Ux
55 tweets
Introducing json-render AI-generated UI. Deterministic output. 1. Define your component catalog 2. AI steams JSON 3. Render interactive UI Let users prompt dashboards, widgets and apps - safely constrained to components and actions you define
Just shipped a little quality of life improvement to Agentation: computed styles. Click the chevron to expand computed CSS styles for the selected element. Really useful for debugging styling issues, communicating design specs, etc.
Intro Telegram is a great messenger. But the recent Liquid Glass update highlighted an interface issue: multiple ongoing activities inside the app overload the screen. Check it out for yourself: Activities hang over the interface like a stalactites Problem Statement In my view, there are a few problems here: - The Activities UI is now so small that it leads to mis-taps into neighboring activities - Activities take up too much space when there are many of them - Most of these elements are attached to folders, even though they have nothing to do with folders - Not all activities are needed at the same moment. They can (and should) be prioritized Solution Telegram already has a solid pattern for web pages and mini apps: a small sheet at the bottom of the screen. That’s how Telegram shows websites and mini apps We can extend that sheet component to cover all ongoing activities. Let’s call it the Chin: In the case of voice messages and music, Chin solves an extra job: it gives you a convenient timeline scrubber for the current track. Birthday reminder Chin can host different types of ongoing activities: voice messages, music, mini apps, safety messages, and active calls — or even birthday reminders, like in the example above. Live location Activities stack If activities start to pile up, the Chin doesn’t grow taller (a single chin always looks better than multiple ones). Instead, it stays the same size and uses an internal stack: you can expand it to view what’s active, and close whatever you don’t need. — But what if the user taps the chat input and the keyboard pops up? Then Chin will just get pushed under the keyboard and won’t be visible. Same as the modal preview does right now. Conclusion By evolving current sheet preview into the Chin, we unlock three improvements: - More space for content: less persistent UI on the chat list - Cleaner structure: ongoing activities are no longer tied to message folders - Richer interactions: scrubbing music or voice playback directly from the activity bar Closing Thoughts Mature products don’t only grow by adding features, they also grow by refactoring the patterns that no longer scale. The result: a cleaner UI today, and more room to evolve tomorrow. If my take and examples resonate, I’d love to collaborate — just send me a DM on X. Thank you.
if you use @shadcn ui for your apps, you're gonna love these 7 ui libraries: > http://kokonutui.com > http://cult-ui.com > http://pro.cult-ui.com > http://tailark.com > http://smoothui.dev > http://patterncraft.fun > http://motion-primitives.com imagine spending thousands on overpriced designers to make your app sexy when you have prebuilt components like these that elevate the shadcn experience i sprinkle em in all my apps and everyone loves using it for a reason...
we broke software into “design” and “engineering” and trapped ourselves in frames and specs. Cursor’s new visual editor lets you play with ideas and designs in code, live. no more hand-offs, just click, chat, tweak the tiniest detail, in the actual thing you will ship.
A small quality of life detail: you can now press tab to add more instructions when accepting/rejecting a permission prompt. We tried probably a dozen iterations of this UX over the last few weeks before deciding to ship this one. Let us know what you think!
Hiring designers for Claude Code What we’re looking for: high craft, uses Claude Code or other agentic coding tools regularly, experience shipping *really* quickly.
If want to use Claude Code but are don't like the terminal interface, you can now use local Claude Code from Claude Desktop! To do so: 1. download Claude Desktop 2. open the sidebar and click 'Code' toggle 3. select the folder that you want Claude Code to have access to 4. submit your prompt!
It feels pretty obvious at this point that someone’s going to make billions building a social app that’s just for friends, no AI slop, no brainrot, calm design, chronological feed and no concept of followers.
im building a content engine ◆ listens to github releases ◆ turn them into beautiful blogs, changelogs ◆ clean Cursor x Notion interface
Cursor feels like a company without product management. Just devs and designers running seemingly random experiments with little higher-level strategy. I use Cursor a lot, and it is becoming a very frustrating experience: — The interface is cluttered with tiny icons that get shuffled around every week — Are they building an agent or an editor? Pick one. This hybrid approach, where they pivot weekly, is frustrating — “Everything and the kitchen sink” isn't a great way to manage a product. A better approach is focusing on the core, and make that great instead of changing/adding useless things — Focus on stability. People use this for real work. Running into bugs and issues daily isn't the experience anyone wants Compare this to Claude Code: one text box, clear identity as an agent. Simple and focused. It's no wonder it's growing a lot.
BREAKING: Within the past 72 hours: - Apple's AI Chief steps down - Apple's Head of UI Design leaves to Meta - Apple's Policy Chief steps down - Apple's Head of General Counsel steps down
Good Products are Opinionated. “Every great founder I’ve seen up close, or even from afar, is highly opinionated and they’re almost dictatorial in how they run things. Also, early-stage teams are opinionated. And the products they build are opinionated. Opinionated means they have a strong vision for what it should and should not do. If you don’t have a strong vision of what it should and should not do, then you end up with a giant mess of competing features. @Jack Dorsey has a great phrase: “Limit the number of details and make every detail perfect.” And that’s especially important in consumer products. You have to be extremely opinionated. All the best products in consumer-land get there through simplicity. You could argue the recent success of ChatGPT and similar AI chatbots is because they’re even simpler than Google. Google looked like the simplest product you could possibly build. It was just a box. But even that box had limitations in what you could do. You were trained not to talk to it conversationally. You would enter keywords and you had to be careful with those keywords. You couldn’t just ask a question outright and get a sensible answer. It wouldn’t do proper synonym matching, and then it would spit you back a whole bunch of results. That was complicated. You’d have to sift through and figure out which ones were ads, which ones were real, were they sorted correctly, and then you’d have to click through and read it. ChatGPT and the chatbot simplified that even further. You just talk to it like a human—use your voice or you type and it gives you back a straight answer. It might not always be right, but it’s good enough, and it gives you back a straight answer in text or voice or images or whatever you prefer. So it simplifies what we looked at as the simplest product on the Internet, which was formerly Google, and makes it even simpler. And you just cannot make a product that’s simple enough. To be simple, you have to be extremely opinionated. You have to remove everything that doesn’t match your opinion of what the product should be doing. You have to meticulously remove every single click, every single extra button, every single setting. In fact, things in the settings menu are an indication that you’ve abdicated your responsibility to the user. Choices for the user are an abdication of your responsibility. Maybe for legal or important reasons, you can have a few of these, but you should struggle and resist against every single choice the user has to make. In the age of TikTok and ChatGPT, that’s more obvious than ever. People don’t want to make choices. They don’t want the cognitive load. They want you to figure out what the right defaults are and what they should be doing and looking at, and they want you to present it to them.”
The real moats in 2025: specific workflows, proprietary data with real switching costs, distribution, and UX that makes AI disappear into the job-to-be-done. Simultaneously: we are early (only a % are using AI properly) so this is an amazing time to start a startup.
Can someone build this app: It scrolls like social media. The users are books you’ve read on kindle. The posts are the parts you’ve highlighted.
Because of LLMs, the only type of people I’d hire now are what I’d call “super-unicorns” - Developer - Designer (or great design taste) - Product-focused (vs feature-focused) - Marketer - Agent expert - High emotional intelligence - 5+ years experience creating web app products - Extreme ownership (h/t @jockowillink) There are very few folks with all these traits … but I just wouldn’t want to work with someone who didn’t have all these skills/behaviors. This will keep team sizes very small. 2026 is going to be very interesting for the whole industry.
