AWS Certified Generative AI – Professional (AIP-C01) — Question 54

A company deploys multiple Amazon Bedrock based generative AI (GenAI) applications across multiple business units for customer service, content generation, and document analysis. Some applications show unpredictable token consumption patterns. The company requires a comprehensive observability solution that provides real-time visibility into token usage patterns across multiple models. The observability solution must support custom dashboards for multiple stakeholder groups and provide alerting capabilities for token consumption across all the foundational models that the company's applications use.
Which combination of solutions will meet these requirements with the LEAST operational overhead? (Choose two.)

Answer options

• A. Use Amazon CloudWatch metrics as data sources to create custom Amazon QuickSight dashboards that show token usage trends and usage patterns across FMs.
• B. Use Amazon CloudWatch Logs Insights to analyze Amazon Bedrock invocation logs for token consumption patterns and usage attribution by application. Create custom queries to identify high-usage scenarios. Add log widgets to dashboards to enable continuous monitoring.
• C. Create custom Amazon CloudWatch dashboards that combine native Amazon Bedrock token and invocation CloudWatch metrics. Set up CloudWatch alarms to monitor token usage thresholds.
• D. Create dashboards that show token usage trends and patterns across the company's FMs by using an Amazon Bedrock zero-ETL integration with Amazon Managed Grafana.
• E. Implement Amazon EventBridge rules to capture Amazon Bedrock model invocation events. Route token usage data to an Amazon Data Firehose delivery stream that targets Amazon OpenSearch Serverless. Use OpenSearch dashboards to analyze usage patterns.

Correct answer: B, C

Explanation

Option B is correct as it allows for detailed analysis of invocation logs to understand token consumption patterns, enabling targeted action. Option C is also correct because it combines metrics and alarms for proactive monitoring. Options A and D, while useful, do not provide the same level of real-time monitoring and alerting as B and C. Option E introduces additional complexity with EventBridge and OpenSearch, increasing operational overhead.