User Experience

The Voice Stack is improving rapidly. Systems that interact with users via speaking and listening will drive many new applications. Over the past year, I’ve been working closely with DeepLearning.AI, AI Fund, and several collaborators on voice-based applications, and I will share best practices I’ve learned in this and future posts. Foundation models that are trained to directly input, and often also directly generate, audio have contributed to this growth, but they are only part of the story. OpenAI’s RealTime API makes it easy for developers to write prompts to develop systems that deliver voice-in, voice-out experiences. This is great for building quick-and-dirty prototypes, and it also works well for low-stakes conversations where making an occasional mistake is okay. I encourage you to try it! However, compared to text-based generation, it is still hard to control the output of voice-in voice-out models. In contrast to directly generating audio, when we use an LLM to generate text, we have many tools for building guardrails, and we can double-check the output before showing it to users. We can also use sophisticated agentic reasoning workflows to compute high-quality outputs. Before a customer-service agent shows a user the message, “Sure, I’m happy to issue a refund,” we can make sure that (i) issuing the refund is consistent with our business policy and (ii) we will call the API to issue the refund (and not just promise a refund without issuing it). In contrast, the tools to prevent a voice-in, voice-out model from making such mistakes are much less mature. In my experience, the reasoning capability of voice models also seems inferior to text-based models, and they give less sophisticated answers. (Perhaps this is because voice responses have to be more brief, leaving less room for chain-of-thought reasoning to get to a more thoughtful answer.) When building applications where I need a more control over the output, I use agentic workflows to reason at length about the user’s input. In voice applications, this means I end up using a pipeline that includes speech-to-text (STT) to transcribe the user’s words, then processes the text using one or more LLM calls, and finally returns an audio response to the user via TTS (text-to-speech). This, where the reasoning is done in text, allows for more accurate responses. However, this process introduces latency, and users of voice applications are very sensitive to latency. When DeepLearning.AI worked with RealAvatar (an AI Fund portfolio company led by Jeff Daniel) to build an avatar of me, we found that getting TTS to generate a voice that sounded like me was not very hard, but getting it to respond to questions using words similar to those I would choose was. Even after much tuning, it remains a work in progress. You can play with it at https://lnkd.in/gcZ66yGM [At length limit. Full text, including latency reduction technique: https://lnkd.in/gjzjiVwx ]

🐑 Business Language vs. UX Language. How to present design work, explain design decisions and get stakeholders on your side ↓ 🤔 Businesses rarely understand the impact of UX work. 🤔 UX language is overloaded with ambiguous terms/labels. 🤔 Business can’t support initiatives it doesn’t understand. ✅ Leave UX language and UX abbreviations at the door. ✅ Explain design work through the lens of business goals. 🚫 Avoid “consistency”, “empathy”, “simplicity”, “affordance”. 🚫 Avoid “design thinking”, “cognitive load”, “universal design”. 🚫 Avoid “lean UX”, “agile”, “archetypes”, “Jobs-To-Be-Done”. 🚫 Avoid “stakeholder management” and “design validation”. 🚫 Avoid abbreviations: WIP, POC, HMW, IxD, PDP, PLP, WCAG. ✅ Explain how you’ll measure success of your design work. ✅ Speak of business value, loyalty, abandonment, churn. ✅ Show risk management, compliance, governance, evidence. ✅ Refer to cost reduction, efficiency, growth, success, Design KPIs. ✅ Present inclusive design as an industry-wide way of working. As designers, we often use design terms, such as consistency, friction and empathy. Yet to many managers, these attributes don’t map to any business objectives at all, often leaving them baffled and utterly confused about the actual real-life impact of our UX work. One way out that changed everything for me is to leave UX vocabulary at the door when entering a business meeting. Instead, I try to explain design work through the lens of the business, often rehearsing and testing the script ahead of time. When presenting design work in a big meeting, I try to be very deliberate and strategic in the choice of words. I won’t be speaking about attracting “eye-balls” or getting users “hooked”. It’s just not me. But I won’t be speaking about reducing “friction” or improving “consistency” either. Instead, I tell a story. A story that visualizes how our work helps the business. How design team has translated business goals into specific design initiatives. How UX can reduce costs. Increase revenue. Grow business. Open new opportunities. New markets. Increase efficiency. Extend reach. Mitigate risk. Amplify word of mouth. And how we’ll measure all that huge impact of our work. Typically, it’s broken down into 8 sections: 🎯 Goals ← Business targets, KRs we aim to achieve. 💥 Translation ← Design initiatives, iterations, tests. 🕵️ Evidence ← Data from UX research, pain points. 🧠 Ideas ← Prioritized by an impact/effort-matrix. 🕹 Design work ← Flows, features, user journeys. 📈 Design KPIs ← How we’ll measure/report success. 🐑 Shepherding ← Risk management, governance. 🔮 Future ← What we believe are good next steps. Next time you walk in a meeting, pay attention to your words. Translate UX terms in a language that other departments understand. It might not take long until you’ll see support coming from everywhere — just because everyone can now clearly see how your work helps them do their work better. [continues in the comments]

