Big Medium - Full Feed

Sentient Design: Crafting Intelligent Interfaces with AI

Josh Clark & Veronika Kindred — Wed, 15 Apr 2026 13:31:46 UT

Sentient Design: Crafting Intelligent Interfaces with AI

What does AI do to software?

Josh Clark — Sat, 11 Apr 2026 18:45:43 UT

Benedict Evans surveys what AI does to software, and it certainly doesn’t kill it. He covers the familiar shifts: faster development, new AI-powered features, and likely disruption of incumbent software solutions. But then he turns to the most interesting question: what forms will intelligent interfaces take, and how will those forms change both business and customer?

Evans considers how SaaS and mobile both changed what software (and software companies) look like:

One way to think about both of these is that the first step was to do the old thing with a new tool, but the next step was to think of things that were native to the new form. We started by making a Flickr app for mobile, and then we made Instagram, and then we got Snap and TikTok, which embraced the fact that this was a device with a camera, and a touchscreen, and its own compute instead of just a website. Some of the early thinking around AI software is to look at generative interfaces, to think about how dynamic and intelligent the screens could be, and to wonder if you might move away from carefully fixed screens and predefined workflows. No one really knows, but a lot of people will have fun experimenting. …

As I say, in almost every essay, meanwhile, this is all very 2007, or 1997, or very 1982. We know this is huge, we can sort of see some of what’s coming, but we don’t really know how any of this is going to work. And so, there is an enormous amount of white space out there, for people to go out and create things, that have nothing to do with stupid ideas like ‘software is dead’.

Generative interfaces. Dynamic and intelligent screens. A shift away from static workflows.

Amen. That white space is where a new era of intelligent interfaces lives, and it’s exactly the territory that Sentient Design maps out. If you’re one of those people who will “have fun experimenting,” Sentient Design’s framework and design patterns will give you a head start. Get after it.

What Does AI Do to Software? | Benedict Evans

AI is the Closest Thing to a Genie Lamp

Josh Clark — Sat, 11 Apr 2026 18:15:21 UT

“AI is the closest thing in the world to a genie lamp,” writes Alberto Romero in the Algorithmic Bridge newsletter. His point: while the “magic” might be remarkable, it shifts the effort to the wish. When AI can manifest what you ask on demand, the hard part becomes naming what you actually want. Alas, most people (and organizations) aren’t very good at that part.

The idea of thinking about “single-use” magical objects is that they invert the effort allocation 100%: the “how” is fully outsourced. How does the genie get you a billion dollars? How does it make you extremely handsome? You don’t care, you don’t want to know. So, you automatically realize that your mental effort must now be fully devoted to the complementary question: what do you want? …

The belief that doing takes more resources than deciding what to do has been the default operating mode for basically all of human life. The how has always been so expensive that the what barely matters. You didn’t need to be good at wishing because you were never going to get most of what you wished for anyway.

So now you can get what you wished for (in software and software-shaped problems, at least). As that capability becomes more equally absorbed, the differentiator won’t be speed or execution but knowing what to make in the first place. Romero points out that sometimes people call this critical POV by a number of different names: taste, judgment, decision-making, agency, curiosity, or imagination. “For a while, I thought these were all the same thing in various disguises,” he writes. “But I think they’re actually different skills that all became load-bearing at once.”

All these skills share a family resemblance—they’re all “what” skills rather than “how” skills—but they’re not interchangeable. Someone can have extraordinary taste and zero agency (the critic who never creates). Someone can have strong agency and terrible judgment (the founder who moves fast toward the wrong thing). Someone can have all the curiosity in the world and zero agency (the vibe-coder who is handling 10 projects at once but none of them will have any impact in the world). Etc.

All these skills are also well-known to those who have dedicated time to thinking about these matters, but for the rest of us, they were all invisible before because the “how” bottleneck was sitting in front of them like a boulder blocking a cave entrance. Now the boulder is rolling away and it turns out there’s an entire stack of capacities behind it that most people never developed because they never had to.

When you suddenly have the ability to do anything—and fast—then the critical skill becomes knowing what to build. And those people Romero mentions, the ones with “dedicated time to thinking about these matters”? Those people are called designers. The best designers have the skill to learn the outcomes that people truly need… and from there, work through the frictions blocking those outcomes to finally understand the deep, twisty heart of the problem. Naming the outcome and the problem is how you begin to work toward a solution—the what, not the how.

