🚀 Day 4 of My AI Automation Engineering Journey Today, I started building an Enterprise AI Customer Support Agent using n8n, OpenAI, and Retrieval-Augmented Generation (RAG). This project goes beyond a traditional chatbot. The objective is to create an intelligent support system capable of understanding customer queries, searching a knowledge base, maintaining conversation context, and escalating complex requests to a human support team when required. 🔹 Technologies • n8n • OpenAI • RAG • AI Agents • Knowledge Base • Google Sheets CRM • Slack • Email Automation ✅ Phase 1 Features • AI Customer Support Agent • Webhook-Based Customer Requests • Knowledge Base Search • Conversation Memory • AI Response Generation • Confidence Scoring • Human Handoff Logic • Support Ticket Creation • CRM Integration • Slack & Email Notifications • Execution Logging My goal is to build production-ready AI systems that solve real business problems, while continuously improving my automation engineering skills through hands-on projects. 📌 Upcoming Phases → Multi-Source RAG (PDFs, Websites & FAQs) → Advanced AI Reasoning → Live Chat Widget → Human Handoff Dashboard → Multi-Channel Support (WhatsApp, Telegram, Facebook & Instagram) → Voice AI Customer Support Agent Every project is an opportunity to learn, improve, and build something closer to enterprise-grade AI automation. Feedback and suggestions are always appreciated. 🚀 #n8n #OpenAI #AIAgents #ArtificialIntelligence #Automation #WorkflowAutomation #CustomerSupport #RAG #LLM #GenerativeAI #NoCode #LowCode #CRM #BusinessAutomation #Tech #Innovation #MachineLearning #SoftwareEngineering #AIEngineering #BuildInPublic

Building a B2B outbound voice agent on Retell (n8n picks who gets called and when, hands the context to the agent, Retell executes the call). Works well for outbound — the agent always knows exactly who it's calling and why, so the prompt is fully tailored to that one scenario. Now I want to support inbound too — someone sees a missed call and calls back, or hears about us and calls in cold. Problem: my current prompt assumes outbound context everywhere. It opens with "Is this [name]?" and assumes it already knows her city — none of that holds for an inbound call from an unknown number. I see two ways to solve this: 1. One agent, bigger prompt — add a full inbound branch: "if this is inbound with no known context, do X instead." One agent, one number to manage, but the prompt grows a lot, and now the model has to figure out which branch applies on every single call, on top of holding both sets of instructions. 2. Two specialized agents — a lean outbound-only agent and a lean inbound-only agent, each with a fully dedicated single-purpose prompt, routed by call direction at the phone number level (inbound_agent vs outbound_agent on Retell). My honest concern with option 1: does a longer, branchy prompt with in-call conditional logic measurably hurt response quality or latency, or meaningfully raise cost, compared to two lean single-purpose prompts? Or am I overthinking it and modern models handle this fine? Curious how people running production voice agents (Retell or similar) handle this — one flexible agent, or multiple specialized ones per direction/use case? Real experience > theory here, especially anything on cost or quality tradeoffs you've actually measured.