Persona Selection by Use Case

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)

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},
)

# 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": [...],
}

# 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"]