nerdexam
Amazon

AIP-C01 · Question #80

A company is building a serverless application that uses AWS Lambda functions to help students around the world summarize notes. The application uses Anthropic Claude through Amazon Bedrock. The…

The correct answer is C. Enable invocation logging in Amazon Bedrock. Monitor key metrics such as Invocations. Option C enables Amazon Bedrock invocation logging and monitors key metrics such as Invocations, ThrottledCount, and ModelLatency through Amazon CloudWatch. The solution then uses cross-region inference profiles (a native Bedrock feature) to automatically route overflow traffic…

Deployment, Operations, and Optimization

Question

A company is building a serverless application that uses AWS Lambda functions to help students around the world summarize notes. The application uses Anthropic Claude through Amazon Bedrock. The company observes that most of the traffic occurs during evenings in each time zone. Users report experiencing throttling errors during peak usage times in their time zones. The company needs to resolve the throttling issues by ensuring continuous operation of the application. The solution must maintain application performance quality and must not require a fixed hourly cost during low traffic periods. Which solution will meet these requirements?

Options

  • ACreate custom Amazon CloudWatch metrics to monitor model errors. Set provisioned throughput
  • BCreate custom Amazon CloudWatch metrics to monitor model errors. Set up a failover
  • CEnable invocation logging in Amazon Bedrock. Monitor key metrics such as Invocations,
  • DEnable invocation logging in Amazon Bedrock. Monitor InvocationLatency, InvocationClientErrors,

How the community answered

(64 responses)
  • A
    8% (5)
  • B
    17% (11)
  • C
    72% (46)
  • D
    3% (2)

Explanation

Option C enables Amazon Bedrock invocation logging and monitors key metrics such as Invocations, ThrottledCount, and ModelLatency through Amazon CloudWatch. The solution then uses cross-region inference profiles (a native Bedrock feature) to automatically route overflow traffic to the same model in other AWS Regions when the primary Region is throttled - providing continuous operation with no fixed hourly cost because you pay only for actual invocations. Option A involves provisioned throughput, which incurs a fixed hourly charge regardless of traffic, violating the budget constraint. Option B's failover approach may introduce inconsistency and does not use Bedrock's native cross-region routing. Option D monitors different metrics and may lead to a configuration that still involves fixed reserved capacity.

Topics

#Amazon Bedrock#Throttling#Monitoring#Performance Optimization

Community Discussion

No community discussion yet for this question.

Full AIP-C01 Practice