Workshops

In this hands-on workshop, you build, test, and optimize an agentic self-service experience in Amazon Connect Customer using the agentic CX designer (ACXD). You start in a prebuilt Amazon Connect environment, pick one of ten industry scenarios, and take a conversational agent from its first prompt to a tested, deployed experience on chat and voice. No coding is required.

Welcome! This hands-on workshop guides you through the key features of the Amazon Quick using a practical automotive and manufacturing scenario — from Chat and Spaces to Flows and QuickSight analytics, run end-to-end.

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.

In this workshop, you will deploy a serverless backend that supports a pop-up coffee shop. You will then test your application using 3 front-end applications that are provided.

Welcome, brave adventurer, to the ultimate Strands framework quest! This comprehensive workshop will transform you from a coding apprentice into a master of AI agent orchestration. Through five epic chapters, you'll learn to create, equip, and command digital companions that can think, act, and collaborate like a legendary adventuring party.

EC2 flex instances are a more cost-efficient choice for workloads that don't keep their CPUs busy all the time. In this workshop, you move SnapShelf, an object detection service on Amazon EKS Auto Mode, from 8th generation Intel EC2 instances to flex instances with a single NodePool change. You compare latency, throughput and cost before and after, and learn which node metrics to watch when you run flex instances in production

Kiro Crew is an open-source AI agent workspace that runs on your own hardware and keeps working between conversations. In this hands-on workshop you'll learn its workflow engine, define and teach your own agents, and compose a team of specialized agents. You'll give them persistent knowledge and memory, then schedule jobs that run overnight and brief you before your day starts. You leave with a working Kiro Crew setup you'll actually use for daily development.

Getting started on AgentCore: Let's build an end-to-end use case using Amazon Bedrock AgentCore.

SageMaker HyperPod removes the undifferentiated heavy lifting involved in building and optimizing machine learning (ML) infrastructure for training foundation models (FMs), reducing training time by up to 40%. In this builders’ session, learn how to pre-train a large language model (LLM) using Slurm on SageMaker HyperPod. Explore the model pre-training workflow from start to finish, including setting up clusters, troubleshooting convergence issues, and running distributed training.

This workshop provides hands-on experience in cloud computing basics, containers, High Performance Computing (HPC), and AI/Machine Learning for researchers and research IT staff with little to no cloud computing background.