What specific problem does RAG solve that plain prompting to an LLM cannot?

An LLM's knowledge is frozen at training time and it can't answer accurately about your private/proprietary/recent documents it never saw. RAG retrieves the most relevant chunks from your own document store at query time (via vector similarity search) and injects them into the prompt as context, so the model answers grounded in real, current, specific data instead of guessing from stale training knowledge.