "SMB SaaS Buyer",
        "persona_type": "B2B",
        "role_title": "Operations Manager",
        "company_size": "SMB_51_200",
        "buying_stage": "DECISION",
        "decision_role": "CHAMPION",
        "budget_authority": "RECOMMENDER",
        "goals": ["Automate workflows", "Scale operations", "Reduce manual errors"],
        "pains": ["Manual processes", "Team bandwidth", "Tool sprawl"],
        "triggers": ["Growth phase", "New funding round", "Key employee departure"],
        "channels": ["LinkedIn", "Industry podcasts", "Peer recommendations", "G2 reviews"],
        "tech_stack": ["Slack", "HubSpot", "Notion", "Zapier"],
        "workspace_id": "your_workspace_id"
    }
)

const response = await fetch("https://app.mavera.io/api/v1/personas", {
  method: "POST",
  headers: {
    Authorization: "Bearer mvra_live_your_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    pipeline_type: "ADVANCED",
    name: "SMB SaaS Buyer",
    persona_type: "B2B",
    role_title: "Operations Manager",
    company_size: "SMB_51_200",
    buying_stage: "DECISION",
    decision_role: "CHAMPION",
    budget_authority: "RECOMMENDER",
    goals: ["Automate workflows", "Scale operations", "Reduce manual errors"],
    pains: ["Manual processes", "Team bandwidth", "Tool sprawl"],
    triggers: ["Growth phase", "New funding round", "Key employee departure"],
    channels: ["LinkedIn", "Industry podcasts", "Peer recommendations", "G2 reviews"],
    tech_stack: ["Slack", "HubSpot", "Notion", "Zapier"],
    workspace_id: "your_workspace_id",
  }),
});

Custom persona creation costs 300 credits. Personas are permanent and reusable across all API calls at no additional cost.

Single vs Multi-Persona Strategies

Choosing between one persona and several depends on your research goal.

Strategy	When to Use	Example
Single persona	You have a clear target audience and want depth	”How would a Gen Z consumer react to this ad?”
Multi-persona comparison	You need to compare reactions across segments	Chat with 3 different personas and compare answers
Focus Group panel	You need quantitative + qualitative data at scale	Run a Focus Group with 4 personas, N=50
Expert + audience pair	You want strategic analysis grounded in audience reality	Ask a Brand Strategist, then validate with a Gen Z persona

Multi-Persona Comparison in Code

from openai import OpenAI

client = OpenAI(
    api_key="mvra_live_your_key_here",
    base_url="https://app.mavera.io/api/v1",
)

personas = {
    "Gen Z": "gen_z_consumer",
    "Millennial": "millennial_consumer",
    "Gen X": "gen_x_consumer",
}

question = "Would you pay a premium for sustainable packaging?"

for label, persona_id in personas.items():
    response = client.responses.create(
        model="mavera-1",
        input=[{"role": "user", "content": question}],
        extra_body={"persona_id": persona_id},
    )
    print(f"\n--- {label} ---")
    print(response.output[0].content[0].text[:300])

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "mvra_live_your_key_here",
  baseURL: "https://app.mavera.io/api/v1",
});

const personas = {
  "Gen Z": "gen_z_consumer",
  "Millennial": "millennial_consumer",
  "Gen X": "gen_x_consumer",
};

const question = "Would you pay a premium for sustainable packaging?";

for (const [label, personaId] of Object.entries(personas)) {
  const response = await client.responses.create({
    model: "mavera-1",
    input: [{ role: "user", content: question }],
    persona_id: personaId,
  });
  console.log(`\n--- ${label} ---`);
  console.log(response.output[0].content[0].text.slice(0, 300));
}

Best Practices

Match persona to use case

Use generational personas for consumer insights, professional personas for B2B research, expert personas for strategic analysis, and lifestyle personas for psychographic segmentation. Don’t use a CTO persona to test consumer messaging.

Layer personas with system prompts

Persona intelligence is most powerful when combined with a clear task. “You are a market researcher interviewing this persona about brand loyalty” produces richer results than a bare question.

Create custom personas for niche audiences

If your target audience isn’t covered by pre-built personas, invest the 300 credits to create a custom one. The Advanced pipeline gives you full control over psychographics and behavioral triggers.

Reuse personas across products

A persona created for Chat also works in Focus Groups and Speak. Build your persona library once and leverage it across all Mavera products.

Start broad, then narrow

Begin with a pre-built persona to validate your research direction, then create a custom persona for precision. This saves credits during the exploratory phase.

Use analysis mode to quantify differences

When comparing personas, enable analysis_mode in Chat to get confidence scores and emotional analysis. This turns qualitative comparisons into quantifiable data.

Personas simulate audience perspectives based on behavioral models — they are not real people. Use persona outputs as directional input for research, not as definitive audience data. Always validate critical business decisions with real user research.

Next Steps

Responses API

Use personas in the Responses API

Focus Groups

Run persona-powered synthetic focus groups

Persona Selection Cookbook

Choose the right personas by use case

API Reference

Full API specification for persona endpoints

Getting Started

Core Concepts

Features

SDKs & Libraries

Why Personas Matter

Persona Types

Pre-built Personas

Custom Personas

Pre-built Categories

Listing Personas

Filtering by Category

Persona Response Object

Using Personas

In the Responses API

In Focus Groups

In Speak (Video)

Creating Custom Personas

North Star (Simplest)

Intermediate (Guided)

Advanced (Full Control)

Single vs Multi-Persona Strategies

Multi-Persona Comparison in Code

Best Practices

Next Steps

Responses API

Focus Groups

Persona Selection Cookbook

API Reference

​Why Personas Matter

​Persona Types

Pre-built Personas

Custom Personas

​Pre-built Categories

​Listing Personas

​Filtering by Category

​Persona Response Object

​Using Personas

​In the Responses API

​In Focus Groups

​In Speak (Video)

​Creating Custom Personas

​North Star (Simplest)

​Intermediate (Guided)

​Advanced (Full Control)

​Single vs Multi-Persona Strategies

​Multi-Persona Comparison in Code

​Best Practices

​Next Steps

Responses API

Focus Groups

Persona Selection Cookbook

API Reference

Why Personas Matter

Persona Types

Pre-built Categories

Listing Personas

Filtering by Category

Persona Response Object

Using Personas

In the Responses API

In Focus Groups

In Speak (Video)

Creating Custom Personas

North Star (Simplest)

Intermediate (Guided)

Advanced (Full Control)

Single vs Multi-Persona Strategies

Multi-Persona Comparison in Code

Best Practices

Next Steps