AI For Enhancing User Experience

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 👇

🤖 How To Design Better AI Experiences. With practical guidelines on how to add AI when it can help users, and avoid it when it doesn’t ↓ Many articles discuss AI capabilities, yet most of the time the issue is that these capabilities either feel like a patch for a broken experience, or they don't meet user needs at all. Good AI experiences start like every good digital product by understanding user needs first. 🚫 AI isn’t helpful if it doesn’t match existing user needs. 🤔 AI chatbots are slow, often expose underlying UX debt. ✅ First, we revisit key user journeys for key user segments. ✅ We examine slowdowns, pain points, repetition, errors. ✅ We track accuracy, failure rates, frustrations, drop-offs. ✅ We also study critical success moments that users rely on. ✅ Next, we ideate how AI features can support these needs. ↳ e.g. Estimate, Compare, Discover, Identify, Generate, Act. ✅ Bring data scientists, engineers, PMs to review/prioritize. 🤔 High accuracy > 90% is hard to achieve and rarely viable. ✅ Design input UX, output UX, refinement UX, failure UX. ✅ Add prompt presets/templates to speed up interaction. ✅ Embed new AI features into existing workflows/journeys. ✅ Pre-test if customers understand and use new features. ✅ Test accuracy + success rates for users (before/after). As designers, we often set unrealistic expectations of what AI can deliver. AI can’t magically resolve accumulated UX debt or fix broken information architecture. If anything, it visibly amplifies existing inconsistencies, fragile user flows and poor metadata. Many AI features that we envision simply can’t be built as they require near-perfect AI performance to be useful in real-world scenarios. AI can’t be as reliable as software usually should be, so most AI products don’t make it to the market. They solve the wrong problem, and do so unreliably. As a result, AI features often feel like a crutch for an utterly broken product. AI chatbots impose the burden of properly articulating intent and refining queries to end customers. And we often focus so much on AI that we almost intentionally avoid much-needed human review out of the loop. Good AI-products start by understanding user needs, and sparkling a bit of AI where it helps people — recover from errors, reduce repetition, avoid mistakes, auto-correct imported files, auto-fill data, find insights. AI features shouldn’t feel disconnected from the actual user flow. Perhaps the best AI in 2025 is “quiet” — without any sparkles or chatbots. It just sits behind a humble button or runs in the background, doing the tedious job that users had to slowly do in the past. It shines when it fixes actual problems that it has, not when it screams for attention that it doesn’t deserve. Useful resources: AI Design Patterns, by Emily Campbell https://www.shapeof.ai AI Product-Market-Fit Gap, by Arvind Narayanan, Sayash Kapoor https://lnkd.in/duEja695 [continues in comments ↓]

AI products like Cursor, Bolt and Replit are shattering growth records not because they're "AI agents". Or because they've got impossibly small teams (although that's cool to see 👀). It's because they've mastered the user experience around AI, somehow balancing pro-like capabilities with B2C-like UI. This is product-led growth on steroids. Yaakov Carno tried the most viral AI products he could get his hands on. Here are the surprising patterns he found: (Don't miss the full breakdown in today's bonus Growth Unhinged: https://lnkd.in/ehk3rUTa) 1. Their AI doesn't feel like a black box. Pro-tips from the best: - Show step-by-step visibility into AI processes - Let users ask, “Why did AI do that?” - Use visual explanations to build trust. 2. Users don’t need better AI—they need better ways to talk to it. Pro-tips from the best: - Offer pre-built prompt templates to guide users. - Provide multiple interaction modes (guided, manual, hybrid). - Let AI suggest better inputs ("enhance prompt") before executing an action. 3. The AI works with you, not just for you. Pro-tips from the best: - Design AI tools to be interactive, not just output-driven. - Provide different modes for different types of collaboration. - Let users refine and iterate on AI results easily. 4. Let users see (& edit) the outcome before it's irreversible. Pro-tips from the best: - Allow users to test AI features before full commitment (many let you use it without even creating an account). - Provide preview or undo options before executing AI changes. - Offer exploratory onboarding experiences to build trust. 5. The AI weaves into your workflow, it doesn't interrupt it. Pro-tips from the best: - Provide simple accept/reject mechanisms for AI suggestions. - Design seamless transitions between AI interactions. - Prioritize the user’s context to avoid workflow disruptions. -- The TL;DR: Having "AI" isn’t the differentiator anymore—great UX is. Pardon the Sunday interruption & hope you enjoyed this post as much as I did 🙏 #ai #genai #ux #plg

