I want to take a moment to celebrate one of our students @Cosmina Balu who just blew us away with her progress. In just four weeks, she managed to build a fully automated system using Airtable and n8n. The salespeople use a UI to enter a certain campaign and then the n8n automation finds past customers from a database and uses AI to write personal upselling and reactivation emails. The emails are genuinely indistinguishable from something a human would write, warm, realistic, and effective. It’s amazing to see how quickly you can go from "learning a tool" to "building a business asset" when you have the right focus. Huge congrats on the execution!

Careful if you implement the n8n backup to Github workflow in Week 4: Bonus Course: n8n backup to Github - n8n Cohort 1 (start 03.11.2025) · Real-World n8n Builders If you save your workflows with pinned data, the backup to Github will fail if the text strings in the Base64 node are too long. That happened to me trying to upload the Fathom workflow from week 2 with pinned data, where the long transcripts were preserved over several nodes. Archiving the workflow didn't work, because archived workflows are still retrieved. Just unpin the nodes, save the workflow and run the Github workflow again. But more importantly: great workflow! Now everything runs smoothly. So thanks, Serop!

Hi Serop, Nadia, and the community, I have a question that goes a bit beyond the standard Week 4 assignment. It touches on customer strategy before you start building automation. The short version: How do you combine customer segmentation (BCG Matrix + mindset alignment) with AI email templates to get consistent output per customer segment, without the AI making things up? I've written out my thinking in the attached document. It includes a "4D Customer Model" that I use to segment customers based on value, growth potential, mindset alignment, and time (where is this customer heading over the next 3-5 years?). I'd be curious to hear your thoughts, both for the Week 4 assignment and as a potential service offering for automation consultants. Has anyone else experimented with customer segmentation before building email workflows? Would love to hear different approaches. See attachment for the full version. Wouter

Hi @Nadia Privalikhina & @Serop B , I have a client project using n8n and I need some advice on the RAG setup. The client has 12 large textbooks (PDFs). I need to build an automation where the AI generates course lessons, but it must use only specific books or chapters as the source material (not the whole library at once). I know that you will teach us about this in the upcoming course, but I just want to quickly understand it because I need it right now. My questions: 1. What is the best strategy to "chunk" or split these large files? Should I split them by chapter before uploading? 2. How do I set up the metadata so the AI knows which book is which? 3. Are there any specific tutorials or resources you recommend for building a "Textbook RAG" system in n8n? Thanks in advance!

We’re kicking off Week 4 this afternoon, and it’s a big one. We’ll dive into building a full customer reactivation system using Airtable + n8n. This powerful combination will help you automate outreach, bring dormant customers back, a system for which I sold the MVP for 5k. 🧠✨ Fill in your brainstorming homework → it’ll make the session 10x more valuable. See you all this afternoon! Let’s build something awesome. 🚀