In today's events industry, personalization isn't just a buzzword - it's the key to creating meaningful experiences for each attendee. In this architecture and development session, I'll show you how we're actually using AI (not just talking about it 😉) to make events better for everyone involved. I'll take you through our journey of implementing Microsoft Semantic Kernel and LLMs to develop intelligent agents for run.events. No marketing fluff - we'll dive deep into real-world scenarios where we analyze attendees' interests, session participation, and professional background to enable practical personalization features like: * Smart matchmaking that actually makes sense * Targeted expo recommendations * Intelligent meeting scheduling * Personalized agenda suggestions We'll cover: * The tech stack we chose and why (including what didn't work) * Architecture decisions and lessons learned * Live examples from run.events (because theory is nice, but seeing is believing) Join me for a no-nonsense look at how to actually use AI to create better networking experiences. Whether you're writing code, organizing events, or just curious about practical AI applications, you'll walk away with concrete knowledge about implementing intelligent personalization in the real world.

Can Europe AI? You have probably heard about "Le Chat", and AI chat similar in its functionality to ChatGPT or Claude.ai. But, Mistral AI, French company behind "Le Chat" has much more to offer, and at the moment, together with German DeepL, it is the best what Europe has to offer in the AI arena. Also, Mistral AI is committed to open-source development and has released several models under open-source licenses, which makes it a competitor not only to Open AI and Anthropic, but also to DeepSeek and Meta's Llama. This will be a deep dive session into Mistral: it's capabilities, it's lovely French quirks, and how can you make the use of it. In this session we will discuss: - Mistral AI basics - Hosting and consuming Mistral AI (Mistral APIs, Azure AI, self-hosting) - Using Microsoft tech stack (Semantic Kernel and Microsoft AI Extensions) to work with Mistral AI - Real life example of using Mistral AI within a product development on the example of run.events À bientôt!

The world of AI is no longer reserved for cloud providers — some AI models can run on your own machines, with surprisingly good results. But how far can you really go? In this session, we'll explore what you can achieve with solutions like Ollama and Stable Diffusion, right on your own hardware — whether that's a high-end laptop, a beefy desktop, or a small local server. We’ll cut through the hype and focus on the real-world capabilities, limitations, and practical considerations. What models can you run? How much performance do you need? What use cases make sense? Where does local AI shine — and where does it fall short? Along the way, we'll dive into concrete examples how we utilized Ollama for run.events, using Semantic Kernel, Microsoft's framework for building AI-driven applications, to show how you can combine local models with powerful orchestration to create real, working solutions. If you're curious about the real possibilities of self-hosted AI — and what’s just wishful thinking — this is the session for you.

This session is designed specifically for .NET developers looking to transition into the dynamic world of artificial intelligence. We’ll explore the current state of AI development, clarify key concepts, and provide actionable guidance to help you kickstart your AI journey. Whether you're curious about leveraging existing AI models or building custom solutions, this session offers a comprehensive introduction tailored to your .NET background. What You Will Learn: AI Development Today: Gain an overview of the modern AI landscape, including the current trends, tools, and methodologies that are shaping how developers build intelligent systems. Understand the interplay between traditional software development and AI, and learn how AI is transforming business and technology. Introduction to Semantic Kernel: Discover the Semantic Kernel framework and how it integrates with your .NET environment. We’ll dive into its architecture, use cases, and how it facilitates the creation of AI applications by bridging semantic understanding with conventional programming paradigms. Large Proprietary Models vs. Self-Hosted Models: Examine the benefits and limitations of large, proprietary AI models compared to self-hosted alternatives. Learn about the trade-offs in terms of performance, cost, privacy, and control, and find out which approach might be best suited for your projects. Different Model Types and Capacities: Explore the diverse range of AI models available today—from language models to vision and multimodal systems. Understand their capacities, how they differ in terms of scale and functionality, and what that means for real-world applications. Extending Models with Custom Data: Learn how to enhance existing models by integrating your own data. This segment covers practical techniques for fine-tuning, customizing, and extending AI models to better meet your specific business or development needs. Real-Life Examples with run.events: See theory in action with practical, real-world examples using run.events. This hands-on portion will demonstrate how AI can be applied to create innovative solutions, showcasing end-to-end examples that connect AI insights with event-driven development. Who Should Attend: .NET developers at all levels who are curious about AI and looking for a clear, practical path to integrate AI capabilities into their development toolkit. Whether you’re a beginner or have some experience with AI, you’ll find valuable insights and resources to help you start your journey.

Join us for a candid look behind the scenes at run.events, the platform that has become essential for many event organizers worldwide who want to manage their events efficiently. Taking the road less traveled, without relying on outside funding and with a dedicated, compact team, was what formed run.events into its current state. Our reliance on the robust Microsoft Azure public cloud platform (we'll share why we eliminated the last two AWS services from our architecture only a few weeks ago), a focus on user experience, and the integration of automation workflows have been the foundation of what run.events is today, enabling us to serve a global audience. In this session, we'll share the architectural, developmental, technological, and emotional challenges encountered while building the platform. We'll discuss the good and not-so-good decisions. We will discuss how our first European Collaboration Summit taught us that standard Azure load testing isn't always sufficient, leading us to scale our Azure SQL Server to the max to get through the event (which we did!). We'll also talk about why you should be in Microsoft for Startups program during the initial development and early go-to-market stages of building a SaaS product, and how being in that program has saved our money and our skin. :) To wrap up, we'll provide some insights into where we are now, the challenges we're currently facing and how we're addressing them, our ideas for the future, and how Microsoft taught us that a bug in production is not the end of the world. :)