AI x design 2026 — Morning

Let’s be honest. Most of them aren’t that good. They work, but they don’t hold up. They’re usable, but not especially useful. AI has massively scaled our ability to produce output, but it hasn’t scaled the taste that differentiates great products from average ones.

Drawing on experience building and designing AI systems, I argue that taste is not a soft skill but a critical one. It is a muscle built when curiosity meets discernment, and exercised through decision-making. As making becomes easier, the challenge shifts to deciding what is good, what matters, and what should exist at all.

AI is exceptional at optimisation. Give it a goal and it will refine, accelerate, and automate within that frame. It will generate better outputs, faster workflows, cleaner systems. But it cannot decide that the question itself is wrong.

That's not a limitation of the technology. That's design's opening. The strategic value of design has never been execution. It's the power of reframing ... dissolving inherited assumptions and asking what actually needs to exist. In the AI era, this difference becomes critical. As optimisation becomes abundant in an era of intelligent systems, the most valuable design capability may be the disciplined courage to ask a different question.

AI will give you better horses indefinitely. Your job is to ask why we're still in the stable.

For many designers, "vibe coding" sits in an uncomfortable gap. We see the hype, but the reality often feels like a parlour trick: great for messy experimentation, but unreliable for professional work. It challenges everything we’ve learned about pixel perfection, forcing us into a new, non-deterministic medium where we must "guide" rather than "draw."

At Google Maps, we have moved past this disillusionment by treating AI prototyping not as a magic wand, but as a rigorous design discipline. By reviving foundational patterns from computer science and creative coding—such as state machines, parametric design, and recursion—we are moving from generating raw code to intentionally designing behaviour.

This session takes you inside the Google Maps UX pipeline to show how we integrate vibe prototyping into workflows that serve billions. We will explore how we use scrappy, AI-driven prototypes to validate the "feel" of dynamic interfaces and complex user flows long before engineering handover. You will leave with a practical framework for professionalizing your own AI prototypes, turning the unpredictable messiness of LLMs into scalable, human-centered experiences.