Google for Developers

Here’s a Kotlin focused developer challenge: A system is supposed to catch duplicate requests by comparing IDs. Two IDs are clearly the same. The logs confirm it. The values match. However, the duplicate check fails, and the same request goes through twice. Watch the clip and share what you think is going on in the comments. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Anaya Mehta

Here are some prompting tips that can save you time and yield a better product. Resources: Learn more → https://goo.gle/Build-With-AI Subscribe to Google for Developers → https://goo.gle/developers

Watch our Build with AI 2026 highlights and see how AI architecture brings together all types of developers. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Google AI

Want to speed up your prototyping? Here is how to use AI Studio to build and deploy a native Android app using just prompts. Subscribe to Google for Developers → https://goo.gle/developers

When you ask an agent to update a feature, it has to search your entire codebase, which can limit the effectiveness of your AI coding agents. The fix? Separation of concerns. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Christy Yao

Fixing bugs is definitely a process. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Pete King

See a behind-the-scenes look at how Google developers got to network, connect and create at I/O Connect Berlin! Subscribe to Google for Developers → https://goo.gle/developers

This video demonstrates how to create and install a personalized Android application using AI Studio without requiring technical or Android-specific knowledge. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Google AI, Android

Hear from Erin Walsh and Mohammadreza Heydary to discover how to build powerful AI features directly into your users' hands. Explore Google's product suite to integrate on-device AI across mobile, web, and more, to keep data private, latency low, and enable offline capabilities by deploying your favorite models directly to your apps. Dive deeper into how to use the LiteRT-LM APIs to run LLMs on your device, and harness your model's agentic capabilities by creating your own Skill. Note: this is a live workshop recorded at I/O Connect Berlin, discover more about: Skills Notebook: goo.gle/4d78UHX LiteRT-LM Open Source Project: https://github.com/google-ai-edge/LiteRT-LM AI Edge Gallery: https://github.com/google-ai-edge/gallery Subscribe to Google for Developers → https://goo.gle/developers Speaker: Erin Walsh, Mohammadreza Heydary Products Mentioned: Google AI, Gemini

Learn about the new dynamic callbacks feature available for Google Pay on Android, designed to enhance your checkout experiences. We’ll dive into the mechanics of listening and responding to user modifications—such as shipping address or shipping option changes—directly within the native checkout sheet in real-time, highlighting callbacks like onPaymentDataChanged and onPaymentAuthorized. Developers will find clear explanations and an example of implementing these secure callbacks to dynamically update pricing, adjust taxes, and execute secure inline payment authorizations before the transaction completes, ensuring a seamless purchasing experience for their users. Resources: Get started → https://goo.gle/pay-android-dpu Connect with us: Join the conversation in the #payments channel on Discord → https://goo.gle/payments-dev-community Watch more Live Google Pay integrations on Android → https://goo.gle/live-google-pay Follow @GooglePayDevs on X for more content like this → https://goo.gle/GooglePayDevs Subscribe to Google for Developers → https://goo.gle/developers Get support: For assistance with your implementation, create a support ticket from the Google Pay & Wallet Console → https://goo.gle/4hSy658 Subscribe to Google for Developers → https://goo.gle/developers Speaker: Dominik Mengelt Products Mentioned: Google Pay

Unpack the latest capabilities of Google's state-of-the-art GenMedia suite—including Veo, Nano Banana, Genie, and Lyria—and learn how to build the next generation of creative applications with Guillaume Vernade. Guillaume explores real-world examples, and share best practices for prompting and generation, alongside how to seamlessly integrate these models into your products. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Guillaume Vernade Products Mentioned: Google AI, Gemini

Philipp Schmid and Mariano Cocirio demystify agent development and discover the fastest path to production with Gemini. Experience the power of "vibe coding" in Google AI Studio to rapidly build and iterate on applications using natural language and dive deeper into building your own agents with the Gemini Interactions API and Managed Agents. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Philipp Schmid, Mariano Cocirio Products Mentioned: Google AI, Gemini

No, but really. Did you review the generated tests? Subscribe to Google for Developers → https://goo.gle/developers

What three emojis would you use? Make sure to comment them! Subscribe to Google for Developers → https://goo.gle/developers

Sameer Samat, President of Android at Google, joins host Logan Kilpatrick to discuss Android 17 and what it means to shift from operating systems to intelligence systems. Their conversation covers why Android didn't say the word AI once at the Android Show, the new Gemini Intelligence feature suite including Rambler, app automation, Superfill, and generative widgets, and what it looks like when Gemini can see the road with you in a live demo inside a Volvo EX60. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Logan Kilpatrick, Sameer Samat Products Mentioned: Google AI, Gemini

