Leave it to NN/g to evaluate the AI prompt-to-code tool landscape with some rigor. Huei-Hsin Wang and Megan Brown cover over a dozen tools, including ChatGPT, Claude, UX Pilot, Uizard, Relume, Stitch, Bolt, Lovable, v0, Replit, Figma Make, Magic Patterns, and Subframe. They use a human designer as the control.

Among their conclusions:

AI’s limited grasp of design nuances and inconsistent output make it best suited for ideation, concept exploration, and early-phase prototype testing, rather than later stages. While you likely won’t take an AI-generated prototype straight to production, these tools can help you break through creative blocks and explore new directions quickly.

I think the best part is they shared screenshots of outputs in a FigJam board.

I’ve been a big fan of node-based UIs since I first experimented with Shake in the early 2000s. It’s kind of weird to wrap your head around, especially if you’re used to layers in Photoshop or Figma. The easiest way to think about nodes is to rotate the layer stack 90-degrees. Each node has inputs on the left, a distinct process that it does to the input, and outputs stuff on the right. You connect up multiple nodes to process assets to form your final composition. Popular apps with node-based workflows today include Unreal Engine (Blueprints), DaVinci Resolve (Fusion and Color), and n8n.

ComfyUI is another open source tool that uses the same node graph architecture. Made in 2023 to add some UI to the visual generative AI models like Stable Diffusion appearing around that time, it’s become popular among artists to wield the plethora of image and video gen AI models.

Fast-forward to last week, when Figma announced they had acquired Weavy, a much friendlier and cloud-based version of ComfyUI.

Weavy brings the world’s leading AI models together with professional editing tools on a single, browser-based canvas. With Weavy, you can choose the model you want for a task (e.g. Seedance, Sora, and Veo for cinematic video; Flux and Ideogram for realism; and Nano-Banana or Seedream for precision) and compose powerful primitives using generative AI outputs and hands-on edits (e.g. adjusting lighting, masking an object, color grading a shot). The end result is an inspiring environment for creative exploration and a flexible media pipeline where every output feeds the next.

This node-based approach brings a new level of craft and control to AI generation. Outputs can be branched, remixed, and refined, combining creative exploration with precision and craft. The Weavy team has inspired us with the balance they’ve struck between simplicity, approachability, and power. They’ve also created a tool that’s just a joy to use.

I must admit I had not heard about Weavy before the announcement. I had high hopes for Visual Electric, but it never quite lived up to its ambitions. I proceeded to watch all the official tutorial videos on YouTube and love it. Seems so much easier to use than ComfyUI. Let’s see what Figma does with the product.

I’ve been on the receiving end of Layer 1226 before and it’s not fun. While I’m pretty good with my layer naming hygiene, I’m not perfect. So I welcome anything that can help rename my layers. Apparently, when Adobe showed off this new AI feature at their Adobe MAX user conference last week, it drew a big round of applause. (Figma’s had this feature since June 2024.)

There’s more than just renaming layers though. Adobe is leaning into conversational UI for editing too. For new users coming to editing tools, this makes a lot of sense because the learning curve for Photoshop is very steep. But as I’ve always said, professionals will also need fine-grained controls.

Writing for CNET, Katelyn Chedraoui:

Renaming layers is just one of many things Adobe’s new AI assistants will be able to do. These chatbot-like tools will be added to Photoshop and Express. They have an emphasis on “conversational, agentic” experiences — meaning you can ask the chatbot to make edits, and it can independently handle them.

…

Express’s AI assistant is similar to using a chatbot. Once you toggle on the tool in the upper left corner, a conversation window pops up. You can ask the AI to change the color of an object or remove an obtrusive element. While pro users might be comfortable making those edits manually, the AI assistant might be more appealing to its less experienced users and folks working under a time crunch.

