Form Submission Analysis

import os, json, requests
from openai import OpenAI

HS = os.environ["HUBSPOT_ACCESS_TOKEN"]
MV = os.environ["MAVERA_API_KEY"]

# 1. Pull form submissions (paginated)
FORM_ID = "your-form-guid"
subs, after = [], ""
while len(subs) < 200:
    params = {"limit": 50}
    if after: params["after"] = after
    r = requests.get(f"https://api.hubapi.com/form-integrations/v1/submissions/forms/{FORM_ID}",
        headers={"Authorization": f"Bearer {HS}"}, params=params)
    r.raise_for_status()
    data = r.json()
    subs.extend(data.get("results", []))
    after = data.get("paging", {}).get("next", {}).get("after", "")
    if not after: break

# 2. Extract free-text
texts = []
for s in subs:
    for f in s.get("values", []):
        if f.get("name") == "biggest_challenge" and f.get("value", "").strip():
            texts.append(f["value"].strip())

# 3. Categorize in chunks
mavera = OpenAI(api_key=MV, base_url="https://app.mavera.io/api/v1")
schema = {"type": "json_schema", "json_schema": {"name": "cats", "strict": True, "schema": {
    "type": "object", "required": ["categories"],
    "properties": {"categories": {"type": "array", "items": {"type": "object",
        "required": ["index", "pain_point", "urgency", "use_case"],
        "properties": {
            "index": {"type": "number"}, "pain_point": {"type": "string"},
            "urgency": {"type": "string", "enum": ["high", "medium", "low"]},
            "use_case": {"type": "string"},
        }}}}}}}

all_cats = []
for i in range(0, len(texts), 50):
    chunk = texts[i:i+50]
    numbered = "\n".join(f"{j+1}. {t[:200]}" for j, t in enumerate(chunk))
    result = mavera.responses.create(model="mavera-1",
        input=[{"role": "user", "content": f"Categorize these {len(chunk)} form responses by pain point, urgency, use case.\n\n{numbered}"}],
        extra_body={"persona_id": os.environ.get("CUSTOMER_PERSONA_ID",""), "response_format": schema})
    parsed = json.loads(result.output[0].content[0].text)
    all_cats.extend(parsed.get("categories", []))

# 4. Summary
points = {}
for c in all_cats:
    points[c["pain_point"]] = points.get(c["pain_point"], 0) + 1
print(f"Categorized: {len(all_cats)} | Unique pain points: {len(points)}")
for pp, n in sorted(points.items(), key=lambda x: -x[1])[:10]:
    print(f"  {pp}: {n}")
print(f"High urgency: {sum(1 for c in all_cats if c['urgency']=='high')}/{len(all_cats)}")

const OpenAI = require("openai").default;
const HS = process.env.HUBSPOT_ACCESS_TOKEN;
const MV = process.env.MAVERA_API_KEY;

// 1. Pull form submissions
const FORM_ID = "your-form-guid";
const subs = [];
let after = "";
while (subs.length < 200) {
  const params = new URLSearchParams({ limit: "50" });
  if (after) params.set("after", after);
  const data = await fetch(
    `https://api.hubapi.com/form-integrations/v1/submissions/forms/${FORM_ID}?${params}`,
    { headers: { Authorization: `Bearer ${HS}` } }
  ).then(r => r.json());
  subs.push(...(data.results || []));
  after = data.paging?.next?.after || "";
  if (!after) break;
}

// 2. Extract free-text
const texts = subs.flatMap(s =>
  (s.values || []).filter(f => f.name === "biggest_challenge" && f.value?.trim()).map(f => f.value.trim())
);

// 3. Categorize
const mavera = new OpenAI({ apiKey: MV, baseURL: "https://app.mavera.io/api/v1" });
const allCats = [];
for (let i = 0; i < texts.length; i += 50) {
  const chunk = texts.slice(i, i + 50);
  const numbered = chunk.map((t, j) => `${j+1}. ${t.slice(0, 200)}`).join("\n");
  const result = await mavera.responses.create({
    model: "mavera-1",
    input: [{ role: "user", content: `Categorize these ${chunk.length} form responses by pain point, urgency, use case.\n\n${numbered}` }],
    extra_body: { persona_id: process.env.CUSTOMER_PERSONA_ID || "", response_format: {
      type: "json_schema", json_schema: { name: "cats", strict: true, schema: {
        type: "object", required: ["categories"],
        properties: { categories: { type: "array", items: { type: "object",
          required: ["index", "pain_point", "urgency", "use_case"],
          properties: { index: { type: "number" }, pain_point: { type: "string" },
            urgency: { type: "string", enum: ["high", "medium", "low"] }, use_case: { type: "string" } }
        }}}
      }}
    }},
  });
  allCats.push(...(JSON.parse(result.output[0].content[0].text).categories || []));
}

// 4. Summary
const points = {};
allCats.forEach(c => { points[c.pain_point] = (points[c.pain_point] || 0) + 1; });
console.log(`Categorized: ${allCats.length} | Pain points: ${Object.keys(points).length}`);
Object.entries(points).sort(([,a],[,b]) => b-a).slice(0,10).forEach(([p,n]) => console.log(`  ${p}: ${n}`));