AI is just a technology. It’s a strange and powerful one, but in the end it’s an implementation detail (so is the genie and its lamp). We’ve got a new and burgeoning ability to make our ideas real, and a whole set of newly possible shapes those ideas can take. What shall we do with that? The genie can grant the wish, but it can’t tell you what to wish for. That’s always been the designer’s job.

You Spent Your Whole Life Getting Good at the Wrong Thing | The Algorithmic Bridge

Commit & Push: Josh Clark and Veronika Kindred

Sat, 11 Apr 2026 17:25:53 UT

Josh Clark and Veronika Kindred joined developer Damien Filiatrault on the Commit & Push podcast for a conversation that gets concrete about how Sentient Design actually works: the patterns, the architecture, and the design decisions behind intelligent interfaces.

Josh and Veronika walk through the principles of Sentient Design and then get hands-on with examples. They demo Google’s Genie world model where experiences are generated on the fly based on the user’s actions. They show Salesforce’s Generative Canvas, which assembles dashboards based on what you need right now. And they walk through how to make AI translate user intent into a working UI.

Damien brings a developer’s healthy skepticism throughout: What happens when the dashboard rearranges while you’re reading it? How do you debug a UI that’s different for every user? Josh and Veronika’s answers are grounded in real constraints.

The conversation covered a lot of ground:

What the “sentient” in Sentient Design means: interfaces that are aware of context and intent
The principles behind Sentient Design: contextually aware, collaborative, deferential, ambient
Promoting productive humility in systems and productive skepticism in users
The “bespoke UI” design pattern: AI assembling design-system components on demand
The “NPC” design pattern: AI participating as another user in multi-user interfaces
Defensive design: guardrails and graceful recovery when AI stumbles
Why the happy path is over (and what replaces it)
Veronika’s “helpful impatience” with traditional best practices

Quotable

“There is no happy path anymore.” — Veronika Kindred

“We can create genuinely new kinds of experiences when we weave intelligence into the interface.” — Josh Clark

“We want to delegate decisions to AI, not abdicate them.” — Josh Clark

“Part of the Sentient Design philosophy is the ethics around using [AI]: employing things like ‘defensive design’ to make sure that users aren’t being thrown to the wolves by integrating AI into these systems.” — Veronika Kindred

Tune in

Lean Stories: AI as Design Material

Sat, 11 Apr 2026 17:04:01 UT

Josh Clark and Veronika Kindred join Jonathan Bertfield on the Lean Stories podcast for a conversation that connects Sentient Design to the lean startup mindset—and the messy realities of innovation in big orgs. The conversation covers Sentient Design, of course, but also digs into tough questions about working with emerging technology: team culture, failure, and what it actually takes to ship new kinds of products. And naturally, Veronika explains why AI is just like Leonardo DiCaprio.

Throughout, the conversation explores how the lean startup ethos of early, small failures is perfect for expoloring an unpredictable material like AI. But failure isn’t easy to metabolize, and Josh and Veronika dig into the organizational side of innovation: why some companies say they want to be industry-leading but really want to be industry-standard, and why that distinction matters more than most teams admit.

The conversation also gets personal about how this dad-daughter team learns from each other, and how Veronika’s AI-native perspective sharpens Josh’s decades of established best practices. They talk about the importance of allowing failure, as well as the damage of communication failures in the teams they work with.

The episode was thick with lots more insights:

Why “good” is the only worthwhile differentiator in the good/fast/cheap triangle when fast and cheap are commodities.
How AI-powered research can deliver in days what used to take weeks, but you have to be ready to act on the learnings.
The flattening effect: how AI lets marketers, designers, and engineers participate in each other’s disciplines.
Why organizations need to be honest about where they actually want to innovate versus where they want to be safe.
The system prompt as a shared space that does triple duty as business requirements, design spec, and technical document.
Communication as the root cause of tech debt and stalled innovation.
Why AI makes it even more important to start with real users and real research.
Watch or listen on YouTube

An Anti-AI Moral Stance?

