We scan new podcasts and send you the top 5 insights daily.
In traditional software, designers predict and control the exact visual state of every screen. Because personalized AI systems yield wildly different visual artifacts and content for every individual user, designers must shift their focus toward systemic architecture, scaffolding, and accepting varied outputs.
As AI agents become the primary 'users' of software, design priorities must change. Optimization will move away from visual hierarchy for human eyes and toward structured, machine-legible systems that agents can reliably interpret and operate, making function more important than form.
Transitioning from static, predefined design widgets to dynamic, real-time UI generated on the fly by frontier models upends conventional product design practices. When model outputs determine not just text but complete layout and interactive components non-deterministically, designers can no longer blueprint fixed states. Instead, design teams must integrate directly with AI researchers to build evaluation frameworks and steering tools that teach models design systems natively.
AI will soon create a unique user interface for every individual, adapted to their needs. For designers, this means shifting from creating fixed systems to defining flexible boundaries within which form and function can blend, balancing personalization with brand identity and usability.
As AI automates UI generation, a designer's strategic value shifts. Instead of designing pixels, they will architect user experiences by defining which components are fixed for consistency (like a login flow) and which are flexible canvases for AI-driven personalization (like a user dashboard).
Instead of completely altering entire screen layouts on every session, effective generative UI keeps stable native rails while populating contextual dynamic assets. Muse anchors core primitives like feeds and status bars, varying only details like personalized prompt suggestions or custom avatar animations.
For non-deterministic AI systems where every output can't be controlled, designers' roles must evolve to creating "evals"—systems that define and test for quality. Figma's CDO argues this is crucial for ensuring experiences generated by algorithms or LLMs consistently meet the desired standard of "good."
Giving AI freedom to generate custom layouts dynamically risks disorienting users if interface patterns shift with every response. Rhiannon Bell explains that while AI can assemble components from design systems, designers must enforce human-defined rules. Predictability in where answers, interactive widgets, and links appear is critical so users do not have to learn a brand-new interface on each query.
For generative UI, designers move from defining exact layouts to creating a "skill" that guides the AI. This skill defines a design language, references tokens, and suggests best practices, steering the model's output without over-constraining it.
Unlike traditional software, the core of an AI product is its dynamic, often unpredictable output. Static wireframes, even with placeholder text, are mere 'gargoyle rain spouts'—decoration that fails to represent the actual system. You can't validate an AI idea without building and testing the real, content-generating thing.
Designing for AI is less about crafting pixel-perfect UIs in Figma and more about creating the underlying system or "harness." This involves enabling the agent to perform long-running tasks, verify its own work, and operate effectively within technical constraints, which is where the real design work lies.