User trust in high-performance interfaces

𝐎𝐧𝐞 𝐥𝐞𝐬𝐬𝐨𝐧 𝐦𝐲 𝐰𝐨𝐫𝐤 𝐰𝐢𝐭𝐡 𝐚 𝐬𝐨𝐟𝐭𝐰𝐚𝐫𝐞 𝐝𝐞𝐯𝐞𝐥𝐨𝐩𝐦𝐞𝐧𝐭 𝐭𝐞𝐚𝐦 𝐭𝐚𝐮𝐠𝐡𝐭 𝐦𝐞 𝐚𝐛𝐨𝐮𝐭 𝐔𝐒 𝐜𝐨𝐧𝐬𝐮𝐦𝐞𝐫𝐬: Convenience sounds like a win… But in reality—control builds the trust that scales. 𝐋𝐞𝐭 𝐦𝐞 𝐞𝐱𝐩𝐥𝐚𝐢𝐧 👇 We were working on improving product adoption for a US-based platform. Most founders would instinctively look at cutting down clicks and removing steps in the onboarding journey. Faster = Better, right? That’s what we thought too—until real usage patterns showed us something very different. Instead of shortening the journey, we tried something counterintuitive: -We added more decision points -Let the user customize their flow -Gave options to manually choose settings instead of setting defaults And guess what? Conversion rates went up. Engagement improved. And most importantly—user trust deepened. 𝐇𝐞𝐫𝐞’𝐬 𝐰𝐡𝐚𝐭 𝐈 𝐫𝐞𝐚𝐥𝐢𝐬𝐞𝐝: You can design a sleek 2-click journey…  …but if the user doesn’t feel in control, they hesitate. Especially in the US market, where data privacy and digital autonomy are hot-button issues—transparency and control win. 𝐒𝐨𝐦𝐞 𝐞𝐱𝐚𝐦𝐩𝐥𝐞𝐬 𝐭𝐡𝐚𝐭 𝐬𝐭𝐨𝐨𝐝 𝐨𝐮𝐭 𝐭𝐨 𝐦𝐞: → People often disable auto-fill just to manually type things in.  → They skip quick recommendations to do their own comparisons.  → Features that auto-execute without explicit confirmation? Often uninstalled. 💡 Why? It’s not inefficiency. It’s digital self-preservation. It’s a mindset of: “Don’t decide for me. Let me drive.” And I’ve seen this mistake firsthand: One client rolled out a smart automation feature that quietly activated behind the scenes. Instead of delighting users, it alienated 15–20% of their base. Because the perception was: "You took control without asking." On the other hand, platforms that use clear confirmation prompts (“Are you sure?”, “Review before submitting”, toggles, etc.)—those build long-term trust. That’s the real game. Here’s what I now recommend to every tech founder building for the US market: -Don’t just optimize for frictionless onboarding. -Optimize for visible control. -Add micro-trust signals like “No hidden fees,” “You can edit this later,” and clear toggles. -Let the user feel in charge at every key point. Because trust isn’t built by speed. It’s built by respecting the user’s right to decide. If you’re a tech founder or product owner: Stop assuming speed is everything. Start building systems that say, “You’re in control.” That’s what creates adoption that sticks. What’s your experience with this? Would love to hear in the comments. 👇 #ProductDesign #UserExperience #TrustByDesign #TechForUSMarket #DigitalAutonomy #businesscoach #coachishleenkaur Linkedin News LinkedIn News India LinkedIN for small businesses

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.