Josh Clark — Sat, 11 Apr 2026 14:54:27 UT

AI is powerful and strange, but the technology itself is also deeply fraught. I’m generally optimistic about what AI will unlock, but let’s not be naive: AI threatens steep environmental, social, and creative costs. It raises urgent questions about copyright, labor, and what it means to make things. The cynical deployment of AI wrings out efficiencies at human expense. The creators of the leading AI models have engaged in the purest form of extractive capitalism to date, slurping up all the world’s content without compensating its creators. So yeah, that’s a lot.

Mainstream surveys from Pew, Quinnipiac, Gallup, and others show a general unease about trust and consequences with AI, even as usage increases. (A 2025 Gallup study found that 64% of Americans plan to “resist using AI as long as possible.” And indeed, a more recent Pew study finds that 65% don’t use AI much at work.)

But what if your feeling is stronger than unease? What if you find the whole enterprise so immoral that you can find no ethical use for AI?

“Mike in Massachusetts” asked that very question in the Work Friend advice column of the New York Times. The columnist’s pragmatic answer echoes how you might think about living within any system whose foundations or effects you can’t abide (late-stage capitalism, fossil fuels, fast fashion, industrial food,etc.):

What’s your goal in refusing to use A.I.? Saving your immortal soul? Throwing a small wrench in the enormous cogs of capital? Will refusing its use do anything to stop its relentless advancement, or just make you feel righteous?

A.I. boosters and critics alike often talk about the technology in revolutionary — if not apocalyptic — terms, which can make the risks of using A.I. (or not) feel overwhelming. To use A.I. feels like participating in morally bankrupt process of technological exploitation, on the one hand; to refuse it feels like consigning yourself to obsolescence and unemployment.

But the stakes are just not that high. If you decline to use A.I., you may end up working a bit harder than your peers, but the process of adopting A.I. will occur over a long timeline, in stops and starts, and the risk of being left fatally and irreversibly behind is low. At the same time, your individual decision to use it won’t make a huge difference to the tech companies you’re wary of on their march to economic domination.

Which is why my recommendation is to refuse the choice you’re offering yourself. Why not use A.I. in circumscribed and deliberate ways to make your work life better? You won’t be refused entry to heaven because you prompted Claude to organize a data set and saved yourself some time and eye strain.

Meanwhile, you could channel your outrage into organized political action rather than an individual ethical choice by joining and supporting climate or labor advocacy groups that are thoughtfully working on the issue. If you’re morally against A.I., you owe yourself and the people in your community more than just a private protest.

An Anti-AI Moral Stance? | New York Times

This Is Running

Josh Clark — Sat, 11 Apr 2026 13:51:48 UT

This Is Running (Batsford, 2026)

If you’re a runner (or just running-curious), you’ll love the beautiful, thoughtful new book This Is Running by Raziq Rauf, author of the wonderful Running Sucks newsletter.

Raz was kind enough to send me a copy and even kinder to include me in the book (an interview about the origin and impact of Couch to 5K). But that’s not why I’m recommending it.

This Is Running is both a wonderful artifact of cultural research—UX researchers take note!—and a love letter to a world that Raz clearly adores, like so many of us. It’s an expansive exploration of why we run: What on earth motivates anyone not only to do this hard thing but to fall in love with it?

The book applies many lenses to that question: community, consumer culture, technology, identity, history, and place. Raz takes you from childhood playgrounds to high-mountain trails to everyday run clubs to the inside of tech labs and apparel companies. It goes deep into all the rituals and emotions that runners invest in the sport, individually and with others. It feels like every kind of runner is represented here.

It’s also a gorgeous book, well-designed and full of striking photography. It’s one of those rare books that is BOTH a cover-to-cover bedside read and a pride-of-place object on the coffee table.

I’ve already read the thing twice. I love it. Highly recommend.

This Is Running | Amazon

Look Up from Your Tools: AI for Product over Production

Josh Clark — Fri, 10 Apr 2026 16:26:17 UT

Designers coding. Product managers shipping. Developers running hot. Figma to code, code to Figma. Everyone’s atingle about what AI is unlocking in the production process.

But friends, look up from the tools for a sec. There’s a much bigger opportunity for designers, products, and businesses. We’re still really early on the value curve here.

Industries and organizations adopt new technology in a progression, each stage unlocking more value than the last.