Product managers & designers working with AI face a unique challenge: designing a delightful product experience that cannot fully be predicted. Traditionally, product development followed a linear path. A PM defines the problem, a designer draws the solution, and the software teams code the product. The outcome was largely predictable, and the user experience was consistent. However, with AI, the rules have changed. Non-deterministic ML models introduce uncertainty & chaotic behavior. The same question asked four times produces different outputs. Asking the same question in different ways - even just an extra space in the question - elicits different results. How does one design a product experience in the fog of AI? The answer lies in embracing the unpredictable nature of AI and adapting your design approach. Here are a few strategies to consider: 1. Fast feedback loops : Great machine learning products elicit user feedback passively. Just click on the first result of a Google search and come back to the second one. That’s a great signal for Google to know that the first result is not optimal - without tying a word. 2. Evaluation : before products launch, it’s critical to run the machine learning systems through a battery of tests to understand in the most likely use cases, how the LLM will respond. 3. Over-measurement : It’s unclear what will matter in product experiences today, so measuring as much as possible in the user experience, whether it’s session times, conversation topic analysis, sentiment scores, or other numbers. 4. Couple with deterministic systems : Some startups are using large language models to suggest ideas that are evaluated with deterministic or classic machine learning systems. This design pattern can quash some of the chaotic and non-deterministic nature of LLMs. 5. Smaller models : smaller models that are tuned or optimized for use cases will produce narrower output, controlling the experience. The goal is not to eliminate unpredictability altogether but to design a product that can adapt and learn alongside its users. Just as much as the technology has changed products, our design processes must evolve as well.

As consumers seek more individual experiences and interactions, companies turn to #AI to deliver 𝙥𝙚𝙧𝙨𝙤𝙣𝙖𝙡𝙞𝙯𝙚𝙙 𝙥𝙧𝙤𝙢𝙤𝙩𝙞𝙤𝙣𝙨 𝙖𝙩 𝙨𝙘𝙖𝙡𝙚. For some time now, companies have been trying to address customer needs through #personalization, using data and analytics to craft more relevant consumer experiences. Using improved analytics models, brands and retailers can better provide valuable offers to micro-communities wherever they want to engage. Meanwhile, #genAI enables marketers to create tailored content that is relevant to those groups. According to McKinsey & Company, marketers should unlock personalization at scale, by upgrading five areas of their #martech stack and processes: 1. Data: by improving #data collection and analysis, marketers can gain deeper insights into customer behaviors and preferences. 2. Decisioning: to develop personalized promotions and content through more robust targeting, companies can also benefit from refreshing their #decision engines with new AI models. 3. Design: a sophisticated design layer that oversees offer management and #content production helps manage the process, fueling both operational excellence and agility. 4. Distribution: achieving true, real-time personalization requires a sophisticated #marketing architecture that delivers seamless and consistent messaging to the right audiences at the right time on the right channel. 5. Measurement: to validate the #ROI of personalization efforts, rigorous incrementality testing, standardized performance metrics, and measurement playbooks are essential. Are there other capabilities or technologies required for marketers to better target promotions and deliver individual content?

