Building AI Agents You Can Trust & Evaluate

Building AI Agents You Can Trust & Evaluate Most AI projects stop when the demo works. This series starts there. Join me as we build a real Agentic RAG support assistant from scratch and then progressively transform it into a production-ready AI system using observability, evaluations, testing, release gates, and monitoring. In Session 1 we will build: ✅ Agentic RAG architecture ✅ Knowledge-base retrieval ✅ Deterministic tool calling ✅ Order lookup workflow ✅ Support ticket workflow ✅ OpenAI and Ollama support ✅ ChromaDB local vector search ✅ Multi-turn conversation handling This is not another chatbot tutorial. This is AI Engineering. What you'll learn: • How Agentic RAG differs from traditional RAG • How agents make decisions • How retrieval and tools work together • How to design reliable AI systems • How to prepare for tracing, evaluations, and monitoring Series roadmap: Build → Observe → Analyze → Measure → Improve → Release → Monitor Speaker: Toni Ramchandani LinkedIn: https://www.linkedin.com/in/toni-ramchandani/ #AgenticRAG #AIEngineering #GenAI #LLM #RAG #AIAgents #EvaluationDrivenDevelopment #Ollama #OpenAI #ChromaDB