In this session, we'll explore different GenAI use cases using ML Kit APIs to understand when on-device GenAI is ideal for an app and also understand how to evaluate existing GenAI use cases to see if on-device models can satisfy their quality bar.
Resources:
Android ML Kit overview → https://goo.gle/4kd3hM1
Android AICore Developer preview → https://goo.gle/4izxio1
Android AI Edge gallery → https://goo.gle/4smvtOK
Android ML Kit samples → https://goo.gle/4sDJS9z
Jetpacker samples → https://goo.gle/4iBaynK
Speakers: David Chou
Chapters:
0:00 - Introduction to on-device AI
4:32 - Optimizing Gemini nano performance and benchmarks
8:27 - Overview of new Gemini API capabilities
10:00 - End-to-end scam detection walkthrough
13:40 - Triaging inputs using prompt API and function calling
16:17 - Retrieving order data with embeddings and appsearch
18:58 - Comparing order details and defining audit verdicts
23:00 - Recap and closing remarks
Watch the intelligent apps sessions from Android Dev Summit 2026 → https://goo.gle/ADS26-Intelligent-Apps
Watch all the sessions from Android Dev Summit 2026 → https://goo.gle/ADS26-All-Sessions
Subscribe to Android Developers → https://goo.gle/AndroidDevs
#AndroidDevSummit2026
Event: Android Dev Summit 2026
Products Mentioned: ML Kit, ML Kit GenAI, Android Performance