import os, requests, time, json
G2 = os.environ["G2_API_KEY"]
MV = os.environ["MAVERA_API_KEY"]
G2_H = {"Authorization": f"Token token={G2}", "Content-Type": "application/vnd.api+json"}
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}
# 1. Pull reviews
reviews = []
page = 1
while len(reviews) < 200:
r = requests.get(f"https://data.g2.com/api/v1/survey-responses",
headers=G2_H, params={"page[size]": 50, "page[number]": page})
if r.status_code == 429: time.sleep(1); continue
r.raise_for_status()
data = r.json().get("data", [])
if not data: break
reviews.extend(data)
page += 1
time.sleep(0.1)
# 2. Extract "dislike" and "recommendation" text
feature_texts = []
for rev in reviews:
attrs = rev.get("attributes", {})
for key, val in attrs.get("comment_answers", {}).items():
text = val if isinstance(val, str) else val.get("text", "")
k = key.lower()
if ("dislike" in k or "wish" in k or "improve" in k or "recommend" in k) and text.strip():
feature_texts.append(text[:300])
# 3. Use Mave to categorize feature requests
from openai import OpenAI
mavera = OpenAI(api_key=MV, base_url="https://app.mavera.io/api/v1")
feature_block = "\n".join(f"{i+1}. {t}" for i, t in enumerate(feature_texts[:50]))
categorization = mavera.responses.create(model="mavera-1",
input=[{"role": "user", "content": f"""Categorize these G2 review comments into feature request categories.
{feature_block}
Return JSON with: feature_name, description, mention_count, representative_quotes (2 each).
Group similar requests. Minimum 3 mentions to include."""}],
extra_body={"response_format": {"type": "json_object"}})
features = json.loads(categorization.output[0].content[0].text)
feature_list = features.get("features", features.get("feature_requests", []))
print(f"Identified {len(feature_list)} feature request categories")
# 4. Create product user personas
PRODUCT_PERSONAS = [
{"name": "Power User PM", "desc": "Uses product daily. Deeply invested in feature depth."},
{"name": "Executive Sponsor", "desc": "Bought the product. Cares about ROI and team adoption."},
{"name": "New User", "desc": "Onboarding. Wants simplicity and quick wins."},
]
persona_ids = []
for pp in PRODUCT_PERSONAS:
p = requests.post(f"https://app.mavera.io/api/v1/personas", headers=MV_H, json={
"name": f"G2: {pp['name']}", "description": pp["desc"],
}).json()
persona_ids.append(p["id"])
time.sleep(0.2)
# 5. Focus Group: rank features
feature_options = "\n".join(
f"({chr(65+i)}) {f.get('feature_name', f.get('name', 'Unknown'))}: {f.get('description','')[:80]}"
for i, f in enumerate(feature_list[:8])
)
fg = requests.post(f"https://app.mavera.io/api/v1/focus-groups", headers=MV_H, json={
"name": "G2 Feature Request Prioritization",
"persona_ids": persona_ids,
"questions": [
{"type": "ranking", "text": f"Rank these features by impact on YOUR workflow:\n{feature_options}"},
"Which feature would make you upgrade to a higher tier?",
"Which feature, if missing, would make you consider switching products?",
"Describe a workflow you currently can't do that these features would enable.",
],
"responses_per_persona": 3,
}).json()
for _ in range(20):
time.sleep(5)
data = requests.get(f"https://app.mavera.io/api/v1/focus-groups/{fg['id']}", headers=MV_H).json()
if data.get("status") == "completed": break
print(f"\nFocus Group: {fg['id']}")
for resp in data.get("responses", []):
print(f"\n{resp.get('question','')[:60]}")
print(f" → {resp.get('answer','')[:300]}")
