• Hana Elster, a college senior, used Claude during winter break to create a website in five days.
• She spent under $2,000 to get an online vintage marketplace up and running.
• Elster said she hopes that it'll be a successful side hustle as she moves into the corporate world.

This as-told-to essay is based on a conversation with Hana Elster, a 22-year-old senior at Boston University who founded VYA, an online vintage marketplace. It has been edited for length and clarity.

I'm a senior at college studying business law at Boston University, graduating in May.

I've always loved the idea of being your own boss and building something for yourself.

I'm also surrounded by a big founder community in Boston and New York. Seeing all these other people my age or a little bit older building things for themselves inspired me to do something for myself.

Over winter break, I used Claude to build an app that now has hundreds of users.

My love for vintage gave me a business idea

I went thrifting for the first time when I was around 14. You'd go to the regular mall and find a shirt for $30, but I could find 10 shirts for $30 at my nearest Goodwill, and I'd be wearing something nobody else had.

So it piqued my interest in secondhand shopping, getting good value, and developing a unique style. Now, I would say 80% of my closet is secondhand.

Last year, I was talking with one of my friends about our favorite stores in our hometowns, and she told me about an amazing vintage store in Chicago. I'm originally from Washington, DC, and I wouldn't have known about this store unless we'd had this conversation.

I realized there is space for a centralized vintage platform.

I reached out to many shops to learn about their pain points and where they want to grow. The sellers mainly said they want more eyes on their products.

Brick-and-mortar vintage stores told me they had websites, but most of their sales come from foot traffic. Shop owners said they put a lot of work into their website, yet they only got one sale a month on that platform.

Stores that are fully online said they had to post three times a day on Instagram and TikTok because marketing was the only way to get their name out. A lot of these sellers also had full-time jobs, and vintage sales were their side hustle, so they didn't have time to do much work.

Using Claude to code a website in five days

To build the app, I started vibe coding. I have some coding experience, but Claude Code has let me move at a pace I would never have been able to.

I connected with a friend who had built a fashion app years ago, and he prompted me to learn how to vibe code. In January, I started with Cursor and eventually began coding with Claude, and the project accelerated really fast.

I started on January 9 and built a mock website for VYA by January 13, over winter break. It got me so excited, thinking about how I was turning lines of code into something visual, with buttons and functions and everything.

Five days later, I had a website. Friends in tech also helped me look over the code and make sure everything flowed correctly.

Monetization

I've spent under $2,000 on app development so far, which covers all technical and operational costs. It's self-funded by my savings, and I've also received some grants from Boston University.

More than three months on, we have 38 stores fully onboarded and continuing to grow, and roughly 900 approved users, of whom 50% are daily active users. My goal is that when you're checking out vintage websites like The RealReal, you also open VYA.

To monetize it, I'm charging a 7% commission per item sold, with an average price of about $350. I'm also trying out a model called "source for requests," in which we charge customers a flat fee for finding a particular product, like a rare 90s Chanel bag.

Usually, one of the 38 stores can fulfill the order, and if we can't, the fee is refunded.

AI has both dropped and raised barriers

I've always wanted to start my own business, but this was the first time I was hit with inspiration, and I could actually execute it. I don't know if I would've done it if I'd known I'd have to hire engineers and other staff, because I would've had to raise money.

So AI has definitely dropped the barrier to entry.

The biggest barrier used to be engineering, but now it's getting people to hear about your brand and then convert and buy, which is why my first hire is going to be a CMO.

I'm thinking of how to raise money so that I can add to my head count. I'm focusing on growing and getting more people to help me out so that I can grow exponentially faster.

After graduation, I'm supposed to work in consulting — I've got a return offer, and the role doesn't start until September.

I'm planning to accept it and see how this business grows on the side. If I can build it up enough, grow my head count, and automate it, I would love to do it alongside my corporate job.

Being a young founder has changed me. The other founders I've seen are super bold, confident, and courageous, and I feel like I've developed that side of myself, too.

• Raghav and Ansh Kumar quit city life, moved to the Himalayas, and built a house by hand.
• The brothers, architects by training, wanted to prove that natural materials could be durable and luxurious.
• The house took three years to build, and it's now a functional Airbnb.

Perched on the side of a hill near the Himalayas is a whimsical house made of mud, stone, and straw that two brothers built by hand.

