ExamPark
Course menuAIP-C01

Exams / AIP-C01 / Filtering harmful input (Bedrock Guardrails content filters and denied topics) / Question 1

AIP-C01 practice question: Filtering harmful input (Bedrock Guardrails content filters and denied topics) (1 of 2)

AI Safety, Security, and Governance A free question from our original AIP-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 media company runs a reader comment assistant on Amazon Bedrock. It summarizes thousands of reader comments on each news article and answers editors' questions about the coverage, using the Converse API with a guardrail attached.

Reader comments often contain hateful or threatening language. The moderation team needs that input blocked before it reaches the model, and the newsroom needs the guardrail to stay active on the summaries too.

Summaries of stories about wars, shootings and riots must still be generated, because they describe violence in factual terms and editors depend on them every day. A hostile comment must be stopped, but a factual news summary must not be refused.

Which guardrail configuration meets these requirements?

Choose one answer.

  1. A. Set the hate and violence content filters to HIGH strength for input and to MEDIUM strength for output, and keep the other categories at their defaults.
  2. B. Set the hate and violence content filters to HIGH strength for both input and output, and have the application retry any blocked summary with a rephrased prompt.
  3. C. Set the hate and violence content filters to LOW strength for input and output, and add a denied topic for violence that blocks requests about violent acts.
  4. D. Remove the content filters and add a custom word filter that lists offensive terms and violent phrases, which the moderation team keeps up to date.
Show the answer and explanation

Answer: A

  • A. Right: Content filters have separate input and output strengths, so the input side can be strict while the output side stays tolerant of factual reporting. A medium output strength still blocks harmful generated text while letting summaries of violent events through. The team should test these thresholds in Detect mode against sample stories before enforcing them. Learn more: Content filters in Amazon Bedrock Guardrails (opens in a new tab)
  • B. Wrong: HIGH output strength blocks many factual summaries of violent news, and retrying with a rephrased prompt adds latency and cost without a dependable fix. The stricter input setting is right, but the output setting breaks the requirement that editors still receive summaries.
  • C. Wrong: LOW input strength lets much hostile reader text reach the model, so the moderation requirement fails. A violence denied topic would also block factual summaries of news about violent events, which breaks the second requirement. Learn more: Block denied topics to help remove harmful content (opens in a new tab)
  • D. Wrong: Word filters match only the listed words and phrases, so hateful or threatening comments written in other words still get through. Content filters with strength settings are the way to cover hate and violence as categories, and this option gives no graded control. Learn more: Remove a specific list of words and phrases from conversations with word filters (opens in a new tab)

Explanation

Bedrock content filters take separate input and output strengths for each category, so the input side can be strict while the output side stays tolerant of factual news. Blanket strictness or a violence denied topic would block legitimate summaries, while low input strength and word lists would let hostile comments through.

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 AIP-C01 practice examPractice Filtering harmful input (Bedrock Guardrails content filters and denied topics)All Filtering harmful input (Bedrock Guardrails content filters and denied topics) questions

Want more on Filtering harmful input (Bedrock Guardrails content filters and denied topics)? The 5 full-length practice sets have 5 more Filtering harmful input (Bedrock Guardrails content filters and denied topics) questions, 375 in all, none of them in the free exam. One payment of $14.99, no subscription. See the practice sets