There’s nothing fun about apps, until you try to make them useful

After a week of programming apps with Nothing’s Essential Apps Builder, I was at a loss. I support the smartphone maker’s vision of software that adapts to you, not the other way around, but right now it’s not working. It’s hard to see how this goes from a cool novelty to a reliable tool without serious improvement, and a level of consumer patience that may be hard to find.

Nothing clears the playing field for “Native operating system based on artificial intelligence“Last year: something that would go to the heart of its hardware and make it feel more personal and more adaptable. While it’s not really an operating system – It’s more of an AI layer layered on top of Android – It’s a backend for Essential, said CEO Carl Pei Edge It is the umbrella company “name for all our AI-related products”. Under this umbrella are core apps, which are small, AI-designed widgets that reside on your home screen. Given this limitation, “Basic Tools” would probably be a more honest name.

These apps are created in the Apps Builder within Playground, nothing is available in the App Store. The presentation is very simple: describe what you want in plain language, Builder will do it, and then send it to your phone. There’s no setup and no need to know how to program, although I’m sure that wouldn’t hurt. The Builder will sometimes ask clarifying questions, and if you don’t like his first attempt (usually you don’t), you can repeat instead of starting from scratch.

Creating widgets that you want to keep on your home screen is another matter. I’ll admit that I don’t really use the tools in the first place, so I’m averse to selling them, but even when I judge them on their own terms, I immediately notice how stark a gap there is between “it works” and “I’ll use this.”

First, I asked Builder for a water tracker to reward me with a smiley face if I drank eight cups. The result wasn’t pretty, but it worked. The widget that displays upcoming appointments for the day, taken from my connected Google Calendar, was fairly easy to implement and was effective on the first try. I then switched to the little yellow widget that offered a different smiley emoji every time I unlocked my phone, which I later edited to blue. Updates were easy, just tweaked the Builder and installed it on my phone. If you need to retrieve things, everything is stored and neatly organized in project folders in Playground.

However, not everything was smooth sailing, and creating more ambitious tools was a much messier process. The shopping list highlighted the limitations of pushing app functionality into a widget-sized space, while displaying only one of the items I typed. I noticed that many of my UI elements would cut off parts of the text in some places. The location was also difficult. Instead, I used a custom weather widget for the four London locations I gave Builder as an example, and it showed me all four forecasts on one interface.

The ugly Pomodoro timer was even worse: it stopped counting down the moment I locked my phone, which conflicted with the point of setting it and coming back later. I tried troubleshooting, but nothing stuck. Even the simple photo tool, which pulls photos from the camera roll, didn’t work at all, and Builder’s “Fix with AI” button didn’t help either.

Upon reflection, I feel that there are two main issues that prevent me from embracing Nothing’s vision of an ever-evolving ecosystem of biometric applications. The first is the natural result of using the product in early beta. Builder is limited to Nothing’s Phone (3), only supports 2×2 and 4×2 widget sizes, and only fully supports site, contact, and calendar connections.

In the future, nothing says that apps will fully support a much wider range of functionality, including fetching data from the Internet, media library, camera access, and access to Bluetooth devices. Additional widget sizes are planned for around late March, including compact 1×2 layouts and larger 4×4 layouts. More devices will also be supported and the general launch will open up a much wider range of user-created apps, which are part of The new ecosystem for creators The company hopes to sponsor other people’s apps and let you “remix” them. It is not clear when this will happen; Nothing says “public release will follow once system integrations are stable, permissions handling is reliable and cross-device compatibility is confirmed.”

The second issue is a potentially fatal obstacle to a project like this: me. I’ve been reporting on AI tools for years, and there’s one pattern that keeps recurring — no matter how capable a system is, the hardest part is knowing how to use it to achieve its potential. I experienced this right away with Nothing’s Essential App Builder. She seemed very capable and had a lot of potential, but I didn’t always know what I wanted, and when I did, I didn’t always know how to ask for it. An ecosystem built on emotions is a great idea, but sometimes emotions aren’t enough.