Explanation:
Correct Answer: D
Why Option D is correct:
Parallel processing for prompt safety classification and PII detection with entity redaction - This addresses the performance requirement by processing filters in parallel, ensuring all pre-processing finishes before content reaches the FM. Entity redaction protects customer privacy by removing PII.
Toxicity detection with thresholds configured to 0.5 - This handles offensive content detection with a defined threshold for filtering.
Comprehensive coverage - The solution addresses all three requirements:
Performance optimization: Parallel processing ensures acceptable response times as required.
Why other options are incorrect:
Key AWS Services Used:
Ultimate access to all questions.
No comments yet.
The company wants to use Amazon Comprehend to implement layered content filtering. The layered content filtering must prevent sharing of offensive content, protect customer privacy, and detect potential inappropriate advice solicitation. Inappropriate advice solicitation includes requests for unethical practices, harmful activities, or manipulative behaviors.
The solution must maintain acceptable overall response times, so all pre-processing filters must finish before the content reaches the FM.
Which solution will meet these requirements?
A
Use parallel processing with asynchronous API calls. Use toxicity detection for offensive content. Use prompt safety classification for inappropriate advice solicitation. Use personally identifiable information (PII) detection without redaction.
B
Use custom classification to build an FM that detects offensive content and inappropriate advice solicitation. Apply personally identifiable information (PII) detection as a secondary filter only when messages pass the custom classifier.
C
Deploy a multi-stage process. Configure the process to use prompt safety classification first, then toxicity detection on safe prompts only, and finally personally identifiable information (PII) detection in streaming mode. Route flagged messages through Amazon EventBridge for human review.
D
Use toxicity detection with thresholds configured to 0.5 for all categories. Use parallel processing for both prompt safety classification and personally identifiable information (PII) detection with entity redaction. Apply Amazon CloudWatch alarms to filter metrics.