Google for Developers

@developers.google.com

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

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

Enable on-demand expertise with Agent Skills in Genkit Go- Google Developers Blog

Optimize token usage in Genkit Go using Agent Skills. Learn how to implement progressive disclosure with SKILL.md to load specialized AI workflows on demand.

goo.gle

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.

An evaluation results interface compares two AI-generated summaries of a Titanic article, displaying pass rates of 80% and 90%. A "Metrics / Rubrics" overlay highlights a failed format requirement, explaining that a summary contained five sentences per paragraph instead of the requested four. The dashboard uses green checkmarks and an orange warning icon to show success or failure across categories like language, core tasks, and content requirements.

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

Logo for RadixArk featuring an orange stylized flame icon within an arch on the left. To its right, the text reads "Radix" in black followed by "Ark" in orange.