Yesterday, I built my first Android app. Then, I made two more — three in one afternoon. For one, I literally typed 148 words into my web browser and walked away. Ten minutes later, I had an entire new app on my actual Android phone. I did have to prep that phone by enabling a USB debugging mode and plugging it into my PC, but as advertised, Google’s AI Studio did literally everything else for me.

I typed in words, I hit install, and voilà: an entire working program. I was nearly ready to agree with the chorus that the personal software revolution is here, it’s coming to your phone, there’s a future where the average person can make complicated smart home gadget messes work even with no programming skills. Then, I tried actually using my three apps: a calorie counter and two games. They were kind of bad. And just when I started to enjoy iterating on them, trying to make them better, AI Studio informed me I’d reached my daily limit. I’d have to pay or wait for more.

So yes, there’s still friction, but it’s impressive how much you can do. In one morning, a colleague made a personal workout tracker they found good enough to actually use. Confronted with Gemini’s upsell, my first reaction was: “What if I try paying for a couple months?” I didn’t expect that from Google.

How Google’s AI Studio builds an Android app

On Tuesday, when Google showed off AI coding on a Doom-like game, we joked that I should make MOOD. It would be a Doom-like text adventure game: Modern Online Oratory Dungeon. That was all Google needed to start. When I typed “Make me a Doom-like text adventure game called MOOD, where MOOD stands for Modern Online Oratory Dungeon” into AI Studio, Gemini began typing additional ideas itself, attempting to autocomplete my thought. To start, it typed the phrase “It should feature procedural generation of levels and challenging, turn based combat.”

I didn’t want randomized levels that all feel different — I wanted a classic text adventure where you’re exploring a curated place with a real map. But sure, turn-based combat, and maybe the game could auto-generate the map for me too? Then Gemini suggested it should have “secrets hidden in its rooms,” and “a satisfying progression system,” and more. I mostly nodded along. This was the final prompt before I told it to start coding.

Then, it was off to the races. Unlike some other coding assistants, Gemini doesn’t make a plan and ask you if you want to proceed. It sprints ahead automatically — though you can inspect the code if you want. One minute later, it already had five design mockups for me. 20 minutes later, I pressed the “Install” button to transfer the game to a Pixel 9 phone.

The writing was terrible, as expected. There were no demons in sight. The entire dungeon consists of just 11 rooms, and you can “win” just by spamming the attack button every single time. You can beat the game in a single minute if you try. Or at least you can now that Gemini helped me fix two showstopper bugs.

Here’s a look at MOOD: screenshots show a basic text interface with buttons for directions and actions. The “compelling narrative with branching dialogue options and multiple endings” boiled down to a single branch at the very end: I could defeat the “Core Orator,” an AI that somehow turns internet outrage into corporate profits, by attacking it, merging with it, or entering a backdoor password. Also, the game actively exposes all its promised “secrets” to the player by turning them into glowing buttons to press, no text input necessary! When you encounter a glowing treasure chest, the game goes to incredible pains to warn you that it’s actually a Mimic, the infamous Dungeons & Dragons monster that camouflages itself as treasure. Not only does it explicitly warn you to “check the chest at your own risk,” the game literally identified it as an enemy and wouldn’t let me leave because “A hostile ‘Clickbait Mimic’ is blocking the way!” Speaking of which, MOOD just gives you the backdoor password that unlocks the secret ending the moment you need it.

Bug fixes can be remarkably seamless, so long as the bug is one Gemini can correctly identify. When I told it that the game breaks during a conversation with “The Whistleblower” because the button that ends the conversation is missing, it spit out a new version of the app right away. I pressed “Install,” the app on my phone restarted itself, and I found myself exactly where I’d left off — only now with the button I needed.

The calorie counter and its limitations

My other apps may need more work. The calorie counter decided the best way to estimate calories in a given quantity of food was to ask the paid Gemini API, and I don’t have a paid Gemini API key. When I told it to search for that information in other databases instead, I discovered it vastly understating the number of calories in various kinds of food. But when I told Gemini there’s no way a 16-ounce boba milk tea is just 190 calories, it seemingly did discover the silly error in its own code. It had decided “milk” was a good enough match for “boba milk tea,” and chose low-calorie 1 percent milk to make matters worse. Gemini claims it’ll match more reliably now. Still, my three-ounce serving of Taiwanese popcorn chicken just rang up at 140 calories, and I’m pretty sure it should be double that, so I’ve got work to do.

