> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mavera.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Persona Selection by Use Case
> Choose the right Mavera persona for your audience, product, and research goal — with a practical matrix and code
## When to Use This
You need to **pick a persona** (or a set of personas) for responses, focus groups, or Mave research. Choosing the right persona drastically improves relevance: a Gen Z Consumer and a B2B Decision Maker will give very different answers to the same question.
This cookbook gives you:
* A **use-case → persona matrix** for common scenarios
* **Code** to list, filter, and select personas programmatically
* Guidance on **single vs multi-persona** strategies
* When to use **pre-built vs custom** personas
***
## Persona Categories (Quick Reference)
| Category | Best For | Example Personas |
| ---------------- | -------------------------------------------------------------- | ------------------------------------------------------------------ |
| **Generational** | Consumer insights, brand messaging, product positioning by age | Gen Z Consumer, Millennial Professional, Gen X Parent, Baby Boomer |
| **Professional** | B2B research, enterprise software, sales enablement | B2B Decision Maker, Startup Founder, Enterprise CTO |
| **Lifestyle** | Consumer behavior, purchase drivers, sustainability, budget | Health-Conscious Consumer, Eco-Warrior, Budget Shopper |
| **Industry** | Vertical-specific research, domain expertise | Healthcare Professional, Finance Expert, Tech Enthusiast |
| **Expert** | Strategic analysis, competitive intelligence, market research | Market Analyst, Brand Strategist, UX Researcher |
***
## Use-Case → Persona Matrix
Use this table to pick personas for your scenario. "Primary" = best first choice; "Alternates" = good for comparison or multi-persona runs.
| Use Case | Primary Persona(s) | Alternates | Why |
| ---------------------------------- | --------------------------------------- | ---------------------------------- | ---------------------------------------------------------------------- |
| **Consumer product launch** | Gen Z Consumer, Millennial Professional | Gen X Parent | Generational personas reflect different buying priorities and channels |
| **B2B SaaS positioning** | B2B Decision Maker, Enterprise CTO | Startup Founder | B2B personas focus on ROI, security, and integration |
| **Sustainability / ESG messaging** | Eco-Warrior, Gen Z Consumer | Millennial Professional | These segments care most about environmental claims |
| **Healthcare / pharma** | Healthcare Professional | Finance Expert, B2B Decision Maker | Industry context for compliance and clinical language |
| **Finance / fintech** | Finance Expert, Budget Shopper | B2B Decision Maker | Mix of institutional and retail perspectives |
| **Ad creative testing** | Gen Z Consumer, Millennial Professional | Gen X Parent | Generational differences in creative preferences |
| **Brand authenticity** | Gen Z Consumer, Eco-Warrior | Millennial Professional | These audiences value authenticity highly |
| **Feature prioritization** | UX Researcher, Tech Enthusiast | B2B Decision Maker | Expert + user perspectives |
| **Competitive analysis** | Market Analyst, Brand Strategist | B2B Decision Maker | Strategic, market-aware viewpoints |
| **Focus group (diverse)** | Gen Z + Millennial + Gen X + B2B | Mix generational + professional | Coverage across segments for NPS, Likert, open-ended |
| **Ad copy for young adults** | Gen Z Consumer | Millennial Professional | Tone, channels, and language differ |
| **Enterprise software sales** | Enterprise CTO, B2B Decision Maker | — | Security, scalability, and procurement focus |
***
## Programmatic Persona Discovery
Fetch all personas and filter by category, name, or custom logic. Use this when building dynamic UIs or automating persona selection.
```python Python theme={"dark"}
import requests
API_KEY = "mvra_live_your_key_here"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
BASE = "https://app.mavera.io/api/v1"
def list_personas(category=None, search=None):
"""List personas, optionally filtered by category or name search."""
resp = requests.get(f"{BASE}/personas", headers=HEADERS)
resp.raise_for_status()
personas = resp.json()["data"]
if category:
personas = [p for p in personas if p.get("category") == category]
if search:
search_lower = search.lower()
personas = [p for p in personas if search_lower in p.get("name", "").lower()]
return personas
# Use-case helpers
def personas_for_consumer_research():
"""Best personas for consumer product/messaging research."""
return list_personas() # Then filter by category
# Or hardcode known IDs if your catalog is stable:
# categories = ["Generational", "Lifestyle"]
# return [p for p in list_personas() if p["category"] in categories]
def personas_for_b2b():
"""Best personas for B2B/SaaS research."""
return [p for p in list_personas() if p.get("category") == "Professional"]
def get_persona_by_name(name):
"""Get a persona by exact or partial name match."""
