| Registration | |
| Opening | |
| Google I/O 2026 Keynote Recap | Missed the livestream? We’ve got you covered. This session compresses hours of Google I/O keynote announcements into a high-density, developer-focused recap. |
| Production Reality Check: Balancing Quality, Speed, and Cost at Scale | What does it actually take to ship enterprise AI agents at scale? This session breaks down the architectural blueprints, infrastructure shifts, and governance guardrails required for production deployment. |
| Turn your ideas into real apps with Google AI Studio and Firebase | Sharing and demo session on turning ideas into real applications using Google AI Studio and Firebase. Showcasing practical examples and workflows for developers to leverage these tools effectively. |
| Tunix: Tune in JAX | This session introduces Tunix, a JAX-based framework for efficient fine-tuning and alignment of large language models. Participants will learn how to adapt open-source LLMs using modern techniques such as supervised fine-tuning and preference optimization while leveraging the performance of JAX. |
| Antigravity Challenge: Build with Google AI session | Learn about Google Antigravity use case with GDG Bangkok community. |
| Break | |
| What’s New in the Gemma 4 Open SOTA: From Local to Physical | Unlock the next frontier of open-source AI. In this quick-hitting recap, we’re breaking down the massive leaps forward across the Gemma ecosystem announced at Google I/O. Discover how the brand-new Gemma 4 lineup pushes the boundaries of open models, featuring cutting-edge Quantization-Aware Training (QAT) for ultra-efficient deployments and the debut of DiffusionGemma for advanced generative capabilities.
We’ll dive deep into major upgrades in native multimodal capabilities, advanced reasoning, and complex function calling. Most importantly, we'll shift from theory to practice with hands-on showcases. You’ll see exactly how to deploy Gemma 4 entirely on device.
- Privacy-first, highly capable local LLM (on-device) handling complex tool-calling workflows.
- Low-latency intelligence directly on hardware to power autonomous robotics.
Whether you are a developer, researcher, or hardware enthusiast, this session will show you exactly how to build the future locally with Google's latest open models. |
| Rush Flutter to Native Speed — with Rust | Resizing or processing an image in Flutter feels way too slow next to native — and it's not your fault. In this talk we'll fix it with Rust and hit real native speed. How much faster? Come and see. |
| Expanding Beyond the Phones | Developing for Android has evolved beyond just for phones. Over the past few years, Android OS has been expanded to wearables, auto, tablets, foldables and now, desktop. Developing for just phones are no longer enough for an app to thrive in the Android ecosystem. So, what can we as developers do to make our apps adapt to user's devices and behaviors.
The talk will explore different APIs that Android developers can use to write adaptive UIs and how we can architecture our UI layers so that we can scale it to any devices. |
| Beyond the Click: What the Web Looks Like in the Agentic Browsing Era | For decades, the internet was built for human eyes—we search, we scroll, we click. But the next major user of your website isn’t a human; it’s an AI agent acting on their behalf. As we shift from a web of passive "page views" to a web of autonomous "actions completed," the digital landscape is fundamentally transforming.
This talk explores the rise of the Agentic Web, looking beyond human-centric UX into Machine Experience (MX) design. Discover how websites are evolving from static document libraries into open, machine-readable capabilities—and learn what it takes to build a digital presence that AI agents can seamlessly discover, interpret, and act upon. |
| Closing | |
