August 5, 2025 Smashing Newsletter: Issue #519
This newsletter issue was sent out to 188,247 subscribers on Tuesday, August 5, 2025.
Editorial
We’ve been reminded of it a thousand times. Slowly but surely, AI will take over our role and our work — and if it’s not AI, then other people who have adopted, embraced, and used AI will do that. But personally, I respectfully disagree. I don’t think that any AI can out-care, out-love, and out-perform the human qualities that we, people, bring to the table.
For any technology to be useful, it must be used, and that means that it must deliver value to people and align with business needs. That role — the orchestration of AI experiences — is something that we now have to learn, to create products that people need and love and care about. And I just find it very difficult to see it being done by AI alone any time soon.
This newsletter is about that: the design patterns, the guidelines, accessibility considerations, and an AI search optimization guide on how to orchestrate AI experiences and make them more useful and helpful. Hopefully, you’ll find some useful gems in there. And: we have Smashing Meets AI (Aug 27) on just that. Get your free ticket!
On the Smashing side of things, we are taking it a bit slower this couple of weeks — with a few small and big events that we are preparing for in autumn:
- Build Interactive, Accessible Components, with Stephanie Eckles
- UX Strategy Masterclass, with Vitaly Friedman
- SmashingConf Freiburg 2025 🇩🇪 (only 7 tickets left!)
- In-person UX workshops in Antwerp 🇧🇪 and Madrid 🇪🇸
- SmashingConf New York 2025 🇺🇸
- SmashingConf Amsterdam 2026 🇳🇱
Wishing you a wonderful week ahead, everyone, and we can’t wait to see you online or in-person!
1. Common AI Product Issues
Adding a chat panel to an app is probably the most common kind of AI implementation we see in products these days. But these open-ended interfaces bring along quite some issues, and, as it turns out, they are often the same across products.
In his article “Common AI Product Issues,” Luke Wroblewski reflects on the issues he keeps seeing over and over and shares ways to manage them. In particular, he looks into three key problems: capability awareness (people don’t know what an AI product can do), context awareness (people aren’t sure if or how much they should trust a reply), and walls of text that make it hard to extract and recall information. A must-read for anyone who plans to add AI features to their product. (cm)
2. AI UX Patterns
AI is shifting the paradigm from command-based inputs to intent-based inputs. And while some of our existing UX patterns are still applicable now that this shift is happening, we also need new patterns to design effective AI experiences. Luke Bennis created a fantastic resource that attempts to close this gap: AI UX Patterns.
AI UX Patterns is a collection of UX patterns tailored to the new reality of AI. Covering everything from basic raw text input to full result regeneration, each pattern comes with an abstracted example that makes it easy to review its core elements and interactions and effectively adapt it to your product’s context. A handy toolkit you might want to keep close.
Bonus: AI Verse Design Patterns, a fantastic growing collection of interaction design patterns and examples by Kshitij Agrawal — just in case you are looking for even more patterns! (cm)
3. AI Accessibility
From how a user provides input to how responses are displayed and how resulting processes flow, chatting with AI is quite a different experience from chatting with people. As such, it also brings along some unique accessibility challenges, particularly for screen reader and keyboard users.
Mike Gower wrote two helpful guides (“Usable AI Chat” and “Catching Up On Accessibility With AI Chat”) in which he dives deep into the accessibility of AI chats and how we can work towards a more inclusive AI experience. A great reminder that even though we call it a “chat,” we shouldn’t assume we already understand the interaction. (cm)
4. Upcoming Workshops and Conferences
That’s right! We run online workshops on frontend and design, be it accessibility, performance, or design patterns. In fact, we have a couple of workshops coming up soon, and we thought that, you know, you might want to join in as well.
As always, here’s a quick overview:
- Building Interactive, Accessible Components with Modern CSS & JS Dev
with Stephanie Eckles. Aug 18–27 - UX Strategy Masterclass UX
with Vitaly Friedman. Aug 20–29 - Accessible Typography for Web & UI Design Masterclass Design
with Oliver Schöndorfer. Sep 11–19 - Behavioral Design Workshop UX
with Susan and Guthrie Weinschenk. Sep 18 – Oct 3 - Dataviz Accessibility Workshop Dev
with Sarah L. Fossheim. Sep 22 – Oct 6 - 🎁 Design Patterns UX Bundle UX
with Vitaly Friedman. Video + UX training. - Jump to all workshops →
5. Designing For AI Engineers
How to design for AI developers? Eve Weinberg and her team at Modular AI have tackled the challenge and built and launched a lot of AI workflows this year. If you, too, are working on integrating AI into your product, Eve shares some helpful best practices and references she has established in the process.
In her post “Designing for AI Engineers: UI Patterns You Need To Know,” Eve summarized guiding principles, patterns, and personas to help designers become more AI literate. You’ll gain insights into six key interfaces that Eve and her colleague Will Rust designed, and with them lots of takeaways for your own AI workflows. (cm)
6. Responsible AI Guidelines
With great power comes great responsibility, so when we decide to incorporate AI into our work, we also need to make sure that we do so responsibly. But what exactly does that mean?
The AI platform ServiceNow defines responsible AI as human-centered AI, i.e., AI that prioritizes human needs, values, and wellbeing. In their Responsible AI Guidelines Handbook, they elaborate further on the principles of responsible AI and share worksheets with key questions you can ask to guide meaningful discussions and decision-making in your team. A wonderful resource to help ensure an AI system respects and enhances the human experience. (cm)
7. AI Search Optimization
With 60% of Google searches now ending without a click, we are facing a new reality: traffic is no longer a decisive factor for success. How do we adapt to that? How do we best optimize our content for AI search? How can we drive AI mentions? These are exactly the questions that Vitaly answers in his practical guide to AI search optimization.
Instead of focusing on traffic any longer, Vitaly suggests focusing on the quality of leads that drive traffic and, most importantly, putting your efforts into building a strong brand. As he points out, the best strategy to drive exposure in AI search is to focus on visibility and delivering value with good, specific content. If actual people find your content helpful and share it, chances are good that AI search engines will find it trustworthy, too. (cm)
8. Meet Accessible UX Research, A Brand-New Smashing Book 📚
In the past few years, we were very lucky to have worked together with some talented, caring people from the web community to publish their wealth of experience as printed books. For our newest book, we have teamed up with Dr. Michele A. Williams: Meet “Accessible UX Research.”
“Accessible UX Research” is your practical guide to making UX research more inclusive of participants with different needs — from planning and recruiting to facilitation, asking better questions, avoiding bias, and building trust. Print shipping in August, eBook available for download later this summer. Pre-order the book, and save off the full price.
That’s All, Folks!
Thank you so much for reading and for your support in helping us keep the web dev and design community strong with our newsletter. See you next time!
This newsletter issue was written and edited by Geoff Graham (gg), Cosima Mielke (cm), Vitaly Friedman (vf), and Iris Lješnjanin (il).
Smashing Newsletter
Front-end, design and UX. Sent out 1× a week.You can always unsubscribe with just one click.