What are the most common mistakes in building a RAG system?

Common mistakes include chunking too aggressively or too naively, using a generic embedding model when a domain-tuned one would win, skipping reranking even when it would lift precision substantially, trusting retrieval without evaluation on real queries, ignoring metadata filtering for tenant isolation or freshness, not handling documents larger than context windows, and building no feedback loop from user signals back into evaluation. Each of these silently degrades quality until users complain loudly.