A peek into Adobe’s future reveals more agentic experiences:

Also announced on Tuesday is Project Moonlight, a new platform in beta on Adobe’s AI hub, Firefly. It’s a new tool that hopes to act as a creative partner. With your permission, it uses your data from Adobe platforms and social media accounts to help you create content. For example, you can ask it to come up with 20 ideas for what to do with your newest Lightroom photos based on your most successful Instagram posts in the past. 

These AI efforts represent a range of what conversational editing can look like, Mike Polner, Adobe Firefly’s vice president of product marketing for creators said in an interview. 

“One end of the spectrum is [to] type in a prompt and say, ‘Make my hat blue.’ That’s very simplistic,” said Polner. “With Project Moonlight, it can understand your context, explore and help you come up with new ideas and then help you analyze the content that you already have,” Polner said.

To close us out on Halloween, here’s one more archive full of spooky UX called the Dark Patterns Hall of Shame. It’s managed by a team of designers and researchers, who have dedicated themselves to identifying and exposing dark patterns and unethical design examples on the internet. More than anything, I just love the names some of these dark patterns have, like Confirmshaming, Privacy Zuckering, and Roach Motel.

It’s like Footer, the footer gallery, but for navigation bars! Inspired by the former and incubated on Design Twitter, Christina Liubynska makes a curated space to celebrate navbars.

Celine Nguyen wrote a piece that connects directly to what Ethan Mollick calls “working with wizards” and what SAP’s Ellie Kemery describes as the “calibration of trust” problem. It’s about how the interfaces we design shape the relationships we have with technology.

The through-line is metaphor. For LLMs, that metaphor is conversation. And it’s working—maybe too well:

Our intense longing to be understood can make even a rudimentary program seem human. This desire predates today’s technologies—and it’s also what makes conversational AI so promising and problematic.

When the metaphor is this good, we forget it’s a metaphor at all:

When we interact with an LLM, we instinctively apply the same expectations that we have for humans: If an LLM offers us incorrect information, or makes something up because it the correct information is unavailable, it is lying to us. …The problem, of course, is that it’s a little incoherent to accuse an LLM of lying. It’s not a person.

We’re so trapped inside the conversational metaphor that we accuse statistical models of having intent, of choosing to deceive. The interface has completely obscured the underlying technology.

Nguyen points to research showing frequent chatbot users “showed consistently worse outcomes” around loneliness and emotional dependence:

Participants who are more likely to feel hurt when accommodating others…showed more problematic AI use, suggesting a potential pathway where individuals turn to AI interactions to avoid the emotional labor required in human relationships.

…

However, replacing human interaction with AI may only exacerbate their anxiety and vulnerability when facing people.

This isn’t just about individual users making bad choices. It’s about an interface design that encourages those choices by making AI feel like a relationship rather than a tool.

The kicker is that we’ve been here before. In 1964, Joseph Weizenbaum created ELIZA, a simple chatbot that parodied a therapist:

I was startled to see how quickly and how very deeply people conversing with [ELIZA] became emotionally involved with the computer and how unequivocally they anthropomorphized it…What I had not realized is that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people.

Sixty years later, we’ve built vastly more sophisticated systems. But the fundamental problem remains unchanged.

The reality is we’re designing interfaces that make powerful tools feel like people. Susan Kare’s icons for the Macintosh helped millions understand computers. But they didn’t trick people into thinking their computers cared about them.

That’s the difference. And it matters.

Circling back to Monday’s item on how caring is good design, Felix Haas has a subtly different take: build kindness into your products.

Kindness in design isn’t about adding smiley faces or writing cheerful copy. It’s deeper than tone. It’s about intent embedded in every interaction.

…

Kindness shows up in the patience of an empty state that doesn’t rush you. In the warmth of micro-interactions that acknowledge your actions without demanding attention. In error messages that guide rather than scold. In defaults that assume good intent rather than user incompetence.

These moments seem subtle, even trivial, in isolation. But they accumulate. They shape how we feel about a product over weeks and months. They turn interfaces into relationships. They build trust.