𝔼𝕍𝔸𝕃 field note (2 of 3): Finding the benchmarks that matter for your own use cases is one of the biggest contributors to AI success. Let's dive in. AI adoption hinges on two foundational pillars: quality and trust. Like the dual nature of a superhero, quality and trust play distinct but interconnected roles in ensuring the success of AI systems. This duality underscores the importance of rigorous evaluation. Benchmarks, whether automated or human-centric, are the tools that allow us to measure and enhance quality while systematically building trust. By identifying the benchmarks that matter for your specific use case, you can ensure your AI system not only performs at its peak but also inspires confidence in its users. 🦸♂️ Quality is the superpower—think Superman—able to deliver remarkable feats like reasoning and understanding across modalities to deliver innovative capabilities. Evaluating quality involves tools like controllability frameworks to ensure predictable behavior, performance metrics to set clear expectations, and methods like automated benchmarks and human evaluations to measure capabilities. Techniques such as red-teaming further stress-test the system to identify blind spots. 👓 But trust is the alter ego—Clark Kent—the steady, dependable force that puts the superpower into the right place at the right time, and ensures these powers are used wisely and responsibly. Building trust requires measures that ensure systems are helpful (meeting user needs), harmless (avoiding unintended harm), and fair (mitigating bias). Transparency through explainability and robust verification processes further solidifies user confidence by revealing where a system excels—and where it isn’t ready yet. For AI systems, one cannot thrive without the other. A system with exceptional quality but no trust risks indifference or rejection - a collective "shrug" from your users. Conversely, all the trust in the world without quality reduces the potential to deliver real value. To ensure success, prioritize benchmarks that align with your use case, continuously measure both quality and trust, and adapt your evaluation as your system evolves. You can get started today: map use case requirements to benchmark types, identify critical metrics (accuracy, latency, bias), set minimum performance thresholds (aka: exit criteria), and choose complementary benchmarks (for better coverage of failure modes, and to avoid over-fitting to a single number). By doing so, you can build AI systems that not only perform but also earn the trust of their users—unlocking long-term value.

Effective AI augmentation of human decision-making requires clarity on the specific role of AI relative to humans. An interesting research study used two different AI agents - ExtendAI and RecommendAI - each optimized to play different roles in a financial investment decision process. The findings give useful insight into both the design of AI tools to augment human decisions, and how we deliberately choose to use AI to enhance our decision competence. 🧠 ExtendAI encourages self-reflection and informed decisions. Participants who used ExtendAI—an assistant that builds on users' own rationales—spent more time reflecting and revising their plans. They made 23.1% of trades that diverged from their original ideas, showing that feedback embedded in their own reasoning helped identify blind spots and improve diversification and balance. ⚡ RecommendAI sparks new ideas with low effort. RecommendAI, which directly suggests actions, led to a 45% adoption rate of its recommendations. It was perceived as more insightful (67% vs. 52% for ExtendAI) and easier to use, requiring half the time (8.6 vs. 17.5 minutes) compared to ExtendAI. 🧩 Feedback format impacts trust and comprehension. ExtendAI’s suggestions, interwoven into the user's rationale, were found easier to verify and interpret. Participants felt more in control (76% vs. 71% trust) and reported that it “supports how I’m thinking” instead of dictating actions. RecommendAI, by contrast, sometimes felt like a “black box” with unclear reasoning. 🌀 Cognitive load differs by interaction style. Using ExtendAI imposed more cognitive effort—an average NASA-TLX score of 57 vs. 52.5 for RecommendAI—due to the need for upfront reasoning and engagement with nuanced feedback. This reflects the trade-off between deeper reflection and ease of use. 💡 Users want AI insights to be both novel and relatable. Participants valued fresh insights but were most receptive when suggestions aligned with their reasoning. ExtendAI sometimes felt too similar to user input, while RecommendAI occasionally suggested strategies users rejected due to perceived misalignment with their views or market context. 🧭 Decision satisfaction and confidence diverge. Despite feeling more confident with RecommendAI (86% vs. 67%), participants reported higher satisfaction after using ExtendAI (67% vs. 43%). This suggests that while direct suggestions boost confidence, embedded feedback might lead to decisions users feel better about in hindsight. More coming on AI augmented decision making.