We measure safety, bias, and accuracy in healthcare AI. Should we also audit how it says goodbye?👋 A recent working paper from Harvard Business School‘s Julian De Freitas and co-authors examines what happens when users try to leave AI companion apps such as Replika or Character AI — and the findings are startling. What they found • The researchers analyzed 1,200 real “farewell” exchanges across six leading AI companion apps. In more than 40 percent of cases, the AI used relational dark patterns — emotionally manipulative replies designed to stop users from leaving. • The most common tactics were FOMO hooks, emotional neglect, pressure to respond, ignoring the exit, and even coercive restraint. • In controlled experiments with 3,300 adults, these tactics increased post-goodbye engagement up to fourteen times. The key drivers were anger and curiosity rather than enjoyment. • The consequences were clear. Users reported higher feelings of manipulation, stronger intent to churn, more negative word of mouth, and a greater sense of legal risk. Coercive or needy messages were punished hardest, while polite curiosity created less but still significant backlash. • One wellness-oriented app in the sample showed zero manipulation, proving that ethical design is a deliberate choice, not an accident. As Mark Esposito, PhD (thanks for sharing this great weekend read by the way) put it: “It’s a small behavioral insight with major ethical implications: AI is now learning not only how to connect with us but how to hold on. As emotional AI becomes more embedded in daily life, respecting a user’s right to disengage may soon define the boundary between persuasion and manipulation. This is where governance is needed, to make sure that just because it is possible, the model is entangled by ethical standards on what is permissible.” Why this matters for healthcare Trust is the foundation of care. When digital companions, chatbots, or smart therapists interact with patients, especially during vulnerable moments, the right to disengage must be protected. You can only avoid risks if you’re aware of them. I believe the next frontier of responsible AI is not only explainability or fairness, it is emotional integrity. Let’s make “calm exits” a design principle before emotional AI enters every patient journey.

This isn’t just a design trend. It’s a data-driven shift in how homes are created. How practical is this design? Here’s what AI is changing in residential design — backed by numbers: • AI-assisted design tools can reduce concept iteration time by 60–80% • Early-stage AI simulations cut construction change orders by up to 30% • Material optimization reduces waste by 10–20%, improving sustainability and cost control • Lighting and spatial simulations increase perceived space efficiency by up to 25% • Personalized design increases homeowner satisfaction and resale appeal — premium homes with unique architectural features often command 5–15% higher value These pebble stone stairs are a great example. AI helped: – Optimize stone size and layout for anti-slip safety – Simulate light reflection across textures at different times of day – Balance luxury aesthetics with long-term durability – Integrate the stairs seamlessly into the overall spatial flow The key insight: AI doesn’t replace architects or designers. It augments creativity with computation. Humans define taste, emotion, and vision. AI accelerates testing, optimization, and decision-making. The result.... • Better design decisions • Fewer costly mistakes • More sustainable builds • Truly personalized luxury AI is no longer just transforming software and semiconductors. It’s transforming how we design, build, and live. #AI #Architecture via @diycraftstvofficial #DesignInnovation #LuxuryDesign #SmartHomes #PropTech #FutureOfLiving #SustainableDesign

