Google for Developers

Google for Developers

@developers.google.com

Your source for developer best practices, updates, and resources.

6.4K followers4 following1K posts

Pinned

Introducing Gemini 3.7 Flash ⚡ It is our most intelligent workhorse model yet for coding and agents. It delivers better intelligence for complex workflows —all at the introductory price of $0.75/1M input tokens and $3.75/1M output tokens through the end of year. 🧵

Introducing Gemini 3.7 Flash ⚡ It is our most intelligent workhorse model yet for coding and agents. It delivers better intelligence for complex workflows —all at the introductory price of $0.75/1M input tokens and $3.75/1M output tokens through the end of year. 🧵

Gemini 3.7 Flash… ✓ Reduces manual debugging and failed agent loops. ✓ Enables agents to reliably execute high-quality code. ✓ Generates web and UI layouts with much higher design adherence. Available in Google Antigravity and the Gemini API via Google AI Studio and Android Studio.

A fully offline translator, built with Gemma 4, Google Antigravity, and a Raspberry Pi 5. 🛠️ The Gemma Translator is a portable AI experiment with a custom interface, printed case, and wired electronics, powered by the smallest Gemma model. Build your own → goo.gle/4x2jvLQ

Competition speeds up innovation. 🚀 Google Cloud G4 VMs equipped with NVIDIA RTX PRO 6000 Blackwell GPUs gave over 5,000 Kagglers the foundation to push model limits, with the goal of improving reasoning accuracy. Explore the five lessons that emerged: goo.gle/4wb3C4j

Keep your agent's context lean without sacrificing expertise. ⚡ Learn how Agent Skills in Genkit Go package specialized knowledge into capabilities that load only when needed, helping reduce token usage while making AI agents more reliable. Get started → goo.gle/4pS9BcG

goo.gleEnable on-demand expertise with Agent Skills in Genkit Go- Google Developers BlogOptimize token usage in Genkit Go using Agent Skills. Learn how to implement progressive disclosure with SKILL.md to load specialized AI workflows on demand.

Looking for the latest developer updates? July's #GoogleDeveloperNews has you covered 🧵 This month's episode covers Android Studio Quail 2, Android Bench updates, an inside look at how YouTube ships AI prototypes with AI Studio and Google Cloud, and Build with Gemini XPRIZE.

View full thread

Looking for the latest developer updates? July's #GoogleDeveloperNews has you covered 🧵 This month's episode covers Android Studio Quail 2, Android Bench updates, an inside look at how YouTube ships AI prototypes with AI Studio and Google Cloud, and Build with Gemini XPRIZE.

Agent and Model Evaluations in Gemini Enterprise Agent Platform are now Generally Available (GA)! 🎉 Measure, test, and monitor your AI agents in dev and production—using one engine with consistent metric definitions.

Build voice agents with visibility into every interaction ✨ Learn how Caroline di Vittorio from LangChain uses the Google ADK, the Gemini Live model, and LangSmith to trace voice agent behavior, inspect tool calls, review interruption events, analyze token costs, and more.

View full thread

Build voice agents with visibility into every interaction ✨ Learn how Caroline di Vittorio from LangChain uses the Google ADK, the Gemini Live model, and LangSmith to trace voice agent behavior, inspect tool calls, review interruption events, analyze token costs, and more.

Big news: Google and RadixArk are partnering to bring SGLang to Google Cloud TPUs! ✅ Run SGLang on TPU today via SGL-JAX ✅ Coming soon: SGL-torchtpu for a PyTorch-native experience ✅ No more migration tax—just ultimate flexibility for devs Learn more 🛠️: goo.gle/3U2JVOC

Google for Developers reposted

Straight from the floor of #GoogleIOConnect India! We spoke with redBus Director of Engineering, Amit Kumar, for a quick lightning round about HTML-in-Canvas. Hear how they are using the new API to level up their web UI experiences 👇 #BuildwithGemini

The standard software validation loop takes too much time, time you often don’t have. See how YouTube engineers moved at lightspeed and democratized AI prototyping by rebuilding a full mirrored version of the platform using AI Studio, letting anyone safely test prototypes against live data.