AI coding agents feel like magic... right up until they collide with production code.

For teams maintaining legacy systems, these agents often hallucinate APIs, run off on tangents, and shatter trust faster than an unreviewed hotfix at 5pm. Ignoring the past won't save us, because new code becomes old!

We can do better, and we will. In this session we'll go over emerging strategies for improving the accuracy of coding agents on real codebases, benchmarks such as SWE-bench that evaluate our progress, and their limitations. Expect to walk away with actionable techniques and a renewed respect for code that came before us and the challenges ahead.

When the backend can reason, what does that mean for the frontend?
Let's take a look at how we can create UI's that can handle the reasoning capabilities of LLMs and adapt to perform any task.

Designers and developers work on different timelines—designers look to the future while developers build from what’s already been designed. They speak different languages and follow different processes. How can we bridge these gaps and build a more collaborative development process? In this talk, we will explore the integration of modern techniques and AI-driven tools to enhance design systems, fostering improved communication between cross-functional teams. By leveraging artificial intelligence, we can not only boost productivity and innovation but also create a more harmonious and efficient workflow for both designers and developers