AIF-C01 Guidelines for Responsible AI Practice Question

A public sector agency is building a chatbot on Amazon Bedrock that answers citizen questions about benefits eligibility. The agency must ensure the chatbot never provides medical or legal advice, and that responses stay grounded in the agency's official policy documents rather than the foundation model's general knowledge. Which Amazon Bedrock Guardrails configuration should the team apply?

⚠ Common exam trap

The trap here is using a word filter or sensitive information filter to enforce a topical prohibition, when those mechanisms match or redact specific strings rather than classifying whether a response constitutes prohibited advice.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Configure a denied topics policy for medical and legal advice, and use contextual grounding checks with the official policy documents supplied as the grounding source.

Two constraints must be enforced: no medical or legal advice, and answers grounded in official policy documents. A denied topics policy names and blocks those advice categories at both input and output. Contextual grounding checks compare each response against the supplied policy documents and intervene when support is weak, which prevents the model from answering from its own general knowledge.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Configure a sensitive information filter to redact medical terms and legal citations, and enable the profanity filter at HIGH strength to keep responses professional.
Why it's wrong here
Redacting medical terms would remove legitimate benefits-related vocabulary, such as references to medical eligibility criteria, damaging correct answers. The profanity filter addresses offensive language, which is unrelated to preventing medical or legal advice, and neither setting grounds responses in the agency's official documents.
✓
Configure a denied topics policy for medical and legal advice, and use contextual grounding checks with the official policy documents supplied as the grounding source.
Why this is correct
A denied topics policy blocks prompts and responses that fall within the defined medical and legal advice subjects, directly enforcing the prohibition. Contextual grounding checks evaluate each response against the supplied policy documents and intervene when the answer is not supported by that source, which keeps the chatbot anchored to official agency content instead of the model's general knowledge.
✗
Configure automated reasoning checks against a formal policy of eligibility rules, and rely on the foundation model's built-in knowledge to answer general questions.
Why it's wrong here
Automated reasoning checks validate outputs against formal logical rules, which suits deterministic eligibility calculations but not the open-ended prohibition on advice topics. Relying on the foundation model's general knowledge is the opposite of the grounding requirement, because it allows responses that are not supported by the agency's official policy documents.
✗
Configure a word filter containing a blocklist of medical and legal terms, and set the guardrail action to NONE so responses are flagged for human review instead of blocked.
Why it's wrong here
A word filter performs literal matching, so a blocklist of medical and legal terms would misfire on legitimate benefits content that mentions health conditions or statutes. Setting the action to NONE means nothing is blocked, so the chatbot could still deliver prohibited advice, simply with a flag attached after the fact.

Go deeper

AIF-C01 Guidelines for Responsible AI Practice Question

Why each option matters

Option-by-option breakdown

Related to this question