New apartment. Landlord sends 23-page lease. Standard form, he says. Sign here. Built lease analyzer. Found 4 red flags. Including early termination penalty buried on page 17. THE RENTER'S BLIND SPOT: You need the apartment. You're excited. You sign what they give you. $2,400 early termination fee. 60-day notice requirement. Landlord can enter with 12-hour notice. All buried in legalese. THE DISCOVERY: Dual document extraction. First call pulls structured terms. Second call generates tenant advice. Same pattern as contract review. But optimized for renters. THE WORKFLOW: Google Drive trigger → Download lease → Document extraction pulls rent, deposit, terms, pet policy, termination clauses, red flags → Merge combines with binary → Second extraction generates tenant advice → Code calculates move-in costs and risk level → Sheets logs analysis → IF checks risk level → High risk: Alert channel → Normal: Completion notification. 9 nodes. Tenant protection automated. THE RED FLAG DETECTION: Extraction looks for concerning clauses. Returns array with severity: High, Medium, Low. Code determines overall risk: - 2+ high severity flags → High Risk - 1 high OR 3+ total flags → Medium Risk - Otherwise → Low Risk THE TENANT ADVICE: Second extraction prompt: "Summarize this lease for a tenant. What are the top 3 things to negotiate? Is this tenant-friendly, neutral, or landlord-friendly? What warnings should I know?" Natural language advice. Not just data extraction. THE MOVE-IN COST CALCULATION: Code adds: First month rent + security deposit + any fees = total move-in cost. No surprises on signing day. THE TRANSFORMATION: Before: Sign and hope. Discover problems when moving out. After: Every lease analyzed. Red flags surfaced. Negotiation points identified. THE NUMBERS: 23-page lease analyzed in 45 seconds 4 red flags identified $2,400 early termination fee discovered Move-in cost calculated automatically Template in n8n and All workflows in Github

Today I worked on a small proof of concept for a B2B lead generation setup called NexaGrowth. The goal was to see how AI could quickly qualify incoming leads without adding complexity. The workflow starts with new leads coming in through a Google Form and webhook trigger. Once a submission comes in, the data is sent to OpenAI where the lead is analyzed to classify the industry, estimate company size based on the description, and assign a lead score from 1 to 10. That output is then structured cleanly and pushed into Airtable so the data is easy to review and filter later. If the lead score comes back as 8 or higher, the automation instantly sends a Slack notification so the team can act fast on high intent leads. Nothing fancy, just clean logic, clear prompts, proper data mapping, and basic error handling to keep the flow stable. This kind of setup is a great example of how AI can support lead qualification without replacing existing systems or overengineering the process. Simple automations like this often deliver the quickest wins.