The easiest thing to do is often what causes hours of debugging down the line. With LLMs becoming increasingly normalized in the industry, an overreliance on them can allow bugs to slip through the cracks.

In this talk, I'll demonstrate a practical debugging workflow: Debug first. Prompt second. I'll show how browser DevTools reveal what's actually happening faster than any AI can guess.

You'll learn:

• Essential DevTools features that improve your bug-fixing prowess
• When to reach for your browser and when AI can actually help
• The almost forgotten art of breakpoints and strategic console messages

AI in your codebase represents growth, but understanding your runtime state represents mastery. This talk is about balancing both and knowing which tool to reach for first.

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.

Shipping one application is hard enough. Coordinating 20 releases in a single week is a monumental challenge. In this talk, I'll take you behind the scenes of how our engineering organization pulled off this ambitious project. Whether you're looking to accelerate delivery or strengthen team collaboration, you'll walk away with actionable insights for your engineering toolkit.

Recently, Superhuman (formerly Grammarly) launched Superhuman Go, an AI assistant that works alongside you on every platform. To build it, we needed a scalable solution that supports an unlimited number of agents that dynamically shapes the user interface and looks similar across all supported desktop and mobile platforms. Join me to find out how we discovered solutions for this innovative new product.