Sample Agentic AI Acceleration KR
This is a curated archive of agentic AI sample projects and reusable tooling from an AWS-run Agentic AI Acceleration program in Korea, covering production-grade agent architectures built on Amazon Bedrock and AgentCore.
Each sample lives in its own self-contained folder with a dedicated README and setup guide, and the collection currently includes an e-commerce analytics agent demonstrating a full AgentOps pipeline of gateway, observability, evaluation and improvement steps; a step-by-step guide for promoting a Claude Code data-analytics agent to production on Amazon Bedrock AgentCore Runtime and Gateway with minimal code changes; and an agentic text-to-SQL solution where a Strands Graph orchestrator turns natural language into validated SQL through Runtime-hosted MCP tools, streaming results to a CopilotKit interface.
A separate Claude Code plugin included in the repository helps plan, track and verify AWS-based AI agent projects as a reference companion while building, independent of any single sample.
It is written in Python and released under the MIT-0 license.