The five stages of technology adoption.

Invent and bloom are the meaningful stages that most companies haven’t yet reached with AI. Not all organizations (and not all technologies) make it through all five stages, and that’s okay. But everyone should be thinking about what that path might look like—and what’s blocking you from the next stage.

1. Retool

The first stage focuses on automation and productivity by applying the technology to current processes and products. It fits easily into practitioners’ mental models for how work is done. And it appeals to business leaders with the promise of immediate return by wringing out new efficiencies.

This is where most of the digital product industry is focused with AI right now. Developers adopt Claude Code to churn out code ten times faster than before. Designers quickly build working prototypes with more interaction and greater fidelity. Design system teams align Figma and code with new speed and accuracy, while automating front-end code for developer handoff. Teams ship more quickly.

In this retool stage, the shape of the output and the overall process remains the same, but we accelerate it with the new technology. This is good work and has real value. It feels mind-blowing when you first see it. Follow Big Medium’s longtime collaborator TJ Pitre to see him reinvent design system tooling and process on the daily. Nobody is doing more on this front right now than TJ and his team at Southleft. It’s great stuff, powerful and immediately useful. But there’s more.

2. Reorganize

Soon enough, transformative tools start to bend or break existing roles and processes, revealing new opportunities.

The classic example: As factories adopted electric motors, it no longer made sense to use older floor layouts organized around a central steam engine. Factories reorganized to put motors at individual machines, rearranging the floor for workflow efficiency, and eventually moving to assembly lines. The technology shift reorganized the whole workflow and often the nature of the work.

Product organizations have only begun wrestling with this with AI. What happens when anyone can code? Or when developers move faster than designers? It flips the traditional understanding of where the expensive part of product design sits. Process and roles have to change to take advantage of the new tools. This is challenging, uncomfortable, and sometimes painful.

The naive move here is to eliminate roles.

The naive move here is to eliminate roles: “we don’t need designers anymore” (or coders or product managers, depending on your perspective). Even more dangerous, I’m seeing an initial tendency for teams to fragment into independent creators instead of collaborators. When everyone can make a thing quickly on their own, you get new kinds of silos. People spin off with different assumptions, different prototyping tools, different design conventions, different codebases. The “army of one” looks like an opportunity, but it actually means you get a million armies, and that’s impossible to wrangle.

Here’s the bigger production opportunity: Now that everyone can use AI to speak code, we can compile our work into a common workspace to explore and make together. At Big Medium, product managers and designers now do their work in the same code repo as developers, contributing requirements and prototypes as new branches. Meanwhile, that shift means everyone also works in the same problem space, too. The handoff waterfall has finally disappeared for us as development, design, and product all riff together through tight iterative cycles from start to finish. (There’s lots more to say about this, and we’ve started doing workshops with our clients to help them work this way, too.)

But this is still only about production process, which is just a means to an end. Only one deliverable matters: the thing we actually ship. The big leap to make with AI is shifting the thinking from production to product.

3. Invent

What are the entirely new things we can make with this technology that we couldn’t do before? What new experiences does it enable? Instead of squeezing value through new efficiencies, how might we grow value for business and customer alike by creating extraordinary new products and services?

Instead of focusing on new tools for old products, these questions shift the thinking to what’s next. And that’s where things get really exciting. This is where AI can elevate design through invention rather than replace it with automation. Design imagination and insights are the scarce resources that become even more essential.

Design imagination and insight are the scarce resources that become even more essential.

A vanguard of companies across industries, in startups and enterprises alike, have begun demonstrating what AI-powered products can be. Cisco with its AI canvas. Miro with its NPC agents working as users (“sidekicks”) on the board. Intercom with its Fin customer service agent working the phones. Even stalwarts like Salesforce and its generative dashboards.

But it’s early, and many companies are still focused on creating text-based agent and chat experiences with AI. Or worse, designers “add AI” by strapping a chat sidebar onto the side of their app. It’s like bolting a spoiler onto a beat up Honda Civic; it’s performative novelty dressed up as innovation.

Early automobiles were horse carriages with steam engines bolted on. It takes effort to imagine the new form a technology unlocks, but it’s rarely the same as what came before.

