A client recently asked me if I could make all the info from their website instantly available inside WhatsApp. So I explored a RAG chatbot setup and built the following flow in n8n: - Create a form to collect the website URL. - Scrape the site with Firecrawl. - Send all the content into a Google Doc. - Push it into a MongoDB vector DB (create an index). - Connect it to WhatsApp (the trickiest part with Meta). It got me thinking back to my travels in South America & Asia, where WhatsApp is the default, this kind of setup could be a huge value-add for hotels and service businesses. Also, for more control over the conversation flow, I’d recommend layering Voiceflow on top of this. Curious if anyone else has tried something similar or sees other use cases for this stack?

Hi all, I’ve been struggling with applying Alex Hormozi’s frameworks in a practical way. Every time I read $100M Offers or $100M Leads, I’d get inspired… but then forget the exact quote or framework when I needed it most. I know a lot of people here have felt the same. So last week I built something to fix that: a RAG chatbot trained on Hormozi’s books. Now I can just ask: • “Give me 3 ways to increase perceived value in my offer” • “What’s Hormozi’s take on pricing guarantees?” • “Summarize how to get attention for my business” And it answers instantly, with exact references from the books. Here’s how I set it up: 1. Scraped + cleaned the books into Markdown (so the data is structured). 2. Used a vector database (Supabase) to store the chunks. 3. Plugged it into a simple RAG flow in n8n with OpenAI for the responses. 4. Wrapped it in a lightweight chat UI built with NextJS so it feels like ChatGPT—but with Hormozi’s brain on tap. If anything is unclear, let me know. Hope this helps you if you also want an “Hormozi GPT” for when you’re working on your business.

I heard Alex Hormozi talk about the power of giving free value. So I built a new Lead Magnet for SaaS founders: a Free SaaS Valuation Calculator. You enter a few metrics — ARR, profit, growth, churn, etc. — and instantly get a valuation range. At the end, it asks for name/email/phone so I can follow up, + a CTA to book a call on my Calendly. But here’s the fun part 👉 I connected it directly to an automation tool (n8n): - As soon as a founder submits, the data is pushed into my CRM. - n8n triggers an AI-based speed-to-lead flow: instant personalized email. - This way, I never lose a hot lead while they’re still thinking about their valuation. ⚡️ Why this matters: - Founders love free, useful tools. - I get qualified inbound leads with data. - Automation ensures zero manual lag — prospects get contacted within minutes. Building this took me just a couple of hours, and now it’s a fully automated funnel running in the background. 👉 Curious? You can test the valuation tool here: monoclick.ai/valuation Would you like me to also drop the n8n workflow JSON I used for the speed-to-lead automation? Happy to help. Henry

8,000 cold emails. 27 new opps. 0 hours spent replying. i tested AI reply agents on a B2B SaaS campaign. not AI hype. real results. The setup → instantly. ai → trained it with my past replies → integrated Slack + Calendly → gave it tone, rules, and edge The numbers (30 days) → 8,000 emails sent → 27 opps booked → 74% of replies handled without me → 4.4 hours saved → not one awkward message sent What surprised me most → it turned “i’m too busy” into “circle back in 2 weeks” → handled objections like a pro → sounded human every time How to get this right → train with your real replies → give it strict rules + clear tone → start with human-in-the-loop → scale to full autopilot later this isn’t about saving time it’s about scaling smart without killing personalization

Professor emails at 2 AM: "Need 200 citations for grant proposal. Due Thursday. Help?" This is Dr. Sarah Chen, molecular biology, Harvard. Her grant applications get $2M+ funding. No pressure. HER MANUAL NIGHTMARE - Search 6 different academic databases - Cross-reference citations - Format in 3 different styles (APA, MLA, Chicago) - Remove duplicates manually - Verify impact factors - Total time estimate: 40 hours MY n8n SOLUTION (Built in 6 hours) The Workflow Architecture (12 nodes): 1. Google Sheets trigger → research topics input 2. Multi-database search node (parallel): PubMed API; ArXiv search; Semantic Scholar; Google Scholar; ERIC database. 3. Results aggregation and deduplication 4. Citation impact factor lookup 5. Automatic citation formatting (3 styles) 6. Relevance scoring based on keywords 7. Output to structured database THE MAGIC MOMENT Demo call Tuesday morning:"Input your 12 research topics here..."types topics in Google Sheet 3 minutes later: - 847 relevant papers found - Duplicates removed (312 eliminated) - 535 unique citations - All formatted in required styles - Ranked by relevance and impact factor Her reaction: "This is impossible. You built a research assistant." WEDNESDAY DELIVERY Final results: - 200 top-ranked citations - 3 formatting styles - Impact factor analysis - Relevance scores - Export formats: BibTeX, EndNote, Zotero Processing time: 8 minutes Manual equivalent: 40 hours Time saved: 39 hours 52 minutes THE FOLLOW-UP PROJECT "Can this monitor for new papers weekly?" Added scheduled triggers: - Monday search for new publications - Automatic relevance filtering - Weekly digest with top 10 papers - Direct integration with her reference manager SCALING THE MAGIC Current setup serves: - 8 professors across 4 universities - 15,000+ papers processed monthly - Average search time: 4.3 minutes - Manual equivalent time saved: 320 hours/month REVENUE BREAKDOWN - Professor subscriptions: $600/month each - Enterprise university licenses: $2,400/month - Custom research workflows: $1,800 one-time - Total monthly: $4,800