aws-solutions-library-samples

Guidance For Agentic Ai Operational Foundations On Aws

Name: Guidance For Agentic Ai Operational Foundations On Aws
Author: aws-solutions-library-samples

DevOps community

SOURCE https://github.com/aws-solutions-library-samples/guidance-for-agentic-ai-operational-foundations-on-aws

Description

Agentic AI application built on top of a lightweight but well-architected generative foundation components.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Agentic AI Foundation - Generative AI Customer Experience Platform

The CX Agent is an intelligent customer experience platform built on **LangGraph** and designed for deployment on **AWS Bedrock AgentCore Runtime**. This agentic AI solution leverages multiple generative AI foundations including LLM Gateway, observability and guardrails to deliver sophisticated customer service capabilities through a conversational interface.

![](assets/agent01.png "Screenshot of Streamlit-based chat UI showing controls for configuring where the backend agent is hosted and to send feedback on AI responses received in the conversation.")

Overview
Foundational Components
Prerequisites
Deployment Steps
Deployment Validation
Running the Sample
Next Steps
1. Local Development Workflow
2. Evaluation
Cleanup

High Level Architecture

For many of these AI platform capabilities, there are multiple alternative technologies that could be used. The right choices will depend on your needs, and there are also different ways to handle these choices: From committing to a particular preferred tool, to building (and maintaining) an abstraction layer for easy portability, or finding a balance somewhere in the middle.

In this sample we've tried to choose tools that are popular with our customers, and keep the code simple (avoid introducing extra abstraction layers) - so switching where needed would require some effort but should be reasonably straightforward. The overall architecture is as shown below:

![](assets/platform_arch.jpg "Architecture overview diagram. Components include a (local) Streamlit application; Langfuse; Amazon Cognito; Amazon Bedrock AgentCore; Amazon Bedrock Guardrails; Amazon Bedrock Knowledge Base (backed by OpenSea