LLMs are optimized for next turn response. This results in poor Human-AI collaboration, as it doesn't help users achieve their goals or clarify intent. A new model CollabLLM is optimized for long-term collaboration. The paper "CollabLLM: From Passive Responders to Active Collaborators" by Stanford University and Microsoft researchers tests this approach to improving outcomes from LLM interaction. (link in comments) 💡 CollabLLM transforms AI from passive responders to active collaborators. Traditional LLMs focus on single-turn responses, often missing user intent and leading to inefficient conversations. CollabLLM introduces a :"Multiturn-aware reward" system, apply reinforcement fine-tuning on these rewards. This enables AI to engage in deeper, more interactive exchanges by actively uncovering user intent and guiding users toward their goals. 🔄 Multiturn-aware rewards optimize long-term collaboration. Unlike standard reinforcement learning that prioritizes immediate responses, CollabLLM uses forward sampling - simulating potential conversations - to estimate the long-term value of interactions. This approach improves interactivity by 46.3% and enhances task performance by 18.5%, making conversations more productive and user-centered. 📊 CollabLLM outperforms traditional models in complex tasks. In document editing, coding assistance, and math problem-solving, CollabLLM increases user satisfaction by 17.6% and reduces time spent by 10.4%. It ensures that AI-generated content aligns with user expectations through dynamic feedback loops. 🤝 Proactive intent discovery leads to better responses. Unlike standard LLMs that assume user needs, CollabLLM asks clarifying questions before responding, leading to more accurate and relevant answers. This results in higher-quality output and a smoother user experience. 🚀 CollabLLM generalizes well across different domains. Tested on the Abg-CoQA conversational QA benchmark, CollabLLM proactively asked clarifying questions 52.8% of the time, compared to just 15.4% for GPT-4o. This demonstrates its ability to handle ambiguous queries effectively, making it more adaptable to real-world scenarios. 🔬 Real-world studies confirm efficiency and engagement gains. A 201-person user study showed that CollabLLM-generated documents received higher quality ratings (8.50/10) and sustained higher engagement over multiple turns, unlike baseline models, which saw declining satisfaction in longer conversations. It is time to move beyond the single-step LLM responses that we have been used to, to interactions that lead to where we want to go. This is a useful advance to better human-AI collaboration. It's a critical topic, I'll be sharing a lot more on how we can get there.

We have to internalize the probabilistic nature of AI. There’s always a confidence threshold somewhere under the hood for every generated answer and it's important to know that AI doesn’t always have reasonable answers. In fact, occasional "off-the-rails" moments are part of the process. If you're an AI PM Builder (as per my 3 AI PM types framework from last week) - my advice: 1. Design for Uncertainty: ✨Human-in-the-loop systems: Incorporate human oversight and intervention where necessary, especially for critical decisions or sensitive tasks. ✨Error handling: Implement robust error handling mechanisms and fallback strategies to gracefully manage AI failures (and keep users happy). ✨User feedback: Provide users with clear feedback on the confidence level of AI outputs and allow them to provide feedback on errors or unexpected results. 2. Embrace an experimental culture & Iteration / Learning: ✨Continuous monitoring: Track the AI system's performance over time, identify areas for improvement, and retrain models as needed. ✨A/B testing: Experiment with different AI models and approaches to optimize accuracy and reliability. ✨Feedback loops: Encourage feedback from users and stakeholders to continuously refine the AI product and address its limitations. 3. Set Realistic Expectations: ✨Educate users: Clearly communicate the potential for AI errors and the inherent uncertainty involved about accuracy and reliability i.e. you may experience hallucinations.. ✨Transparency: Be upfront about the limitations of the system and even better, the confidence levels associated with its outputs.

Everyone’s excited to launch AI agents. Almost no one knows how to measure if they’re actually working. Over the last year, we’ve seen brands launch everything from GenAI assistants to support bots to creative copilots but the post-launch metrics often look like this: • Number of chats • Average latency • Session duration • Daily active users Useful? Yes. But sufficient? Not even close. At ALTRD, we’ve worked on AI agents for enterprises and if there’s one lesson it’s this: Speed and usage mean nothing if the agent isn’t solving the actual problem. The real performance indicators are far more nuanced. Here’s what we’ve learned to track instead: 🔹 Task Completion Rate — Can the AI go beyond answering a question and actually complete a workflow? 🔹 User Trust — Do people come back? Do they feel confident relying on the agent again? 🔹 Conversation Depth — Is the agent handling complex, multi-turn exchanges with consistency? 🔹 Context Retention — Can it remember prior interactions and respond accordingly? 🔹 Cost per Successful Interaction — Not just cost per query, but cost per outcome. Massive difference. One of our clients initially celebrated their bot’s 1 million+ sessions - until we uncovered that less than 8% of users actually got what they came for. That 8% wasn’t a usage issue. It was a design and evaluation issue. They had optimized for traffic. Not trust. Not success. Not satisfaction. So we rebuilt the evaluation framework - adding feedback loops, success markers, and goal-completion metrics. The results? CSAT up by 34% Drop-off down by 40% Same infra cost, 3x more value delivered The takeaway: Don’t just measure what’s easy. Measure what matters. AI agents aren’t just tools - they’re touchpoints. They represent your brand, shape user experience, and influence business outcomes. P.S. What’s one underrated metric you’ve used to evaluate AI performance? Curious to learn what others are tracking.

