A company has a generative AI (GenAI) application that uses Amazon Bedrock to provide real- time responses to customer queries. The company has noticed intermittent failures with API calls to…

Question

Options

• AImplement a custom retry mechanism with a fixed delay of 1 second between retries. Configure
• BConfigure the AWS SDK with standard retry mode and exponential backoff with jitter. Use AWS
• CImplement client-side caching of all FM responses. Add custom logging statements in the
• DConfigure the AWS SDK with adaptive retry mode. Use AWS CloudTrail distributed tracing to

• A
  31% (13)
• B
  45% (19)
• C
  7% (3)
• D
  17% (7)

Explanation

Option B best meets the combined resiliency and observability requirements because it applies AWS-recommended retry behavior for transient throttling and enables true distributed tracing across service boundaries. During peak traffic, intermittent failures are commonly caused by throttling and other transient conditions. The AWS SDK standard retry mode provides exponential backoff with jitter, which reduces synchronized retry storms, prevents cascading failures, and improves overall system stability. Jitter is important because it spreads retry attempts over time, reducing load amplification during throttling events. For observability, AWS X-Ray provides distributed tracing that follows a request across components such as API Gateway or load balancers, application services, and downstream calls to Amazon Bedrock. X-Ray can identify where latency is being introduced and which downstream call is contributing most to end-to-end response time. This is required to "identify latency contributors" and isolate performance issues under load. The requirement also states that the company must correlate performance issues with specific FM characteristics. X-Ray annotations are designed for this purpose: the application can annotate traces with the model ID, inference parameters, region, or inference profile used. This enables filtering and analysis (for example, comparing latency or error patterns by model, parameter set, or endpoint configuration) without building a separate telemetry system.

No community discussion yet for this question.