# Lakshmi Narayanan: Product Designer > Lakshmi Narayanan is a product designer in Chennai, India: making confusing products feel obvious. Currently Product Designer at Timeless Ventures (Feb 2025 to Present), designing Ditto Insurance and Aarokya. Skills: UX research, User experience testing, Personas, Competitive analysis, Vector design, Motion design, AI frontend development, AI image and 3D asset generation. Tools: Figma, Figma Motion, Framer, Claude, Magnific, Canva. - Email: lakshmi.narayanan3002@gmail.com - Portfolio: https://portfolio.ksln.me - LinkedIn: https://www.linkedin.com/in/lakshmi-narayanan-ks/ - Resume: https://portfolio.ksln.me/resume This file is the portfolio at https://portfolio.ksln.me as plain text: the work by quality, the resume, then each case study in full. Pictures are given as their descriptions. # The work by quality ## Problem solving and product thinking - Worked out why Ditto's existing fix, slides over Google Meet, had not worked: it solved visibility but not engagement. Redesigned for engagement instead. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - Saw that improving the inputs of the AI-generated concept was not enough, and that its structure, hierarchy and flow needed rethinking. Rebuilt it as two cards: inputs, then plans. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - Set aside the obvious answer, an analytics dashboard, because it cannot serve 260 million people with very different comfort with charts. Chose a conversation. ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) ## Research and user empathy - Reviewed recordings of real advisor consultations, and traced lost engagement to 30-minute calls and short attention spans. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - Grounded the problem in usage data (81.1% of UPI users pay every day, over 30 transactions a month) as well as personal experience. ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) - Treated mobile as the priority, because most users were on mobile. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) ## Design taste and visual craft - Replaced long paragraphs with simple visuals and minimal text, and used avatars and a 3D character set to make a long questionnaire approachable. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - Critiqued the AI-generated concept on clarity, hierarchy and readability; gave the plan estimates clearer hierarchy and benefits as short pills; widened the mobile cards for readability and visual balance. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - This portfolio presents each case study as a book with its own cover, set in one type system across the site. ([This portfolio](https://portfolio.ksln.me/)) ## Interaction design - Matched each control to its data (radio buttons for binary choices, sliders for cover amount and term, dropdowns and steppers for the rest) and added system feedback while the premium is calculated. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - Recognition rather than recall for returning users, a failure state that helps the next attempt, skeleton loading for perceived speed, and answers that can be reshaped as simple, a graph or detailed. ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) - The advisor controls the flow; on selected screens the customer interacts with the content. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) ## Systems thinking - Two interfaces for one live session, advisor and customer, with the advisor seeing exactly what the customer sees; the consultation broken into six guided sections. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - One experience carried from desktop to mobile, reworked into grouped steps rather than shrunk. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) ## Business sense - Goals tied to the business: lead-to-conversion rate and customer drop-offs, alongside engagement and understanding. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - Added a conversion trigger, and designed for trust-building, customer acquisition, engagement and SEO visibility as well as for users. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - Weighed engagement, retention, transaction value, competitive edge and a possible subscription. ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) ## Working with AI - Took a PM's AI-generated concept, identified where it fell short on UX fundamentals, and turned it into a usable product. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - Designed a conversational, generative AI feature, including its limits: privacy, vague questions and how far back the data goes. ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) - Lists AI front-end development and AI image and 3D asset generation among skills. ([Resume](https://portfolio.ksln.me/resume)) ## Ownership, collaboration and communication - Owned the calculator end to end, working from the product manager's starting point. ([Term Insurance Calculator](https://portfolio.ksln.me/work/term-insurance-calculator)) - Designed the consultation experience together with their manager, Udhaya Chandran, starting from how Ditto's advisors actually ran their calls. ([Demystifying Insurance](https://portfolio.ksln.me/work/demystifying-insurance)) - Published this study as a write-up on Medium (Bootcamp, 2024). ([AI in the Google Pay app](https://portfolio.ksln.me/work/ai-google-pay)) # Resume: Lakshmi Narayanan K S ## Experience ### Product Designer, Timeless Ventures (Feb 2025 to Present) - Ditto Insurance: Insurance platform helping customers choose and buy insurance. (Product and Marketing Design) - Aarokya: Health insurance for Namma Yatri auto drivers. (Product Design) ### UI/UX Design Intern, Timeless Ventures (Jun 2024 to Jan 2025) - Bookmarks application. - Website design. ### UI/UX Design Intern, Fox Academy (Oct 2023 to Jan 2024) - Web pages. - Social media posts and marketing content. ## Education - Growth School: UX Design Career Accelerator Program (Mar 2023 to Dec 2023) - PSG College of Technology, Coimbatore: BSc Applied Science · CGPA 7.5 (Aug 2020 to May 2023) - AKKV Aarunadu MHSS, Trichy: Class 12 · 69.5% (Jun 2019 to Mar 2020) ## Skills UX research, User experience testing, Personas, Competitive analysis, Vector design, Motion design, AI frontend development, AI image and 3D asset generation ## Tools Figma, Figma Motion, Framer, Claude, Magnific, Canva --- # Case study: Demystifying Insurance https://portfolio.ksln.me/work/demystifying-insurance Redesigned how Ditto Insurance sells term insurance: a 30-minute advisor phone call became a guided, interactive session on two linked interfaces, a control panel for the advisor and a step-by-step experience for the customer. ## The new insurance buying experience We reinvented the term insurance buying experience, combining a seamless digital experience with real-time human advisor support, so users can learn, compare, and choose the right plan. - Role: Product Designer - Team: Two: me and my manager, Udhaya Chandran - Company: Ditto Insurance - Objective: Turn ditto's half-hour advisor phone calls into a shared, interactive session, so customers stay engaged, understand term insurance, and choose a plan with confidence, raising the conversion rate. [Image: Four tablet screens from the consultation experience, fanned out and captioned “Some of the screens”.] ### Why explaining term insurance is difficult? Many people expect term insurance to provide returns like an investment. Advisors explain the trade-offs between different plan options, including return-of-premium plans, and help users understand where their money can create the most value. Beyond this, users also need guidance on choosing the right cover amount, policy term, and add-ons. Explaining all these concepts in a simple and engaging way is one of the biggest challenges in the term insurance buying journey. ### How ditto is selling insurance now? [Image: “How does Ditto currently generate leads?” — four numbered steps, from discovering Ditto on Instagram to speaking with an advisor by phone.] ### Gap: Lost focus during phone calls Advisor calls usually last around 30 minutes. Today, people get distracted easily and have **shorter attention spans**. Since the conversation happens only over a phone call, it is hard for customers to stay fully focused, and advisors have limited ways to keep them engaged. [Image: A ditto advisor in a headset explaining at his laptop, and a puzzled customer on his phone, with jargon labels like “claim settlement ratio” and “payment tenure & frequency” piled above his head.] ### The aftereffects Without full customer engagement, advisors found it harder to communicate the value of insurance and convert leads. Customers also missed important concepts, felt confused, and struggled to make informed decisions. [Image: “The ripple effect” — four consequences: affecting conversion rate, phone calls limit engagement, higher drop offs, average customer experience.] ### Ditto’s first solution To make consultations more engaging, Ditto started conducting calls over **Google Meet** instead of relying only on phone calls. Advisors used **PowerPoint presentations** to visually explain complex term insurance concepts. [Image: Four of the dark-blue PowerPoint slides advisors used, captioned “Some of the ppt slides created by ditto”.] [Image: A grid of recorded consultation videos, captioned “We got access to call recordings”.] ### What we observed We reviewed multiple consultation recordings conducted over Google Meet to understand how advisors explained term insurance using PowerPoint presentations. While the addition of visuals was an improvement over phone calls, we noticed that the experience still lacked meaningful interaction between the advisor and the customer. ### Why wasn't this enough? Although visual slides improved understanding, the experience was still one-way. - Slides were static. - Customers could only watch. - Comparing plans was difficult. - Users couldn't interact with the information. - Advisors still had to do most of the explanation. ### The Opportunity The presentation solved the visibility problem, but not the engagement problem. Instead of making customers passive viewers, we thought what if they could **actively interact with the information while