So much more is possible when you weave intelligence into the interface itself. It takes time to coax out the possibilities for a new design material like AI. It took well over a decade to figure out what mobile “wants.” For years, mobile apps were just stunted versions of desktop software. Slowly designers learned that mobile wanted to be something else entirely: single-tap experiences like Uber, card-like feeds like Instagram, and camera-based interfaces like TikTok.

We’re still learning what intelligent interfaces will become. This is a time for wild ideas, for taking leaps beyond the familiar or incremental. Let’s look up from our tools and consider what we might make with them. This is where the big creative and business opportunities lie.

At Big Medium, we’re working this stage hard. In our client work, we’re creating intelligent interfaces that reinvent journalism for a post-article generation. We’re delivering AI-backed research canvases that bloom with data visualizations and spawn agents that collaborate on visual research. We’re building new publishing interfaces to reinvent digital marketing for one of the world’s biggest pharma companies.

Sentient Design (Rosenfeld Media, 2026)

This stage requires hefty doses of mad science, but it’s rewarded especially by thoughtful methodology.

Sentient Design is our practice for creating intelligent interfaces: experiences with the awareness and agency to adapt to your users in the moment. These are dashboards that design themselves, agents that show up as “just another user” in a multiplayer UI, apps that manifest on demand, and much more. We developed a whole framework and methodology around Sentient Design to help support our exploration and invention, with lots of concrete examples. We identified 14 experience patterns that give us archetypes for our work.

We created Sentient Design because we needed it. We’re sharing it because we think you might need it, too. Veronika Kindred and I wrote a new book about it: Sentient Design: Crafting Intelligent Interfaces with AI (Rosenfeld Media). The book is the first comprehensive map of the territory, exploring and naming an expansive set of experience models that go way beyond text dialogue. We think you’ll enjoy it, and we hope you find it useful.

The invent stage is exciting and creative. The industry has spent the last decade focused on consolidating and streamlining design through design systems and the like. It was necessary work for operations, but product invention stagnated. Now we’re finally turning back to product innovation. This is the important corner for companies to turn now, because this stage unlocks the next.

4. Bloom

When you get it right, the new product changes what you do entirely. It creates a new way of relating to customers, or realizing the latent value of your service. A new line of business blooms.

Getting to this stage is hard to predict because it’s about creating a new market and marshaling your organization and capabilities in new ways. It can be designed, but good fortune helps here. When lightning strikes, the magic happens.

When Netflix created a streaming service to replace their DVD shipping, they suddenly got a ton of viewing data. That product innovation transformed the company from a movie delivery shop to a data warehouse for taste. That in turn gave it the foundation to turn into a media studio.

Great products have a habit of taking a company into new (and sometimes unexpected) directions. We haven’t started seeing this happen quite yet with AI-powered products, since the innovation of the prior invent stage is only beginning, but we will. And when we do, it won’t just be companies that change; some whole industries will likely shift, too. We just don’t know where yet. That’s the final stage.

5. Disrupt

Once in a great while, blooming a new line of business is enough to reshape a whole industry: the familiar examples of Uber and taxis, or AirBnB and hotels. The disruption is often surprising to most, especially the incumbent industry. Nobody would have thought the internet was a threat to yellow cabs or the hotel industry. And yet.

This is classic Clayton Christensen stuff around market disruption, and I won’t go too far here. Disruption isn’t the goal for most companies, though they would be wise to look out for disrupters around them. For those who pull it off, it changes the landscape for everyone else in the industry.

You have to use it to understand what you can make with it.

Either way, it all begins with invention of that new product, and that means understanding the underlying design material of the new technology. That’s why even the early stages—where most companies find themselves with AI—are important, too. Now is when companies are starting to use AI to understand its grain: what it’s good at, bad at, and just plain quirky. You have to use it to understand what you can make with it.

A call to action

For all of you who are exploring and applying new AI tools, keep going. You’re doing the important work of getting familiar with this strange and powerful new technology.

But also, push farther. Use AI to elevate product, not just production. The product and what happens next are the things that matter—and the place where design insight and creativity will realize the biggest value. In rare and special cases, that new product vision will even bloom into a new business or reinvent the industry.

Faster production is quickly becoming table stakes. What we create will change everything. Think big, and go make something amazing.