What happens when frontier-level AI no longer requires an internet connection? Gemma 4 is empowering developers and communities across the globe by bringing advanced intelligence directly to local devices. By maximizing "intelligence per byte," Gemma 4 breaks down connectivity barriers, allowing powerful, multi-modal, and agentic AI to run efficiently anywhere, on anything. In this video, explore how creators and organizations are using Gemma 4 to solve real-world problems today: Empowering Local Healthcare: Organizations like Crane AI Labs in Uganda are building impactful, offline systems to help reduce maternal mortality rates in low-connectivity areas. Preserving Culture and Language: Discover how developers are easily fine-tuning Gemma 4 for indigenous languages like Quechua, providing new digital resources for underrepresented communities. Democratizing Technology: Hear from Google DeepMind engineers and global partners like Typhoon AI on why open-source AI is critical for global freedom and technological access. Learn how the open Gemma 4 ecosystem can help you build systems for your own community. Resources: Learn more→ https://goo.gle/3RdSm8O Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Google AI, Gemini, Gemma

A small Kotlin challenge from a real permissions bug: each user has a set of roles. A teammate adds a role to one user, and a completely different user ends up with that role too. What happened? Watch the clip and share what you think below. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Anaya Mehta

An inside look at Google's latest creative tools from the people using them to make film, art, games, music and more. See how musicians, designers, coders, and filmmakers at Google Creative Lab and Labs are using Google Flow, Antigravity, Genie and Google Flow Music in their creative processes. Speakers: Matthew Carey ,Alex Chen, Sanchit Sawaria, Khyati Trehan, Kaloyan Kolev Shashwath Santosh, Samuel Lawton, Henry Ives, Kendall Rankin

Ian Ballantyne, Developer Relations Engineer at Google DeepMind, shows how Gemma runs on hardware like Raspberry Pi, Jetson, and Nano, letting a model see, hear, and act the way a robot would. The demo is Reachy Mini, the open source robot from Hugging Face and Pollen Robotics, a small robot that sees with cameras, reacts with emotion and head movement, and holds a conversation through its microphone and speaker. What's covered: A live conversation with Reachy Mini about why local on-device models matter for privacy and speed, the robot's ability to move its head, show emotion, and take pictures to understand its surroundings, controlling smart devices and APIs like lights, thermostats, calendars, and live data, and an early look at the robot reasoning about a chessboard and explaining how a knight moves. Explore the Reachy Mini project from Hugging Face and Pollen Robotics, and try running Gemma on your own hardware. What would you build with Gemma on a robot or IoT device? Drop it in the comments. Resources: Reachy Mini → https://goo.gle/4xJNpVJ Local Reachy Mini → https://goo.gle/4f1dOXC Gemma Docs → https://goo.gle/4xMnVXS Gemma Cookbook → https://goo.gle/4epYEuZ Subscribe to Google for Developers → https://goo.gle/developers Speaker: Ian Ballantyne Products Mentioned: Google AI, Gemini

Welcome back to Developer News! Host Anaya Mehta breaks down the latest major Google developer announcements from Google I/O, including near real-time translation Gemini 3.5 Live Translate, local agentic workflows with Gemma 4 12b, and Gemini in Xcode, where we bring Gemini directly to Apple platform developers. See how these tools can uplevel your developer workflows! Chapters: 0:00 - Introduction 0:25 - Gemini 3.5 Live Translate 0:54 - Live Translate demonstration 2:09 - Gemma 4 12B on AI Edge 3:23 - Gemini in Xcode 4:01 - Conclusion Resources: Introducing Gemini 3.5 Live Translate Video → https://goo.gle/4oFhX6W Gemini 3.5 Live Translate blog → https://goo.gle/4ogWS2D Gemma 4 12b Announcement Blog → https://goo.gle/3QElqWJ Gemini in Xcode Blog → https://goo.gle/44nPLMt Watch more Google Developer News → https://goo.gle/4e8Rysd Subscribe to Google for Developers → https://goo.gle/developers #GoogleDeveloperNews Speaker: Anaya Mehta Products Mentioned: Google AI, Gemini, Gemma

While prompting is great for runtime steering, fine-tuning teaches repeatable patterns—delivering the exact JSON shapes you need! Subscribe to Google for Developers → https://goo.gle/developers Speaker: Christy Yao

