Agenda

This session explores the Model Context Protocol (MCP) from basic concepts to practical applications. We’ll start with generative AI fundamentals and quickly move to how MCP enhances AI systems through structured context handling. We’ll examine MCP’s technical architecture and how it improves conversations with AI by enabling RAG systems …

ip.labs is the world’s leading white label e-commerce software imaging company and processes millions of images every day. The workflows of our users consist of designing, saving, loading, ordering and delivering to the printing facilities the photo products like prints, photobooks, calendars, gift products among others. In this talk we’ll …

In this session I talk about all things that can be represented as code: starting from the very basic software and ending modern approaches such as infrastructure as code and observability as code

DynamoDB powers everything from indie apps to Amazon-scale workloads, yet many teams barely scratch the surface of what it can do. In this session we’ll strip away the mystique, explore the service’s key building blocks, and see how they work together in practice. Then we’ll tackle the (in)famous single-table design - why it’s worth …

Explore a clear path from your first AI agent to production multi-agent systems. We start with what an agent is and why multi-agent designs are popular. Then we outline how to build a local agent on your laptop using the open-source Strands framework and extend it to multi-agent collaboration. Finally, we map the production blueprint on AWS with Amazon …

As software developers, we’re all guilty of having at least a few unfinished side projects collecting dust on our GitHub repositories. For me, blogging was one of those ideas that stayed on my to-do list for ages until AWS Amplify changed the game. In this session, I’ll share how I used AWS Amplify to stop procrastinating and finally build a platform to …

AWS doesn’t have a Flux Capacitor per se, but it relies on a key concept that, without it, we wouldn’t be able to use its services at all: the network. Sometimes, I think we just grant it this and forget that it is the base, and when we give a peak to the available network services, the number of them can be overwhelming. Some of them run in the …

In complex data platforms powered by AWS Glue, AppFlow, Airflow, and Step Functions, operational issues are inevitable. This talk shares how we built a self-healing system that automatically detects issues, tags them with context, uses Bedrock-based LLMs to suggest resolutions, and keeps stakeholders informed via GitLab and Slack. The result: a 40% drop in …

Examples of functionless (a.k.a. Lambda-less) integration pattern, where a direct integration between two AWS services is configured instead of using custom code in an intermediary Lambda function, based on Step Functions, AppSync, EventBridge.

AWS Strands Agents is fresh out of the lab, a brand-new framework for building and orchestrating intelligent agents. In this session, we’ll explore how to tame that new power with a familiar toolset: object-oriented design. You’ll learn how to break agents into clean, testable components, keep their state organized, and build systems that are easy to extend …

Building RAG-powered agents doesn’t have to come with sky-high vector database costs. In this session, learn how to create an Amazon Bedrock Agent backed by Amazon S3 Vectors, a new low-cost vector storage option that cuts vector storage and query costs by up to 90%. We’ll walk through: Setting up a Bedrock Knowledge Base using S3 Vectors for …

Cloud cost optimization isn’t about clever billing tricks, there are no shortcuts here. It’s about engineering maturity. If you’re serious about lowering your cloud spend without breaking your velocity, join this presentation. We’ll look at why savings plans and tools aren’t enough, how finance and engineering often misalign, and what high-maturity teams do …

This presentation highlights the business and customer impact of downtime in critical services. It also demonstrates how Hapag-Lloyd’s Web&Mobile department introduced a multi-region architecture to build resilience and ensure business continuity.

Search engines guide users from their initial goals to the information that fulfills those goals. The retrieved items are deemed relevant when they align with the user’s intent. Ensuring relevant results involves having the data in the catalog, analyzing it accurately, representing it through text and vectors, ranking it appropriately, and performing …

An epic adventure requires proper preparation, whether in a fantastical RPG world or in the realm of AWS cloud-based projects. To succeed, you must assemble a team, plan your journey, and choose the right equipment – because just as one sword cannot defeat every enemy, one set of AWS services does not fit every project. In this session, we will embark on a …

In this hands-on workshop you will learn how to build agentic applications on AWS using the Model Context Protocol (MCP) and the AWS Strands SDK. We will cover the core concepts, how to define tools and capabilities, how to ground agents in enterprise knowledge, and how to orchestrate complex tasks securely. You will leave with practical examples you can …

What happens when AI makes code writing the easiest part of development? The rise of Generative AI has transformed software development, making rapid prototyping more accessible than ever. This keynote examines the evolving role of developers as AI reshapes traditional coding practices. The presentation cuts through both hype and fear to explore what truly …