Search is (currently) the surface on which AI will affect human decision making at the greatest scale. But, we know AI Search hallucinates, as Google’s AI Search has advised users to “eat rocks," glue cheese to pizza, and that “doctors recommend smoking 2-3 cigarettes per day during pregnancy.” So, we ran 12,000 search queries across 7 countries, generating 80,000 real-time GenAI and traditional search results, to understand current global exposure to GenAI search. We then used a preregistered, randomized experiment on a large study sample to understand when humans trust AI Search. The results were surprising and a bit unnerving... 🚩 First, our study shows that GenAI search results are globally pervasive but vary greatly by topic. Over half of all Health (51%) and General Knowledge (56%) queries returned AI results while only 5% of Shopping and 1% of Covid queries returned AI results. The pervasiveness of AI in search results suggests we should be concerned with the conditions under which humans trust AI search. 🤔 🚩 Second, the format of the query predicts whether you get AI or traditional search results with questions returning GenAI answers 49% of the time, statements 16% of the time and navigational searches returning GenAI only 4% of the time. 🚩 Third, in the RCT, while participants trust GenAI search less than traditional search on average, reference links and citations significantly increase trust in GenAI, even when those links and citations are incorrect or hallucinated. In other words, the veneer of rigor in AI design creates trust even when references and links are not rigorous. 🤯 🚩 Uncertainty highlighting, which reveals GenAI’s confidence in its own conclusions, makes us less willing to trust and share generative information whether that confidence is high or low. 🚩 Positive social feedback increases trust in GenAI while negative feedback reduces trust. These results imply that GenAI interface designs can increase trust in inaccurate and hallucinated information and reduce trust when GenAI’s certainty is made explicit. 🚩 Trust in GenAI varies by topic and with users’ education, industry employment and GenAI experience, revealing which sub-populations are most vulnerable to GenAI misrepresentations. 🚩 Trust then predicts behavior as those who trust GenAI more click more and spend less time evaluating GenAI search results. These findings suggest directions for GenAI design to address the AI "trust gap.” The paper, coauthored with Haiwen Li, is linked in the first comment. We thank the MIT Initiative on the Digital Economy for support and are grateful to SerpApi for assistance with query scaling. As always, thoughts and comments highly encouraged! Wondering especially what Erik Brynjolfsson Edward McFowland III Iavor Bojinov John Horton Karim Lakhani Azeem Azhar Sendhil Mullainathan Nicole Immorlica Alessandro Acquisti Ethan Mollick Katy Milkman and others think!

Thinking: what makes chat such an optimal UI for AI agents? Research shows that when we treat AI as a teammate, not just a product feature, tasks are completed faster, with fewer errors, and users are more satisfied. One example: a 2025 Frontiers study found that subtle human cues in a chatbot boosted perceived empathy and trust, driving a 50% increase in overall experience scores. In autonomous systems, research repeatedly shows the same results: operators under high cognitive load perform better and trust the system more when the robot feels like a teammate rather than a tool. I’ve seen this firsthand building interfaces for autonomous assets. When software lets users engage AI like another team member, they offload more, stay more engaged, and let the autonomy do its job. A button labeled “Do the thing” is far less effective than a UI that communicates status and intent: “Completed search of area B. Recommend moving to sector C for coverage. Approve?” Chat is just the on-ramp. The real unlock is treating the AI as someone on the team—not something bolted onto the stack. That’s how you get people to work with it, not around it.

Here’s the easiest way to make your products 10x more robust: Start treating your AI evals like user stories. Why? Because your evaluation strategy is your product strategy. Every evaluation metric maps to a user experience decision. Every failure mode triggers a designed response. Every edge case activates a specific product behavior. Great AI products aren’t just accurate; they’re resilient and graceful in failure. I recently interviewed a candidate who shared this powerful approach. He said, "𝘐 𝘴𝘱𝘦𝘯𝘥 𝘮𝘰𝘳𝘦 𝘵𝘪𝘮𝘦 𝘥𝘦𝘴𝘪𝘨𝘯𝘪𝘯𝘨 𝘧𝘰𝘳 𝘸𝘩𝘦𝘯 𝘈𝘐 𝘧𝘢𝘪𝘭𝘴 𝘵𝘩𝘢𝘯 𝘸𝘩𝘦𝘯 𝘪𝘵 𝘴𝘶𝘤𝘤𝘦𝘦𝘥𝘴." Why? Because 95% accuracy means your AI confidently gives wrong answers 1 in 20 times. So he builds: • Fallback flows • Confidence indicators • Easy ways for users to correct mistakes. In other words, he doesn’t try to hide AI’s limitations; he designs around them, transparently. He uses AI evaluations as his actual Product Requirements Document. Instead of vague goals like “the system should be accurate,” he creates evaluation frameworks that become product specs. For example: Evaluation as Requirements - • When confidence score < 0.7, show “I’m not sure” indicator • When user corrects AI 3x in a session, offer human handoff • For financial advice, require 2-source verification before display Failure Modes as Features - • Low confidence → Collaborative mode (AI suggests, human decides) • High confidence + wrong → Learning opportunity (capture correction) • Edge case detected → Graceful degradation (simpler but reliable response) • Bias flag triggered → Alternative perspectives offered Success Metrics Redefined - It’s not just accuracy anymore: • User trust retention after AI mistakes • Time-to-correction when AI is wrong • Percentage of users who keep using the product after errors • Rate of escalation to human support Plan for failure, and your users will forgive the occasional mistake. Treat your AI evaluations like user stories, and watch your product’s robustness soar. ♻️ Share this to help product teams build better AI products. Follow me for more practical insights on AI product leadership.