I think these guidelines from Vercel are great. It’s a one-pager and very clearly written for both humans and AI. It reminds me of the old school MailChimp brand voice guidelines and Apple’s Human Interface Guidelines which have become reference standards.

Nielsen Norman Group weighs in on iOS 26 Liquid Glass. Predictably, they don’t like it. Raluca Budiu:

With iOS 26, Apple seems to be leaning harder into visual design and decorative UI effects — but at what cost to usability? At first glance, the system looks fluid and modern. But try to use it, and soon those shimmering surfaces and animated controls start to get in the way.

I get it. Flat—or mostly flat—and static UI conforms to the heuristics. But honestly, it can get boring and homogenous quickly. Put the NNg microscope on any video game UI and it’ll be torn to shreds, despite gamers learning to adapt quickly.

I’ve had iOS 26 on my phone for just a couple of weeks. I continue to be delighted by the animations and effects. So far, nothing has hindered the usability for me. We’ll see what happens as more and more apps get translated.

As much as I defended the preview, and as much as Apple wants to make Liquid Glass a thing, the new UI is continuing to draw criticism. Dan Moren for Six Colors:

“Glass” is the overall look of these updates, and it’s everywhere. Transparent, frosted, distorting. In some places it looks quite cool, such as in the edge distortion when you’re swiping up on the lock screen. But elsewhere, it seems to me that glass may not be quite the right material for the job. The Glass House might be architecturally impressive, but it’s not particularly practical.

It’s also a definite philosophical choice, and one that’s going to engender some criticism—much of it well-deserved. Apple has argued that it’s about getting controls out of the way, but is that really what’s happening here? It’s hard to argue that having a transparent button sitting right on top of your email is helping that email be more prominent. To take this argument to its logical conclusion, why is the keyboard not fully transparent glass over our content?

I’ve yet to upgrade myself. I will say that everyone dislikes change. Lest we forget that the now-ubiquitous flat design introduced by iOS 7 was also criticized.

Jason Spielman put up a case study on his site for his work on Google’s NotebookLM:

The mental model of NotebookLM was built around the creation journey: starting with inputs, moving through conversation, and ending with outputs. Users bring in their sources (documents, notes, references), then interact with them through chat by asking questions, clarifying, and synthesizing before transforming those insights into structured outputs like notes, study guides, and Audio Overviews.

And yes, he includes a sketch he did on the back of a napkin.

I’ve always wondered about the UX of NotebookLM. It’s not typical and, if I’m being honest, not exactly super intuitive. But after a while, it does make sense. Maybe I’m the outlier though, because Spielman’s grandmother found it easy. In an interview last year on Sequoia Capital’s Training Data, he recalls:

I actually do think part of the explosion of audio overviews was the fact it was a simple one click experience. I was on the phone with my grandma trying to explain her how to use it and it actually didn’t take any explanation. I’m like, “Drop in a source.” And she’s like, “Oh! I see. I click this button to generate it.” And I think that the ease of creation is really actually what catalyzed so much explosion. So I think when we think about adding these knobs [for customization] I think we want to do it in a way that’s very intentional.

Chatboxes have become the uber box for all things AI. The criticism of this blank box has been the cold start issue. New users don’t know what to type. Designers shipping these product mostly got around this problem by offering suggested prompts to teach users about the possibilities.

The issue on the other end is that expert users end up creating their own library of prompts to copy and paste into the chatbox for repetitive tasks.

Sharang Sharma writing in UX Collective illustrates how these UIs can be smarter by being predictive of intent:

Contrary, Predictive UX points to an alternate approach. Instead of waiting for users to articulate every step, systems can anticipate intent based on behavior or common patterns as the user types. Apple Reminders suggests likely tasks as you type. Grammarly predicts errors and offers corrections inline. Gmail’s Smart Compose even predicts full phrases, reducing the friction of drafting entirely.

