While perhaps not as restrictive as some had feared, Android’s upcoming sideloading changes to reduce exposure to malicious apps are undoubtedly controversial. Power users are the most inconvenienced, either having to remember to go through Google’s new Advanced flow (complete with a 24-hour wait) ahead of time or push an app install over the Android Debug Bridge tool. While the latter is very powerful, it’s not particularly user-friendly.
I don’t have a problem using ADB via the command line every now and again. But between remembering where I put the executable, opening a terminal window, connecting a device, and pasting in the APK file path, it’s a bit of a chore. Booting up a small app on my PC to handle much of the legwork would be much faster.
Yes, there are already options on the market, such as ADB AppControl, EasyADB, or QuickADB. However, I wanted to build something myself that specifically focuses on the APK installation workflow — wireless debugging pairing, file/directory browsing, and bundle unpacking — rather than a full ADB control suite.
Have you ever use Google's ADB tool? 552 votes I use it fairly often 45 % I've used it one or twice 37 % Never used it 11 % I have no idea what ADB is 7 %
While I’m a moderately capable programmer, between work and two kids, I don’t have the time to write an app entirely from scratch. So I thought I’d give AI-assisted “vibe coding” a try. This had the added benefit of letting me try out a new programming language I wasn’t familiar with: Go.
Why Go? It’s a simple language that’s a perfect fit for a compact project like this (no need for Rust), yet it easily compiles into a small, cross-platform executable (sorry, Python). Plus, I wanted to build a cool-looking terminal app using the beautiful Bubble Tea TUI framework that I’d recently come across. With the design in mind, I set off to find an AI agent to help me.
The trials and tribulations of vibe coding
Robert Triggs / Android Authority
I’ve dabbled in AI tools enough to know that simply asking one to build an application for you is a gamble. Expensive models from Anthropic and OpenAI can one-shot simple tasks, but you often end up in an exhausting back-and-forth to resolve bugs when you let an agent loose on a complex project. To interact with ADB and build a terminal-based UI, I decided I wanted a more hands-on approach.
I wasn’t about to spend hundreds of dollars on Opus 4.6 for this little project. Even with careful planning, there’s always a risk that models get stuck in an expensive build loop or hit an inescapable problem. Instead of asking Claude or Codex to handle the task themselves, I paired my usual IDE with OpenCode and its very affordable $10 Go subscription. That gave me access to MiniMax M2.7 and the very impressive GLM 5 to use alongside my slower human brain and keyboard-worn fingers.
... continue reading