Augmented Coding is more than just asking an AI to help you write code.

You externalize your decision points, heuristics, and workflows into artifacts the agent can follow. The agent becomes your mentee.

As you do that, you change your focus from low-level details to high-level intent and methodology. Decisions that were unconscious become explicit.

In this talk, I’ll share my story of how I learned to teach AI a Software Crafter’s approach to development.

The agent follows a rigorous TDD process with 121 unique nodes and 131 directed edges that can run autonomously for hours, creating dozens of commits.

It covers advanced context engineering and techniques to increase autonomy while aiming to maintain quality.

And I will tell real stories of AI-enabled breakthroughs in real-world product development.

Chat interfaces are everywhere, but what challenges are there to overcome to create a truly joyful user experience? In this talk, we’ll explore the key problems and solutions across the entire stack: from the tools you can give your agent to better respond to real human behaviour, to the underlying infrastructure and optimisations required to handle client disconnects, cancellations, and multi-device usage gracefully.

React 19.2 just landed, and it’s not just another version bump — it’s a real upgrade for how we build apps. From smoother background updates with Activity, cleaner side effects with useEffectEvent, to smarter server-side handling with cacheSignal, React 19.2 is all about making your code faster, cleaner, and easier to understand.

In this talk, we’ll walk through the new features, what problems they solve, and how you can use them right away in your projects. We’ll also look at Performance Tracks in Chrome DevTools — a new way to actually see how your app performs under the hood.

Whether you’re a beginner or an experienced React dev, you’ll walk away knowing how to use these tools to write less buggy code, improve app speed, and enjoy coding with React a little more.

Nowadays most of our code is opensource, and we use a large amount of it in our systems. But we need to keep an eye on those opensource components, as new vulnerabilities are discovered every day. What happens if we let our guard down? And what can we do to avoid it? In this presentation we take a look at a simple RCE vulnerability, how it can be exploited, sending pure (?) JSON to a server, in order to take control of it, in a live demo. After explaining what's happening, we then take a look at a free plugin to use directly in our IDE to prevent this, giving the power back to developers!

We've been experimenting with how Claude Code can help us migrate the functionality in FS-klienten (our legacy PowerBuilder application) to our new frontend FS Admin. The results are really promising and indicate that if we manage to use Claude correctly, this is a game changer.

I'll demonstrate how a team at Sikt used Claude to analyze screens in our legacy application, then plan and finally extend our existing GraphQL schema with the neccessary changes for this screen to be migrated.

Kjetil Høybråten is a Tech Lead at Sikt where he's working on FS, our Student Information System. During the last few years he's been hard at work replacing the old APIs with GraphQL. He'll be sharing what's worked well and what's been painful during this transition.

Tim Couper, Chief Architect at 1EdTech, will explore how emerging movements in education technology are intersecting with AI. He’ll discuss how advances in interoperability and AI are driving the demand for dynamic schema discovery and smarter data ecosystems for learning.

Tim Couper is the Chief Architect at 1EdTech with 20+ years of software and infrastructure development across a wide range of industries, including Telecommunications, Pharmaceuticals, and Education.

A hands-on session working through pernicious React bugs, and how to squash them for good. By working through a concrete Todo List example, we’ll leverage TypeScript and JavaScript features to gradually improve the reliability and performance of our code. We might even push beyond the limit of what’s sensible, inviting a reflexion on the balance of code readability and its runtime performance.