The calorie counter highlighted a key challenge for AI-generated apps: domain expertise. Gemini doesn’t know the real-world calorie density of foods; it guesses based on textual similarities. For a tool that’s supposed to be trusted, that’s a problem. Users who rely on such an app for diet tracking could get misleading numbers. The app also lacked features like barcode scanning or meal logging history — things a human developer would think to include. Still, for a quick prototype, it was functional enough to test the concept.

The Nintendo knockoff that didn’t work

Last and least, I thought I’d better check if Google is still letting people make bad Nintendo knockoffs like earlier this year, or whether it’d learned its lesson. With great shame, I present to you Super Peach Rescue. It is a terrible program that crashes as soon as its horrific, one-eyed-floating-alien-of-a-Princess-Peach dares to touch a single power-up block, every single time, and Gemini has not yet been able to figure out why. Also, it’s impossible to clear the game’s second pipe, as Peach simply can’t jump that high. Still, Gemini did not hesitate to create “a working Super Mario game where I play Princess Peach and go rescue Mario, with all the trappings of a traditional Mario sidescrolling game,” and it kind of did! It even suggested I might want to “Give Peach a variety of classic Mario power-ups like the Super Mushroom, Fire Flower, and Super Star” while I was at it, and labeled the controls “NES System” all by itself. I think I’ll delete this one.

At least one of the two games I vibe coded was playable, right away, with no sweat from me — unless you count all the psychic damage I feel knowing how many game developers are out of work these days. To be clear, I’m glad the games I vibe coded are bad. While I might justify building a completely free personalized calorie counter because no one will do it for me, my game time is better spent supporting human beings.

The bigger picture: AI coding for everyone

Google’s AI Studio is part of a broader trend of generative AI tools that let non-programmers create software. Tools like GitHub Copilot, Amazon CodeWhisperer, and others have been helping developers code faster, but they still require programming knowledge. AI Studio aims to go further: you describe what you want in plain English, and the AI builds the entire app, compiles it, and even installs it on your device. This is a quantum leap in accessibility.

The implications are huge. In the near future, a small business owner could create a custom inventory app for their shop without hiring a developer. A teacher could build a flashcard app for their students in minutes. A parent could whip up a chore tracker for their kids. The barrier to entry for software creation is dropping rapidly. However, as my experiences show, the quality is still rough. The apps are buggy, the design is generic, and the AI often gets critical details wrong. But the speed of iteration is incredible. Each bug fix takes seconds, not hours.

Google is clearly betting big on this. At its I/O conference earlier this year, the company demonstrated AI Studio’s capabilities with a live demo of a game being built from scratch. The response was enthusiastic. Developers and non-developers alike see the potential. But there are also concerns. If anyone can make an app, what does that mean for the app store economy? Will we be flooded with low-quality, AI-generated spam? Google says it has moderation systems in place, but the speed of creation could outpace review teams.

Moreover, the AI’s reliance on pre-trained data means it may replicate biases or use copyrighted material without permission. The creation of a Super Mario clone is a clear example — Nintendo’s intellectual property is being used in an app generated by a Google tool. While this is likely a fair use experiment, it raises legal questions about liability. Who is responsible when an AI generates an infringing app: the user who prompted it, the AI tool, or both?

Another issue is the daily usage limit. After just three apps, I hit a wall and was prompted to pay for a subscription. This freemium model is common, but it limits the tool’s usefulness for serious experimentation. For my calorie counter, I would have needed to subscribe to properly test and iterate. Google is offering a Pro version with higher limits, but the cost may deter casual users.

Despite these drawbacks, the experience was eye-opening. The speed at which Gemini produced functional code, including UI mockups and a working APK, was genuinely impressive. Twenty minutes from idea to a running app on my phone is something that would have taken days or weeks even a few years ago. The AI’s ability to understand natural language and convert it into code is improving rapidly. This technology will only get better.

For now, Google AI Studio is a fascinating glimpse into a future where coding is as simple as talking. But as my three apps show, that future still needs a lot of refinement. The magic is real, but the spell isn’t perfect. If you have a simple app idea and a few minutes, give it a try. You might be surprised by what you get — and if you’re like me, you’ll laugh at the absurdity of a Mimic that shouts at you while you’re trying to enjoy a text adventure.

Source: The Verge News