LLMs have made AI assistants a standard feature across SaaS. AI assistants allow users to instantly retrieve information and interact with a system through text-based prompts. Mathias Biilmann, in his article " Introducing AX: Why Agent Experience Matters," discusses two distinct approaches to building AI assistants. The Closed Approach involves a conversational assistant embedded directly within a single SaaS product. Examples include Zoom's AI Companion, Salesforce CRM's Einstein, and Microsoft's Copilot. The Open Approach involves external conversational assistants, such as Claude, ChatGPT, and Gemini,
How does generation work? (Does it generate source code?)Generated UIs must be secure, reusable and cacheable. As such, syntux does not generate source code. It generates a schema for the UI, known as a "React Interface Schema" (RIS). See the question below to get a better understanding. This schema is tailored to the value that you provide. It is then hydrated by syntux and rendered.
Last Tuesday, I watched a designer at a design tools company sketch a FigJam interface on paper, snap a photo, and ask an AI model to build it. Twelve seconds later, they had a working prototype with animations, interactive components, and proper design system implementation. No mockups. No handoff documentation. Just a sketch and a conversation. This wasn't science fiction. It was Gemini 3 Pro, and it's forcing us to rethink what "design" actually means.
Service design is evolving and we're quickly moving past static screens and pages toward dynamic, contextual experiences. In my previous article, Service Design in the Era of AI Agents, I discussed this evolution in detail. After reading it, many people reached out with one specific question: what exact design patterns will we use for GenUI apps? In this article, I decided to discuss specific foundational patterns for GenUI apps.
