One Feature, Two Timelines: Flying Solo or with an AI Copilot

Two years ago, I worked on a visually challenging feature in an Android project. This feature involved a wide variety of animations, a custom collision detection algorithm, and the need to maintain acceptable performance across a wide range of devices. The development process was bumpy and quite long — and ultimately costly for the project. But what if I hadn’t been alone with Android Studio? How much time and effort could I have saved with a Copilot by my side? This talk isn’t about promoting or rejecting AI tools. It’s a side-by-side comparison between the actual development of a real-world feature, and what it could have been like with a bit of AI assistance. I’ll walk you through the original implementation: the technical challenges, the decisions made, and the time it took. Then, I’ll rebuild a similar feature using AI tools like GitHub Copilot — highlighting the pros, the cons, and whether it’s worth the hype. Let’s face the changes AI is bringing to our daily work, and explore where — and how — it could actually be useful, through this hands-on case study.

  • Sandra Dupré DNA.inc Android Developer


Summary

  • Dates 2025.09.11 / 12:20 ~ 13:00 (40min)
  • Place Meerkat
  • Language English (Japanese interpretation available)

Intended audience

People who: Develop Android specific features Want to learn from real-case experience Ask themself questions around AI position in our daily work life

Android is a trademark of Google LLC. The Android robot is reproduced or modified from work created and shared by Google and used according to terms described in the Creative Commons 3.0 Attribution License. Android, Google Play and the Google Play logo are trademarks of Google LLC.

© 2014- DroidKaigi Committee