import os, requests, time
SEG_TOKEN = os.environ["SEGMENT_TOKEN"]
MV = os.environ["MAVERA_API_KEY"]
MB = "https://app.mavera.io/api/v1"
MH = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}
SH = {"Authorization": f"Bearer {SEG_TOKEN}", "Content-Type": "application/json"}
SB = "https://api.segmentapis.com"
SPACE_ID = os.environ.get("SEGMENT_SPACE_ID", "spa_xxxxx")
r = requests.get(f"{SB}/spaces/{SPACE_ID}/audiences", headers=SH)
r.raise_for_status()
audiences_data = r.json()
audiences = audiences_data.get("data", {}).get("audiences", [])
if not audiences:
audiences = [
{"id": "aud_001", "name": "High-Value Customers", "description": "Users with >$500 LTV who purchased 3+ times in 90 days", "estimatedSize": 2400},
{"id": "aud_002", "name": "Churning Users", "description": "Active users whose engagement dropped >50% in last 30 days", "estimatedSize": 1800},
{"id": "aud_003", "name": "Trial Converters", "description": "Users who converted from free trial to paid within 14 days", "estimatedSize": 960},
{"id": "aud_004", "name": "Power Users", "description": "Users in top 10% by event volume over last 30 days", "estimatedSize": 500},
]
print(f"Found {len(audiences)} audiences\n")
personas = []
for aud in audiences[:6]:
name = aud.get("name", "Unknown Audience")
desc = aud.get("description", "")
size = aud.get("estimatedSize", aud.get("estimated_size", 0))
persona = requests.post(f"{MB}/personas", headers=MH, json={
"name": f"Segment: {name}",
"description": (
f"Behavioral audience from Segment Engage. {desc}. "
f"Estimated size: {size:,} users. "
f"This persona represents users who match the audience criteria in real product behavior."
),
"demographic": {
"source": "segment_audience",
"audience_id": aud.get("id", ""),
"estimated_size": size,
},
}).json()
personas.append({"audience": name, "persona_id": persona["id"], "size": size})
print(f" {name} → {persona['id']} ({size:,} users)")
time.sleep(0.3)
audience_context = "\n".join(
f"- {p['audience']}: {p['size']:,} users (Persona: {p['persona_id']})"
for p in personas
)
fg = requests.post(f"{MB}/focus-groups", headers=MH, json={
"name": "Segment Audience Research",
"persona_ids": [p["persona_id"] for p in personas],
"questions": [
"Describe your typical week using this product. What do you use it for, and how often?",
"What's the single most valuable thing this product does for you? If that feature disappeared, what would you do?",
"What's your biggest frustration with the product right now? Be specific about what happens and how it affects your work.",
"If you could add one capability, what would it be? How much would you pay extra for it?",
"When was the last time you recommended this product to someone? What did you say? If you haven't recommended it, why not?",
],
"context": f"""Segment audience research study. Each persona represents a behavioral audience from Segment Engage:
{audience_context}
These audiences are defined by real product behavior — purchases, engagement levels, conversion patterns, and usage intensity. The goal is to understand WHY these behavioral patterns exist.""",
"responses_per_persona": 2,
}).json()
for _ in range(30):
time.sleep(5)
data = requests.get(f"{MB}/focus-groups/{fg['id']}", headers=MH).json()
if data.get("status") == "completed":
break
print(f"\nFocus Group: {data.get('id')} — {data.get('status')}\n")
for resp in data.get("responses", []):
print(f"[{resp.get('persona_id','?')}] {resp.get('question','')[:70]}")
print(f" → {resp.get('answer','')[:300]}\n")
