Jesse Wellenberg
Software Engineer at Xebia
Utrecht, The Netherlands
Actions
Jesse is a software & cloud architect at Xebia in the Netherlands. His passion lies in all things that make the lives of developers and users easier. Recently, he's focused on cutting through the noise and help developers make sense of developments around AI.
Area of Expertise
Topics
Build your own coding agent
Every application is an agent now, or is it? There is a clear difference between simple chatbots and tools like Claude Code and GitHub Copilot. Building a powerful agent might seem daunting, but in this workshop, we'll implement the inner workings of an agent that can autonomously chase a goal and complete tasks. You'll learn the fundamentals using Microsoft Agent Framework, including tool usage, memory management, and skill integration, enabling you to create effective agents that go beyond simple RAG chatbots.
The day kicks off with an introductory presentation that sets the stage for our hands-on labs. Together, we'll construct the foundational elements of a coding agent. Your agent will learn to find the right files, make changes, and even commit them to Git. In the afternoon, we'll focus on adding features such as specialised subagents. Throughout the workshop, you'll have access to two experts ready to answer your questions and provide guidance.
Prerequisites:
- A laptop
- Some experience with C#
- A GitHub account
- Visual Studio Code (or permission to install software)
- No prior experience in agent development is necessary
What you'll walk away with: A fully functional coding agent and the confidence to implement your own agents in future projects.
Introduction to evaluating generative AI applications
Demos are easy; dependable AI is not. This session shows how to verify that your LLM apps actually work using Azure AI Foundry and Microsoft's agent framework. We’ll cover what to measure and how to spot and reduce hallucinations with groundedness checks. You’ll see evaluators in action, and learn how to continuously evaluate your AI applications to ensure the quality of the outputs remains up to par across releases.
Context is all you need: building reliable long-running agents
If you have used an LLM agent, you probably have noticed that at the start of a new conversation the agent is smart, helpful and to the point. But as the conversation goes on it starts to make more and more silly mistakes, forgets important facts, or even gets stuck entirely. This 'context rot' is inherent to how LLMs work, but production AI agents must be able to remember key information and not go off the rails when working on a bigger task. So how do we make our agents more reliable?
This session introduces Context Engineering as an evolution of prompt engineering: the discipline of dynamically constructing the right context at the right time across an agent’s lifecycle.
In this session, you will learn how to practice Context Engineering by writing, selecting, compressing, and isolating information to keep agents accurate and stable over time. The session will also cover how to design agent memory, combining short-term state with long-term memory using patterns like rolling summaries and structured user profiles.
Azure AI Winter Jam Sessionize Event
devCampNoord Sessionize Event
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