Mike Chambers

Explore the practical challenges and solutions for deploying AI agents in real-world production environments. Through detailed technical analysis and practical examples, we'll examine strategies for building and orchestrating agent systems at scale. We'll cover critical infrastructure decisions, scalability frameworks, and best practices for creating robust, production-ready agent architectures.

Generative AI is rapidly becoming integral to everyday applications, extending far beyond chatbots. In this session, Alan reveals how he built an app that uses LLMs and serverless architectures to track AWS service releases across AWS Regions in real-time.

Dive into the world of LLMOps in this interactive session and explore how to leverage AWS services like Amazon Bedrock, Amazon SageMaker, and many more to build, deploy, and manage large language model solutions at scale.

Are you building a generative AI application for your customers? In this session, learn how AWS built an interactive solution that generates prompts for an LLM through the physical world and combines them with a live data feed.

In the fast-paced AI world, advanced generative AI concepts are crucial. To stay competitive and innovative, businesses must grapple with understanding and implementing complex methodologies.

As artificial intelligence permeates modern life, generative models are increasingly applied in various fields from art to science. However, many people still have basic questions or concerns about this fast-paced innovation.

In this workshop, learn how to build a fitness and activity tracker using sensor data collected from your phone to train a machine learning model to detect a range of motion activities such as running, walking, sitting, and more. Walk through the entire process of data collection, data processing, model training, and deploying a fitness and activity detection service to generate both cloud and...