Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to build and evaluate RAG agents using n8n and Qdrant through a hands-on, no-code approach in this 26-minute conference talk. Build a complete agent workflow by indexing a knowledge base with Qdrant vector database and implementing continuous evaluation methods using n8n's native tools. Master the LLM-as-a-Judge evaluation technique with ideal answer sets, discover how to track performance regressions over time, and set up automated alerts for quality drift detection. Explore essential evaluation concepts including test set design, citation faithfulness measurement, and failure case analysis for issues like missing context and brittle prompts. Gain practical skills to create repeatable evaluation workflows that enable confident agent deployment without requiring custom evaluation infrastructure development.
