Prompt Engineering MCQ

Correct answer: Prompt injection is when untrusted text tries to override your instructions. From lesson: Prompt injection basics

Correct answer: Separate instructions from data, and tell the model to treat data as untrusted. From lesson: Defending against injection

Correct answer: Don't put secrets in prompts; assume anything sent could be logged. From lesson: Avoiding data leakage

Correct answer: Design prompts that decline unsafe or out-of-scope requests gracefully. From lesson: Refusals and boundaries

Correct answer: Ask for balanced perspectives and check outputs for stereotyping. From lesson: Reducing bias

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

Q121. Which best captures the key idea of "Prompt injection basics"? Medium

Permalink →

Q122. Which best captures the key idea of "Defending against injection"? Medium

Permalink →

Q123. Which best captures the key idea of "Avoiding data leakage"? Medium

Permalink →

Q124. Which best captures the key idea of "Refusals and boundaries"? Medium

Permalink →

Q125. Which best captures the key idea of "Reducing bias"? Medium

Permalink →

Q126. Which best captures the key idea of "Content safety"? Medium

Permalink →

Q127. Which best captures the key idea of "PII handling"? Medium

Permalink →

Q128. Which best captures the key idea of "Responsible disclosure of limits"? Medium

Permalink →

Q129. Which best captures the key idea of "Prompt injection"? Medium

Permalink →

Q130. Which best captures the key idea of "Injection defences"? Medium

Permalink →

🎯 Want a real test?

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

Browse Quizzes