UX News
A look at what's going on in the field of user experience.
Everything I know about AI, I learned from a genie
, UX Collective - Medium
A content designer's guide to not wasting your wishes on something stupidI Dream of JeanieI was a lucky child. My parents and grandparents spent hours reading and reciting fairytales to me. Most of them weren’t age-appropriate, of course, involving children being eaten and loved ones dying on every other page. But there was always enough moral to the story to distract from the horrors and drive home a message. Trying to understand what it all meant kept me up at night ruminating.
I recently had an epiphany: these stories were excellent preparation for what I’m currently facing in my career: Dealing with artificial intelligence. Understanding it. Giving it instructions, it simply cannot misinterpret. Getting something valuable from it in return. Judging that.
How to make Claude Code follow your design system in Figma
, UX Collective - Medium
4 Skills that bind every value to your design system, so you can actually iterate on what Claude builds.Claude Code can now write directly to the Figma canvas through Figma MCP.
You describe an interface in natural language; it builds it. Visually, the result can be pixel-perfect. But click into any layer and you’ll find #5C6AC4 where color/brand/primary should be, 14 where text/body-sm is defined, a freshly minted one-off component where an existing Button instance is sitting right there in the library.
The prompt is not an interface
, UX Collective - Medium
Why AI sent us back to the command line — On direct manipulation, visual intent, and the regression of AI tooling.Image generated via Google Gemini“Seeing comes before words. The child looks and recognises before it can speak.” — John Berger, Ways of Seeing, 1972 [1]The most advanced artificial intelligence systems in history now ask us to communicate through a blinking cursor in an empty text box.
We have, in the most literal sense, gone backwards.
Designing data-intensive applications — advice for interaction designers
, UX Collective - Medium
The things on the screen — numbers, tables, graphs, forms, dashboards — are just two-dimensional projections of a multi-dimensional data landscape. That data landscape in turn is just a representation of real-world phenomena and domain concepts. The design practices in this article will help you “see through” the product surface into the data and domain layers, and re-orient your work around them.Photo by Milad Fakurian on UnsplashAfter 30 years in design, I’ve spent the last year building a data-intensive product as a solo builder, learning software engineering and data science on the way. Obviously, I had to learn a lot of new technical skills — but I’ve also been pleasantly surprised by how much this has taught me about design. Both reinforcing things I already knew, and highlighting blind spots in my design practice. I’ve distilled these lessons into 10 suggestions — not a comprehensive canon, but hard-earned and hopefully useful for fellow designers tackling similar challenges.
Learn Python.Learn your users’ job.Let the data draw the page for you.Strip back the chrome.Design the empty state.Work with real(istic) data.Pre-populate intelligently.Bridge mental models and data models.Words matter.Simple and explicit navigation.A key challenge in Studymodel.ai was how to represent milestones not as a single point in time, but as a probability distribution. The solution turned out to be an adaptation of an existing graphical convention — the whisker plot — into a milestone gantt chart. Combining two familiar conventions into a new form made an unfamiliar concept — a “probabilistic milestone” — feel familiar and accessible to the users.Learn PythonWith a few notable exceptions, most advice on “learning code” for designers emphasises front-end and web frameworks. That makes sense if your focus is UI. But if you are interested in shaping interaction and functionality in complex, data-intensive products — which probably includes LLM-powered interactions — Python is the natural choice. It gives you a concise, readable, powerful language in which to describe data and logic. You need this for communication even if an LLM writes all your code.
What is DESIGN.md and How To Use It
, UX Planet - Medium
One of the biggest challenges when using AI design generators is producing consistent output. Even when you feed AI tools specific…
Vibe Coding Makes You a Bad Designer
, UX Planet - Medium
Vibe coding is no longer an abstract concept; it’s a modern-day reality. Google says 75% of new code is now AI-generated. Many product…
Can AI Detect Usability Problems Like Researchers?
, MeasuringU
AI can “watch” videos.
It can even generate a list of problems. In some cases, these problem lists seem to be reasonably consistent (reliable).
Designed a prompt end-to-end for the design process and it will make you faster
, UX Planet - Medium
I designed a detailed prompt for the end-to-end design process which covers research to handoff. This took me almost a month to test and refine it works perfectly. Took my 4 weeks of weekly token limit to test till it reached to this point a well refined.
(This works with all AI agents but I tested and run with the Claude Sonnet 4.5, 4.6) and Opus 4.7) Hope this template will save your time…
Is Codex better than Claude Code?
, UX Planet - Medium
OpenAI Codex surpassed Claude Code in downloads sharply after the April 30 release. Considering the rapid divergence in developer adoption…
How Reliable Is AI at Finding UI Problems?
, MeasuringU
It looks like AI can “watch” videos. And if AI can watch videos, it can likely extract UI problems. That suggests it has the potential to support UX research.
So maybe AI can “watch” a video and detect some problems. But if you run the same video through AI multiple times, do you get the same results?
