Explanation:
Why Option B is correct:
Sensitive Information Filters: The requirement is specifically about preventing exposure of personal information. Amazon Bedrock guardrails have sensitive information filters designed for this purpose (PII detection like names, addresses, emails, etc.).
Mask mode during development/testing: This allows the company to evaluate effectiveness by seeing what would be masked without actually blocking, enabling assessment of false positives/negatives.
Block mode for production: Once effectiveness is validated, switching to block mode prevents actual exposure of personal information to customers.
Regional deployment: Deploying copies to each Region ensures compliance with data residency requirements and provides consistent protection across all operational regions.
Why other options are incorrect:
Option A: Uses cross-Region guardrail which may not comply with data residency requirements. Also uses detect mode (which only logs) instead of mask mode for testing - mask mode is better for evaluation as it shows what would be masked.
Option C: Uses content and topic filters instead of sensitive information filters. Content filters are for inappropriate content, not PII. Also keeping detect mode in production doesn't prevent exposure.
Option D: Uses content and word filters instead of sensitive information filters. Mask mode in production may still expose masked information structure, while block mode is more secure for PII protection.
Key AWS Concepts:
Ultimate access to all questions.
No comments yet.
The company wants to evaluate how effective the AI assistant is at preventing the exposure of personal information before the company makes the AI assistant available to customers. Which solution will meet these requirements?
A
Configure a cross-Region Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to detect mode during development and testing. Switch to block mode for production deployment.
B
Configure an Amazon Bedrock guardrail to apply sensitive information filters. Set the guardrail to mask mode during development and testing. Switch to block mode for production deployment. Deploy a copy of the guardrail to each Region where the company operates.
C
Configure an Amazon Bedrock guardrail to apply content and topic filters. Set the guardrail to detect mode during development, testing, and production. Disable invocation logging for the Amazon Bedrock model.
D
Configure a cross-Region Amazon Bedrock guardrail to apply a set of content and word filters. Set the guardrail to detect mode during development and testing. Switch to mask mode for production deployment.