UX design

UX design

Last month, I ran an experiment with our own product at Promer. I asked Claude to write a product brief for our AI Creative Studio homepage. Clear requirements: target e-commerce sellers, emphasize speed and ease of use, highlight the "paste your product URL and get ads" value prop. Then I fed that brief into Figma's Make AI. Hit generate. What came back looked... professional. Clean layout. Orange CTA button. Three value props with checkmarks. Stats prominently displayed (10,000+ users, 1M+ ads created, 4.9 stars). A hero headline that said exactly what the product does. Template showcase below the fold.

One of the challenges teams face when working with large boards or displaying multiple fields on work item cards is limited screen space. This became even more noticeable with the rollout of the New Boards hub, which introduced additional spacing and padding for improved readability. While this enhances clarity, it can also reduce the number of cards visible at once.

At Payflows, we build software that helps large companies manage and automate their payment workflows. It's not the flashiest part of a business-but it's one of the most critical. When invoices, approvals, and payments slow down, the whole company feels it. But we're not here just to make a better workflow tool. We believe the future of finance operations is not faster clicking: It's no clicking at all 🫳🎤

This same sense of uncertainty can be triggered in software products. Many digital experiences consist of background tasks, file imports, system updates, and other long-running processes that run quietly and invisibly, leaving users with no indications of progress or feedback. The user initiates an action, like a sync, a publish, or a bulk update, and is responsible for the outcome, while the system does all the work out of sight.

Autonomy is an output of a technical system. Trustworthiness is an output of a design process. Here are concrete design patterns, operational frameworks, and organizational practices for building agentic systems that are not only powerful but also transparent, controllable, and trustworthy. In the first part of this series, we established the fundamental shift from generative to agentic artificial intelligence. We explored why this leap from suggesting to acting demands a new psychological and methodological toolkit for UX researchers, product managers, and leaders.

I'm looking at the stage but I don't know what I saw, even though the message is somehow clear. I was invited into the self-reflection of a lost person, projected inward through an attempt to escape from the simulation of post-apocalyptic reality, which through our human stupidity has turned our world into a capitalist grey wasteland, where you can survive if you accept that you don't exist, and there is only us.

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."

I have ADHD and have found Home Assistant to be a valuable tool for managing executive dysfunction. I use it for audible calendar reminders, laundry reminders, timers, and monitoring my doorbell camera and my nanny cam for my dog. Its also a great source of pure nerdy joy for me. And I recently took the most joyously nerdy step yet in my home automation fixation.

When Sonos released its redesigned app in May 2024, the backlash was immediate and brutal. Users couldn't access basic features like volume control and alarms. Systems became unusable. The company's stock plummeted 25%. Eventually, the CEO was replaced, and lawsuits claimed over $5 million in damages from customers who'd lost functionality they'd paid for.

Hi everyone, I'm a solo developer who recently built a fan-made tool for the Roblox game https://www.forgeore.com The main goal of the site is to help players: Calculate forging probabilities based on different ore combinations Automatically find optimal ore recipes using a Smart Optimizer (this is the unique part) Browse a complete database of all 88 in-game ores with stats Share their builds via URL links for easy discussion in Discord/forums

One of the first places users notice gaps in visibility is Instagram Stories. The platform tells you who viewed a story, but it does not tell you who wanted to look without being noticed. That absence shapes behaviour. People avoid checking stories to prevent awkward signals, misunderstandings, or emotional reactions. How Instagram obscures story viewing and follower context Tools like the insta story viewer by FollowSpy exist

There's a particular kind of guilt that visits me when I open my feed reader after a few days away. It's not the guilt of having done something wrong, exactly. It's more like the feeling of walking into a room where people have been waiting for you, except when you look around, the room is empty. There's no one there. There never was.

The question dropped into the Slack channel before the user research summary. Before the problem was clearly defined. Before anyone asked if users actually needed this feature. Your product manager already generated three interface options in ChatGPT. Now they're asking which one to build. Not whether to build. Not why to build. Which. And when you slow the conversation down to ask those questions, you're about to discover that strategic thinking now reads as bottleneck behavior.

Using a pre-built template strategy: The Atlassian team realized that AI was often messing up core elements and not completely understanding complex commands. So they created a sort of "design system" for their AI led prototyping. Here they feed a page with pre-coded elements which AI doesn't change, but lets the tool work on other elements which are open to interpretation in a way.

My role was straightforward: write queries (prompts and tasks) that would train AI agents to engage meaningfully with users. But as a UXer, one question immediately stood out - who are these users? Without a clear understanding of who the agent is interacting with, it's nearly impossible to create realistic queries that reflect how people engage with an agent. That's when I discovered a glitch in the task flow.

Google is testing the ability to add color to your search results page with a color palette picker. There is this palette icon at the top of the results that when clicked on says "Add a splash of color to the top of Search," and "Pick color." When you click on pick color it loads 10 colors to "Choose an accent color for the top of Search."

To be honest, for many years, I was mostly reacting. Life was happening to me, rather than me shaping the life that I was living. I was making progress reactively and I was looking out for all kinds of opportunities. It was easy and quite straightforward - I was floating and jumping between projects and calls and making things work as I was going along.

The other day I was browsing YouTube - as one does - and I clicked a link in the video description to a book. I was then subjected to a man-in-the-middle attack, where YouTube put themselves in the middle of me and the link I had clicked: Hyperlinks are subversive. Big Tech must protect themselves and their interests.