Explanation:
The combination of Options A and B provides the most scalable and AWS-native architecture for building reasoning agents with persistent memory, session awareness, secure access control, and flexible invocation models. Amazon Bedrock AgentCore is purpose-built to manage agent memory, session context, and identity-aware reasoning across interactions. It eliminates the need for developers to manually store and retrieve agent state, manage session lifecycles, or implement custom memory layers. AgentCore natively supports both synchronous requests and event-driven execution, making it ideal for support workflow automation. Option B complements AgentCore by enabling seamless tool invocation. By registering AWS Lambda functions and REST APIs as agent actions through API Gateway and EventBridge, the agent can invoke tools reactively or synchronously without custom orchestration code. EventBridge enables event-driven execution, while API Gateway supports synchronous request-response patterns. This combination provides built-in security, observability, and scaling, while avoiding the operational burden of managing queues, databases, or custom workflow engines. Option C introduces unnecessary orchestration complexity. Option D increases infrastructure management and cost. Option E stores agent state in S3, which is not suitable for low-latency, session-based reasoning. Therefore, A and B together deliver the most scalable, secure, and low-overhead solution for production- grade reasoning agents on AWS.
Ultimate access to all questions.
No comments yet.
A company is using AWS Lambda and REST APIs to build a reasoning agent to automate support workflows.
The system must preserve memory across interactions, share relevant agent state, and support event-driven invocation and synchronous invocation. The system must also enforce access control and session-based permissions.
Which combination of steps provides the MOST scalable solution? (Select TWO.)
A
Use Amazon Bedrock AgentCore to manage memory and session-aware reasoning. Deploy the agent with built-in identity support, event handling, and observability.
B
Register the Lambda functions and REST APIs as actions by using Amazon API Gateway and Amazon EventBridge. Enable Amazon Bedrock AgentCore to invoke the Lambda functions and REST APIs without custom orchestration code.
C
Use Amazon Bedrock Agents for reasoning and conversation management. Use AWS Step Functions and Amazon SQS for orchestration. Store agent state in Amazon DynamoDB.
D
Deploy the reasoning logic as a container on Amazon ECS behind API Gateway. Use Amazon Aurora to store memory and identity data.
E
Build a custom RAG pipeline by using Amazon Kendra and Amazon Bedrock. Use AWS Lambda to orchestrate tool invocations. Store agent state in Amazon S3.