Added memory to AWS AI Assistant

Built a AWS AI Assistant which gives information about AWS services. The assistant uses AgentCore memory to maintain stateful conversation.

Architecture

Key Features

• Stateful conversation with AI Assistant.

• Conversation history using AgentCore Memory.

• Memory obsevability through metrics.

Chat Example Tested

User:I am learning AWS

User:My favourite service is Amazon AWS

User:I deployed a spring boot application to ECS

User:Which AWS service is my favorite

{ "result": "Your favourite AWS service is Amazon Elastic Container Service (ECS), a highly scalable, high performance container management service that supports Docker containers and allows you to easily run applications on a managed cluster of Amazon Elastic Compute Cloud (Amazon EC2) instances." }rite your text here...

Challenges Solved

• To the default role additional IAM permission need to be included as it was failing.

• Application errors debugged through cloudwatch

• Improved prompts to generate context-aware responses using conversation history.