You are helping me build the following AI agent workflow. ## Goal Real Estate Listing Scraper: Every week, it scrapes LoopNet for new commercial listings and saves the structured data to your Google Sheet. ## Specification - What it does: You receive new commercial real estate listings from LoopNet every week, automatically organized in your Google Sheet so you can analyze titles, links, and sizes without manual entry. - Trigger: On a schedule (Scheduled ยท weekly) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Scrapeless: Web scraping LoopNet listings - n8n: Workflow orchestration - Google Sheets: Storing structured property data - Code: Parsing Markdown with regex ## Known pitfalls, handle each one explicitly in your implementation 1. LoopNet frequently updates its DOM structure so you must add manual monitoring alerts when parsing fails unexpectedly. 2. Scrapeless proxies can sometimes return cached or incomplete pages, so implement a retry mechanism with distinct user agents. 3. Google Sheets has row limits per API call, so batch your inserts if the weekly scrape returns more than 50 listings at once. 4. Regex parsers are brittle against minor HTML changes, so wrap the parsing step in a try-catch block to prevent workflow crashes. ## Reference implementation https://n8n.io/workflows/5878 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/automated-real-estate-listing-scraper/ via usecasesforagents.com