How proactive AI will change UX - 📆 schedule ChatGPT requests! OpenAI has introduced a new task scheduling feature for ChatGPT. This means you can now ask ChatGPT to handle tasks at a future time — like sending you a weekly global news update, recommending a daily personalized workout, or setting reminders for important events. 💡 Why is this interesting from a UX perspective? This shift is a step toward proactive AI — moving from reactive systems (waiting for user input) to anticipatory, context-aware experiences that help users save mental energy and stay on top of their routines. Let’s break it down from a real-life use case - creating daily recipes: I currently eat sugar-free, gluten-free (because I am celiac), and generally low-carb and like to let ChatGPT create recipes for me. I don’t want a fixed meal plan, but I do need flexible, personalized recipe suggestions that fit my nutrition goals. Ideally, I’d want ChatGPT to  → suggest automatically 3-4 recipes daily around 3 PM → send them to me  → and based on my choice adjust future suggestions for the next days based on what I’ve already eaten that week (for balanced nutrients). With the new task feature, this kind of personalized experience could become much much more seamless. I wouldn't need to ask repeatedly — the assistant would learn my preferences over time and adapt its suggestions accordingly. 🎯 What can we learn from this in AI-UX design? 1️⃣ From static interactions to dynamic experiences: We often design AI tools that rely on users asking for something. But this update shows the value of continuous, evolving interactions. Users shouldn’t need to start from scratch every time — systems can proactively adjust to their needs and context. 2️⃣ Mental models of AI assistants: For users to trust AI routines, they need to understand what the assistant will do and when. It’s about designing predictability and transparency in a way that still allows for flexibility and spontaneity. 3️⃣ Proactive ≠ intrusive: There’s a fine balance between helpful and annoying. The best AI interactions feel like a supportive partner — offering assistance at the right time, based on context and past behavior, without overwhelming users with irrelevant notifications. In AI-UX, we’re increasingly designing for systems that adapt and evolve with the user.  This new feature is a great example of how AI can shift might be able rom a passive tool to an active assistant — can’t wait to try it. How do you see proactive AI changing the way we design user experiences? Would love to hear your thoughts! 👀

Last week at an AI healthcare summit, a Fortune 500 CTO admitted something disturbing: "We spent $7M on an enterprise AI system that sits unused. Nobody trusts it." And this is not the first time I have come across such cases. Having built an AI healthcare company in 2018 (before most people had even heard of transformers), I've witnessed this pattern from both sides: as a builder and as an advisor. The reality is that trust is the real bottleneck to AI adoption (not capability). I learned this firsthand when deploying AI in highly regulated healthcare environments. I have watched brilliant technical teams optimize models to 99% accuracy while ignoring the fundamental human question: "Why should I believe what this system tells me?" This creates a fascinating paradox that affects both enterprises, as well as people like you and me, so we can effectively use AI today: Users want AI that works autonomously (requiring less human input) yet remains interpretable (providing more human understanding). This tension is precisely where UI design becomes the determining factor in market success. Take Anthropic's Claude, for example. Its computer use feature reveals reasoning steps anyone can follow. It changes the experience from "AI did something" to "AI did something, and here's why" – making YOU more powerful without requiring technical expertise. The business impact speaks for itself: their enterprise adoption reportedly doubled after adding this feature. The pattern repeats across every successful AI product I have analyzed. Adept's command-bar overlay shows actions in real-time as it navigates your screen. This "show your work" approach cut rework by 75%, according to their case studies. These are not random enterprise solutions. They demonstrate how AI can 10x YOUR productivity today when designed with human understanding in mind. They prove a fundamental truth about human psychology: Users tolerate occasional AI mistakes if they can see WHY the mistake happened. What they won't tolerate is blind faith. Here's what nobody tells you about designing UI for AI that people actually adopt: • Make reasoning visible without overwhelming. Surface the logic, not just the answer • Signal confidence levels honestly. Users trust systems more when they admit uncertainty • Build correction loops that let people fix AI mistakes in seconds, not minutes • Include preview modes so users can verify before committing This is the sweet spot. — The market is flooded with capable AI. The shortage is in trusted AI that ordinary people can leverage effectively. The real moat is designing interfaces that earn user trust by clearly explaining AI's reasoning without needing technical expertise. The companies that solve for trust through thoughtful UI design will define the next wave of AI. Follow me Nicola for more insights on AI and how you can use it to make your life 10x better without requiring technical expertise.