G2 Score Tracking → Market Positioning

import os, requests, time

G2 = os.environ["G2_API_KEY"]
MV = os.environ["MAVERA_API_KEY"]
G2_BASE = "https://data.g2.com/api/v1"
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 product scores (replace with your product ID)
PRODUCT_ID = "your-product-id"
product = requests.get(f"{G2_BASE}/products/{PRODUCT_ID}",
    headers=G2_H).json().get("data", {})
attrs = product.get("attributes", {})

scores = {
    "satisfaction": attrs.get("satisfaction_score", 0),
    "market_presence": attrs.get("market_presence_score", 0),
    "implementation": attrs.get("implementation_score", 0),
    "results": attrs.get("results_score", 0),
    "review_count": attrs.get("review_count", 0),
    "avg_rating": attrs.get("average_rating", 0),
}

# 2. Pull competitor scores for comparison
COMPETITOR_IDS = ["comp-a-id", "comp-b-id", "comp-c-id"]
comp_scores = []
for cid in COMPETITOR_IDS:
    r = requests.get(f"{G2_BASE}/products/{cid}", headers=G2_H)
    if r.status_code == 200:
        ca = r.json().get("data", {}).get("attributes", {})
        comp_scores.append({
            "name": ca.get("name", "Unknown"),
            "satisfaction": ca.get("satisfaction_score", 0),
            "market_presence": ca.get("market_presence_score", 0),
            "avg_rating": ca.get("average_rating", 0),
            "review_count": ca.get("review_count", 0),
        })
    time.sleep(0.1)

# 3. Simulate historical trend (in production, store and compare)
previous_scores = {
    "satisfaction": scores["satisfaction"] - 3,
    "market_presence": scores["market_presence"] + 2,
    "implementation": scores["implementation"] - 1,
}

# 4. Mave positioning analysis
score_block = "\n".join(f"- {k}: {v}" for k, v in scores.items())
comp_block = "\n".join(
    f"- {c['name']}: Satisfaction={c['satisfaction']}, Presence={c['market_presence']}, Rating={c['avg_rating']}, Reviews={c['review_count']}"
    for c in comp_scores
)
trend_block = "\n".join(
    f"- {k}: {previous_scores[k]} → {scores[k]} ({'+' if scores[k]>previous_scores[k] else ''}{scores[k]-previous_scores[k]})"
    for k in previous_scores
)

analysis = requests.post("https://app.mavera.io/api/v1/mave/chat",
    headers=MV_H,
    json={"message": f"""Analyze our G2 market position and recommend messaging adjustments.

OUR SCORES:
{score_block}

COMPETITOR COMPARISON:
{comp_block}

SCORE TRENDS (previous → current):
{trend_block}

Produce:
1. Position summary (leader/contender/niche/high performer quadrant)
2. Strengths to amplify in messaging (where we beat competitors)
3. Weaknesses to address (where competitors beat us)
4. Specific messaging updates (what to say differently this quarter)
5. Review generation strategy (how to improve review volume and scores)
6. Competitive talking points for sales"""}).json()

print("=== G2 Market Positioning Analysis ===")
print(analysis.get("content", "")[:2000])

const G2 = process.env.G2_API_KEY;
const MV = process.env.MAVERA_API_KEY;
const G2_BASE = "https://data.g2.com/api/v1";
const G2_H = { Authorization: `Token token=${G2}`, "Content-Type": "application/vnd.api+json" };
const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };

// 1. Our scores
const product = (await fetch(`${G2_BASE}/products/your-product-id`, { headers: G2_H })
  .then((r) => r.json())).data || {};
const attrs = product.attributes || {};
const scores = {
  satisfaction: attrs.satisfaction_score || 0,
  market_presence: attrs.market_presence_score || 0,
  implementation: attrs.implementation_score || 0,
  avg_rating: attrs.average_rating || 0,
  review_count: attrs.review_count || 0,
};

// 2. Competitor scores
const compScores = [];
for (const cid of ["comp-a-id", "comp-b-id"]) {
  const r = await fetch(`${G2_BASE}/products/${cid}`, { headers: G2_H });
  if (r.ok) {
    const ca = ((await r.json()).data || {}).attributes || {};
    compScores.push({ name: ca.name || "?", satisfaction: ca.satisfaction_score || 0,
      market_presence: ca.market_presence_score || 0, avg_rating: ca.average_rating || 0 });
  }
  await new Promise((r) => setTimeout(r, 100));
}

// 3. Trends (simulated — store real history in your DB)
const prevScores = { satisfaction: scores.satisfaction - 3, market_presence: scores.market_presence + 2 };

// 4. Mave analysis
const analysis = await fetch("https://app.mavera.io/api/v1/mave/chat", {
  method: "POST", headers: MV_H,
  body: JSON.stringify({
    message: `G2 position analysis:\n\nOUR: ${JSON.stringify(scores)}\nCOMPETITORS: ${JSON.stringify(compScores)}\nTRENDS: satisfaction ${prevScores.satisfaction}→${scores.satisfaction}\n\nProduce: 1) Quadrant 2) Strengths 3) Weaknesses 4) Messaging updates 5) Review strategy 6) Sales talking points`,
  }),
}).then((r) => r.json());

console.log("=== G2 Positioning ===");
console.log((analysis.content || "").slice(0, 2000));