Matthijs van der Veer
Coding Architect & Microsoft MVP at Xebia
Utrecht, The Netherlands
Actions
Matthijs is a Coding Architect at Xebia. With a strong focus on Azure and AI, he helps clients achieve more on Azure. Matthijs has a passion for good work environments, great code, and amazing teams.
Matthijs trained and led teams in different countries. He strongly believes that remote and distributed teams can be just as (or more) effective than sitting in the same old office together. Matthijs received the Microsoft MVP Award four years in a row.
Badges
Area of Expertise
Topics
Your RAG Bot Is Boring; Five More Exciting Ways to Use Generative AI!
Let's break free from the monotony of Retrieval Augmented Generation chatbot development to explore exciting and innovative applications of generative AI. Find out how to use LLMs, image generation, and AI Speech across various scenarios and why creating your own quirky tools and discover how creating your own quirky tools and apps can be the ultimate way to learn new technologies. Expect to leave with both inspiration for your next project and practical ideas you can apply in real business contexts.
This talk is tailor-made for developers tired of the same old solutions, as well as managers and product owners seeking fresh ideas. Join me in stepping out of the shadow of mediocrity and igniting your creativity!
Unmasking Model Bias - The Overlooked Metric In GenAI
Join us for a thought-provoking session that uncovers the critical concept of model bias in generative AI - a metric often overlooked in model selection. We will explore why model bias is not the same as model performance, its significance in model selection, and how it impacts your projects, whether you're developing niche applications or seeking broader solutions. You'll walk away with the knowledge to incorporate model bias into your selection criteria and strategies to navigate the complexities of generative AI models.
This talk welcomes anyone interested in generative AI - whether you're a sceptic or a developer. Together, let's examine the hidden biases that shape the models we use and understand their implications for our work.
Write Drunk, Edit Sober: Creating Generative Content Responsibly
Let's examine the growing concern over low-quality generative AI content and explore how we can build automated systems that produce high-quality output. You’ll learn to identify the signs of 'AI Slop' and implement strategies that counteract our automation bias, ensuring that the content we create meets the standards we expect. Using session abstract generation as a case study, I will provide practical guidelines to elevate the quality of your AI-generated content.
This talk is designed for developers and IT professionals who are dedicated to improving the quality of AI-driven content in their organisations. Get ready to roll up your sleeves and discover how a little effort can lead to significant improvements in the content we create.
Creating Self-Guided Meditations With Azure AI
What happens when you stack GPT-3.5 Turbo, GPT-5, GPT Image 1, Azure AI Speech and Azure Machine Learning together? You get unlimited potential for generating unique content. In this session, I will take you through my adventures with generative AI to create self-guided meditations automatically uploaded to YouTube daily. You can use these principles to enhance your own applications with artificial intelligence.
What you will learn:
- Leveraging OpenAI's Large Language Models to generate unique content.
- Create human-like interactions with Azure AI Speech. Let's go beyond accents and languages and add some style.
- Automating prompt engineering using AI techniques for more dynamic content.
Throughout the session, you will be bombarded with live demonstrations and real-life examples that will provide you with actionable insights into building robust applications with the latest AI technologies. Whether you're interested in the meditative or the technical aspect, this session promises to be enlightening and inspiring.
Bringing Animatronics to Life with Large Language Models and Azure AI
Discover how to combine Azure's AI technologies, including Azure OpenAI and AI Speech, with Arduino to create interactive animatronics. This session offers a straightforward look at using advanced AI to animate robots, making them more responsive and engaging. Perfect for AI enthusiasts and software developers, we will demonstrate a real animatronic that listens, speaks, and interacts, showing the practical use of AI in robotics. Learn how these technologies can be used together to bring animatronics to life in a clear and accessible way.
Code-First LLMOps With Semantic Kernel & Prompty
In this session, you will learn the entire LLMOps journey, from selecting the right model to writing your first prompt, developing locally and deploying to production confidently. We will use Azure OpenAI, Semantic Kernel and Microsoft's new Prompty extension.
This session is for anybody interested in developing with LLMs. Expect many demos!
Toxic Trust: The Psychology of Automation Bias in Generative AI
Explore the hidden dangers of automation bias in the realm of generative AI and automation—a cognitive trap where we too readily trust machine-generated content. We'll examine the psychological aspects of this bias and its impact on text, images, and code and provide actionable strategies for increasing awareness and reducing bias. We will close with a live demo showcasing practical examples and innovative approaches to transform your interaction with generative AI.
This talk is ideal for anyone interested in generative AI and how we work with it. Come prepared to challenge your assumptions and change your relationship with AI.
How We Built A Generative Trading Card Game With Stable Diffusion & Semantic Kernel
Explore the exciting world of generative AI-powered trading card games in this session! Learn how to transform real-time camera input into unique cartoon characters using Stable Diffusion on the edge. Discover the magic of creating a one-of-a-kind trading card game by integrating Azure AI Services and leveraging the power of Semantic Kernel with LLMs in C#. We'll walk you through the process of combining AI and traditional programming to build an innovative collectible card game.
This session is ideal for developers, AI enthusiasts, and card game aficionados. Expect to leave with the know-how to run Stable Diffusion locally and start creating your own unique images.
Mastering Multi-Agent Madness With Microsoft Agent Framework
Let's discover how to effectively combine pre-built orchestrations with custom workflows to create sophisticated multi-agent applications. Learn how agents can communicate to achieve greater results or when a more deterministic approach is necessary to prevent communication breakdowns. We will also cover adding tools to your agents, recognising when to solicit human input, and leveraging Microsoft Agent Framework with the Azure AI Agent Service.
This talk is perfect for software engineers eager to dive into the world of agents. Expect many demos that will pave the way for you to build your first multi-agent application confidently!
Build Stuff 2025 Lithuania Sessionize Event Upcoming
Techorama 2025 Netherlands Sessionize Event
NDC Copenhagen Developers Festival 2025 Sessionize Event
AgentCon Utrecht 2025 Sessionize Event
Future Tech 2025 Sessionize Event
Cloud Technology Townhall Tallinn 2025 Sessionize Event
AI Community Day Sessionize Event
Build Stuff 2024 Lithuania Sessionize Event
Techorama 2024 Netherlands Sessionize Event
NDC Oslo 2024 Sessionize Event
AI Community Day Sessionize Event
Cloud Technology Townhall Tallinn 2024 Sessionize Event
AI Summer Jam
Kick off the Microsoft learn AI skills challenge together with likeminded people at our Azure AI Summer Jam.
20:00 – 20:45 Building your own GenAI solution on Azure
Speakers: Matthijs van der Veer & Duncan Roosma
MS Tech Summit Poland
Copy The World With Azure Digital Twins
Techorama Netherlands 2022 Sessionize Event
Matthijs van der Veer
Coding Architect & Microsoft MVP at Xebia
Utrecht, The Netherlands
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top