Ansh and Raghav Kumar, a pair of architect siblings from New Delhi, moved to a remote town in India to escape the noise and chaos of corporate city life and built the house that they now list on Airbnb.

"Someone sees it as a Harry Potter house, someone sees it as a hobbit house, someone sees it as a fairytale house," Raghav, 32, said.

"For us, it's a labor of love, and every curve tells the story of all the beautiful people who had come and put in the effort."

Corporate burnout

Raghav interned with a German architectural company after architecture school and transitioned into a full-time role at another German company based in Ahmedabad. He said he loved the work culture, the people, and the company's flat hierarchy — but he struggled with working long hours.

"When you're in a corporate setup, the environment makes you believe that the longer you work, you can wear that as a badge of honor," he said. "There were days when I ended up working 48 hours at a stretch trying to cope with all the side deadlines."

Raghav also said there was a disconnect between the architect and the laborer.

"The architect sits in this air-conditioned office, designing and dreaming visionary things, whereas the laborer who builds the project doesn't get any credit," Raghav said. "As architects, we're not able to comprehend or appreciate that labor that goes into a project."

During his three-year stint at the German company, he started traveling more to destress, going to remote mountainous parts of India.

"I realized I was living for the weekends," he said. "That's when I realized I didn't want to climb the corporate ladder."

His younger brother Ansh, 29, also interned in Germany, then freelanced on sustainable architecture projects in mountainous and rural areas of India, where he got a taste for mountain life.

During the pandemic, while quarantining at home in New Delhi, the duo began experimenting with making their own building materials. They tested mycelium from homegrown mushrooms and learned about making cob, a natural material made from soil, straw, and water.

That's where the idea to move away from the chaos of the city and build a house in the mountains took root.

"Covid showed us life is short," Raghav said. "We agreed that we needed to take a leap of faith."

Moving and adapting to Rishikesh

The pair decided on Rishikesh, a town located in the foothills of the Himalayas, known as India's yoga capital. It is about 150 miles northeast of New Delhi.

It's historically been a pilgrimage destination, built on the banks of the Ganges River, but has recently become a hot spot for digital nomads, cafés, and corporate and wellness retreats.

The pair leased land in Rishikesh from a family friend, promising to build a sustainable building on it. And in March 2021, they packed their bags and moved into a house in a small village near Rishikesh.

"From where the car drops you off, you have to cross a tributary of the Ganga on foot via a wooden bridge," Ansh said, "Then you hike for more than a mile to reach the village. So that was another challenge altogether."

Building a house with their hands

In their past architectural work, the brothers used software to do concept drawings. But here, they used sticks and stones around the plot of land to mark out the house plan.

Then came the building phase. They carried thousands of rocks to the building site, trekked in sand on mules, and sourced most of the other materials from around the house.

They put out a call for volunteers on Workaway — a platform that connects travelers with hosts who provide food and accommodation in exchange for work.

The brothers estimated that, over the three years it took to build the house, more than 100 volunteers from 18 countries were involved in construction, along with about 20 local laborers they employed.

They spent about $30,000 on the project, from their savings and their parents' investment.

"You can see the progress every day; the house was getting taller daily, by about six inches to a foot," Ansh said. "So that is quite rewarding compared to eight hours of work in front of the laptop in the corporate world, where you feel exhausted but also like you didn't get anything done."

Finally, in 2024, they finished the house.

Raghav called the final project a "living sculpture."

It's full of organic shapes, with a whimsical thatched roof, and spiral patterns running around its walls.

They listed the two-bedroom, one-bathroom home on Airbnb in April 2024 for around $140 per night.

"Proceed to book only if you are comfortable hiking for 1.5 kilometers in a forest with a backpack, as the property is not accessible by car," says the Airbnb listing. "There's no WiFi in the forest, but you'll get a stronger connection with yourself, your loved ones, and your passions."

They said it's booked out about 60% of the time.

Fittest they have ever been

Now, the duo has built an architecture and design studio in Rishikesh and is working on other natural building projects across India.

Running the studio from Rishikesh has its challenges. They deal with a choppy network — they're eagerly awaiting Starlink — and must deal with safety concerns because the house is near a forest with wild elephants.

But mountain life has changed them.

"We've become the fittest version of ourselves, living here," Raghav said. On the first day of their chapter in Rishikesh, just the hike up to the site winded them both, but they can now do four trips up and down.

