Retrieval-augmented generation (RAG) is powering a new breed of AI interfaces — but with great flexibility comes messy state. In this talk, we’ll dive into the real-world challenge of managing UI state in apps powered by generative backends. You’ll learn practical patterns to track sources, follow user intent, and tame AI responses, all without reinventing your frontend architecture.

Retrieval-augmented generation (RAG) is powering a new breed of AI interfaces — but with great flexibility comes messy state. In this talk, we’ll dive into the real-world challenge of managing UI state in apps powered by generative backends. You’ll learn practical patterns to track sources, follow user intent, and tame AI responses, all without reinventing your frontend architecture.

Thanks to AI, designers and PMs are now prototyping and deploying faster than ever, sometimes without writing a single line of code. Tools like Lovable, Bolt and others can generate entire applications directly from prompts, while design tools are blurring the lines between mockups and implementation. So where does that leave React engineers?

As AI tools become UI builders, one trend is clear: React is becoming their default output. It's quickly turning into the universal framework of AI, putting React developers at risk of seeing their core skills commoditized.

In a world where AI can generate impressive UIs and ship entire components from a single prompt, it's tempting to declare the death of frontend engineering.

But what if we're just looking at it wrong?

The pixel-pushing days may be over, but the complexity is just shifting layers. Welcome to the age of the back of the frontend. This talk explores how AI is fragmenting the frontend into fast, flashy outputs and deeply nuanced logic, and why the real value now lies beneath the surface.

We'll break down what's actually being automated (spoiler: it's not the hard stuff), the logic, flows, edge cases, performance, that's still on us. We'll examine where human acuity still matters, why knowing when not to use AI might be your new superpower, and how the integration of AI-generated React components into complex, multi-framework applications creates new engineering challenges.

This talk doesn't shy away from the uncomfortable question: what is your job when everyone can "build"?

If you're a frontend dev wondering whether you still have a job, you do. But it may not look the same as the one you trained for. The new frontier isn't just building components, but designing the systems that allow AI-generated components to function in the beautiful complexity of production applications.

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.