Ian Ballantyne, Developer Relations Engineer at Google DeepMind, demonstrates Gemma 4's multi-agent capabilities by spinning up 10 independent subagents on a single local machine. A high-level prompt goes to an orchestrator, which delegates the work, and within seconds the agents return a complete SVG art gallery, coded locally, simultaneously, and autonomously. What's covered: Running the Gemma 4 26B model locally, batch processing across 10 concurrent agents, orchestrator-and-subagent task delegation, inference speeds above 170 tokens per second, and what parallel local agents unlock for enterprise workflows and private on-prem deployments. What would you build with parallel local agents? Drop it in the comments. Resources: Github → https://goo.gle/4gzUwd9 Gemma Docs → https://goo.gle/3StWr9e Gemma Cookbook → https://goo.gle/4vsfKhF Subscribe to Google for Developers → https://goo.gle/developers Speaker: Ian Ballantyne Products Mentioned: Google AI, Gemini

A small CI pipeline puzzle from a very real build-system pattern. The app moves from React 18 to React 19. The next CI build runs faster than expected. Then production crashes. The clue is in the cache setup. Watch the clip and share the most likely cause in the comments. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Christine Rafla

Olivier Lacombe, Director of Product Management for Gemma, sits down with Gus Martins and Alice Zheng to dig into what Gemma 4 unlocks inside the Google AI Edge Gallery app. Alice walks through the app's growth since launch, more than five million model downloads in the first month, and demos two of the most popular use cases: asking Gemma to explain why the sky is blue completely offline, and using audio input to generate a structured shopping list on the spot. Gus covers the agent skills framework and what the community is building with it, from Wikipedia and WebFetch integrations to HTML rendering and mini games. They also preview MCP integration coming to Android first and then iOS, persistent chat history, and what it means that the 2B model this year is matching the performance of last year's 27B dense. Resources: Google AI Edge Gallery for Android → https://goo.gle/4vmF2Op Google AI Edge Gallery for IOS → https://goo.gle/44jkpqk Explore Gemma → https://goo.gle/44jktX6 The app is free, open source on GitHub, and available on the Play Store and App Store. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Olivier Lacombe Products Mentioned: Google AI, Gemma

Ian Ballantyne, Developer Relations Engineer at Google DeepMind, shows what Gemma can do on a Pixel 10 Pro using the Google AI Edge Gallery app. Image understanding, audio transcription, agent skills that route prompts to the right app on your phone, all running locally with no connectivity required. What's covered: Using Agent Skills to route a voice prompt to a mood tracker app, taking a photo and outputting structured JSON Schema from it, generating suggestions from an image of plants, recording voice notes for transcription and translation, and identifying objects offline with multimodal image understanding. Download the Google AI Edge Gallery app on Android or iOS and try Gemma on your own device. What are you running on-device with Gemma? Drop it in the comments. Resources: Google Play → https://goo.gle/3SXkrSe App Store → https://goo.gle/44oSgy7 Github → https://goo.gle/4xLOgW2 Gemma Docs → https://goo.gle/4uQXVYs Gemma Cookbook → https://goo.gle/4oLWJEC Subscribe to Google for Developers → https://goo.gle/developers Speaker: Ian Ballantyne Products Mentioned: Google AI, Gemini

What does easy, AI code generation mean for the future of our software systems? Let's find out. Subscribe to Google for Developers → https://goo.gle/developers #GoogleDeveloperNews Speaker: Adam Bender Products Mentioned: Google AI

Sometimes greatness is bestowed upon us. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Pete King

We feel for the SWE’s, am I right? Subscribe to Google for Developers → https://goo.gle/developers Speakers: Justine Lai, M.E Francis, Pete King

This is the Coral Board, a small, low-power dev board with Google's Coral NPU machine learning accelerator inside, built for developers to experiment with on-device AI. It runs Gemma, and everything happens on the board. For I/O it ships as a kit with a screen, a camera, microphones, and LEDs, so you can see what's possible on the edge. What's covered: Live translation with speech in and translated speech out running entirely on the board, natural language controlling physical hardware, and vision and sound working together in a lightweight version of the pre-I/O show that generates music from an aquarium of jellyfish, all on a single board. The Coral Board is available this summer. Every demo in the video is open source and on GitHub to get you started. Follow the links below to learn more. What will you build on the edge with Gemma? Drop it in the comments. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Ian Ballantyne Products Mentioned: Google AI, Gemini

A package import can look simple on the surface. Same application code. Same package name. Different behavior after deployment. Watch the clip and share which file gets loaded in production. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Christine Rafla