all_p = list_personas()
for p in all_p:
if name.lower() in p.get("name", "").lower():
return p
return None
# Example: pick personas for a focus group
personas = list_personas(category="Generational")
persona_ids = [p["id"] for p in personas[:4]] # Gen Z, Millennial, Gen X, Boomer
print("Focus group persona IDs:", persona_ids)
```
```javascript JavaScript theme={"dark"}
const API_KEY = "mvra_live_your_key_here";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
const BASE = "https://app.mavera.io/api/v1";
async function listPersonas({ category, search } = {}) {
const resp = await fetch(`${BASE}/personas`, { headers: HEADERS });
const { data: personas } = await resp.json();
let filtered = personas;
if (category) {
filtered = filtered.filter((p) => p.category === category);
}
if (search) {
const s = search.toLowerCase();
filtered = filtered.filter((p) => (p.name || "").toLowerCase().includes(s));
}
return filtered;
}
async function personasForConsumerResearch() {
return listPersonas(); // Then filter by category as needed
}
async function personasForB2B() {
return listPersonas({ category: "Professional" });
}
async function getPersonaByName(name) {
const all = await listPersonas();
return all.find((p) => (p.name || "").toLowerCase().includes(name.toLowerCase()));
}
// Example: pick personas for a focus group
const personas = await listPersonas({ category: "Generational" });
const personaIds = personas.slice(0, 4).map((p) => p.id);
console.log("Focus group persona IDs:", personaIds);
```
***
## Single Persona: Responses
For a single chat, pick one persona that matches your target audience. Use the matrix above, or filter by category.
```python Python theme={"dark"}
from openai import OpenAI
client = OpenAI(api_key="mvra_live_your_key_here", base_url="https://app.mavera.io/api/v1")
# Option A: Hardcode a known persona ID (fastest)
PERSONA_ID = "clx1abc2d0001abcdef123456" # e.g. Gen Z Consumer
# Option B: Resolve by name at startup
persona = get_persona_by_name("Gen Z Consumer")
PERSONA_ID = persona["id"] if persona else None
response = client.responses.create(
model="mavera-1",
input=[{"role": "user", "content": "What makes a brand feel authentic to you?"}],
extra_body={"persona_id": PERSONA_ID},
)
```
```javascript JavaScript theme={"dark"}
const persona = await getPersonaByName("Gen Z Consumer");
const personaId = persona?.id;
const response = await client.responses.create({
model: "mavera-1",
input: [{ role: "user", content: "What makes a brand feel authentic to you?" }],
persona_id: personaId,
});
```
***
## Multi-Persona: Focus Groups
For focus groups, use **3–6 diverse personas** so you get segment-level variation. Mix generational + professional or lifestyle depending on your product.
```python Python theme={"dark"}
# Diverse consumer focus group (generational spread)
generational_ids = [p["id"] for p in list_personas(category="Generational")][:4]
# B2B focus group (different roles)
b2b_ids = [p["id"] for p in list_personas(category="Professional")][:4]
# Hybrid: 2 Gen Z, 2 Millennial, 1 B2B (for a product that spans consumer + SMB)
all_p = list_personas()
gen_z = [p["id"] for p in all_p if "Gen Z" in p.get("name", "")][:2]
millennial = [p["id"] for p in all_p if "Millennial" in p.get("name", "")][:2]
b2b = [p["id"] for p in all_p if p.get("category") == "Professional"][:1]
persona_ids = gen_z + millennial + b2b
# Use in focus group payload
payload = {
"name": "Product Launch Feedback",
"sample_size": 30,
"persona_ids": persona_ids,
"workspace_id": "ws_xxx",
"questions": [...],
}
```
***
## When to Create a Custom Persona
Use **pre-built** personas when your target fits a common segment (Gen Z, B2B, etc.). Create a **custom persona** when:
* Your audience is **niche** (e.g. "Sustainable Fashion Buyer", "SMB Operations Manager").
* You need **specific psychographics** (goals, pains, buying stage) not in pre-built personas.
* You're running **repeated research** and want a reusable, tailored profile.
Custom personas cost **300 credits** to create but are then free to use. See [Personas](/features/personas#creating-custom-personas) for `NORTH_STAR`, `INTERMEDIATE`, and `ADVANCED` pipelines.
```python Python theme={"dark"}
# North Star: Minimal input, AI fills in the rest
resp = requests.post(
f"{BASE}/personas",
headers=HEADERS,
json={
"pipeline_type": "NORTH_STAR",
"name": "Sustainable Fashion Buyer",
"description": "Eco-conscious millennial, values transparency and circular economy",
"workspace_id": "ws_xxx",
},
)
persona = resp.json()
custom_persona_id = persona["id"]
```
***
## Tips and Pitfalls
Listing personas is free but adds latency. Fetch once at app start and cache by name or category. Refresh periodically (e.g. daily) if you create new custom personas.
For "How would you describe X?", use a consumer persona. For "What features matter most for enterprise adoption?", use B2B or Expert personas.
4–6 personas is usually enough for segment diversity. More personas increase cost and can dilute clear patterns.
Use persona for audience perspective; use system prompt for task (e.g. "You are a concise reviewer. Keep answers under 50 words.").
***
## See Also
Pre-built categories, custom creation pipelines, API reference
First response with a persona
Multi-persona focus group setup
List and filter personas