A rare and magical moment of perfect code review alignment 🪄
Google for Developers
Technology, Information and Internet
Mountain View, CA 4,106,161 followers
Join a community of creative developers and learn how to use the latest in technology—from AI and cloud, to mobile & web
About us
Discover the latest technologies, resources, events, and announcements to help you build smarter and ship faster. Explore more at developers.google.com
- Website
-
http://developers.google.com
External link for Google for Developers
- Industry
- Technology, Information and Internet
- Company size
- 10,001+ employees
- Headquarters
- Mountain View, CA
- Specialties
- coding, engineering, firebase, android, cloud, web development, and mobile development
Updates
-
Google for Developers reposted this
To close the week of #googeio, the Blooms team was selected to participate in groundbreaking projected led by Ajeet Mirwani and a team of Google Developer Experts, including Henry Ruiz, Ph.D Taha Bouhsine Brian Luc Rabimba Karanjai among others. Jorge Gerardo Mendieta Mayen and I had the opportunity to work in building a definitive reference architecture for mission-critical AI. The system uses Google’s cutting-edge "Reflex vs. Strategy" approach: Reflex: Instantaneous, on-device decision-making using next-gen edge devices (Pixel 10 / TPU). Strategy: High-level, complex planning using cloud infrastructure (Gemini 3 / Vertex AI). To prove this hybrid architecture is perfectly reliable with zero margin for error, the teams stress-tested it using live, high-frequency telemetry data at 100+ MPH at Sonoma Raceway and having #AI coaching the driver. The diver in the picture broke the raceway speed record while driving with the agent. 😉 The framework works perfectly for Blooms mission of strengthening the fresh produce supply chain for North America, as we deal we perishables, price and volume volatility and logistic challenges, using telemetry data and a "split brain" AI model to make fast decisions in underwriting and financing offering together with an strategic view, to secure food availability, quality and reduce food waste. Thanks to Ashley Francisco Erchit Sood PMP Chantelle Uribe David McLaughlin and Ajeet Mirwani for this amazing opportunity. #produce #breakfornothing #ai #crossborder
-
-
-
-
-
+4
-
-
Google for Developers reposted this
What do a high-speed race car at Sonoma and your pet have in common? 🏎️🐕 They both generate mission-critical data—and in both cases, latency is the enemy. This past weekend, I had the privilege of joining an incredible Google Developer team at the Sonoma Race Track. It was a masterclass in taking complex data and turning it into real-time certainty. A massive thank you to Ajeet Mirwani and Chantelle Uribe for the invitation and leadership. Watching Brian Luc translate raw car telemetry into immediate, actionable understanding for the team was mind-blowing. I also got to watch Henry Ruiz, Ph.D with Jorge Gerardo Mendieta Mayen from Blooms, Taha Bouhsine, and Rabimba Karanjai deploy and iterate their AI models in real-time, right in the middle of the track. They separated the signal from the noise in seconds. The result? The driver hit his best time yet with the power of AI.⏱️ Here is my biggest takeaway as a technical founder: Watching them solve this high-stakes puzzle validated exactly the architecture we are building at WUUFY. In preventative pet health, biological markers and behavioral drift are our "telemetry." The "latency" is the months a chronic disease progresses silently before physical symptoms ever appear. But here is the massive difference: A race car relies on million-dollar hardware sensors. At WUUFY, the most powerful sensor is the pet parent. We are completely lowering the barrier to preventative care by using the hardware people already own. We are taking the smartphone camera, combining the intuition of human eyes with the analytical power of Edge AI, and actually training the human to see what was previously invisible. Just like that race car, a pet's health requires an AI Orchestrator—a system capable of ingesting that fragmented data, finding the hidden patterns, and giving pet parents and veterinarians the certainty to intervene early. Because whether you are on the track or managing a pack's health and behavior, catching the drift early changes the entire outcome and builds a stronger human-pet bond. Thank you, Google team, for the inspiration. The future of preventative care isn’t just clinical; it is a complex data orchestration challenge. And WUUFY is building it. 🚀 #EdgeAI #GoogleGemini #Startups #HealthTech #VeterinaryMedicine #DataScience #DigitalHealth
