My Experience Writing Zone 2 Trainer for Android

Zone 2 Trainer started as a simple idea: I wanted a lightweight way to stay honest about easy aerobic work without committing to another subscription or buying another dedicated device. The app became both a fitness tool and a test case for how far modern AI coding assistants can carry a non-mobile developer.

For the last couple of months, I have been developing an Android application to enhance my endurance and recovery. Most applications on the market require an active subscription and a special device. With the current developments in AI-assisted software development, I was able to step out of my comfort zone and build an application from scratch using Android Studio, Antigravity, and Codex.

That matters to me because I am not a developer by trade. I am closer to a tinkerer who is comfortable with scripts, databases, and infrastructure than someone who spends every day building polished mobile apps. Zone 2 Trainer became a useful test of how far AI coding tools can take someone like me when the goal is a real app, not a weekend demo.

Starting With Android Studio and Gemini

Android development has come a long way since I first dabbled with it. I began with Android Studio because it was the environment I already knew. The built-in chat interface gave me enough help to write a first version with a functional, if rough, interface in a couple of days.

That first phase was all about getting the app to exist. Gemini was helpful for moving quickly through unfamiliar Android patterns, but the output still needed a lot of shaping. The app worked, but it had the feel of a prototype.

Adding Polish With Antigravity

The second phase was a mix of Android Studio and Antigravity. This is where the app started to feel more professional. The built-in skills from Antigravity were especially useful for visual polish and user experience work.

At this point, the difference was not just that the app looked better. The workflow changed. I could describe the direction I wanted, review the result, and keep tightening the interface without getting stuck on every small Android implementation detail.

Stabilizing With Codex

The third phase was stability and acceleration. This is where I added Codex to the mix and stabilized the app end to end. I improved the test coverage, chased down rough edges, and built a stronger foundation for future enhancements.

Gemini was useful, but the limits were painful. The Gemini Pro plan had strict limits, and the most time-consuming part of the work became waiting between rate-limit windows before I could finish a feature. That was extremely limiting.

I first used Codex through my ChatGPT Plus subscription. It helped with memory leaks and race conditions, but it still required a lot of waiting between sessions. After upgrading to the Pro tier, I was able to complete an entire feature set for a given session in one go. That changed the way I worked.

The biggest difference was trust. Codex understood the nuance of my prompts better than Gemini did during this project, and the code quality improved. My Crashlytics reports stopped firing alerts about race conditions and crashes after I adopted Codex as the main coding assistant.

What I Learned

The lifecycle of the app ended up falling into three phases:

  • Android Studio with Gemini for the first functional version.
  • Android Studio with Antigravity for polish and product feel.
  • Codex for stability, test coverage, and end-to-end implementation.

This work predates my testing of Gemini 3.5, and most of Zone 2 Trainer was built using Gemini 3.1. I still plan to run 3.5 through its paces. But for this project, Codex became the tool that helped me finish the work instead of only starting it.

The larger lesson is that AI coding tools are not magic, but they are changing who can build useful software. I still had to make decisions, test the app, and care about the details. The difference is that I was able to stay in the work long enough to turn an idea into something real.

References

Comments

Post a Comment

Popular posts from this blog

Running CockroachDB with Docker Compose and Minio, Part 2

This is my second post on creating a multi-service architecture with docker-compose. This is meant to be a learning exercise and typically docker-compose is used to set up a local development environment rather than a production-ready set up. I regularly, find myself building these environments to reproduce customer bugs. For a production-specific application, refer to your platform vendor documentation. At some later time, I will cover Kubernetes deployments that can be used as a stepping stone for a real-world application. Until then, let's focus on the task at hand. We're building a microservice architecture with CockroachDB writing changes in real-time to an S3 bucket in JSON format. S3 bucket is served by a service called Minio. It can act like an S3 appliance on premise or serve as a local gateway to your cloud storage. Let's dig in:
Read more

VirtualBox options to start VM in Normal, Detached and Headless Modes

Image
I've been an avid user of VirtualBox for a long time! Much of what I've learned in my career had something to do with VirtualBox. I do all my testing and new tutorials in VirtualBox, I use Hortonworks Sandbox VirtualBox image for my work. This is probably not a new feature but it is definitely new to me because I just noticed it, VirtualBox has an option to run in different modes, at least from the GUI perspective. I know there's a lot of untapped potential in using the VBox CLI but I haven't had much need for it yet. Back to the topic, you can now launch your VMs in headless and detached modes right from the GUI! Usually, when I launch a VM in normal way, the VM window just hangs there and is pretty annoying. I prefer to SSH to a running VM from a console instead of using the VM window. Now I can launch a VM in headless mode and it's business as usual. No extra windows, and I bet the memory toll on my machine is also smaller. When you click on start your VM, you no...
Read more

Digsby is bringing out a Linux and Mac client very soon

Hey all, my new favorite multi-protocol IM client is soon to become a multi-platform client. It is still in beta and they're already rolling out a client for the other two platforms. It is a great news to me because I literally fell in love with Digsby on Windows and every time I find myself using Kopete or Pidgin on Linux I yearn for Digsby. It is just so great at what it does. Hope the Linux client is not crippled and offers just as many features as Windows. Sign up for notification here . p.s. Ars did a nice and simple review of Digsby here . Talk to you soon.
Read more