"You don't even know when you clock 10,000 steps. You have nature all around you, better air, and you feel your anxiety melt away," Raghav said.

• A trio of journalists tried three big vibe coding apps to see how they stack up.
• We each attempted to build an app on Cursor, Lovable, and Base44.
• With the same prompt on each system, we wanted to see how far we could get.

We three writers have been handed a gift with seemingly infinite potential. A sparkling promise, from vibe coding startups, that we can build anything without understanding a word of code.

Gone are the days, these companies say, when coding novices needed to rely on their techie friends to troubleshoot mistakes.

Over a dozen firms have rolled out tools offering the ability to build apps in seconds. All you need is a good idea and the platforms' free coding credits.

With a growing wave of vibe-coding startups raising big money, questions are emerging: Are these tools meaningfully different? Is the market already crowded? And can this be a sustainable business?

We tried three of the most popular platforms — Cursor, Lovable, and Base44 — to find out what each platform really offers and where they fall short.

Our prompts

We started this experiment at different levels of proficiency.

Chong Ming had coded an app at a vibe-coding workshop. Cheryl, self-taught, had experimented with five vibe-coding platforms and made three web apps. Aditi was a true beginner.

We each set out to make an app. For Chong Ming, a writing companion in the shape of a cute creature. For Cheryl, a newsroom dashboard, a lite version of Asana to keep her team's work organized. And for Aditi, an app that acted like a newsroom photo coach, to deem whether a photo was good to publish.

First impressions

Chong Ming: When I asked Base44 to plan the app, it responded with a few questions to clarify my prompt, with cute emojis. The plan it generated wasn't as detailed as what I've seen from Cursor, but it was user-friendly.

Lovable's plan was even simpler, pared down to a few bullet points. It was just as easy to use as Base44. Within minutes, it generated a web app similar to Base44's.

Cursor's interface seemed built for serious builders looking to ship real products. Its planning questions were more advanced and thoughtful, asking if I wanted an MVP build plan, a clickable prototype, or a full product spec — the kind of distinctions a software engineer would make.

Cheryl: I've always been one for the rule of cool, and Cursor looked really cool, with its all-black dashboard. But there was some charm in logging onto Lovable, with its girlypop, pink-heavy interface, and Base44 offered some cheerful vibes on its tangerine-colored interface, too.

Base44 and Lovable felt more like signing into a website and conversing with a chatbot. With Cursor and its MacBook app, I felt like I was hacking into the mainframe, with all its complicated scrolling lines of code.

Aditi: Off the bat, Cursor looked intimidating, and the option to sync GitHub when logging in made me think it wasn't a platform for a non-technical user.

Meanwhile, Base44 and Lovable were friendly and reassuring, with their gentle prompts: "What will you build next?" and "Ready to build, Aditi?"

Learning curve

Chong Ming: Base44 and Lovable were easy to use. The app plans were written in plain language for everyday users, and the interface was beginner-friendly. It was clear where to click if I needed help or wanted to tweak something.

Cursor was a different story. There were things I had to decipher on my own, like "frontend built with Next.js, React, and TypeScript."

Cheryl: I have never felt more like a dinosaur than when I first tried using Cursor. It was embarrassing having to look up basic terms to know what I was dealing with.

On Base44 and Lovable, I consistently typed in plain English and made the app edits accordingly. I felt like a wizard, watching the app preview morph and shift into view.

Aditi: I'd never tried vibe coding, so I asked AI for help understanding AI. I asked ChatGPT to help me refine my initial prompt into something I could plonk into the vibe coding platforms.

With Lovable and Base44, the learning was intuitive, and it felt like I was talking to ChatGPT. With Cursor, I was completely lost and had no idea where to start.

Then it was time to build the apps

Chong Ming: Base44 built me a writing companion app with a cute egg. The layout felt bland, but it was a full-fledged, functional app created without using up all my credits.

Lovable's build was similar and didn't use all credits.

Both platforms could generate the app; the main variation was in aesthetics. I did appreciate that Base44 and Lovable let me edit the app directly in the interface.

The Cursor build process wasn't as hands-off. Unlike Base44 and Lovable, which ran start to finish, Cursor required me to approve commands and grant permissions to override folders on my computer. As it generated code, I could pause and review it, something that would likely appeal to developers who want control.