Sharma says that the goal of predictive UX is to “reduce time-to-value and reframe AI as an adaptive partner that anticipates user’s intent as you type.”

Imagine a little widget that appears within the chatbox as you type. Kind of a cool idea.

Thinking about this morning’s link about web forms, if you abstract why it’s so powerful, you get to the point of human-computer interaction: the computer should do what the user intends, not the buttons they push.

Matt Webb reminds us about the DWIM, or Do What I Mean philosophy in computing that was coined by Warren Teitelman in 1966. Webb quotes computer scientist Larry Masinter:

DWIM is an embodiment of the idea that the user is interacting with an agent who attempts to interpret the user’s request from contextual information. Since we want the user to feel that he is conversing with the system, he should not be stopped and forced to correct himself or give additional information in situations where the correction or information is obvious.

Webb goes on to say:

Squint and you can see ChatGPT as a DWIM UI: it never, never, never says “syntax error.”

Now, arguably it should come back and ask for clarifications more often, and in particular DWIM (and AI) interfaces are more successful the more they have access to the user’s context (current situation, history, environment, etc).

But it’s a starting point. The algo is: design for capturing intent and then DWIM; iterate until that works. AI unlocks that.

Brad Frost, of atomic design fame, wrote a history of themeable UIs as part of a deep dive into design tokens. He writes, “Design tokens may be the latest incarnation, but software creators have been creating themeable user interfaces for quite a long time!”

About Mario and Luigi from Super Mario Bros.:

It’s wild that two of the most iconic characters in the history of pop culture — red-clad Mario and green-clad Luigi — are themeable UI elements born from pragmatic ingenuity to overcome technological challenges. Freaking amazing.

DOC is a publication from Fabricio Teixeira and Caio Braga that I’ve linked to before. Their latest reflection is on interfaces.

A good user interface is a good conversation.

Interfaces thrive on clarity, responsiveness, and mutual understanding. In a productive dialogue, each party clearly articulates their intentions and receives timely, understandable responses. Just as a good conversationalist anticipates the next question or need, a good interface guides you smoothly through your task. At their core, interfaces translate intent into action. They’re a bridge between what’s in your head and what the product can do.

Reflection is the best word I’ve found to describe these pieces. They’re hype-free, urging us to take a step back, and—at least for me—a reminder about our why.

In the end, interfaces are also a space for self-expression.

The ideal of “no interface” promises ultimate efficiency and direct access—but what do we lose in that pursuit? Perhaps the interface is not just a barrier to be minimized, but a space for human expression. It’s a canvas; a place to imbue a product with personality, visual expression, and a unique form of art.

When we strip that away, or make everything look the same, we lose something important. We trade the unique and the delightful for the purely functional. We sacrifice a vital part of what makes technology human: the thoughtful, and sometimes imperfect, ways we present ourselves to the world.

Hard to believe that the Domino’s Pizza tracker debuted in 2008. The moment was ripe for them—about a year after the debut of the iPhone. Mobile e-commerce was in its early days.

Alex Mayyasi for The Hustle:

…the tracker’s creation was spurred by the insight that online orders were more profitable – and made customers more satisfied – than phone or in-person orders. The company’s push to increase digital sales from 20% to 50% of its business led to new ways to order (via a tweet, for example) and then a new way for customers to track their order.

Mayyasi weaves together a tale of business transparency, UI, and content design, tracing—or tracking?—the tracker’s impact on business since then. “The pizza tracker is essentially a progress bar.” But progress bars do so much for the user experience, most of which is setting proper expectations.

I have always wanted to read 6,200 words about color! Sorry, that’s a lie. But I did skim it and really admired the very pretty illustrations. Dan Hollick is a saint for writing and illustrating this chapter in his living book called Making Software, a reference manual for designers and programmers that make digital products. From his newsletter:

I started writing this chapter just trying to explain what a color space is. But it turns out, you can’t really do that without explaining a lot of other stuff at the same time.

