🎟️ Once you RSVP 👉 here , you'll automatically receive an email with the link to join the online event. ❗ This event will be held in Greek language.

----------------------------------------------------------------------------------------

Another #GDGAthens meetup is just around the corner! Save the date for Wednesday, 15th July between 19:00 - 20:00 and join us (online). This is a workshop meetup about AppFunctions and how to make your Android App discoverable by AI Agents!

----------------------------------------------------------------------------------------

👊 7:00 PM - 7:05 PM: Welcome

💬 7:05 PM - 7:45 PM: AppFunctions: Making Your Android App Discoverable by AI Agents

💬 7:45 PM - 8:00 PM: Q&A & Closing

----------------------------------------------------------------------------------------

⏰ 7:05 PM - 7:45 PM
💬 AppFunctions: Making Your Android App Discoverable by AI Agents
🎤 Ioannis Anifantakis | Android Google Developer Expert (GDE)

💻 Instructions: Attendees should have the latest version of Android Studio installed, along with an Android 16+ emulator that includes Google APIs / Google Services. A Starter Code Repo and a Finished Code Repo will be provided on GitHub, so even those who cannot actively follow along can still watch the workshop and access the completed code afterward.

At Google I/O 26, Google demonstrated AppFunctions. This is a new Jetpack library that turns parts of your app into tools an AI agent can discover and execute on-device. If you have worked with the Model Context Protocol (MCP) on the server side, this is the Android-native equivalent: same idea, but the tool lives inside your app and runs locally.

This workshop is a hands-on introduction. Starting from a small Compose + Room sample app. We will add a working AppFunction step by step. We finish by executing the function end-to-end with adb, against the same OS-level registry a real agent would read. Along the way, we discuss the shift in mindset AppFunctions is asking us to make; most notably, that your KDoc becomes runtime input to an LLM rather than only documentation. By the end, attendees will have a function on their own device that an external caller can discover by description and execute even when the app is closed. A laptop with the latest version of Android Studio and adb available to your terminal is all you need to follow along.