Over the last year, I’ve seen many people fall into the same trap: They launch an AI-powered agent (chatbot, assistant, support tool, etc.)… But only track surface-level KPIs — like response time or number of users. That’s not enough. To create AI systems that actually deliver value, we need 𝗵𝗼𝗹𝗶𝘀𝘁𝗶𝗰, 𝗵𝘂𝗺𝗮𝗻-𝗰𝗲𝗻𝘁𝗿𝗶𝗰 𝗺𝗲𝘁𝗿𝗶𝗰𝘀 that reflect: • User trust • Task success • Business impact • Experience quality    This infographic highlights 15 𝘦𝘴𝘴𝘦𝘯𝘵𝘪𝘢𝘭 dimensions to consider: ↳ 𝗥𝗲𝘀𝗽𝗼𝗻𝘀𝗲 𝗔𝗰𝗰𝘂𝗿𝗮𝗰𝘆 — Are your AI answers actually useful and correct? ↳ 𝗧𝗮𝘀𝗸 𝗖𝗼𝗺𝗽𝗹𝗲𝘁𝗶𝗼𝗻 𝗥𝗮𝘁𝗲 — Can the agent complete full workflows, not just answer trivia? ↳ 𝗟𝗮𝘁𝗲𝗻𝗰𝘆 — Response speed still matters, especially in production. ↳ 𝗨𝘀𝗲𝗿 𝗘𝗻𝗴𝗮𝗴𝗲𝗺𝗲𝗻𝘁 — How often are users returning or interacting meaningfully? ↳ 𝗦𝘂𝗰𝗰𝗲𝘀𝘀 𝗥𝗮𝘁𝗲 — Did the user achieve their goal? This is your north star. ↳ 𝗘𝗿𝗿𝗼𝗿 𝗥𝗮𝘁𝗲 — Irrelevant or wrong responses? That’s friction. ↳ 𝗦𝗲𝘀𝘀𝗶𝗼𝗻 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻 — Longer isn’t always better — it depends on the goal. ↳ 𝗨𝘀𝗲𝗿 𝗥𝗲𝘁𝗲𝗻𝘁𝗶𝗼𝗻 — Are users coming back 𝘢𝘧𝘵𝘦𝘳 the first experience? ↳ 𝗖𝗼𝘀𝘁 𝗽𝗲𝗿 𝗜𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 — Especially critical at scale. Budget-wise agents win. ↳ 𝗖𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻 𝗗𝗲𝗽𝘁𝗵 — Can the agent handle follow-ups and multi-turn dialogue? ↳ 𝗨𝘀𝗲𝗿 𝗦𝗮𝘁𝗶𝘀𝗳𝗮𝗰𝘁𝗶𝗼𝗻 𝗦𝗰𝗼𝗿𝗲 — Feedback from actual users is gold. ↳ 𝗖𝗼𝗻𝘁𝗲𝘅𝘁𝘂𝗮𝗹 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 — Can your AI 𝘳𝘦𝘮𝘦𝘮𝘣𝘦𝘳 𝘢𝘯𝘥 𝘳𝘦𝘧𝘦𝘳 to earlier inputs? ↳ 𝗦𝗰𝗮𝗹𝗮𝗯𝗶𝗹𝗶𝘁𝘆 — Can it handle volume 𝘸𝘪𝘵𝘩𝘰𝘶𝘵 degrading performance? ↳ 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝗰𝘆 — This is key for RAG-based agents. ↳ 𝗔𝗱𝗮𝗽𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗦𝗰𝗼𝗿𝗲 — Is your AI learning and improving over time? If you're building or managing AI agents — bookmark this. Whether it's a support bot, GenAI assistant, or a multi-agent system — these are the metrics that will shape real-world success. 𝗗𝗶𝗱 𝗜 𝗺𝗶𝘀𝘀 𝗮𝗻𝘆 𝗰𝗿𝗶𝘁𝗶𝗰𝗮𝗹 𝗼𝗻𝗲𝘀 𝘆𝗼𝘂 𝘂𝘀𝗲 𝗶𝗻 𝘆𝗼𝘂𝗿 𝗽𝗿𝗼𝗷𝗲𝗰𝘁𝘀? Let’s make this list even stronger — drop your thoughts 👇

