Your question is Prompt Engineering and RAG Basics. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You're discussing how to improve an LLM-powered question answering feature. Some answers are strong when the prompt is clear, but the model still struggles when it needs facts that are not in its training data.
Explain the concepts of prompt engineering and Retrieval-Augmented Generation (RAG). How do they differ, and when would you use each to improve answer quality?