Part of the issue is color is really complicated and full of confusing terms that need a maths degree to understand. Gamuts, color models, perceptual uniformity, gamma etc. I don’t have a maths degree but I do have something better: I’m really stubborn.

And here are the opening sentences of the chapter on color:

Color is an unreasonably complex topic. Just when you think you’ve got it figured out, it reveals a whole new layer of complexity that you didn’t know existed.

This is partly because it doesn’t really exist. Sure, there are different wavelengths of light that our eyes perceive as color, but that doesn’t mean that color is actually a property of that light - it’s a phenomenon of our perception.

Digital color is about trying to map this complex interplay of light and perception into a format that computers can understand and screens can display. And it’s a miracle that any of it works at all.

I’m just waiting for him to put up a Stripe link so I can throw money at him.

Vitaly Friedman writes a good primer on the design possibilities for users to interact with AI features. As AI capabilities become more and more embedded in the products designers make, we have to become facile in manipulating AI as material.

Many products are obsessed with being AI-first. But you might be way better off by being AI-second instead. The difference is that we focus on user needs and sprinkle a bit of AI across customer journeys where it actually adds value.

John Calhoun joined Apple 30 years ago as a programmer to work on the Color Picker.

Having never written anything in assembly, you can imagine how overjoyed I was. It’s not actually a very accurate analogy, but imagine someone handing you a book in Chinese and asking you to translate it into English (I’m assuming here that you don’t know Chinese of course). Okay, it wasn’t that hard, but maybe you get a sense that this was quite a hurdle that I would have to overcome.

Calhoun was given an old piece of code and tasked with updating it. Instead, he translated it into a programming language he knew—C—and then decided to add to the feature. He explains:

I disliked HSL as a color space, I preferred HSV (Hue, Saturation, Value) because when I did artwork I was more comfortable thinking about color in those terms. So writing an HSV color picker was on my short list.

When I had my own color picker working I think I found that it was kind of fun. Perhaps for that reason, I struck out again and wrote another color picker. The World Wide Web (www) was a rather new thing that seemed to be catching on, so I naturally thought that an HTML color picker made sense. So I tackled that one as well. It was more or less the RGB color picker but the values were in hexadecimal and a combined RGB string value like “#FFCC33” was made easy to copy for the web designer.

So an engineer decided, all on his own, that he’d add a couple extra features. Including the fun crayon picker:

On a roll, I decided to also knock out a “crayon picker”. At this point, to be clear, the color picker was working and I felt I understood it well enough. As I say, I was kind of just having some fun now.

And Calhoun makes this point:

It was frankly a thing I liked about working for Apple in those days. The engineers were the one’s driving the ship. As I said, I wrote an HSV picker because it was, I thought, a more intuitive color space for artists. I wrote the HTML color picker because of the advent of the web. And I wrote the crayon picker because it seemed to me to be the kind of thing Apple was all about: HSL, RGB — these were kind of nerdy color spaces — a box of crayons is how the rest of us picked colors.

Making software—especially web software—has matured since then, with product managers and designers now collaborating closely with engineers. But with AI coding assistants, the idea of an individual contributor making solo decisions and shipping code might become de rigueur again.

This is an amazing article and website by Marcin Wichary, the man behind the excellent Shift Happens book.

…I had a realization that the totemic 1984 Mac control panel, designed by Susan Kare, is still to this day perhaps the only settings screen ever brought up in casual conversation.

I kept wondering about that screen, and about what happened since then. Turns out, the Mac settings have lived a far more fascinating life than I imagined, have been redesigned many times, and can tell us a lot about the early history and the troubled upbringing of this interesting machine.

Indeed, Wichary goes through multiple versions of Mac operating systems and performs digital paleontology, uncovering long lost Settings minutiae. It’s also a great lesson in UI along the way. Be sure to click in the Mac screens.

I remember the article from 2016 titled “Hamburger Menus and Hidden Navigation Hurt UX Metrics” where the conclusion from NN/g was:

Discoverability is cut almost in half by hiding a website’s main navigation. Also, task time is longer and perceived task difficulty increases.

