I’ve been getting this question a lot lately. With AI automations becoming easier to build with AI, and OpenAI releasing AgentKit, people are wondering if n8n is even worth learning anymore. But here’s the truth: if I had to start all over again knowing nothing, I’d still learn everything I could about n8n. Because when you learn n8n, you’re not just learning one tool, you’re learning how systems think. You start to see how triggers connect, how data flows, and how logic turns into results. And once you understand that, you can jump to any platform in the world and master it instantly. You become tool-agnostic, and that’s where the real freedom lies. When you learn how to build workflows yourself, you also learn lessons that can’t be taught through flashy AI demos. You start to see what automations can really do, how reliable AI actually is, and what’s possible when you combine logic with creativity. You learn how to build systems that save time, cut costs, and actually work in the real world, not just on paper. That skill separates you from everyone else trying to sell the same thing. Because when clients hire you, they’re not hiring you to drag nodes on a screen, they’re hiring you to think like an automator. They want someone who understands the logic behind the system, can identify what’s going wrong, and knows how to make it better. The people who skip this step, the ones relying entirely on “AI agents that build workflows for you”, are like someone trying to sell a cake after only seeing a picture of it. They don’t know the ingredients, how it was baked, or even the flavor. So when they try to explain it to others, they sound the same as everyone else. But when you’ve actually baked the cake yourself, you can describe the flavor, the texture, the process, and that builds trust. And in this space, trust is everything. Automation is one of the few skills in the world that directly compounds over time. Once you know how to identify bottlenecks, map processes, and connect systems, you can apply that skill to any business or industry. And the ROI is real, recent studies by Deloitte and McKinsey show companies that invest in automation see up to a 30% reduction in operating costs and often double or triple their productivity within months. The people who understand how to build and maintain these systems are the ones leading that transformation.

Hey n8n community 👋 I’m looking for someone to help me complete my Amazon FBA Inventory sync workflow in n8n. I’ve already got multiple Amazon SP-API workflows working in n8n — including: - 🧾 Orders - 🌍 Marketplace Participation - 📦 AWD Inventory (Amazon Warehousing & Distribution) But I’m now trying to connect to the /fba/inventory/v1/summaries endpoint to get real-time FBA inventory levels for all of my SKUs — and this one has been a tough nut to crack. 💡 Who I’m Looking For: Ideally someone who has: - Experience working with Amazon SP-API endpoints in n8n - Familiarity with: 🔧 Tech Stack: - Self-hosted n8n - Amazon Seller Central (private developer app) - NodeJS signature script for SigV4 - Google Sheets (final destination for synced inventory data) 💬 Current Status: - LWA and IAM flows are already working - RDT enabled + scopes selected - Can successfully call some endpoints - Still receiving 403 or RDT-related errors for this FBA inventory endpoint 📨 If you’re confident with Amazon Seller endpoints or love a challenge, hit me up. We’re right on the edge of something game-changing — and I’d love your help getting across the finish line.

Ever felt like this? Either if its a personal project, project for you clients for you agency. This always gets you feeling FRUSTRATED, as you are just THAT CLOSE to finishing this project, and needed tech support to finish it. Well you are in luck my friends, AIS+ offers FREE tech support with a great team (including a support specialist) and members to help you out, ALMOST 1000 questions have been solved (specificly 943) All for literally just $89/Month, and I know, that doesnt sound very cheap, but if you sign up through the yearly plan, it is only $58/Month, and when you sign up for the yearly plan, you dont just get a discount, you also unlock your access to the 3 Million dollars savings vault with over 500 discounts for many different services and websites, such as Bolt, Zapier, Make, etc.. So what are you waiting for? Join now here: https://www.skool.com/ai-automation-society-plus/about?ref=82bef5b395ca4b95a5bd8560d4b7df52

I know I'm not the only beginner here. I had a bit of a challenge in fully understanding RAG and Vector. Once I grasped it, I decided to create this post to hopefully help someone else out there with the same confusion I had. They work together but do different things, like a librarian and a teacher teaming up. What’s a Vector Database? Think of a vector database as a super-smart librarian who “speaks computer.” It stores data (like text or images) as high-dimensional vectors or numerical codes (e.g., 768 numbers long) that capture meaning. When you ask a question, it converts your query into a vector and finds the most similar vectors in its collection, like matching documents or image descriptions. For example, if you search “Why is the sky blue?”, it might pull raw snippets like “Rayleigh scattering scatters blue light.” It’s fast and great at finding relevant info, but the results can feel raw or technical, like getting a stack of book pages. What’s RAG? RAG is like the friendly teacher who takes those book pages and explains them in plain English. It combines retrieval (grabbing data, often from a vector database) with generation (using a language model to craft a response). If you ask about the sky, RAG retrieves those snippets and turns them into: “The sky is blue because Rayleigh scattering spreads blue light more in the atmosphere.” It’s conversational, clear, and reduces AI “hallucination” (making stuff up) by grounding answers in real data. How Do They Differ? - Vector Databases: Store and retrieve data as vectors for fast, meaning-based searches. They’re the backbone for apps like recommendation systems or semantic search but don’t “talk” to users directly. - RAG: Uses vector databases (or other sources) to fetch data, then generates human-friendly answers. It’s perfect for chatbots, Q&A systems, or research assistants needing accurate, polished responses. Why Use Both? Vector databases are awesome at finding relevant info but stop there. RAG goes further, translating that info into something you’d actually understand, like summarizing or comparing facts for you. If no data is found, a good RAG system might say, “I don’t know,” keeping things honest.

I tried selfhosting, but had issues with updating the n8n. Anyone have some good solution for good selfhost platform?