UX design
fromMedium
14 hours agoThe rulebook for designing AI experiences
Responsible AI design varies widely, but frameworks from Microsoft, Google, and IBM provide practical guidance for Human-AI Interaction.
Santa Cruz de Tenerife is one of the most idyllic cities in the Canary Islands. At its heart stands the jewel - the Auditorio. It's a place where talent from both worlds, New and Old, comes together. A theatre, opera, dance, and music heaven.
Instructions I created. Instructions I am continuing to hone - instructions that required me to study my own old essays, identifying what I do when I write. The sentence rhythms. The way I move between timescales. The zooming in and out from concept to detail. The instructions tell Claude how I would like ideas composed. I pull together concepts and experiences from my lived expertise to formulate a point of view - in this case, on this new AI technology.
Google recently released a new AI model, Gemini 3.1, that demonstrates great results in UI and web design tasks. I've already tested this model for web design tasks and in this article, I want to experiment with Gemini 3.1 and generate UI for a mobile application.
Model Context Protocol (MCP) is a technology that enables AI models to connect with external tools and data sources (such as GitHub, Slack, databases, and documentation systems). In this article, I want to explore my top 7 favorite MCPs you can use in your design process. I will cover not only benefits but also limitations of the each MCP so you will have a clear idea about what you can & cannot do with it.
AI design tools are everywhere right now. But here's the question every designer is asking: Do they actually solve real UI problems - or just generate pretty mockups? To find out, I ran a simple experiment with one rule: no cherry-picking, no reruns - just raw, first-attempt results. I fed 10 common UI design prompts - from accessibility and error handling to minimalist layouts - into 5 different AI tools. The goal? To see which AI came closest to solving real design challenges, unfiltered.
Something's been slowly shifting in the design zeitgeist. I've been watching my feed on X and the vibe has changed. More and more, I see designers sharing finished experiments or prototypes they coded themselves, rather than static Figma files. Moving from working on a canvas to talking to an LLM. The conversation isn't "here's a design I made" anymore... it's "here's something I shipped this afternoon."
Teams often use customer and user interchangeably until it breaks alignment. Here's how separating the two clarifies research, prioritization, and messaging across B2C, B2B, and B2B2C products.