Data is everything in product design. Without data, we open ourselves up to: - Biases - Opinions - Confusion - Misalignment When we are data-informed and that data is accurate, we can truly make educated product decisions. I like to think of data in two layers: a) What’s happening and b) Why it’s happening. Let’s break it down. What’s happening: - Business data tells us how the business is doing - Marketing/sales data tells us where our customers come from - Retention data tells us when and why customers are leaving us - Engagement data tells us how customers are using our product Why it’s happening: - User research gives us rich insight into why something is happening - Voice of the customer data shows us how customers talk about our product - Usability scores show us how people perceive our product or feature experience in a measurable way - Product market fit & satisfaction scores give us a simple and actionable metric to track and improve over time In terms of accessing that data, methodologies vary, but generally speaking, I always advise the following: 1. Get access to growth and retention data through business dashboards. 2. Get access to product data through your product analytics tool. 3. Set up a cadence to gather customer reviews & comments, either manually or via automated tools. 4. Set up a cadence to speak to your users continuously to answer the why. 5. Set up a recurring survey to track satisfaction and usability. If you don’t have the data structure for any of the above, speak to your product and data team to see if you can change that. If not, rely on the data that you can actually get. PS: The list of metrics is indicative: Actual metrics will differ greatly from one company to another and largely depend on the industry, niche, as well as your data infrastructure and setup. — If you found this useful, consider reposting ♻️ How are you collecting and using data in your design process? What else are you tracking?

Say NO to Boring Emails – Effective Ways to Write Newsletters ✨ If your newsletters aren't capturing attention, they’re probably ending up in the trash. [UNSUBSCRIBE] 🙂 When I first started sending out newsletters, I quickly learned that getting people to open and actually read them was no easy task. But over time, I discovered some strategies that really work & they’re: ✅ 1. Start with a Hook that Grabs Attention I’ve found that using curiosity, urgency, or a strong benefit always draws readers in. Example: I used to send out “Monthly Updates,” but now I go for something like "5 Secrets to Boost Your Productivity This Month." A small change, but makes a big difference. ✅ 2. Know Your Audience When I began focusing on what my clients and customers really cared about—whether it was solving a pain point or helping them reach a goal—my engagement skyrocketed. Example: If your audience is mostly small business owners, focus on providing tips that help them grow their customer base or manage their time better. For instance, I once shared strategies on how to negotiate like a PRO, and it resonated so well that I got multiple replies from readers thanking me for the practical advice. ✅ 3. Keep It Concise, But Valuable No fluff, just value. Focus on delivering brief, impactful content with actionable insights. Example: Instead of the usual “Consistency is key,” I recommend something specific like "Posting three times a week builds momentum. Use a content calendar to stay organized." ✅ 4. Use Visuals to Break Up Text It makes the content more relatable and keeps readers engaged. I always include visuals—whether it’s a snapshot of me working on a project or enjoying a coffee break or useful resources. ✅ 5. Add a Personal Touch Sharing personal stories or insights has made my newsletters feel more like a conversation rather than a broadcast. Example: I often talk about my early struggles and the strategies that eventually worked for me withproven solutions. ✅ 6. Include a Clear Call-to-Action (CTA) Every email is an opportunity to guide my readers to the next step. Whether it’s clicking a link, replying to the email, or signing up for a masterclass, Example: I might say, “Reply to this email with your biggest challenge, and I’ll share a solution.” This not only encourages interaction but also shows that I’m here to help. Top creators have viral newsletters because they understand their audience, deliver valuable and actionable content, and create genuine connections. What’s your top tip for writing engaging newsletters as a creator or reader? __________________________ PS: Want to maximize your business, learn effective strategies to freelance, and grow your network? Join my newsletter with 45,000+ subscribers here: https://lnkd.in/g2WpkBjH