Fast forward nearly 10 years later and NN/g says:

Hamburger menus are a more familiar pattern today than 10 years ago, but the same old best practices for hidden navigation still apply.

Kate Kaplan, revisiting her conclusion from nearly a decade ago:

Over the past decade, the hamburger menu — much like its namesake — has become a classic. As mobile-first design took hold, it offered a clean, space-saving solution, and when design leaders like Apple and Amazon adopted it, others followed. Its growing ubiquity helped standardize its meaning: Through repeated exposure, users learned to recognize and interpret the icon with increasing confidence.

I think the hamburger menu grew in popularity despite NN/g’s authoritative finger wagging. As designers, most of the time, we have to balance between the needs of the project and client with known best practices. Many websites, especially e-commerce, don’t have four or fewer main navigation links. We had to put the links somewhere and the hamburger menu made sense.

Crazy. Methinks there’s a non-zero chance that someone at v0 read my article and decided to give us designers the control we want.

Can’t wait to try it out.

Christopher Butler writes a wonderful essay about the “best interfaces we never built,” exploring the UIs from sci-fi:

Science fiction, by the way, hasn’t just predicted our technological future. We all know the classic examples, particularly those from Star Trek: the communicator and tricorder anticipated the smartphone; the PADD anticipated the tablet; the ship’s computer anticipated Siri, Alexa, Google, and AI voice interfaces; the entire interior anticipated the Jony Ive glass filter on reality. It’s enough to make a case that Trek didn’t anticipate these things so much as those who watched it as young people matured in careers in design and engineering. But science fiction has also been a fertile ground for imagining very different ways for how humans and machines interact.

He goes on to namecheck 2001: A Space Odyssey, Quantum Leap, Inspector Gadget and others. I don’t know Butler personally, but I’d bet $1 he’s Gen X like me.

As UX designers, it’s very easy to get stuck thinking that UI is just pixels rendered on a screen. But in fact, an interface is anything that translates our intentions into outcomes that technology can deliver.

Vincent Nguyen writing for Yanko Design, interviewing Alan Dye, VP of Human Interface Design at Apple:

This technical challenge reveals the core problem Apple set out to solve: creating a digital material that maintains form-changing capabilities while preserving transparency. Traditional UI elements either block content or disappear entirely, but Apple developed a material that can exist in multiple states without compromising visibility of underlying content. Dye’s emphasis on “celebrating user content” exposes Apple’s hierarchy philosophy, where the interface serves content instead of competing with it. When you tap to magnify text, the interface doesn’t resize but stretches and flows like liquid responding to pressure, ensuring your photos, videos, and web content remain the focus while navigation elements adapt around them.

Since the Jony Ive days, Apple’s hardware has always been about celebrating the content. Bezels got smaller. Screens got bigger and brighter. Even the flat design brought on by iOS 7 and eventually adopted by the whole ecosystem was a way to strip away the noise and focus on the content.

Dye’s explanation of the “glass layer versus application layer” architecture provides insight into how Apple technically implements this philosophy. The company has created a distinct separation between functional controls (the glass layer) and user content (the application layer), allowing each to behave according to different rules while maintaining visual cohesion. This architectural decision enables the morphing behavior Dye described, where controls can adapt and change while content remains stable and prominent.

The Apple platform UI today sort of does that, but Liquid Glass seems to take it even further.

Nguyen about his experience using the Music app on Mac:

The difference from current iOS becomes apparent in specific scenarios. In the current Music app, scrolling through your library feels like moving through flat, static layers. With Liquid Glass, scrolling creates a sense of depth. You can see your album artwork subtly shifting beneath the translucent controls, creating spatial awareness of where interface elements sit in relation to your content. The tab bar doesn’t just scroll with you; it creates gentle optical distortions that make the underlying content feel physically present beneath the glass surface.