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 pundits: 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.

How Google's AI Studio builds an Android app

On Tuesday, when Google showed off AI coding on a Doom-like game, I 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 other coding tools, 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.

The first app: MOOD, a Doom-like text adventure

One minute later, it already had five design mockups. 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.

I wasn't too surprised to find Gemini's "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 and iterative development

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. This kind of iterative development, where the AI acts as a co-pilot that can quickly patch problems, is one of the most promising aspects of the tool. However, it also highlights a key limitation: the AI can only fix what it can identify from your description, and it doesn't always understand the full context of a bug.

A calorie counter with questionable data

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.

This experience underscores a broader challenge with AI-generated apps: they are only as good as the data and reasoning the AI can access. While the tool can produce something functional, it often lacks the domain expertise needed for accuracy in specialized areas like nutrition. The calorie counter might be useful for rough estimates, but users need to be aware of its limitations and double-check critical information.

A terrible Mario knockoff: Super Peach Rescue

Last and least, I thought I'd better check if Google is still letting people make bad Nintendo knockoffs like many did with Project Genie 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 broader implications of AI-assisted coding

Google's AI Studio represents a significant leap in democratizing software development. By allowing anyone to type a description of an app and get a running version within minutes, it lowers the barrier to entry for creating custom tools. This could be a boon for hobbyists, small businesses, and people who need niche apps that don't exist in the mainstream app stores. The technology is clearly still in its early stages, but its trajectory suggests that within a few years, building simple software could become as easy as asking a question.

However, there are several concerns that come with this power. The quality of the output varies wildly, as seen with the buggy games and inaccurate calorie counter. The AI's suggestions are often generic and lack the creative flair that a human designer would bring. Additionally, the daily usage limits and eventual paywalls could create a new kind of digital divide, where those who can afford to pay get better and more reliable AI assistance. Moreover, the ease of creating apps might flood app stores with low-quality, derivative works, making it harder for legitimate developers to get noticed.

Another critical issue is intellectual property. The AI has no qualms about generating clones of popular games like Super Mario, complete with Nintendo's iconic characters and gameplay elements. This raises legal and ethical questions about copyright infringement. While the AI itself does not know it is infringing, the end user is still responsible for the apps they distribute. Google has previously taken down tools that allowed for easy creation of infringing content, but the genie may be out of the bottle.

Despite these drawbacks, the technology is undeniably impressive. The ability to go from an idea to a working app on your phone in minutes is something that would have been unthinkable just a decade ago. For developers, it could serve as a rapid prototyping tool, allowing them to test concepts before investing significant time in coding. For non-developers, it offers a tantalizing glimpse of a future where software is truly personalized. The personal software revolution is coming, but it will be a bumpy ride — complete with bad text adventures, questionable calorie counts, and unpassable jumps in knockoff platformers.

At its heart, Google's AI Studio is a testament to how far generative AI has come. It can write code, design interfaces, and even attempt to fix bugs. But it is still a tool that requires human oversight, patience, and a willingness to accept imperfection. The apps I built are not ready for prime time, but they are a proof of concept. For anyone willing to put in the effort to iterate and refine, the potential is enormous. The question is not whether AI will change how we build software, but how quickly we can adapt to a world where anyone can be a developer, even if only temporarily.

Source:The Verge News