Workshops

An ECS Workshop provides an end-to-end application development and deployment experience to demonstrate features of Amazon ECS, using real-world services from an application development perspective in order to educate users about the features of Amazon ECS such as scaling, networking, observability, security and automation.

Facing rising Windows and SQL Server licensing costs? In this hands-on workshop, rehost a Windows IIS and SQL Server app to Amazon EC2 with AWS Transform MGN, then modernize it with agentic AI. Use AWS Transform to convert the schema to Amazon Aurora PostgreSQL and Kiro to convert the PHP code and build the infrastructure, then let AWS Transform containerize the app and deploy it to Amazon EKS. Leave with a repeatable pattern for migrating and modernizing your own Windows workloads.

Build a standardized ML environment on Amazon SageMaker AI covering security controls, MLOps pipelines, CI/CD automation, experiment tracking, deployment and observability.

This workshop is aimed at providing an hands-on experience for you on the wide variety of toolsets AWS offers to setup monitoring and observability on your applications.

Give your coding agent the tools, knowledge, and guardrails to build production-ready infrastructure on AWS.

Discover Kiro, your IDE build from the ground-up to seamlessly integrate AI agents into the development workflow. Explore how to use Kiro as your intelligent partner - helping to understand complex codebases, crystalize detailed requirements, and deliver quality solutions at unprecedented speed. You will iterate with Kiro to finalize your detailed design, before using Kiro to orchestrate AI agents and implement a fully working solution

Turn plain English into specs, working code, and tests — reviewing every step. Build a real app hands-on with Kiro, Amazon's AI-native dev agent, on your surface of choice: IDE, CLI, or IntelliJ. Go from chat-driven edits to full spec-driven development, then steer the agent with skills, MCP, custom agents, and hooks. No backend to deploy — it runs in your browser. ~4 hours, modules stand alone. For developers, from first-timers to automation power users.

Build a multi-agent AI system on Amazon EKS Auto Mode that serves every model on CPU: a fine-tuned intent router and embedding model (ONNX, trained on CPU), a cross-encoder re-ranker, and a quantized generative analyst on llama.cpp grounded by RAG from OpenSearch. Amazon Bedrock generates synthetic training data, judges answers with a faithfulness gate, and handles edge cases small models cannot. A control test puts a frontier LLM in the same seat so you know if the small model is good enough.

Build the offline optimization layer for payment fraud detection. Ingest 24M transactions into Apache Iceberg, construct a Neptune knowledge graph revealing fraud rings, and train a unified XGBoost ensemble combining transaction foundation model embeddings, GNN graph embeddings, and traditional features. Deploy AI agents on Amazon Bedrock AgentCore that autonomously investigate patterns, score customers with explainable predictions, and generate detection rules — compressing weeks into minutes.

Go from "where should we use agents?" to a deployed agentic use case using AWS Transform end-to-end. Discover business processes with EventStorming, identify where agents add value with Cognitive Complexity Analysis, run Agentic Readiness and Modernization analyses, build a prioritized roadmap, and execute an automated transformation — all with first-party AWS tooling including the atx CLI and Kiro CLI.