When the backend can reason, what does that mean for the frontend?

The way we interact with software is changing. LLM-powered applications, with human-in-the-loop, are handling repetitive tasks that used to require forms and workflows. But bolting a chatbot onto your existing UI isn't enough - extracting structured data from natural language is fragile, adding frustration and friction for users.

In this talk, we'll explore how tool-calling and protocols like MCP provide deterministic contracts with non-deterministic systems, what human-in-the-loop looks like when the UI adapts to the task at hand.