Discover the latest technologies, resources, events, and announcements to help you build smarter and ship faster. Explore more at developers.google.com
External link for Google for Developers
See what Gemma 4 can do for your Android app!
Gemma 4 brings the next gen of on-device AI to Android. Get code-assistance in Android Studio and build intelligent experiences that run locally using the ML Kit GenAI Prompt API. Start building agentic experiences on-device → https://goo.gle/4sOiBAv
It’s time to go beyond chatbots, and build your next #AI agent on your own device. 🤖 Introducing Gemma 4, our new family of open models that brings state-of-the-art agentic power directly to the edge. With #GoogleAIEdge, you can now deploy AI agents in your own applications using #Gemma4: 🧪 Explore Agent Skills in the Google AI Edge Gallery app ⚡️ Deploy across mobile, desktop, and IoT with LiteRT-LM 🤖 Create multi-step, autonomous experiences that run entirely locally What will you build? Learn more: https://goo.gle/4tpurAO
Gemma 4 is here! Our most intelligent open models to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source license Start building with the Gemma 4 family: https://goo.gle/4sbKuRM
console.log("here") is valid debugging. We don’t judge.
ADK for Go 1.0 is here! 🎉 Build production-grade #AI agents with idiomatic Go. This release introduces features designed for robust, debuggable, and secure agentic systems, including: ✅ Deep observability: Native OpenTelemetry (OTel) integration for tracing the Reason-Act loop ✅ Extensible architecture: A new plugin system to add capabilities like logging or self-correction (Retry & Reflect) ✅ Enhanced security: Human-in-the-Loop (HITL) confirmation for sensitive tool operations ✅ Flexible configuration: Define agents using YAML ✅ Stable interoperability: Refined Agent2Agent (A2A) protocol Explore these features and learn how #ADK for Go can support building AI agents in production. Resources: ADK documentation → https://lnkd.in/gr9Suh_K ADK Go source code → https://lnkd.in/e2yyaufd ADK Go samples → https://lnkd.in/evtrfhiA Read the blog → https://goo.gle/4dmrGeN
Deepen your expertise in building scalable AI agents with the Agent Development Kit (ADK) 🛠️ Loading every rule into a single prompt can increase latency and token usage. There is a more effective way to manage your agent knowledge using Agent Skills. Learn how to use progressive disclosure to load domain expertise only when needed. This architectural pattern allows agents to load context precisely when it is relevant. We break agent knowledge into three distinct layers: 1️⃣ L1 metadata: Just enough info for the agent to decide relevance 2️⃣ L2 instructions: The full skill body, activated only on demand 3️⃣ L3 resources: External reference files pulled exactly when required The result? You can reduce baseline context usage by up to 90%. 📉 Our latest guide also explores four implementation patterns: 🌟 Inline Skills: Simple checklists for stable rules 🌟 File-based Skills: Reference binders for complex instructions 🌟 External Skills: Community repositories you can import 🌟 The Skill Factory: Meta-skills where agents write their own capabilities By using the SkillToolset, your agents become self-extending. They can generate a security review checklist or a data pipeline validator exactly when they need it. Explore the full developer guide by Lavi Nigam and Shubham Saboo here → https://goo.gle/4bWZ7Cm
Build with AI events help you learn more effectively. What to expect: 💻 Interactive lab sessions 🧠 Guidance from GDEs 🌍 Helpful technology Find an event near you → https://goo.gle/40ZgPQJ
Google for Developers reposted this
🎙️ Join André Cipriani Bandarra and Francois Beaufort on the WeAreDevelopers podcast as they discuss the challenges of the agentic web and how WebMCP is bridging the gap between models and the browser → https://goo.gle/3ZWqkzu They'll go in depth on topics like: 🛠️ Structured Tooling: Replacing visual scraping with the navigator.modelContext API. 🤖 Declarative Agent Support: How to make any HTML form "agent-ready" with simple annotations. 🌐 Native Reliability: Shifting agent logic to the client for better performance and human-in-the-loop trust. and more!
Build a real-time voice agent with Gemini 3.1 Flash Live and Stream's Vision Agents SDK using Stefan Blos’s walkthrough to move from early access to a fully orchestrated multi-step workflow. What’s covered: ✨ Setting up the Vision Agents SDK with the Gemini plugin ✨ Defining tools for image generation and product search ✨ Building a video processor to analyze live frames via Next.js and WebSockets Grab Gemini API keys at Google AI Studio and explore the Vision Agents SDK from Stream to start building. Watch the full video: https://goo.gle/4m4GpgH