You are a market research analyst. Analyze the following scraped product data and produce a brief market intelligence report covering:1. Price positioning (budget, mid-range, premium)2. Common features across listings3. Gaps or opportunities you notice4. A 2-3 sentence executive summaryProduct Name: {{product_name}}Price: {{price}}Description: {{description}}URL: {{url}}

import json, requestsfrom flask import Flask, request, jsonifyfrom anthropic import Anthropicapp = Flask(__name__)client = Anthropic(api_key="your-anthropic-api-key")SLACK_WEBHOOK_URL = "https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK"@app.route("/webhook/browse-ai/analyze", methods=["POST"])def analyze_competitor():    event = request.json    if event.get("event") != "taskFinishedSuccessfully":        return jsonify({"status": "ignored"}), 200    task = event.get("task", {})    captured = task.get("capturedTexts", {})    lists = task.get("capturedLists", {}).get("items", [])    # Build context from all captured data    context = "Captured fields:\n" + json.dumps(captured, indent=2)    if lists:        context += f"\n\nCaptured table ({len(lists)} rows):\n"        context += json.dumps(lists[:50], indent=2)  # Cap at 50 rows    # Ask Claude to analyze    message = client.messages.create(        model="claude-sonnet-4-6",        max_tokens=2048,        system="You are a competitive intelligence analyst. Provide clear, actionable insights.",        messages=[{            "role": "user",            "content": f"""Analyze this competitor data scraped from the web. Produce a briefing with:- Key findings (bullet points)- How this compares to typical market positioning- Recommended actions for our team- Any red flags or opportunitiesData:{context}"""        }]    )    analysis = message.content[0].text    # Post to Slack    requests.post(SLACK_WEBHOOK_URL, json={        "text": f"*Competitor Analysis*\nRobot: {task.get('robotId')}\n\n{analysis}"    })    return jsonify({"status": "analyzed"}), 200if __name__ == "__main__":    app.run(port=5000)

import requests, jsonfrom anthropic import AnthropicBROWSE_AI_API_KEY = "your-browse-ai-api-key"client = Anthropic(api_key="your-anthropic-api-key")# Define the robots to pull data fromROBOTS = {    "competitor_pricing": "robot-id-1",    "industry_news": "robot-id-2",    "job_listings": "robot-id-3",}def get_latest_data(robot_id):    """Fetch the most recent successful task from a robot."""    response = requests.get(        f"https://api.browse.ai/v2/robots/{robot_id}/tasks",        headers={"Authorization": f"Bearer {BROWSE_AI_API_KEY}"},        params={"page": 1}    )    tasks = response.json().get("result", {}).get("robotTasks", {}).get("items", [])    for task in tasks:        if task.get("status") == "successful":            return task    return Nonedef build_analysis_context():    """Collect data from all robots into a single context."""    context_parts = []    for label, robot_id in ROBOTS.items():        task = get_latest_data(robot_id)        if task:            data = {                "captured_texts": task.get("capturedTexts", {}),                "captured_lists": task.get("capturedLists", {}).get("items", [])[:100]            }            context_parts.append(f"## {label}\n{json.dumps(data, indent=2)}")    return "\n\n".join(context_parts)def generate_report():    """Generate a market intelligence report from all sources."""    context = build_analysis_context()    message = client.messages.create(        model="claude-opus-4-6",        max_tokens=4096,        system="""You are a senior market research analyst. Write structured, data-driven reports with clear sections and actionable recommendations.""",        messages=[{            "role": "user",            "content": f"""Using the following data collected from multiple web sources, generate a comprehensive market intelligence report.Include these sections:1. Executive Summary (3-5 sentences)2. Market Overview (key trends, pricing patterns)3. Competitive Landscape (major players, positioning)4. Hiring Signals (what job listings reveal about strategy)5. Opportunities and Threats6. Recommended Actions (prioritized)Data sources:{context}"""        }]    )    return message.content[0].text# Generate and save the reportreport = generate_report()with open("market_report.md", "w") as f:    f.write(report)print("Report generated: market_report.md")

import requests, jsonfrom anthropic import AnthropicBROWSE_AI_API_KEY = "your-browse-ai-api-key"client = Anthropic(api_key="your-anthropic-api-key")def load_knowledge_base(robot_id):    """Load all scraped content from a robot's task history."""    all_content = []    page = 1    while True:        response = requests.get(            f"https://api.browse.ai/v2/robots/{robot_id}/tasks",            headers={"Authorization": f"Bearer {BROWSE_AI_API_KEY}"},            params={"page": page}        )        tasks = response.json().get("result", {}).get("robotTasks", {}).get("items", [])        if not tasks:            break        for task in tasks:            if task.get("status") == "successful":                texts = task.get("capturedTexts", {})                if texts:                    all_content.append(texts)        page += 1    return all_contentdef query_knowledge_base(knowledge_base, question):    """Ask Claude a question using scraped content as context."""    context = json.dumps(knowledge_base, indent=2)    message = client.messages.create(        model="claude-sonnet-4-6",        max_tokens=2048,        system="""You are a helpful research assistant. Answer questions using ONLY the provided reference data. If the data doesn't contain enough information to answer, say so clearly. Cite specific entries when possible.""",        messages=[{            "role": "user",            "content": f"""Reference data (scraped from the web):{context}Question: {question}"""        }]    )    return message.content[0].text# Load scraped content as knowledge basekb = load_knowledge_base("your-robot-id")print(f"Loaded {len(kb)} pages into knowledge base")# Query itanswer = query_knowledge_base(kb, "What pricing tiers do competitors offer?")print(answer)