the advisor** guided them? [Image: “What We Wanted to Achieve” — increase engagement, simplify complex concepts, increase lead-to-conversion rate, reduce customer drop-offs.] ### The Direction - making it interactive Instead of showing customers a static PowerPoint presentation, we wanted them to interact with the information while the advisor guided the session. The advisor controls the flow, while the customer explores concepts, compares plans, and understands insurance in a simpler way. [Image: “Human expertise + Interactive experience”, over a take on The Creation of Adam: a robot and the painted figure reaching for a glowing orb between their hands.] ### Breaking Down the Consultation To make the consultation easier to follow, we broke it down into a series of guided steps. Each section focuses on a single topic, allowing advisors to explain concepts clearly while customers actively engage with the experience. [Image: “The six sections” listed in two columns: introduction, questionnaire, tenure and cover amount, policies, payment, addons & premium.] ### Two Interfaces, One Experience We built two separate interfaces—one for the advisor and one for the customer. The advisor controls the session, while the customer gets a simple, interactive experience. [Image: The two interfaces side by side — “What advisors see”, a control panel, next to “What customers see”, the guided screen.] ### Advisor Experience The advisor interface is designed as a control panel. Advisors can navigate between sections, select screens to present, and see exactly what the customer is viewing. They also have quick access to tools for sharing quotes, plan PDFs, and WhatsApp. ### Customer Experience Customers follow a guided experience while the advisor controls the flow. On selected screens, customers can interact with the content as the advisor explains concepts and answers questions. This makes the consultation more engaging, interactive, and easier to understand. #### Diving deep into customer experience - 6 sections The experience is structured into six sections, guiding customers through their insurance-buying journey. Starting with the fundamentals of term insurance, the flow gradually helps them determine the right coverage, evaluate policies, understand premiums, and choose a plan that fits their needs. Each section is designed to make complex decisions easier to understand and act upon. #### 01 Introduction The introduction section helps advisors explain the basics of term insurance and why it is important. Instead of long paragraphs, the information is presented through simple visuals and minimal text, making it easier for customers to understand and stay engaged. [Image: “Educate users about term insurance” — tablet screens explaining what term insurance is and who is eligible.] #### 02 Questionnaire To recommend the right term insurance plan, advisors need information such as the **customer's age, health condition, smoking habits, education, and other eligibility factors**. Since this is a lengthy questionnaire, we redesigned it to be more engaging by using avatars, simple interactions, and visual cues. Instead of passively listening, customers actively provide their inputs, making the consultation feel more interactive and hands-on. [Image: “Getting essential input from users” — questionnaire screens using avatars and simple choices.] #### 03 Tenure and Cover Amount [Image: Tenure and cover amount screens, where the customer sets how long the policy runs and how much it pays out.] #### 04 Policies [Image: “Recommended plans” — policy screens, where recommended plans are listed and compared.] #### 05 Payment Configuration [Image: Payment configuration screens, covering premium frequency and payment term.] #### 06 Addons & Premium [Image: “Add-ons” — optional riders shown alongside the base plan.] [Image: “Premium” — recommended plans with their add-ons and the final yearly premium.] [Image: “Compare plans - with different add-ons”, insurers side by side across claim settlement, riders and premium.] [Image: The 3d character set drawn for the product — families, an advisor with a headset, and single figures for each eligibility question.] --- # Case study: Term Insurance Calculator https://portfolio.ksln.me/work/term-insurance-calculator Reworked a product manager's AI-generated concept for Ditto's free term insurance calculator into one people can use on their own, on desktop and on mobile. ## Term Calculator A term insurance calculator is an free tool from ditto that collects inputs from users and recommends the term insurance plan that best suits their needs. - Role: Product Designer - Team: Just me, end to end - Company: Ditto Insurance - Objective: Rework the PM's AI-generated concept into a calculator people can use on their own, with fewer, easier inputs and plans they can compare, so they can explore cover before booking a call with an advisor. ### The Opportunity This calculator created an opportunity for users to learn about and explore coverage options at their own pace, even before booking a call with an advisor. ### The starting point The Product Manager shared an AI-generated UI