Google for Developers

An event announcement banner for a "Discord Exclusive Gemini 3 AMA" from Google Developer Groups. It features two Google DeepMind DevRel Engineers in circular profile photos: Thor Schaeff and Patrick Löber. The banner also highlights "Build with AI" with a blue hexagonal star icon, and the year "2026".

Gemini 3 AMA: Ask us anything! 📣

Join Thor Schaeff and Patrick Löber to talk latest releases, advanced features, and Gemini API tips as we kick off the #BuildWithAI season → goo.gle/4uCJYij

🗓️ March 11 | 11AM ET
📍 Google Dev Discord (Stage)

Bring your Google AI Studio questions!

POV: You’re building for the future of XR and it actually looks... pretty? ✨

Jetpack Compose Glimmer isn't just a toolkit; it's a demonstration of design best practices for display AI glasses.

Start building → goo.gle/4qJnOHW

New to the #GoogleDeveloperProgram forums and not sure where to start? We've got you covered. Léo Kling shares his advice on how the community can support you.

Join the forums today → goo.gle/49YVFX2

What's new in TensorFlow 2.21- Google Developers Blog Google has officially graduated LiteRT into production, delivering up to 1.4x faster GPU performance and enhanced NPU acceleration for high-performance on-device AI. This update streamlines cross-plat...

What’s new:
⚡️ 1.4x faster GPU performance vs. TFLite + new NPU acceleration
💎 Expanded int8/int16/INT4 support (SQRT, Cast, Slice)
🛠️ First-class PyTorch/JAX model conversion
🛡️ Increased resources for critical bug fixes and dependency updates

Upgrade your stack today → goo.gle/4lodjsn

TensorFlow 2.21 has arrived. ⚙️ LiteRT has officially graduated to production, serving as the universal on-device inference framework for the AI era.

You can't stream the energy: A developer's guide to Google Cloud Next '26 in Vegas- Google Developers Blog Get a developer’s inside look at Google Cloud Next ’26 in Las Vegas, focusing on the shift from experimental AI to production-ready agentic workflows. Explore 10 essential technical sessions on Gemini...

Deepen expertise in the new baseline of software engineering with gen AI and modern infrastructure at Google Cloud Next '26 in Las Vegas. Technical sessions offer direct experience with Gemini 3 and zero-trust foundations from April 22 through April 24. Get started ↓ goo.gle/4sxIe8a

Collaborate on projects and gain expert insights by engaging with peers in the forums 💬 👇

Showcase your achievements in your developer profile 🏅 👇

Gain access to events and connect with like-minded developers 👥 👇

Use credits to skill up with structured training on Google Skills 🎓 👇

Build, debug & deploy with AI

Use Gemini CLI to bring Gemini directly into your terminal 💻 👇

5 ways the #GoogleDeveloperProgram can advance your career 👇

Build custom soundtracks in the Gemini app with Google DeepMind’s Lyria 3. 🎹

⌨️ Input prompts for genre and tempo
🖼️ Generate audio from any image, including Nano Banana
🎸 Control genre and vocals

Start creating → goo.gle/2010

🗓️ It’s official: #GoogleIO is back on May 19 to 20, 2026.

Explore the build process of the Save the Date puzzle experience for inspiration on how to speed up prototyping and developer workflows using Google AI Studio and Google Antigravity.

Read the blog → goo.gle/4l9BcnB

A UI section features a large blue button labeled "Get Certified" with a checkmark icon, introduced by a tab reading "♦ GEAR." Below it, text states, "Prepare for your certification exam with courses, labs, and peer support." Above, a yellow circular icon containing a cloud and the numbers "00000" is shown, alongside a horizontal text field and a right arrow. Partially visible at the bottom are a green card with a gear icon and lines, and a small horizontal navigation element with left and right arrows.

A promotional graphic with a blue banner titled "GEAR Get Certified" featuring a diamond icon and a checkbox. Below the banner, text reads: "Prepare for your certification exam with courses, labs, and peer support." The design includes three circular badge icons depicting a yellow cloud, a green asterisk, and a light blue lightning bolt, interconnected by abstract black outline shapes.