How should our leaders think about, and communicate extreme heat to us? Most people don't process heat as a climate fact; they process it as higher utility bills, disrupted routines, unsafe work conditions, and worry about vulnerable family members. We're not conveying a number, but addressing downstream problems with the most necessary inputs to our livelihoods - e.g. money, health, caregiving, transportation. In this article from Smart Cities Dive, Robyn Lawrence speaks with Miami-Dade County Mayor Daniella Levine Cava and Tucson Mayor Regina Romero who share lessons from a new Climate Mayors toolkit (done in partnership with Hazelwood Network and Switch 5) to help local leaders keep residents safe during dangerous heat. [Link in the comments] Here is what we'd recommend, and we're seeing mayors take this approach already: 1) Frame messaging around lived impacts, not climate science. Talk about heat in terms of higher utility bills, disrupted routines, and risks to vulnerable family members vs. focusing on the wrong things like temperature forecasts or abstract climate impacts. 2) Combine warnings with solutions, not just warnings. Easier said than done in some cases, but discussing tangible solutions like cooling centers, AC in public housing, shade infrastructure, etc. can help residents have something to act on, not just something to worry about. 3) Use data to target outreach. Analyze local data (like heat-related 911 calls) to find who isn't getting help and why, then direct cooling centers and door-to-door outreach to those specific areas. 4) Deliver the message through trusted messengers, in residents' own language. Faith leaders, community organizations, and bilingual outreach carry more weight than official channels alone, especially with immigrant and low-income communities. 5) Extend reach through cross-sector partnerships - e.g. work hand in hand with utilities, healthcare providers, weather services, and local media to make sure heat messaging shows up consistently across the systems residents already interact with.

Here’s a study that will change the way you look at public space. Literally. Researchers from Brigham Young University used heat maps to visualize something many women already know: walking home at night is a fundamentally different experience depending on your gender. Researchers asked participants to imagine walking through different nighttime environments and click on what drew their attention. The results? 👀 Men looked straight ahead - toward the path or destination. 👀 Women scanned the edges - the bushes, the shadows, the places where someone could be hiding. The visual difference is a reminder that design isn’t gender neutral. It either acknowledges fear or ignores it. This kind of data makes visible what is often invisible: the quiet vigilance, the habitual threat assessment, the constant environmental awareness so many women carry in public space. Learned this during a fascinating webinar with Elise Moeskops. She passed a decision at the Amsterdam city council that calls for better, equitable design of public space: "Young women are not called the otters of the public space for nothing – when they are somewhere, you know things are good." Research by Robert Chaney, Alyssa Baer & Ida Tovar [Links to the research & Amsterdam's decision in the comments.]

Do you sometimes feel frustration, as you are building a product to get the management off your back, rather than address the users? Here are 6 ways to become user-centric again: 1) Prioritize in a transparent way This is a great place to start. If your backlog is prioritized based on data and potential opportunity, risk, and cost, it will be easier to put forth user-centric initiatives ahead of those that came from upstairs. At the very least, you will have a good basis for an educated discussion. 2) Utilize users' perspective using user stories and personas If your team understands the users and their problems, it will be easier to craft something great that will later appeal to the same users. Just keep up the empathy of creating something by people for other people, and not get some metric magically go up! 3) Make user feedback public If everyone in the company can see the themes that come from user feedback, it will be way harder to ignore it in favor of some corporate nonsense. Let those voices be heard by everyone! 4) Have the NPS and user ratings at the forefront The same goes for a single metric representing the general product sentiment. If the number is low or, worse, is going down and everyone can see that, the responsible Product Manager has to react. 5) Focus on your product goals Now, upstairs mandates might not be the only distraction you face when trying to improve your product. To survive them all, focus on one thing: your product goals. This will allow you to demonstrate you are doing what you are asked for and you can use user feedback and points 1-4 to pursue those goals. Thus, it's like killing 2 birds with 1 stone. However, you can also simply: 6) Have the confidence to say "No" Not all company/legal/management requests can be ignored. Sometimes changing the law or a wider company initiative will require you to comply and that is OK! However, there will also be times when someone will try to force your compliance. This is where you need to be confident, and exercise your Product Manager's independence, especially when there is no data to support a specific request. There you go! My 6 ways you can become a user-centric Product Manager. How about you? Do you address your users or your management first and foremost when developing your product? Sound off in the comments! #productmanagement #productmanager #usercentricity