AWS Certified AI Practitioner (AIF-C01) — Question 161

A company uses Amazon Bedrock for its generative AI application. The company wants to use Amazon Bedrock Guardrails to detect and filter harmful user inputs and model-generated outputs.

Which content categories can the guardrails filter? (Choose two.)

Answer options

• A. Hate
• B. Politics
• C. Violence
• D. Gambling
• E. Religion

Correct answer: A, C

Explanation

The correct answers are A and C because Amazon Bedrock Guardrails are designed to filter content related to hate speech and violence, which can pose significant risks. The other options, while potentially sensitive, are not specifically targeted by the guardrails in the same way.