Advance your career with Google Cloud certifications. 🤩

Google Cloud customers can apply to the Get Certified Program through GEAR and access instructor-led classes, labs, and a network of support to help you prepare for your exams → goo.gle/4qWRWQd

Your AI agents are only as good as the systems they can interact with.

Introducing the new ADK integrations ecosystem. Connect your ADK agents to GitHub, Hugging Face, Notion and many more with tools and plugins.

Start building today: goo.gle/4aTAJAV

⚡️ Execute sophisticated multi-step workflows and manage complex tasks with Gemini 3.1 Pro → goo.gle/40w5HdA

Start building with the model via the Gemini API in Google AI Studio, Gemini CLI, Google Antigravity, and Android Studio.

Can you sniff out the Code Saboteurs before it’s too late? 🏰

On-Device Function Calling in Google AI Edge Gallery- Google Developers Blog Discover FunctionGemma, Google's 270M parameter model for on-device function calling. Build fast, offline mobile agents with Google AI Edge. Try the demos now!

Check out the full guide and open-source code: goo.gle/3ODJJCT

Mobile Actions and Tiny Garden are available out-of-the-box in the Google AI Edge Gallery app, now on both Android and iOS. Benchmark the model performance directly in the app.

Discover how you can use FunctionGemma (270M) and LiteRT-LM to build private, high-performance local assistants.

R8 takes your code to the finish line! 🏁 → goo.gle/46gHZFI

In the latest episode of Android Developers Backstage, the team breaks down how to optimize your builds. Learn about R8 vs. D8 differences, avoiding the "Big 3" build mistakes, and resource shrinking in AGP 9.0.

Have you tried remixing the Google I/O puzzle yet? 🎨

1️⃣ Play any build
2️⃣ Remix in Google AI Studio
3️⃣ Share your work using #GoogleIO

Show us what you've got and mark your calendars for #GoogleIO on May 19–20 → goo.gle/iopuzzle26-6

A UI development environment displays two side-by-side previews of a "TennisScreenPreview" mobile application. On the left, a right-click context menu is open over the app UI, with the option "Transform UI with Gemini" prominently highlighted and marked by a Gemini icon. On the right, an AI interaction is shown where a text input field suggests "Reduce the padding between the two players" to modify the UI layout. Both previews show match details like "Chipmunk Champ vs Jellyfish Juggler" and a "Score 6-4, 6-2".

Describe your design vision and let Gemini handle the code.

👉 Right-click in the Compose Preview
👉 Select "Transform UI With Gemini"
👉 Type a request
👉 Review and approve

goo.gle/4tyruyI

Transform your coding agent into a tireless engine that doesn't stop until the job is done with the Ralph Loop → goo.gle/gemini-cli-ralph

Learn how to:

🌟 Prevent context rot
🔄 Spawn fresh agents per turn
🛠️ Use the Gemini CLI hook system

Generate UI tests using natural language with Journeys for Android Studio → goo.gle/Sneak

Validate visual states and follow Gemini’s step-by-step reasoning as it navigates your app.

Announcing the launch of Hooks in Gemini CLI 🚀🪝

Take full control and customize the agentic loop to your specific needs.

Hooks allow you to add context, validate actions, enforce policies, loop the agent to continue to iterate, and more.

Read the blog → goo.gle/4rDEDFm

Build, deploy, and scale AI agents with ease. ✨

Whether you’re just starting with AI or a seasoned dev, join a global community of developers to level up your AI-agent skills with practical training through GEAR → goo.gle/40p3MYe

Gemini 3.1 Pro preview is now available for AI assistance in Android Studio. Test the new model by plugging in your Gemini API key, and let us know what you think → d.android.com/studio

Google Home APIs help you create helpful, user-centered home experiences. ✨

Whether you’re building apps that adapt to moods like Aniket’s Pulse app or creating new automations, get the docs you need here → goo.gle/3MNEnUZ

#GoogleHomeDevChallenge