Hacks, data breaches, ransomware... you keep hearing about it in the news. To effectively protect your business and/or software, you need to know where the vulnerabilities are. And what better way to find out than by attempting to hack yourself? In this session, we will explore how hackers operate and which tools you can use to hack (your own) applications. Additionally, we will examine the most common types of vulnerabilities, how to practice exploiting them, and what measures can be taken to prevent them. With the rise of AI a whole new attack surface has emerged - how is it being used to hack? Last but not least, I'll share tips on keeping your colleagues alert by applying Social Engineering.

Concerned about data privacy or compliance? Don’t want your sensitive information sent to external AI systems? This session is for you! We’ll explore retrieval-augmented generation (RAG), a method to enhance large language models (LLMs) with your specific, ever-changing data, without it ever leaving your systems. You’ll learn: What is a vector database? How can you vectorize your own data? How to integrate your existing data sources, like SQL databases, to enrich AI interactions. We’ll implement RAG step-by-step, running AI models locally (on the “edge”) while maintaining full control over your data. By the end of the session, you’ll know how to build an AI assistant that uses your private and volatile data, all without relying on external cloud services. Or isn't the cloud a scary thing? We rely on Azure for all our workloads, so let's also take a look on what the cloud can add to this equation.

Azure SQL Databases (and SQL Server 2025) introduces powerful AI capabilities that bring intelligence directly into the database engine. With native vector support and seamless connections to external AI models, developers can now build Retrieval-Augmented Generation (RAG) pipelines and natural language interfaces using only T-SQL, while keeping sensitive data under your control. In this session, you’ll learn how to: - Chunk and enrich your data for RAG workflows - Generate and store embeddings in SQL databases with the new VECTOR data type - Perform semantic vector searches to power smarter applications - Call external AI models directly from T-SQL - Ensure trust by keeping data securely within your systems, minimizing exposure to external services By the end, you’ll have the practical knowledge to combine relational data and AI to build next-generation applications. All with the assurance that your data remains under your control.

Last couple of years AI has entered out lives and jobs - and it’s clearly here to stay. But before we fully hand over everything over to the machines, let’s take a step back and actually understand what’s going on under the hood. What are tokens and embeddings? What do transformers really do (besides being in disguise)? What are these vectors showing up everywhere? We’re not drawing anything, right? In this session, we’ll unpack the core concepts behind large language models: things like training, parameters, vector search, and more. If you’ve ever used an LLM and thought, “Wait… how does this actually work?” - this talk is for you.