Ask any founder about their biggest failure, and they’ll point to the obvious one. Big failures get headlines. But the real collapse rarely gets noticed. Products rarely die from a single mistake. They bleed out in silence every time trust is traded for a shortcut. Betray your best users, lose your edge. Your earliest adopters do more than provide feedback or cheer from the sidelines. They troubleshoot, stretch your product, and set new expectations. When their needs go unmet, or when you break their workflows, you are losing the resilience that keeps your product alive in tough moments. Most teams only notice the damage after the fact, when those users are already gone. How you end matters as much as how you launch. Product migrations and sunsets are never just technical. Every missed detail, whether it’s a broken export, a lost file, or a confusing transition, creates another fracture in user trust. The companies that get this right pay attention to the small stuff and respect what users built with them. The ones that treat it as a checklist always leave a mess behind. A clean, clear ending tells your customers that their time and work mattered. Chasing breadth, losing depth. Expanding into new markets or adding features can look like progress. What usually happens is you lose the discipline and detail that made people care in the first place. Winning new jobs means putting in more effort, not less. Most teams spread themselves thin and become forgettable. The teams that win stay focused long enough to build depth users can’t find anywhere else. Friction is a slow exit. Forced signups and hidden paywalls push users to start searching for alternatives, even if they don’t leave right away. The short-term gains from adding friction almost always come at the cost of long-term loyalty. In the end, trust is what keeps people around. Lose it, and all you’ve done is start a countdown for your competitors. The pattern repeats: The slow decline of a product begins each time trust is traded for a shortcut or a quick win. Protect user trust as fiercely as you fight for every launch or metric. The best teams never make their top users regret the energy or belief they put into the product.

As AI becomes integral to our daily lives, many still ask: can we trust its output? That trust gap can slow progress, preventing us from seeing AI as a tool. Transparency is the first step. When an AI system suggests an action, showing the key factors behind that suggestion helps users understand the “why” rather than the “what”. By revealing that a recommendation that comes from a spike in usage data or an emerging seasonal trend, you give users an intuitive way to gauge how the model makes its call. That clarity ultimately bolsters confidence and yields better outcomes. Keeping a human in the loop is equally important. Algorithms are great at sifting through massive datasets and highlighting patterns that would take a human weeks to spot, but only humans can apply nuance, ethical judgment, and real-world experience. Allowing users to review and adjust AI recommendations ensures that edge cases don’t fall through the cracks. Over time, confidence also grows through iterative feedback. Every time a user tweaks a suggested output, those human decisions retrain the model. As the AI learns from real-world edits, it aligns more closely with the user’s expectations and goals, gradually bolstering trust through repeated collaboration. Finally, well-defined guardrails help AI models stay focused on the user’s core priorities. A personal finance app might require extra user confirmation if an AI suggests transferring funds above a certain threshold, for example. Guardrails are about ensuring AI-driven insights remain tethered to real objectives and values. By combining transparent insights, human oversight, continuous feedback, and well-defined guardrails, we can transform AI from a black box into a trusted collaborator. As we move through 2025, the teams that master this balance won’t just see higher adoption: they’ll unlock new realms of efficiency and creativity. How are you building trust in your AI systems? I’d love to hear your experiences. #ArtificialIntelligence #RetailAI

Confession: I’m a total sucker for “display of effort.” Behavioral-science friends will know this bias well: we feel more confident when a product looks like it’s working hard for us, progress bars that creep along or airlines showing a little plane inching across a map. Harvard’s Ryan Buell and Michael Norton coined it the “labor illusion.” I just caught myself falling for it again. I tend to choose AI "thinking" models over their much faster counterparts -- not necessarily because the output is better, but because my lizard brain is telling me “Wow, this thing is really working for me!” In fact, I often distrust fast responses now because I think "surely, you didn't think about this hard enough" (as if an AI is some kind of undergrad RA). Why does this matter? - Trust & satisfaction: When users witness “effort,” they rate the experience higher—even if the end result is identical. - Perceived value: Effort signals competence and care (“They didn’t phone this in”). - Design takeaway: Sometimes removing every millisecond of wait time isn’t the goal; designing the wait can actually improve the experience. As we build AI tools (or any digital product), let’s remember: blowing people away with speed is great, but showing a bit of thoughtful “sweat” can deepen trust. My suspicion is that this is context dependent, even in AI. I would love image generation to be 10x faster, for example. For some reason I don't harbor the illusion that there's a person on the other end pumping out my Miyasaki dupes.