Keeping Agents Safe

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-agentic-agent-safety

1. What is the main idea of "Keeping Agents Safe"?

   1. Agents that act in the real world need safety measures — spending limits, approval gates, audit logs..
   2. Use AI as the final authority for the whole decision
   3. Avoid checking the answer once it sounds polished
   4. Focus only on speed instead of judgment

2. Which concept is most central to "Keeping Agents Safe"?

   1. guardrails
   2. safety
   3. audit log
   4. sandboxing

3. Which use of AI fits this topic best?

   1. Let the AI decide what matters without your review
   2. Use the answer before checking whether it fits the situation
   3. Set hard spending limits before giving access to money
   4. Use the first answer without checking it

4. What should a careful learner remember about "Three safety basics"?

   1. Use "Three safety basics" as a reminder to verify the AI output before anyone relies on it.
   2. Skip the context so the tool can guess faster
   3. Treat the output as private even after sharing it online
   4. Use the answer without checking the source

5. You want to use AI after this lesson. What is the safest next step?

   1. Act immediately because the AI answer is written clearly
   2. Use the AI answer as a draft, then check it against a reliable source.
   3. Hide uncertainty so the final answer looks cleaner
   4. Use private or sensitive details before checking permission

6. How should AI output about safety be treated?

   1. As proof that no other source is needed
   2. As a replacement for context, consent, or expert review
   3. As a draft or helper output that still needs human judgment and verification
   4. As something that becomes correct when it sounds confident

7. Name one way to verify an AI answer about safety.

8. Which action would help you apply "Keeping Agents Safe" responsibly?

   1. Use the tool to avoid thinking through the tradeoff
   2. Keep going even if the output conflicts with a trusted source
   3. Use the first answer without checking it
   4. Require approval for irreversible actions