Long Document Analysis → Persona Source

import os, time, json, anthropic, requests

MV = os.environ["MAVERA_API_KEY"]
MV_BASE = "https://app.mavera.io/api/v1"
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}
client = anthropic.Anthropic()

with open("acme_annual_report_2025.txt") as f:
    document_text = f.read()
print(f"Document loaded: {len(document_text):,} chars (~{len(document_text)//4:,} tokens)")

# 1. Claude Opus analyzes the full document
analysis = client.messages.create(
    model="claude-opus-4-6-20250725", max_tokens=4096,
    input=[{"role": "user",
        "content": "Market intelligence analyst. Analyze this document and extract:\n\n"
            "1. **Audience Segments** 2. **Pain Points** 3. **Decision Criteria** "
            "4. **Communication Preferences** 5. **Budget Indicators**\n\n"
            "Return JSON: [{name, role, industry, pain_points, decision_criteria, "
            "communication_style, budget_range, key_quotes}]\n\n"
            f"DOCUMENT:\n{document_text}"}],
)
raw_output = analysis.content[0].text
print(f"Claude complete — {analysis.usage.input_tokens:,} input, {analysis.usage.output_tokens:,} output tokens")

# 2. Parse extracted personas
try:
    start = raw_output.index("[")
    end = raw_output.rindex("]") + 1
    personas_data = json.loads(raw_output[start:end])
except (ValueError, json.JSONDecodeError):
    personas_data = [{"name": "Extracted Persona", "description": raw_output[:500]}]
print(f"Extracted {len(personas_data)} persona segments")

# 3. Create Mavera personas
created = []
for p in personas_data[:6]:
    desc = (f"Role: {p.get('role', 'N/A')}. Industry: {p.get('industry', 'N/A')}. "
        f"Pain points: {', '.join(p.get('pain_points', [])[:3])}. "
        f"Style: {p.get('communication_style', 'professional')}. Budget: {p.get('budget_range', 'N/A')}.")
    mv = requests.post(f"{MV_BASE}/personas", headers=MV_H, json={
        "name": p.get("name", "Document Persona"), "description": desc,
    }).json()
    created.append({"id": mv["id"], "name": p.get("name")})
    print(f"  Created: {p.get('name')} → {mv['id']}")
    time.sleep(0.3)

print(f"\nPersonas created: {len(created)}")
for c in created:
    print(f"  • {c['name']} ({c['id']})")

import Anthropic from "@anthropic-ai/sdk";
import fs from "fs";

const MV = process.env.MAVERA_API_KEY;
const MV_BASE = "https://app.mavera.io/api/v1";
const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };
const client = new Anthropic();

const documentText = fs.readFileSync("acme_annual_report_2025.txt", "utf-8");

const analysis = await client.messages.create({
  model: "claude-opus-4-6-20250725", max_tokens: 4096,
  input: [{ role: "user",
    content: `Market intelligence analyst. Extract: 1. Audience Segments 2. Pain Points `
      + `3. Decision Criteria 4. Comms Preferences 5. Budget Indicators\n`
      + `Return JSON: [{name, role, industry, pain_points, decision_criteria, communication_style, budget_range}]\n\n`
      + `DOCUMENT:\n${documentText}` }],
});
const rawOutput = analysis.content[0].text;
console.log(`Complete — ${analysis.usage.input_tokens.toLocaleString()} input tokens`);

let personasData;
try {
  personasData = JSON.parse(rawOutput.slice(rawOutput.indexOf("["), rawOutput.lastIndexOf("]") + 1));
} catch { personasData = [{ name: "Extracted Persona", description: rawOutput.slice(0, 500) }]; }

const created = [];
for (const p of personasData.slice(0, 6)) {
  const desc = `Role: ${p.role || "N/A"}. Pain points: ${(p.pain_points || []).slice(0, 3).join(", ")}. `
    + `Style: ${p.communication_style || "professional"}. Budget: ${p.budget_range || "N/A"}.`;
  const mv = await fetch(`${MV_BASE}/personas`, { method: "POST", headers: MV_H,
    body: JSON.stringify({ name: p.name || "Document Persona", description: desc }),
  }).then(r => r.json());
  created.push({ id: mv.id, name: p.name });
  console.log(`  Created: ${p.name} → ${mv.id}`);
  await new Promise(r => setTimeout(r, 300));
}
console.log(`Personas created: ${created.length}`);