Sessions

SESSION-03

/Automate. Serverless and event-driven approach to DevOps

Room: | Time: 11:25

In today’s fast-paced development environments, reducing manual tasks is crucial for productivity and developer experience. This talk will explore how a fintech market leader in Sweden, created a serverless and event-driven integration with Slack on AWS. Creating a solution, to automate tasks across a multi-account setup. Learn how this journey optimized cost, enhanced productivity and security by eliminating repetitive tasks, by minimizing human error. A key aspect was integrating alarms and notifications directly into Slack, enabling developers to take immediate action on system alerts. We will look at the problems, deep dive into implementation, and the challenges we faced. Join us to gain valuable insights and practical tips for transforming your workflows.

Jimmy Dahlqvist 🇸🇪

AWS Serverless Hero, AWS Ambassador, AWS Certification Lead SME & Cloud architect

OPENING

Opening and welcome

Room: | Time: 10:00

Opening speech, introducing of the crew and AWS User Groups involved.

LÝDIA DELYOVÁ 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]

MICHAL SALANCI 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]

SESSION-01

From Concept to Code: Building Production-Ready with AWS Strands, Kiro & Marketplace Agents

Room: | Time: 10:15

As enterprises transition from model experimentation to AI-first applications, AWS is leading the charge with a robust suite of tools to build, scale, and manage agentic AI. This session explores how developers and architects can accelerate production-grade agent workflows using: **AWS Strands Agents** – an open-source SDK to design autonomous, goal-oriented agents using a model-first, prompt-driven approach **Kiro** – AWS’s AI-native IDE that transforms natural language into structured, testable code with guardrails for production readiness **AWS Marketplace for Agents** – a curated ecosystem of third-party agents and tools that can be extended, composed, or deployed securely within your stack Join us as we walk through real-world use cases, development workflows, and architecture patterns that combine Strands and Kiro to deliver scalable, governable agent-based solutions. You'll leave with a blueprint to build intelligent agents—from automation scripts to full-stack AI applications—while aligning with enterprise-grade security, observability, and developer productivity.

Harini Muralidharan 🇮🇳

Senior Delivery Manager - Presidio

Kiran Ravichandran 🇮🇳

Lead Engineer - Presidio

SESSION-02

RAG Without Breaking the Bank: Create a Bedrock Agent with S3 Vector-Powered Knowledge Bases

Room: | Time: 10:50

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: 1. Setting up a Bedrock Knowledge Base using S3 Vectors for semantic retrieval 2. Creating a Bedrock Agent that can reason over a large-scale knowledge base 3. Designing embeddings, chunking, and metadata filtering strategies for accurate results Whether building internal copilots, customer support bots, or document search, this talk shows how to do RAG at scale without the price tag of high-performance vector databases. This is ideal for developers and teams looking to build practical, budget-friendly GenAI apps on AWS.

Darya Petrashka 🇵🇱

AWS Community Builder, AWS Authorized Instructor & Senior Data Scientist @SLB

SESSION-04

How to use an Event Architecture to solve compliance and security issues

Room: | Time: 12:00

In this session, we will talk about how to use the events of cloudtrail to create an events architecture that can solve security and compliance issues in seconds. The main idea of the session is to demonstrate how to add a new layer of security to respond to any event on our platform. We can use EventBridge to catch some events of cloudtrail and trigger Lambdas to check if the actions comply with our our rules; it is beneficial to forbid some ports on our EC2, launch automatizations when we create any resource on AWS, add some configurations like WAF to our resources by default, add encryption for our resources or delete some resources that can be exposure to bad actors. We commonly use Security policies based on IAM, SCP, and Permission Boundaries on AWS to permit only minimal access, which is usually our first layer of security. Also, it is common to add another layer of security with IaC policies, Terraform modules or CDK constructs, and security libraries on CI/CD pipelines to permit only some configurations that are approved by the security team. It is a good approach but can only succeed if someone can break these layers or if the use of IaC or best practices is low. This extra layer is good for preventing wrong configurations or actions when they happen and is cheaper to implement than using other services like AWS Config or third-party tools.

Miguel Ángel Muñoz Sánchez 🇪🇸

Cloud Architect, AWS Ambassador & AWS Community Builder

SESSION-05

🎬 What Netflix Doesn’t Tell You: How They Stream Live with AWS MediaLive and MediaPackage

Room: | Time: 12:35

Netflix is no longer just about series and movies — it now streams live events like WWE. But how do they deliver high-quality, uninterrupted broadcasts to millions of viewers at the same time? In this session, we’ll explore how to build a live streaming architecture like Netflix, using AWS MediaLive to process the real-time feed and AWS MediaPackage to securely and efficiently deliver it across all devices. We'll cover: ✅ How to set up a live stream workflow with AWS ✅ How MediaPackage enables features like pause, rewind, and protection against overload ✅ The distribution and scalability strategies used by major streaming platforms Perfect for anyone working with live events, OTT platforms, or looking to take their streaming architecture to the next level. 🚀

Luis Valdivia Humareda 🇵🇪

CTO in +1 Development

SESSION-06

From Chaos to Clarity: Choosing the Right Stack for GenAI on AWS

Room: | Time: 13:10

Building generative AI applications in the cloud can feel overwhelming with the vast number of tools, services, and patterns available. In this talk, we’ll cut through the noise and explore a decision-making framework to choose the right stack for your GenAI use case on AWS. We’ll compare options such as Bedrock Agents, SDKs like Vercel AI and Strands, and emerging architectures like Multi-Agent Control Plane (MCP) and Agent-to-Agent (A2A). Through real-world examples and lessons learned, you’ll gain practical insights to avoid common pitfalls and design scalable, observable, and context-aware GenAI solutions. Whether you're starting your first prototype or optimizing for production, this session will help you turn complexity into clarity.

Hazel Saenz 🇬🇹

AWS Serverless Hero

HOW-TO-REGISTER

How to register for AWS pre:Invent experience raffle

Room: | Time: 13:45

Example how to register for AWS Community pre:Invent Warmup

LÝDIA DELYOVÁ 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]

MICHAL SALANCI 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]

RAFFLE-REG

AWS re:Invent experience 2025 raffle registration

Room: | Time: 14:00

The cherrypick of the day: AWS re:Invent experience 2025 raffle registration.

LÝDIA DELYOVÁ 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]

MICHAL SALANCI 🇸🇰

[AWS Community Builder AWS User Group Košice, Slovakia]