concept as an initial direction for the calculator experience. The AI-generated design helped kickstart the direction, but the experience lacked strong UI and UX fundamentals. As I explored the screens further, several issues around clarity, hierarchy, readability, and usability became visible. ### Length of input fields The vertically stacked input fields increased the overall card height, creating unnecessary scrolling and making the experience feel heavier than needed. Since users also had to manually enter multiple inputs, the flow demanded more effort and adding friction to the overall experience. The dropdown used for “Coverage Till Age” was not ideal for the large number of options available. This made selection slower and less intuitive, affecting the overall usability of the form. The “Sum Assured and Annual income” text field required users to manually enter large values, increasing effort and making the input process less convenient. ### Inefficient Layout The plan suggestions and user inputs were placed within the same layout, making it harder for users to clearly associate and compare plans. If users wanted to edit their inputs after viewing the plans, they had to scroll back up again, creating unnecessary friction and affecting the overall experience. ### My Approach Initially, I tried improving the existing AI-generated layout by making inputs easier to fill using sliders, dropdowns, and interactive controls. But while exploring the experience further, I realized the problem was deeper than just input usability the overall structure, hierarchy, and flow itself needed rethinking. ### Sorted out the layout I separated the input flow from the plan recommendations instead of placing both within the same layout. I also introduced contextual placeholders that gave users a clearer sense of what to expect while entering their details. ### Improving the structure I realized the input experience was starting to feel like a long financial form. To reduce that friction, I redesigned the layout to fit the key input fields within the first fold, allowing users to complete the flow without unnecessary scrolling. ### Input fields’ layout Simplified the input layout to reduce the feeling of filling out a long financial form. The key fields were reorganized within the initial viewport, helping users complete the flow faster with minimal scrolling. Using radio buttons for binary options reducing complexity. Sliders for cover amount and coverage duration reduced the effort of manually entering large values. Dropdown and steppers were used for the remaining fields to simplify selection. ### Conversion trigger Added a conversion trigger to create a sense of urgency and encourage users to take action before the premium price increases. ### System feedback An animated calculator illustration provides system feedback, making the premium calculation feel active and real-time. ### Plan estimates The plan estimates were redesigned to improve scanability and make plan comparison easier through clearer hierarchy, pricing visibility, and structured benefit highlights. Key offerings were shortened into pill-based highlights to improve scanability and help users quickly consume plan benefits without reading long paragraphs.. ### Expected outcomes The experience was designed to simplify coverage exploration, improve financial understanding, and help users make more informed decisions before booking a call. From a business perspective, it also aimed to support trust-building, customer acquisition, engagement, and SEO visibility. ### Mobile version - V1 The two-card layout worked effectively on desktop, but adapting it for mobile required rethinking the structure due to limited screen space. Since most users were on mobile, optimizing the experience became a key priority. ### Breaking down for mobile To reduce scrolling and make the experience feel lighter on mobile, the inputs were divided into smaller grouped steps instead of presenting everything at once. This created a more guided flow while reducing the effort required from users. The structure also helped users view plan estimates and input progress within the first fold itself, making the experience feel more connected and easier to navigate. ### Mobile - Final version The layout was refined to give the cards more width, improving readability and creating better visual balance. This also helped the content feel clearer, more spacious, and easier to consume across the experience. --- # Case study: AI in the Google Pay app https://portfolio.ksln.me/work/ai-google-pay A self-initiated concept: Gemini inside Google Pay, so anyone can ask in plain language where their UPI money went, instead of having to read a dashboard. ## How I incorporated AI in the Google Pay app *AI product exploration: a self-initiated concept.