Building with AI on Android | Spotlight Week

Tune in to hear from our panel of experts on topics like hero use cases for AI powered features on Android, how devs can get started with AI on Android, and more!
Featuring: Kateryna Semenova, Miguel Ramos, Oli Gaymond, Khanh LeViet
Chapters:
0:00 - Introduction
2:07 - What is new with AI on Android?
3:13 - What are the benefits of running on-device?
5:08 - How developers can experiment with custom models?
8:05 - What apps are using on-device capabilities?
11:01 - When on-device models work well and when devs should look for cloud solutions?
13:24 - How can developers integrate more powerful features, like chat bots?
16:05 - What about user privacy?
18:55 - How should devs approach AI feature development?
20:57 - Use case scenario: Building a boba tea app
32:44 - What’s coming next in AI?
38:02 - Conclusion
Resources:
Learn more → goo.gle/ai-on-...
Nano blog → goo.gle/4gBq6oD
Gemini API blog → goo.gle/4esXlc7
Watch more Spotlight Weeks → goo.gle/Spotli...
Subscribe to Android Developers → goo.gle/Androi...
#Featured #AndroidDevelopers #AndroidAI

[@AndroidDevelopers]

Watch more Spotlight Weeks → goo.gle/SpotlightWeeks

[@JorgeNonell-p9p]

Great presentation guys! From my readings, seems like one advantage of LiteRT over MediaPipe is having finer grain controls over what models are used, including the ability to quantize them. One use case I am thinking about for adding on-device AI capability to our android app is to be able to support various hardware configurations with more and less memory for example. Do you think it would be possible to switch to a model at runtime that would perform best on the hardware of that particular device? Would that require a ton of work to implement in your opinion?

[@shubhamjain608]

Nice conversation 👍