AWS Certified Generative AI Developer - Professional
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
No comments yet.
A company is building a generative AI application that provides personalized recommendations to users. The application runs on Amazon EC2 instances and calls Amazon Bedrock foundation models. The company wants to monitor the application for intermittent performance issues and detect when recommendation quality deviates from established baselines. The solution must generate alerts within 10 minutes of degradation detection and provide insights into root causes. Which solution meets these requirements with minimal operational overhead?
A
Use Amazon CloudWatch to monitor EC2 instance metrics and set static thresholds for CPU, memory, and network utilization. Configure CloudWatch alarms to trigger notifications when thresholds are breached.
B
Implement AWS X-Ray to trace requests through the application and Amazon Bedrock calls. Use X-Ray analytics to identify latency patterns and error rates. Set up CloudWatch alarms based on X-Ray service map metrics.
C
Enable Amazon CloudWatch Application Insights for the EC2-based application. Publish custom metrics using the CloudWatch embedded metric format to track generative AI-specific signals. Use CloudWatch anomaly detection to establish baselines and detect deviations. Configure CloudWatch alarms to trigger when anomalies are detected and use CloudWatch Logs Insights to analyze log patterns.
D
Use Amazon OpenSearch Service with the Observability plugin. Ingest model metrics and logs by using Amazon Kinesis. Create custom Piped Processing Language (PPL) queries to analyze model behavior patterns. Establish operational dashboards to visualize anomalies in real time.