AIP-C01 · Question #59
A company has a recommendation system running on Amazon EC2 instances. The applications make API calls to Amazon Bedrock foundation models (FMs) to analyze customer behavior and generate…
The correct answer is C. Enable Amazon CloudWatch Application Insights. Create custom metrics for recommendation. The key requirements are: monitoring operational metrics, detecting deviations from established baselines, and generating alerts with correlation data within 10 minutes. Amazon CloudWatch Application Insights is specifically designed to automatically detect and correlate…
Question
A company has a recommendation system running on Amazon EC2 instances. The applications make API calls to Amazon Bedrock foundation models (FMs) to analyze customer behavior and generate personalized product recommendations. The system experiences intermittent issues where some recommendations do not match customer preferences. The company needs an observability solution to monitor operational metrics and detect patterns of performance degradation compared to established baselines. The solution must generate alerts with correlation data within 10 minutes when FM behavior deviates from expected patterns. Which solution will meet these requirements?
Options
- AConfigure Amazon CloudWatch Container Insights. Set up alarms for latency thresholds. Add
- BImplement AWS X-Ray. Enable CloudWatch Logs Insights. Set up AWS CloudTrail and create
- CEnable Amazon CloudWatch Application Insights. Create custom metrics for recommendation
- DUse Amazon OpenSearch Service with the Observability plugin. Ingest metrics and logs through
How the community answered
(51 responses)- A6% (3)
- B22% (11)
- C57% (29)
- D16% (8)
Explanation
The key requirements are: monitoring operational metrics, detecting deviations from established baselines, and generating alerts with correlation data within 10 minutes. Amazon CloudWatch Application Insights is specifically designed to automatically detect and correlate anomalies across application metrics and logs, and it supports custom metrics for domain-specific data like recommendation quality scores. It can establish performance baselines and trigger alarms when deviations occur. Option A (Container Insights) is focused on container-level infrastructure metrics, not application-level behavior correlation. Option B (X-Ray + CloudTrail) provides tracing and audit logs but lacks automated baseline comparison and anomaly detection. Option D (OpenSearch Observability) is a valid observability stack but requires significantly more operational overhead to build baseline detection and correlation within the 10-minute alert window.
Topics
Community Discussion
No community discussion yet for this question.