* [Image: Gemini AI x Google Pay: Ask, Customise, Track — a phone with a ‘pay or ask anything’ bar, and Generative AI + Conversational AI.] A conversational, generative layer over UPI payments, so anyone can simply ask where their money went. A few weeks ago I attended a workshop on generative AI, and came away with a clear sense of how it is being used in today’s applications — and an itch to find a use for it that would matter. While I was looking, something clicked. I had been spending without control, and since linking my bank account to UPI, I found it hard to keep track of where the money went. It isn’t just me: many people have the same problem. So I set out to put AI inside a UPI app to address it. Digital payments in India have surged in recent years, and the Unified Payments Interface has become the preferred choice for millions: India recorded about 131 billion UPI transactions in FY24. As people embrace the convenience, there is a real need for something that gives them back control. [Video: the prototype, end to end, under a minute.] ### The backdrop of the problem When people paid in cash, they felt every rupee leave. With UPI, that awareness fades: a payment barely feels like spending at all, so it happens more often. That shift in behaviour is part of why UPI volumes keep climbing. > “People spend on UPI as if it isn’t real money.” The result is a long, unruly list of transactions that is hard to follow and harder to categorise — and no personal guidance to help anyone set a financial goal, let alone meet it. #### How the user base grew Until 2014, only 53% of adults in India had a bank account. By FY21, nearly 90% did — the result of financial-inclusion schemes such as Jan Dhan Yojana, which put a bank account within reach of almost every Indian. Add UPI’s ease of use, and the fact that everything from bills to shopping has moved online, and more people pay by UPI every year. A survey published on arXiv found that 81.1% of UPI users use it every day — on average more than 30 transactions a month. Of the respondents, 51.6% were students, 42% working professionals and 4.7% business owners. - 131 bn UPI transactions in India, FY24 - 53% → 90% of adults with a bank account, 2014 to FY21 - 81.1% of UPI users pay with it every day - 260 m+ people in India use UPI ### What people run into - **Difficulty in tracking**: With a large number of transactions, keeping track of spending, let alone managing it, becomes hard. - **Identifying patterns**: At that volume, patterns and trends in spending are difficult to see, so finances are harder to manage. - **Limited insights**: The sheer number of transactions gets in the way of any meaningful insight into habits or financial health. - **Overspending**: More transactions lead to more spending, especially when no one is actively watching. - **Lack of personalisation**: Existing finance trackers feel generic: their insights are not tailored to the person using them. - **Lack of guidance**: Nothing helps people set a goal and actually reach it. ### How can I solve this? An analytics page is the obvious answer: charts that let people make informed decisions. But more than 260 million people use UPI in India, and not all of them are comfortable reading analytics. My hypothesis was that a dashboard designed for everyone serves no one well. People with less exposure to charts struggle to draw insight from them; people who read charts easily still don’t get the personal, predictive answers they want. The answer had to work for the broadest possible range of people. Gemini, combining conversational and generative AI, does. People can simply ask — for personalised insights and recommendations, for real-time guidance on budgets and goals — and get an answer shaped to them. - **Conversational AI**: Lets a computer understand and respond to human language naturally. Here, it means tracking your spending is a conversation, not a chore. - **Generative AI**: Creates new content — text, images, audio — much as a person would. Here, it reads spending patterns and generates the insight, suggestion or graph that answers the question. ### Will people understand it? AI is arriving in everyday apps quickly, and people are adapting with it. Amazon and Spotify use generative AI well; WhatsApp and Instagram have put Meta AI in front of billions. These tools explain themselves, and ChatGPT has made talking to an AI feel normal. That familiarity suggests people are ready to understand — and benefit from — an AI-powered search inside a UPI app. > “A dashboard designed for everyone serves no one well. So let people ask.” #### For the business - **User engagement**: An assistant people return to makes them more likely to use the app regularly. - **Revenue streams**: Engagement, retention and transactions grow revenue — and advanced insights could become a subscription. - **Competitive edge**: It sets Google Pay apart from every other payments app. - **User satisfaction**: Simpler money management and real insight build satisfaction and loyalty. - **User retention**: If one app tracks everything accurately, people keep using it for every kind of payment. - **Average transaction value**: More transactions in a single app raise the average transaction value. #### For the people using it - **Convenience**: No manual calculations, and no separate finance-tracking apps. - **Personalisation**: Ask personal questions, the way you would ask a friend — with more capability behind the answer. - **Financial guide**: Predictions turn it into a guide for planning ahead. - **Transparency**: Every rupee accounted for, by date or by category. - **Time saved**: No manual tallying, no copying spends into other apps. - **User experience**: An assistant that is useful in many small ways, and engaging to use. ### Delving into the solution #### Finding it When Google Pay introduces the feature, a bottom sheet presents it, so nobody misses it. From then on, the prompt lives in the same search bar on the home screen. [Image: A bottom sheet: Ask Gemini AI anything.] *A bottom sheet introduces Gemini the first time, saying what it can do.