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…

Question

Options

• AUse Amazon Bedrock AgentCore to manage memory and session-aware reasoning. Deploy the
• BRegister the Lambda functions and REST APIs as actions by using Amazon API Gateway and
• CUse Amazon Bedrock Agents for reasoning and conversation management. Use AWS Step
• DDeploy the reasoning logic as a container on Amazon ECS behind API Gateway. Use Amazon
• EBuild a custom RAG pipeline by using Amazon Kendra and Amazon Bedrock. Use AWS Lambda

• A
  76% (38)
• C
  4% (2)
• D
  8% (4)
• E
  12% (6)

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.

No community discussion yet for this question.