Cheryl: The best things in life are free, and vibe coding credits are one of them. On Base44 and Lovable, both platforms make it clear to users that they're cooking with limited credits, and that's fair — compute is costly. The mileage on each platform, however, was slightly different.

Lovable gave me good bones for the project up front and created something that was, aesthetically and functionally, closest to what I wanted. But it burned through more free credits than my Base44 project did, and some things still weren't working in the web app. I was stuck waiting for new credits to drop before I could make tweaks.

Base44 gave me something very close to a complete dashboard, but it lacked some key functionality — the option to delete tasks, or to drag and drop unscheduled tasks into the calendar frame. But that was ironed out within minutes with two additional message prompts.

Cursor's steeper learning curve and multi-step process made it far harder for me to work things out. After 10 minutes of Googling, I gave in and typed into the Cursor chat: "I'm confused. What do I do now? Give me a guide."

I was told to go to Supabase and make some adjustments to the settings, then try to ship it via a local server. At that point, I was coming up on half an hour of getting frustrated with the process.

Aditi: The development process was smooth sailing with Lovable and Base44. With one initial prompt and two additional tweaks, both platforms gave me usable apps that I thought would be handy newsroom tools.

I first tried Base44 and felt childlike wonder when it produced a clean, minimalist interface that let me drag a photo in and judge its quality.

After the initial merriment wore off, I started testing the features. One thing I had not realized was how specific my prompts needed to be, expecting it to anticipate my needs. For example, both platforms initially did not allow me to crop the image or adjust the framing, and instead automatically chose the subject for me. An easy second prompt brought the apps closer to my initial vision — although I quickly learned how to ration my prompts lest I run out of my daily free credits.

Lovable's interface had a neat little photo-scanning animation that I thought added visual interest to the otherwise simple interface.

Now for Cursor. I had to download the app on the MacBook, while the others could run in the browser. When I finally downloaded it and fed it my prompt, it ran lines of obscure code, asked for permissions to things I didn't understand, and made me lose motivation to build anything.

I eventually gave up on trying to make it work, but the app kept prodding me with pop-ups for permissions all day until I force-quit it.

I'll stick to my beginner-friendly platforms until further notice.

How the platforms stack

Chong Ming: Lovable and Base44 delivered working apps and refinements fast, but the quality didn't match Cursor. Cursor broke down what it added and made changes in detail, even if some of the jargon flew over my head.

When I refined the app, Cursor didn't just tweak surface-level things. It suggested enhancements such as adding extra animation frames or making the pet move faster. When I said I didn't want a simple egg, it flagged that a drawn mascot or pixel pet would require new assets — a level of clarity the others didn't offer.

By comparison, Lovable and Base44 suggested things like adding entrance animations, which felt more gimmicky than meaningful.

If I were building something serious, I'd go with Cursor, even if it takes more time and effort to get up to speed.

Cheryl: On both Lovable and Base44, I managed to build workable newsroom calendars and get them from first prompt to publishing within 10 minutes. Base44 gave me a complete, fully functional project I could immediately use and share with my team — and within the free credit range, too. The next day, I used my new set of credits on Lovable to make final tweaks, resulting in a publishable dashboard with all the functions I wanted.

On Cursor, however, I just couldn't figure out what I was doing wrong and why the code wasn't running as I intended. I never got my dashboard off the ground there. Cursor: It's not you, it's me.

If you have a nontechnical background, a clear vision for the app you want to build, but limited time to pick up a little more coding, a one-stop shop like Lovable and Base44 would be more your speed. If you do have more coding know-how, Cursor will give you access and oversight over the coding process within its free credit limit.

Aditi: As a colors-obsessed, minimalism-loving, non-technical person who just wants to build a simple app, here's my leaderboard: Lovable, Base44, Cursor.

The market's flooded with options, so take your pick while companies are being generous with credits

The apps we tried are just a sampling of the vibe coding offerings out there. Other companies, like Emergent and Replit, also offer one-stop-shop platforms that take ideas from conception to shipping fast.

The barrier to entry is low, particularly with free credits on entry-level plans.

So if there was ever a time to try vibe-coding, it's now.

• Two pilots were killed after an Air Canada plane collided with a ground vehicle at LaGuardia Airport.
• Photos from the scene showed the plane on the ground, at an angle, its nose severely damaged.
• The airport will remain closed until at least 2 p.m. ET as federal investigators examine the incident.

