Explanation:
Why Option C is Correct:
Amazon CloudWatch Application Insights provides automated observability specifically for applications running on Amazon EC2 instances, which matches the company's infrastructure. It automatically detects abnormal behavior patterns without extensive manual configuration.
Custom metrics for recommendation quality, token usage, and response latency directly address the core requirement of monitoring FM behavior and recommendation accuracy, not just infrastructure health.
Dimensions for request types and user segments enable fine-grained correlation between performance issues and specific customer interactions or workloads, which is crucial for identifying why recommendations don't match preferences.
CloudWatch anomaly detection establishes dynamic baselines from historical data and automatically detects deviations, enabling alerts within the required 10-minute timeframe without relying on static thresholds.
CloudWatch Logs Insights provides pattern analysis capabilities to investigate log data associated with degraded recommendations.
Why Other Options Are Incorrect:
Option A (CloudWatch Container Insights): This is designed for containerized applications, not EC2-based applications. While it supports custom metrics, it lacks the automated anomaly detection and application-focused insights of Application Insights.
Option B (X-Ray, CloudTrail, QuickSight): X-Ray is for tracing distributed transactions, CloudTrail is for API auditing, and QuickSight is for business intelligence dashboards. This combination doesn't provide the real-time anomaly detection and operational monitoring needed for FM behavior.
Option D (OpenSearch Service): While OpenSearch can analyze metrics and logs, it requires more complex setup through Kinesis and doesn't provide the automated anomaly detection and alerting capabilities that CloudWatch Application Insights offers out-of-the-box.
Key Requirements Met by Option C:
Ultimate access to all questions.
No comments yet.
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?
A
Configure Amazon CloudWatch Container Insights. Set up alarms for latency thresholds. Add custom token metrics using the CloudWatch embedded metric format.
B
Implement AWS X-Ray. Enable CloudWatch Logs Insights. Set up AWS CloudTrail and create dashboards in Amazon QuickSight.
C
Enable Amazon CloudWatch Application Insights. Create custom metrics for recommendation quality, token usage, and response latency using the CloudWatch embedded metric format with dimensions for request types and user segments. Configure CloudWatch anomaly detection on model metrics. Use CloudWatch Logs Insights for pattern analysis.
D
Use Amazon OpenSearch Service with the Observability plugin. Ingest metrics and logs through Amazon Kinesis and analyze behavior with custom queries.