Big Medium helps teams design what’s next. We do product strategy and experience design to help our clients unlock new value for both the business and the customer. How can we help you?

When Using AI Leads to ‘Brain Fry’

Josh Clark — Tue, 07 Apr 2026 14:02:10 UT

A BCG study of US-based workers found that intensive oversight of AI agents can cause cognitive exhaustion that the researchers call “AI brain fry.” The researchers shared their results in Harvard Business Review:

Participants described a “buzzing” feeling or a mental fog with difficulty focusing, slower decision-making, and headaches. This AI-associated mental strain carries significant costs in the form of increased employee errors, decision fatigue, and intention to quit. … Many participants used the words “fog” or “buzzing.” They described intensive back-and-forth with the tools, followed by an inability to think clearly, like a mental hangover, comprised of difficulty focusing, slower decision-making, and headaches, requiring several to physically step away from their computer to “reset.”

The researchers found that brain fry is linked closely to the amount of oversight and direct monitoring the agents required: a high rather than low degree of oversight caused 14% more mental effort on the job, predicted 12% more mental fatigue, and predicted 19% greater information overload.

So even as productivity increases with agents churning out work, the personal cost of monitoring that work is high. The study found increased fatigue when the use of AI increases workload—producing more simply costs more—and also when users multitask across tools. “As employees go from using one AI tool to two simultaneously, they experience a significant increase in productivity. As they incorporate a third tool, productivity again increases, but at a lower rate. After three tools, though, productivity scores dipped.”

A senior engineering manager in the study described the effect this way: “It was like I had a dozen browser tabs open in my head, all fighting for attention. I caught myself rereading the same stuff, second-guessing way more than usual, and getting weirdly impatient. My thinking wasn’t broken, just noisy—like mental static. What finally snapped me out of it was realizing I was working harder to manage the tools than to actually solve the problem.”

But the kind of task matters. When AI was used to replace routine or repetitive tasks—what the researchers call toil—burnout scores were 15% lower than for those who didn’t use AI that way . The researchers were careful to delineate the difference between burnout (emotional fatigue) and brain fry (mental fatigue). Using AI for unpleasant tasks still caused mental fatigue, but improved emotional state: higher work engagement, more positive associations with AI, and more social connection with colleagues.

As a designer of intelligent interfaces, my takeaway is that people need help managing the overload of extremely productive but not entirely reliable agents. This help might be delivered through a mix of improved experience, tools, and processes that make oversight less effortful—or alternatively that help people regulate and reduce how much they engage in the first place.

“Just as we have norms for spans of control for managing humans, so, too, limits need to be defined for human + agent oversight and for agents alone,” the researchers wrote. “Tools that require less intense attention or working memory, which instead support creative mind wandering, foster social engagement, or scaffold skill development can produce even more business value but sustainably, while encouraging innovation, fostering growth, and sparking joy for users.”

That sounds like a design challenge.

When Using AI Leads to “Brain Fry” | Harvard Business Review

How Many Products Does Microsoft Have Named ‘Copilot’?

Josh Clark — Mon, 06 Apr 2026 11:20:58 UT

Names matter. That’s especially true when we’re all trying to establish shared meaning in something new.

Alas, at Microsoft, the name “Copilot” means very little except for a hand-wavey gesture in the direction of “has AI.” Tey Bannerman is doing the heroic work of tracking down the number of products and features named Copilot, and he’s up to 80 and counting.

“There are now Copilots inside Copilots, Copilots for other Copilots, and a physical Copilot key on your keyboard for summoning them,” Bannerman writes. Microsoft applies the label to apps, features, platforms, a keyboard key, and an entire category of laptops. When everything is Copilot, nothing is Copilot.

This is a marketing problem for Microsoft, but it also points to a general fuzziness problem in the industry. The meanings of terms like “agent,” “copilot,” even “AI” itself have grown so diffuse as to be useless for common understanding even within discrete teams or organizations. (Somehow, even traditional automation is called agentic lately, but that’s a post for another time.)

One of the goals that Veronika and I had for writing the Sentient Design book was to create crisp vocabulary and definitions for different experience types. For what it’s worth, “copilot” is one of the four fundamental “postures” in Sentient Design from which all intelligent interfaces derive. Our definition:

Copilots provide continuous, context-aware assistance throughout an activity.