An Air Canada aircraft collided with a ground vehicle at New York's LaGuardia Airport late Sunday, killing two pilots and forcing the airport to shut down as investigators examine the crash.

The Air Canada Express flight, a CRJ-900 operated by Jazz Aviation — a Canadian regional carrier that runs shorthaul flights on behalf of Air Canada — struck a Port Authority rescue and firefighting vehicle on the airfield shortly after landing, authorities said.

New York Port Authority Executive Director Kathryn Garcia told reporters early Monday morning that two pilots on board the aircraft were confirmed dead. New York Port Authority told Business Insider another 41 people were transported to the hospital, including 39 flight passengers and two officers.

Garcia said the fire truck involved in the collision was responding to a separate United Airlines aircraft that had reported an odor issue. Two officers in the truck were taken to hospital and are in stable condition with no life-threatening injuries, she added.

The airport will remain closed until at least 2 p.m. ET Monday to allow the National Transportation Safety Board to investigate, Garcia said, adding that federal investigators are already on-site.

Jazz Aviation said in a statement on its website that the plane was carrying 72 passengers and four crew members. The statement did not provide information about the number of injuries or deaths.

Air Canada has set up a helpline for friends and family of passengers on flight AC8646.

The flight left Montreal around 10:35 p.m. E.T., and touched down at LaGuardia at 11:37 p.m., per data from flight tracking website Flightradar24.

"The airport is currently closed to facilitate the response and allow for a thorough investigation," the Port Authority spokesperson said in the statement.

Per Flightradar24, 271 flights at LaGuardia were canceled on Monday.

An air traffic control recording from LiveATC.net appeared to capture the moments before the collision. In the recording, a controller urgently instructs the vehicle to stop. A few minutes later, the controller announces there was an incident on the airfield.

The Federal Aviation Administration issued a ground stop notice for all planes at LaGuardia Airport, per a notice by the agency.

A New York City Fire Department spokesperson told Business Insider that the department had responded to a call at 11:38 p.m., about an incident involving a plane and a vehicle on the runway.

LaGuardia is one of the three major commercial airports serving New York. It said in an X post earlier on Sunday that "weather conditions have caused LGA Airport flight disruptions," and advised passengers to "check with your airline to determine the status of your flight."

LaGuardia served over 30 million passengers in 2025, per the Port Authority.

• Mark Cuban said AI agents will reduce workdays by an hour.
• He said smart companies would reward employees using AI with more time daily.
• Other executives, like Bill Gates and Jamie Dimon, have talked about AI helping shrink workweeks.

Mark Cuban said AI agents will slash an hour of work from typical workdays.

In an X post on Sunday, the billionaire investor wrote that "smart, bigger companies" will let their employees create and use AI agents to improve their productivity.

But he said that more importantly, "they will reduce their work day by an hour to start."

He said that the employees will work one less hour per day while earning the same pay, adding that companies should "reward people doing the daily with more time."

AI agents work as virtual assistants that can complete tasks from start to finish autonomously, without needing user prompts.

Cuban's comments came from one of his several posts on AI on Sunday. In an earlier post, he said he was not an AI "doomer" and did not think the rise of AI would lead to mass unemployment.

"Over time the same shit is available to everyone. The early adopters, that iterated and executed the best, were the winners," he wrote.

Cuban's comments on shorter work days fall in line with those from other tech executives.

Zoom CEO Eric Yuan said in 2024 said that AI avatars would be able to handle everyday tasks like attending meetings, helping to shorten workweeks to three or four days. Microsoft founder Bill Gates and JPMorgan CEO Jamie Dimon both said in 2023 that AI will lead society to a three or 3.5-day workweek.

Cuban, a former "Shark Tank" investor, has been AI-forward in his recent posts on X. In an interview that aired in February, he said AI has ushered in an era where "some kid in a basement" with a good idea could transform the industry.

Cuban has also talked about AI agents, saying in December that new graduates should go for small to medium businesses and help them adopt AI agents, a task that big companies don't need them to do.

While AI agents have been the latest productivity buzzword, research has found that they still require plenty of human intervention. A Workday survey in January showed that nearly 40% of AI's value is lost to rework and misalignment, due to workers having to check for errors and hallucinations.

Another survey, published in the Harvard Business Review earlier this month, found that some employees are experiencing "AI brain fry," mental fog from using too many AI tools at once.