Google

When multiple AI coding agents work on the same codebase at the same time, things break. They step on each other’s file changes, share credentials they shouldn’t, and create the kind of merge conflict hell that makes engineers question their life choices. Google’s answer to this is Scion, an experimental multi-agent orchestration testbed that the company open-sourced on April 8, 2026. The core philosophy is elegant: instead of constraining what agents can do, isolate them so they can do whatever they need without interfering with each other. ...

If you’ve ever watched a coding agent confidently write Gemini API code that was deprecated six months ago, Google has something for you. Two new tools launched this week from Google’s developer team — Gemini API Docs MCP and Gemini API Developer Skills — and together they do something impressively concrete: push coding agent accuracy on Gemini API tasks from roughly 60% to 96%, according to Google’s own evals. That’s not a marginal improvement. That’s the difference between an agent that’s useful and one that’s reliably useful. ...

Google DeepMind has released Gemma 4, and it’s arguably the most consequential open model drop of the year so far. Not because it’s the most powerful model on any benchmark — it isn’t — but because of what it represents: a fully open-source, Apache 2.0 licensed, agent-ready model family that runs on hardware you already own, including your smartphone. For developers who’ve been waiting for a truly open, production-grade model built for agentic workflows, Gemma 4 is the answer. ...

It doesn’t wear a suit. It doesn’t take breaks. And it just got too popular to let everyone use. Business Insider reported this week that Google has been quietly running an internal autonomous coding tool called Agent Smith — and it’s been causing quite a stir inside the Googleplex. The tool became so heavily used that Google had to restrict access just to keep up with demand. The name is almost certainly a Matrix reference, which either says something about Google’s sense of humor or its appetite for irony when naming the autonomous agent that’s here to change how software gets built. ...

If you want to understand where the AI industry thinks agentic AI is heading, watch where Google moves its engineers. This week, Wired reported that Google is restructuring Project Mariner — its Chrome browser AI agent, which lets AI systems browse the web and click through interfaces the way a human would. Engineers from the Mariner team are being pulled to work on higher-priority coding agent projects. A Google spokesperson confirmed the changes, telling Wired that Mariner’s computer-use capabilities will live on inside the company’s broader agent strategy — but the dedicated browser agent team as it existed is being reorganized. ...

If you’ve been following the “vibe coding” wave — the idea that you can describe what you want in plain English and an AI agent turns it into real software — Google just made the most aggressive move yet to own that space. On March 19, 2026, Google officially relaunched Google AI Studio with a complete full-stack vibe coding experience, powered by the new Antigravity coding agent and deep Firebase integration. This isn’t just a smarter autocomplete. This is an agent that can take a single text prompt and produce a production-ready, authenticated, database-backed web application. ...

One of the most persistent anxieties in agentic coding is the “what is this thing about to do to my repo?” problem. You describe a task. The agent starts executing. And somewhere between your request and the outcome, files get modified, commands get run, and irreversible things happen — sometimes incorrectly. Google just shipped a thoughtful solution to this problem in Gemini CLI: plan mode. Plan mode restricts the AI agent to read-only tools until you explicitly approve its proposed plan. No file writes. No command execution. Just analysis and a detailed proposal — which you review, approve (or reject), and then execute with confidence. ...

Google quietly published something very useful on GitHub in early March: gws, a command-line interface for the full Google Workspace API surface. It ships with 100+ pre-built agent skills covering Gmail, Drive, Docs, Calendar, and Chat — and it includes a built-in MCP server that lets AI clients like Claude Desktop, Gemini CLI, and VS Code access your Workspace directly. This is the thing that used to require a custom OAuth flow, API client library setup, and a day of plumbing. Now it’s a CLI install and a config file. ...

Something genuinely important is shipping in Chrome 146: an early preview of WebMCP, a W3C draft standard jointly developed by Google and Microsoft that fundamentally changes how AI agents interact with websites. Right now, AI agents that browse the web do so by scraping DOM elements — reading HTML, finding buttons, inferring what actions are available. It’s brittle. A website redesign breaks the agent. A modal renders differently across browsers and the agent gets stuck. This approach works well enough for demos but fails at production scale. ...

When Anthropic drew its line against autonomous weapons and mass surveillance, the response came from an unexpected quarter: the employees of its competitors. More than 200 people currently working at Google, DeepMind, and OpenAI signed an open letter published Thursday calling on their own employers to “put aside their differences and stand together” in refusing Pentagon demands for unrestricted AI use in autonomous weapons and domestic surveillance programs. The letter — confirmed by TechCrunch, Forbes, Axios, and the New York Times — represents one of the most significant cross-company acts of worker solidarity in AI history. ...