Prompt Engineering MCQ

Correct answer: Retrieval-Augmented Generation grounds answers in your own documents instead of model memory. From lesson: What is RAG

Correct answer: RAG reduces hallucination and lets models answer about private, current data. From lesson: Why RAG matters

Correct answer: Split documents into passages sized for retrieval and the context window. From lesson: Chunking documents

Correct answer: Embeddings turn text into vectors so similar meanings sit close together. From lesson: Embeddings explained

Correct answer: Find the chunks most similar to the question using vector similarity. From lesson: Vector search

Prompt engineering, LLMs, AI safety, RAG and applied AI questions.

Q161. Which best captures the key idea of "What is RAG"? Medium

Permalink →

Q162. Which best captures the key idea of "Why RAG matters"? Medium

Permalink →

Q163. Which best captures the key idea of "Chunking documents"? Medium

Permalink →

Q164. Which best captures the key idea of "Embeddings explained"? Medium

Permalink →

Q165. Which best captures the key idea of "Vector search"? Medium

Permalink →

Q166. Which best captures the key idea of "Prompting with retrieved context"? Medium

Permalink →

Q167. Which best captures the key idea of "Citations and trust"? Medium

Permalink →

Q168. Which best captures the key idea of "RAG failure modes"? Medium

Permalink →

Q169. Which best captures the key idea of "What is an AI agent"? Medium

Permalink →

Q170. Which best captures the key idea of "The observe-think-act loop"? Medium

Permalink →

🎯 Want a real test?

Take a timed quiz on this topic and see your rank on the leaderboard.

Browse Quizzes