Day 1 done. Ended up combining two skills in one build: Firecrawl scraping + the newsletter automation. Pointed it at my own business instead of a demo topic (real estate in Dubai). Firecrawl pulls recent transaction data, Python turns it into the actual stats (median price/sqft, yields, MoM change), Claude writes the copy in my brand voice, infographic cards get rendered with my branding, and it all drops into Gmail as a draft so I can sanity-check it before it hits my clients' inboxes. AI never makes up a number. Everything on the cards comes straight from a scraped transaction, right down to price per sqft, yields, bedroom mix and the most-traded buildings that month. Screenshots below 👇 If anyone else is using this in the real estate industry, curious to see how you're helping your clients with it.

Today I finished building an AI-powered real estate lead management system using n8n + OpenAI + Airtable. The goal was to automate the journey from a website inquiry to a qualified lead with minimal manual work. Current features: ✅ Website lead capture ✅ AI-powered lead analysis & summaries ✅ Buyer/Seller classification ✅ Lead scoring & quality (Hot / Warm / Cold) ✅ Automated email follow-ups ✅ AI-generated SMS follow-ups ✅ Consultation booking ✅ Airtable CRM for lead, appointment & follow-up management ✅ Google Sheets integration ✅ Error handling throughout the workflow I've attached a few screenshots of the CRM to show how the data is organized after the automation runs. Still improving the system, but it's been a great project for learning how to combine AI with real business workflows. 💬 If you were building this, what feature would you add next? I'd genuinely appreciate any feedback or suggestions. #BuildInPublic #n8n #OpenAI #Automation #AIAgents #Airtable #CRM #WorkflowAutomation #RealEstate #ArtificialIntelligence

fifth rep of 7 - I built a single-page marketing site

Hi friends. I've been a zero to one product manager for over 12 years, and along the way I kept borrowing pieces from different discovery frameworks until I had a methodology of my own, one that actually raises the odds of an idea working. It does that by finding the real emotional problems people are facing, the strongest moats, and the growth loops that help a product pull in its own users. If you find this useful, please upvote me on Product Hunt today. Appreciate it. :the_horns: producthunt.com/products/vibe-check-6 And if you don't care for product hunt, here's the GitHub link. github.com/TexasBedouin/vibe-check

Set up two different ways to let Claude Code work without me watching it. Scheduled task: a daily market check that runs on its own every morning, pulls Nifty/Sensex movement and my watchlist's top gainers/losers, and sends me the summary ,no laptop open, no manual trigger. Loop: a short-term monitor I can spin up inside a live session — "check every 10 minutes if a new comment came in on my latest post" and it fires on schedule until I delete it or the session ends. The distinction matters more than I expected: one is a permanent background process, the other is a temporary watch-and-report you set up on the fly. Different tools for different jobs.