ExamPark
Course menuAIF-C01

Exams / AIF-C01 / Responsible AI and guardrails / Question 1

AIF-C01 practice question: Responsible AI and guardrails (1 of 5)

Guidelines for Responsible AI A free question from our original AIF-C01 practice exam. Try it, then open the answer to see why each option is right or wrong.

Last verified against current AWS documentation ·How we write our questions

A bank's customer chatbot must never give personal investment advice, even when a customer asks for it directly.

The developers want a rule set once in Amazon Bedrock that applies to every response, however the question is phrased.

Which Amazon Bedrock Guardrails feature should they use?

Choose one answer.

  1. A. Denied topics, which block a subject the developers describe in plain language, such as personal investment advice.
  2. B. Word filters, which block exact matches of words and phrases from a custom list the developers maintain.
  3. C. Sensitive information filters, which detect and mask personal data such as account numbers in prompts and responses.
  4. D. Contextual grounding check, which tests whether each answer is supported by a source and relevant to the question.
Show the answer and explanation

Answer: A

  • A. Right: Correct. A denied topic is a subject the chatbot must avoid. Guardrails blocks responses on that subject however the question is worded. Learn more: Create your guardrail - Amazon Bedrock (opens in a new tab)
  • B. Wrong: Word filters match exact words, so a customer who asks for advice in different words would still get a reply. They do not understand the topic.
  • C. Wrong: Sensitive information filters protect personal data. They do not stop the chatbot from giving investment advice.
  • D. Wrong: A grounding check looks at whether an answer is supported by source material. It does not block a whole subject like investment advice.

Explanation

Amazon Bedrock Guardrails has several policy types, and each handles a different risk. Denied topics lets a bank define a subject the assistant must not discuss, which is the requirement here. This question tests matching a requirement to the right guardrail policy.

Study

Keep practicing

Answer questions with a score at the end, or practice just this topic with the explanation after each one. No sign-up needed.

Take the free AIF-C01 practice examPractice Responsible AI and guardrailsAll Responsible AI and guardrails questions

Want more on Responsible AI and guardrails? The 5 full-length practice sets have 21 more Responsible AI and guardrails questions, 325 in all, none of them in the free exam. One payment of $14.99, no subscription. See the practice sets