Hi guys, I'm new to building Voice AI agents so I would need help. I'm currently building a custom project for my client. I've attached a diagram so that it's easier to visualise. Let's keep it simple for now and just focus on the Voice AI section: He essentially wants a simple high level agent that decides the intent of the inbound call. Customer looking for support --> Customer Support Agent Customer interested in their services/product --> Sales Agent Customer has billing issues --> Financial/Admin Agent ... and maybe more agents (potential for scale) I think my main decider between all the Voice AI platforms available would be the agent transfer/routing feature, ease of use, and maintainability. Here are my thoughts and experience so far: Vapi - Overwhelming. Really developer centric. I think I have to manually integrate RAG on n8n/make.com? Can't seem to make routing and transfering work for some reason. ElevenLabs - So far the new Workflow feature does what I want. Just slightly clunky at the moment. Might be too pricey for my client. Retell AI - Has agent transfer feature. Probably by far the most promising of them all. Synthflow - Not sure how to get multi-agent thing to work just yet, or you probably can't? But you can use one agent for Voice/WhatsApp/Email/Widget. Curious what you guys think. Do let me know if there's anything else I need to clarify :)

Hey everyone 👋 I’m looking to collaborate with businesses, creators, or agencies who want to automate parts of their work. I’m offering my help for free (or at a very low cost if you’d like to support me) in exchange for a testimonial 💬 💡 What I Build: - 📊 Smart finance tracking workflow (check out my Loom demo! It’s an original project I use personally.) - ⚙️ Systems that automate everyday tasks like lead tracking or client onboarding - 🔌 Integrations using tools like Notion, Cal.com, Google Sheets, and OpenAI via Make or n8n I’ll be real. I’m new to real-world AI automation projects. But every mentor and YT creator says the best way to learn is by doing, not endlessly preparing. So here I am, taking that step 😬 If you’ve got a project or idea that could use some automation, I’d love to help out. You’ll get a working system, and I’ll get to learn and grow through the process. And if you don’t like it, it costs you nothing :) So let’s build something together 💪 DM or comment if you’d like to chat or see what I can build! p.s. I’m definitely open to long-term partnerships 👀

Today I worked completely on the RAG Platform and checked on different ways to increase the retrieval speed! I started with using Supabase as my vector DB, Local Embedding Model(nomic-embed-text) and I also added a contextual ingestion method! This method is like you have a chunk and you provide that chunk to the llm with the whole document and the llm provides you a context that you can add with that chunk to increase the accuracy! Then, My Mentor suggested on using Redis Vector Store, and it worked really well! The retrieval was really quick and it worked really well! Now, I'm just waiting for the approval to start working on the V2 of the project and connect the Platform with a Database, and expose API's for the frontend! Thats it for today! let me know what you think! #RAGPlatform #VectorDatabase #Supabase #RedisVectorStore #LocalEmbeddingModel #NomicEmbedText #ContextualIngestion #AIIngestion #RAG #LLMIntegration #LearningInPublic #Day50 #DatabaseIntegration #APIDevelopment #FrontendIntegration #AIWorkflow #TechJourney

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

I see this pattern over and over again — in the comments, in the DMs, and in the dozens of messages I get after posting here: “I’ve learned n8n, but I can’t land a single client.” So here’s a provocation that might unlock something for you: What if selling automation or AI agents isn’t the only path? At first glance, it makes sense — you learn a tool, and then try to sell what you’ve built with it. That’s first-level thinking. But here’s the hard truth: Selling automation or AI requires more than knowing how to use n8n. You need business context. Process knowledge. Market intuition. Because most small businesses don’t even know what they want — let alone what they could gain from an automation or an agent. Which means it’s not just about your technical skill. You also have to educate the client — and that takes time, trust, and effort. That’s why selling what’s already familiar to your client is often the fastest path to cash. Think about it: You don’t need to convince a small business that they need a website. You don’t need to explain why having a good Google Review score or posting on social media matters. These are known, accepted needs. So here’s the mindset shift: Use n8n to power solutions for what the client already knows they need. Let me make it concrete. Did you know that over 28% of small businesses in the U.S. still don’t have a website? Yet many of them already have a Google My Business profile — they’re visible but not converting. Now imagine this: You build a simple scraping automation with n8n (Google My Business profile). You target a specific niche. You filter only businesses that don’t have a website, have poor reviews, or outdated social profiles. Now you don’t need to educate — you just need to offer the obvious. No website? Offer a basic, clean website. No content? Offer a monthly content machine. And behind the scenes, let n8n agents do the heavy lifting for delivery. See the shift? You’re not selling AI. You’re solving visible, urgent problems — powered by automation.