-
-
Support your global users with the low-latency Gemini 3.5 Live Translate model 💡 Google DeepMind DevRel Engineers Thor Schaeff and Anuda Weerasinghe are hosting a live Discord stage AMA to help you integrate realtime translation features. Learn more this Tuesday, June 16 at 9 AM PT. This AMA will be available in 70+ different languages thanks to Gemini Live Translate → https://lnkd.in/ew4TPQp4
-
-
What will you build this weekend? Gemini 3.5 Live Translate is now available in Preview via the Gemini Live API, delivering low-latency speech-to-speech translation across 70+ languages in a single, continuous session. Swipe through to see 5 ways you can use the new model. Head straight to Google AI Studio to: Try it now: https://goo.gle/4ggxSq5 Start building apps: https://goo.gle/4xpkFS6
-
Building for the world, together. 🌍 So inspiring to see what our community created at the Google I/O Hackathon hosted by Cerebral Valley and Google DeepMind. Incredible energy, brilliant builders, and innovative projects powered by Gemini 3.5 Flash. Until next time! Check out the winners gallery page: https://goo.gle/4v0Zynj
-
Most AI agent demos reset after one conversation. But what if your agent needs to run for days — pausing, resuming, waiting for human input — without losing context or burning compute? In this episode of The Agent Factory, Smitha Kolan sits down with Addy Osmani, Director at Google Cloud AI, to show what production-grade agent architecture actually looks like using ADK 2.0 and Gemini 3.5 Flash. Three live demos, zero hand-waving: → New hire onboarding coordinator: An event-driven agent that orchestrates IT provisioning, pauses for human actions, and resumes without token bloat. → "AEOS" browser operating system: A coding agent that builds a full window manager, text editor, file browser — and a working version of Doom inside the browser. → 3D asset optimization pipeline: A multi-step agent that takes a 156MB Blender file and compresses it into a fast, browser-ready retro video store scene using Python and GLTF optimization. They also dig into the human side — drawing from Addy's book "Beyond Vibe Coding" to tackle cognitive debt, cognitive surrender, and how dev teams can stay sharp while building with agents. If you're building agents that need to survive beyond a single prompt, this is the episode. Check out this episode and more in the Agent Factory series → https://goo.gle/3QdbgMw
-
Pitch-perfect code meets the beautiful game. Who’s in your starting lineup? ⚽️ SQL: The Goalkeeper 🧤 The ultimate source of truth who keeps a "clean sheet." Organizes the backline, locks down the box, and retrieves the exact data you need the second the team calls for it. C++: The Center Back 🧱 A high-performance powerhouse. Requires elite precision to manually mark every threat, ensuring the foundation remains completely unbreakable under extreme pressure. Python: The Creative Playmaker 🧠 The classic "No. 10." Relies on a massive library of brilliant moves to orchestrate the attack, effortlessly pulling the strings without needing to sprint for every loose ball. Go: The Box-to-Box Midfielder 🏃💨 The engine room. Built for pure stamina, handling thousands of concurrent sprints across the pitch to keep the team’s infrastructure moving in perfect parallel. Kotlin: The Modern Wing-Back ⚡ A polished professional who rarely loses possession thanks to built-in null-safety. Effortlessly shuts down errors and delivers world-class crosses with a clinical, modern touch.
-
Stop fighting with backend infrastructure just to get your AI agents to scale. With Managed Agents in the Gemini API, you can now deploy production-ready agents inside remoteGoogle-hosted sandboxes—with a single API call. Powered by Gemini 3.5 Flash and the Antigravity agent harness, these autonomous agents can plan, reason, write code, and search the web. 🛠️ What you can do right now: • Zero-config environments: Spin up an ephemeral Linux sandbox instantly • State preservation: Pass an environment_id to continuously modify and access files across multi-turn conversations without losing state. • File-based control: Define instructions and specific capabilities using plain markdown files (AGENTS .md and SKILL .md). • Flexible seeding: Mount custom data directly from inline text, Cloud Storage, or public GitHub repositories. The hardest part of building agents is now the part you don't have to build. 📺 Check out the quick walkthrough https://goo.gle/4uab5Q0 and explore the new Agents templates in ai.studio/managed-agents