Câu 39: AWS Certified Generative AI Developer - Professional AIP-C01

A company is developing a generative AI (GenAI) application that uses Amazon Bedrock foundation models (FMs). The application has several custom tool integrations. The application has experienced unexpected token consumption surges despite consistent user traffic. The company needs a solution that uses Amazon Bedrock model invocation logging to monitor InputTokenCount metrics and OutputTokenCount metrics. The solution must detect unusual patterns in tool usage and identify which specific tool integrations cause abnormal token consumption. The solution must also automatically adjust thresholds as traffic patterns change. Which solution will meet these requirements?

1. A. Use Amazon CloudWatch Logs to capture model invocation logs. Create CloudWatch dashboards based on InputTokenCount metrics and OutputTokenCount metrics. Configure static CloudWatch alarms with fixed thresholds for each tool integration.
2. B. Store model invocation logs in an Amazon S3 bucket. Use AWS Glue to catalog the logs. Analyze token consumption patterns by using scheduled Amazon Athena queries that generate reports on tool usage trends.
3. C. Use Amazon CloudWatch Logs to capture model invocation logs. Create CloudWatch metric filters to extract tool-specific invocation patterns. Apply CloudWatch anomaly detection alarms that adjust baselines for each tool's metrics. — đáp án hiện tại
4. D. Store model invocation logs in an Amazon S3 bucket. Create an AWS Lambda function to process logs in real time. Manually update Amazon CloudWatch alarm thresholds based on token consumption trends that the Lambda function identifies.