* [Image: The Google Pay home screen with a ‘pay or ask anything’ search bar.] *Afterwards, the same search bar on the home screen takes a prompt.* [Image: The search screen with suggested categories and example questions.] *Tapping it opens the search, with ways to start.* #### Being guided First-time users are walked through what they can ask, with categories and example questions. Returning users see their recent searches instead — recognition rather than recall. [Image: Search for first-time users, with examples.] *For first-time users: what can I ask?* [Image: Search for returning users, with recent searches.] *For returning users: recent searches, one tap away.* #### When a search fails If the system can’t answer, it says so plainly — and points to a search-help section with tips for better prompts, so the next attempt succeeds. [Image: An error: no results, with a link to search help.] *A clear error, and a way forward.* ### How it works Questions range from a quick lookup to real financial planning. While Gemini works, a skeleton animation shortens the perceived wait; then the answer appears, with ways to reshape it. [Image: Answer to: how much did I spend on food last month.] *Simple: “How much did I spend on food last month?”* [Image: Answer listing upcoming dues with pay and recharge buttons.] *Intermediate: “List my upcoming dues from my past transactions” — with buttons to pay each one.* [Image: Answer: a daily food spend limit to meet a monthly goal.] *Advanced: “My food budget is ₹5,000 this month — how much can I spend a day?”* ### Shaping the answer Every answer can be reshaped to suit the person reading it. - **Simple**: A brief, direct answer, with no jargon and nothing extra. - **Graphs**: The same answer as a chart, to take in at a glance. - **Detailed**: The full picture: every transaction behind the number, with context. [Image: A simple answer.] *Simple* [Image: The answer as a donut chart.] *Graphs* [Image: The answer as a detailed transaction list.] *Detailed* ### Payments to local merchants A payment to a local shop or restaurant arrives with no category, so it can’t be tracked. The fix happens at the moment of paying: add a note. [Image: Paying a merchant, with an ‘Add a note’ button.] *Paying a local shop or restaurant, people add a note before they pay.* [Image: Suggested tags: Food, Grocery, Clothing.] *Tags suggested from past payments to the same kind of place make it a single tap.* [Image: A note made of a single emoji.] *A note can even be an emoji — the AI works out the category.* ### Things to ask #### Simple - How much did I pay to [contact]? - Where did I spend money on May 12? - How much did I spend in the last 10 days? - Food or shopping — which did I spend more on? - How much did I spend on food last month? - Suggest a grocery budget based on my past spending. #### Moderate - How have my spending habits changed over the past year? - Help me earn more rewards with GPay. - Highlight any unusual spending in my recent transactions. - Can you predict my upcoming bills from recent transactions? - Help me make a realistic plan to save ₹10,000 in two months. - Can you predict my total expenses for the next three months? #### Advanced - What if I increase my monthly savings by 20%? How would that affect my budget? - Categorise my expenses differently. - How much would I need to save each month to retire early and keep my lifestyle? - How would a new car loan affect my monthly budget and long-term savings? - How would investing part of my savings in stocks affect my finances? - What if I moved to a city with a higher cost of living? #### Limitations - **Non-text data**: Search may not cover images or videos. - **Context**: Vague terms can be hard to understand. - **History**: Data beyond a certain period may be out of reach. - **Privacy**: Sensitive information is deliberately left unsearched. #### What’s next - **Usability testing**: To find what works, and what doesn’t. - **Voice**: Ask out loud. - **For merchants**: The same assistant in Google Pay for Business. - **Languages**: Multilingual support, for everyone who uses UPI. ### In closing I wrote this to show how a product designer can bring AI into an everyday app to give people more personal, more efficient answers. The apps to come will build in this kind of intelligence as a matter of course. I used Google Pay to demonstrate it, but the idea fits any payments app — PhonePe, Paytm, PayZapp, CRED. Thank you for reading to the end. I love talking about design: write to me.