Explanation:
Option A is the correct answer because it provides a comprehensive solution that addresses multiple aspects of the requirement:
Parallel processing: Step Functions Map states enable running agent workflows in parallel, which improves efficiency and scalability.
Secret management: Passing updated secret metadata through Lambda function outputs ensures secure handling of sensitive information.
Version control and rollback: Using AWS AppConfig to version prompt flows allows for proper gating and rollback of faulty templates, which is crucial for maintaining system reliability.
Why other options are incorrect:
Option B: While Amazon Bedrock Agents and guardrails are useful, this solution is limited to a single agent approach and doesn't address parallel processing or comprehensive version control.
Option C: Amazon EventBridge pipelines can orchestrate workflows, but using TTL-based backoff and retries for agent ordering is not an optimal approach compared to Step Functions' built-in state management and error handling capabilities.
Option D: This solution involves complex event-driven patterns with CloudWatch log patterns and Amazon Q Developer for fallback prompts, but it lacks the structured workflow management and version control capabilities provided by Step Functions and AWS AppConfig in Option A.
Key AWS Services in the correct solution:
This solution provides the most robust, scalable, and maintainable approach for agent workflow management with proper version control and rollback capabilities.
Ultimate access to all questions.
No comments yet.
A company is building a multicloud generative AI (GenAI)-powered secret resolution application that uses Amazon Bedrock and Agent Squad. The application resolves secrets from multiple sources, including key stores and hardware security modules (HSMs). The application uses AWS Lambda functions to retrieve secrets from the sources. The application uses AWS AppConfig to implement dynamic feature gating. The application supports secret chaining and detects secret drift. The application handles short-lived and expiring secrets. The application also supports prompt flows for templated instructions. The application uses AWS Step Functions to orchestrate agents to resolve the secrets and to manage secret validation and drift detection.
The company finds multiple issues during application testing. The application does not refresh expired secrets in time for agents to use. The application sends alerts for secret drift, but agents still use stale data. Prompt flows within the application reuse outdated templates, which cause cascading failures. The company must resolve the performance issues.
Which solution will meet this requirement?
A
Use Step Functions Map states to run agent workflows in parallel. Pass updated secret metadata through Lambda function outputs. Use AWS AppConfig to version all prompt flows to gate and roll back faulty templates.
B
Use Amazon Bedrock Agents only. Configure Amazon Bedrock guardrails to restrict prompt variation. Use an inline JSON schema for a single agent's workflow definition to chain tool calls.
C
Use a centralized Amazon EventBridge pipeline to invoke each agent. Store intermediate prompts in Amazon DynamoDB. Resolve agent ordering by using TTL-based backoff and retries.
D
Use Amazon EventBridge Pipes to invoke resolvers based on Amazon CloudWatch log patterns. Store response metadata in DynamoDB with TTL and versioned writes. Use Amazon Q Developer to dynamically generate fallback prompts.