Hi Guys I have built an AI Receptionist that I plan to sell to medical services in Ireland. I have collected 100's of phones and I plan to be making calls myself to try to book demos. As there are many leads, I'm thinking of the feasibility of making AI to call leads via phone and try to book demo meetings. If anybody tried this, can you comment on the results of such campaigns? Would people be willing to book demos and even take things seriously if they realize they are talking to AI? Anybody can comment on the ratio of calls to demo meeting booked? And how many end up attending such demo calls? Given there are many leads, does it make sense to do actual calls for the highest quality leads and do AI calls with the moderate quality leads? Also can any body comment on the cost and hence the ROI of such campaigns? Regards Shadi Ghaith

Hi I have built a scheduling and answering workflow with ElevenLabs and n8n. I developed n8n calendar workflows (no AI) in n8n and made them available via webhooks as tools to ElevenLabs. The ElevenLabs system prompt provides all the details to the ElevenLabs LLM (using Gemini 2.5 Flash). This is working well but sometimes I feel that I can do with a stronger model like Gemini 2.5 Pro but it is not available and likely to be slow. Also I notice delays in responding while making multiple tool calls. I'm thinking if my approach is the best approach, particularly I wonder if it is going to be better to make an orchestration agent at n8n that has the same n8n tools but to be utilized as sub workflows (no ai) instead of webhooks. In this approach the main system prompt will be at the n8n agent and it will make quick tool calls locally. In this approach the LLM at ElevenLabs will handle the discussions with the user via voice and delegates most requests to the n8n orchestration agent (via webhook). Hence I can use very strong model at the n8n side and tool calls will be faster. The ElevenLabs system prompt will be much simpler. I still didn't try this but I wonder if anybody has a preference on which approach to go? The current approach to allow ElevenLabs to access remote tools individually, while the proposed approach will mean calling a remote agent for almost everything but that agent can have faster access to local tools. The n8n agent may need to ask for extra information which would be slow in this case. My goal of the proposed change will be to both have a stronger LLM and reduce multiple remote tool calls and so reduce delays. Any ideas? Regards Shadi Ghaith

Something pretty exciting just released from Google that I think you need to know about. They just released Genkit Go 1.0 - and before you think "oh great, another coding thing I can't use," hear me out. This could be the missing piece that takes your n8n automations from cool hobby projects to serious money-making businesses. What Is This Thing Anyway? Think of Genkit as a super-powered toolkit that makes building AI apps way easier. You know how n8n makes connecting different services simple with those drag-and-drop nodes? Genkit does something similar but for AI stuff - it connects different AI models (like ChatGPT, Google's Gemini, Claude) and makes them work together smoothly. The coolest part? It now has something called "AI-assisted development" where AI helpers can actually write code FOR you. Imagine having ChatGPT not just answer questions, but actually build entire applications based on what you describe. Why Should You Care as an n8n User? Here's the thing - you're already automating workflows and connecting APIs. You understand how powerful it is when different tools talk to each other. Genkit basically does that same magic but adds AI superpowers on top. For enhancing what you have now: - Your existing n8n workflows could trigger AI-powered analysis - Customer support bots could get way smarter - Data processing workflows could include AI insights - Content creation pipelines could become fully automated For building new businesses: - Custom AI tools for specific industries - AI-powered dashboards and reporting tools - Smart automation services for clients - AI consultants that work 24/7 The Business Opportunity Here Is Huge Think about it - most businesses are still figuring out how to use AI. They know they need it, but they don't know how to build it or make it work with their existing systems. That's where you come in. You already understand automation and workflow design. Now imagine being able to offer clients: - Custom AI chatbots that actually understand their business

In this video, I show you how I built a no-code Photoshop AI agent inside n8n that can combine and edit images, search through all your files for raw content or generated images, and even rename them automatically. Powered by Google’s new state-of-the-art Nano Banana image model, this agent is a game-changer for ad creatives and UGC content, making high-quality image editing and management faster and easier than ever. As always, you can get all the free resources you need to copy this exact system in this post :)

In this video, I dive into n8n’s new Text-to-Workflow builder and show you why it’s such a game-changer for saving time. I run through three live examples so you can see what kinds of prompts work well, where it struggles, and how to think about using it the right way. I also cover the limitations and the mindset you need: this tool is a great starting point to cut down build time, but you’ll still need to understand the fundamentals of how workflows work if you want to make them reliable and improve on what the builder gives you. ⚠️ Quick note: This feature hasn’t officially rolled out to everyone yet. So if you update n8n and don’t see the Text-to-Workflow builder, don’t freak out — it’s being rolled out in phases as they continue improving the product.