This always-on stance of constant monitoring and assistance is different from the other postures of tool, chat, and agent. Posture determines the system’s manner and relationship with the user. More than just differences in functionality, these postures describe the different ways users collaborate with intelligent interfaces:

People use tools.
People talk to chat.
People delegate to agents.
People are backed by copilots.

From those four postures, over a dozen novel experience patterns emerge. Sentient Design describes them all, along with the emerging UI and interaction patterns to make them useful.

When you’re making something new, apply some rigor to what you call it. A crisp definition not only helps you describe the thing, it helps you shape what you make—and make it distinct from its neighbors. It tells you (and your customers) not only what it is, but what it’s not.

How many products does Microsoft have named ‘Copilot’? I mapped every one | Tey Bannerman

Claude Dispatch and the Power of Interfaces

Josh Clark — Wed, 01 Apr 2026 11:50:20 UT

Ethan Mollick reviewed the research that chat interfaces introduce heavy effort that undermines complex, specialized work. His conclusion is that the future of AI-powered interfaces is specialized interfaces built on the fly in response to user intent and context:

Instead of having companies build a specialized interface for every kind of work, the AI generates the right interface on the fly. I suspect the future isn’t one interface to rule them all. It’s AI that generates the right interface for the moment, an agent on your desktop, a chart in a conversation, a custom app to solve a problem. We’re moving from adapting to the AI’s interface to the AI adapting its interface to you.

AI capability has been running ahead of AI accessibility. The models have been smart enough to do extraordinary things for a while now, but we’ve been making people access that intelligence through chatbots. And, as that cognitive load research shows, the chatbot format is actively working against them. As interfaces improve, we’re going to see what happens when a much larger number of people can actually use what AI is capable of. Every new interface that closes even part of that gap will feel like a leap in AI capability, even when the models haven’t changed (though they are still changing). My guess is that a lot of the “AI disappointment” people sometimes express comes not from the AI being bad, but from the interfaces being wrong. We built one of the most powerful technologies in recent history and then made people access it by typing into a chat window. That will change soon.

Friends, this is what Sentient Design is all about, and Veronika Kindred and I wrote an entire book about it, now available for pre-order.

(This isn’t the end of interface design, by the way, far from it. It’s an entirely new era of design. It’s super exciting and twisty and fun, and you’re needed more than ever to help make it work.)

Claude Dispatch and the Power of Interfaces | One Useful Thing

Sentient Design Workshop Courses

Thu, 26 Mar 2026 12:45:00 UT

Sentient Design: Craft Intelligent Interfaces with AI

Two-Day Online Workshop Course: Join product design leaders and Sentient Design authors Josh Clark and Veronika Kindred to explore the already-here future of intelligent interfaces and radically adaptive experiences.

Sentient Design is the practice of creating experiences that are aware of context and intent to adapt to your users in the moment. You’ll learn the framework and techniques to design them responsibly by prototyping an experience over the course of two days.

This hands-on, zero-hype workshop provides measured, practical techniques that you can use today—like right now—to imagine surprising new experiences or to improve existing products. You’ll go way beyond text-based agents and chat to explore the full landscape of intelligent interfaces through four key postures—tools, agents, copilots, and chat—plus a dozen new experience patterns you can put to use immediately.

Who Should Attend

This workshop is perfect for designers, product owners/managers, and design-minded developers who want to understand AI as a design material, not just a tool—AI for product, not just production. If you’re curious about how to make AI work for people (instead of the other way around), this is for you.

What You’ll Learn

Hands-On Prototyping

Prototype a new product: identify, imagine, and bring to life AI-powered features that solve real problems (not just “because AI”)
Get your hands dirty working with models directly to learn their strengths and quirks
Wire interface to intent by using a LLM to control the behavior of your prototype

Design Patterns & Practices

Explore radically adaptive interfaces that are conceived in real-time based on user context and intent
Discover emerging UX patterns that go beyond “slap a chatbot on it”
Adopt techniques for grounded, predictable experiences when your interface has a mind of its own
Guide user behavior to match the system’s ability

Responsible AI Design

Use responsible practices that build trust and transparency
Balance opportunities and risks in AI-powered experiences

What You’ll Need

An open mind
A healthy mix of imagination and skepticism

No prior AI or machine learning experience is required. You bring the human intelligence, and we’ll supply the artificial kind.

Meet Your Instructors

Josh Clark and Veronika Kindred are authors of Sentient Design , the forthcoming book from Rosenfeld Media. Josh is a 30-year design veteran and principal of design agency Big Medium. Veronika is designer and researcher at Big Medium. Both solve problems and design what’s next alongside some of the world’s biggest companies.

Register

May 13–14, 2026

11:00am – 3:00pm ET Check your time zone
$895 ($995 starting April 23)

Training a Team?

Email us about discounts for five or more.

Plan private team training (online or in-person).

Questions?

Contact josh@bigmedium.com for more information.

“I Suppose You Would Call It an Interface for the User”

Josh Clark — Sat, 14 Mar 2026 20:56:19 UT

Nicholas Evans on LinkedIn:

I have enough skills in my Claude setup that I need something to help me remember them. Maybe we could call it a menu or something . And it would group things in a way that matched my mental model and helped me find things. I suppose you would call it an interface for the user.

Nicholas Evans | LinkedIn

Why AI agents need to learn to read the room

Josh Clark — Sat, 14 Mar 2026 20:43:39 UT

Researcher Genna Bridgeman shared practical findings about how AI interactions are affected by social expectations of the specific communication channel.

Bridgeman is a product researcher for Intercom, the company behind the Fin customer service agent. Fin is remarkably effective at managing routine support tasks, and it does it in live phone conversations, chat, email, and WhatsApp.

Each of those channels has its own etiquette, of course. The ways—and even the reasons—people use those channels create expectations for how info will be delivered. Bridgeman’s research found that when AI didn’t get the etiquette right, the result undermined trust as much as any human faux-pas might:

When interactions felt wrong, users didn’t blame the answer. They questioned the system’s understanding. And once that doubt set in, every subsequent response was judged more harshly.

The core takeaways:

In chat: Brevity, clarity, and structure are more important than completeness.
In email: The absence of a formal greeting and a thorough (even dense) answer can seem dismissive or incomplete.
On the phone: If the agent talks like a bot, users will start talking like a bot by simplifying language and avoiding nuance, which makes the system less effective.
In WhatsApp: Users expect speed and continuity more than traditional chat, with little patience for re-establishing context even in new sessions.

Why AI Agents Need To Learn To Read the Room | Fin Ideas

SaaS Is Dead?

Josh Clark — Sat, 14 Mar 2026 20:05:23 UT

In his newsletter, Benedict Evans deflates the frothy talk that AI agents and assistants will eliminate vast swaths of software. That theory says that people will just tell the computer what they want; if anyone can use AI to spin up their own tool to do the job, then who needs ready-made software? (The theory is especially popular among engineers who already make their own tools.)

When you actually go and look at successful software, the users generally didn’t see the problem, didn’t see how you would solve it, and could not have sat down and thought about what should happen on every screen, how it should get built, and how you get everybody to use it. There is an enormous difference between knowing something about how your company and how your job works and being able to identify a set of problems and a set of workflows and think about how those could be automated.

In other words, the fact that you’re writing the code in natural language doesn’t mean that you don’t have to work out what the computer should do.

As AI’s capabilities grow, figuring out where to aim those superpowers becomes especially important.

Understanding the problem, imagining a fresh solution, and crafting the ideal experience… all of that is really hard to do when you’re burdened by the assumptions and expectations of how you’ve always done it. This might be non-intuitive, but the burden of experience means that the people in the trenches are often the wrong people to design the new solution. DIY tools will only take them so far.

Software design is harder than it looks. So is process design. The new era of intelligent interfaces doesn’t mean that we just toss users into the deep end and hope for the best.

Software and user experience are changing, but they’re not going away. Domain- and context-specific solutions will continue to be critical in order to give people the context and platform to do their work, especially inside complex organizations and processes. The future is much more likely to be AI embedded inside a million bespoke workflows, not a million bespoke workflows jammed into a single AI interface.

For product leaders and designers, that’s a big opportunity. What dramatically new tools and exceptional experiences can we create for our users?

SaaS Is Dead? | Benedict Evans