Where we're going, we don't need chatbots: introducing the Antigravity IDE 🚀

Lately, I’ve been living in a new world—specifically, a world called Antigravity. It’s the agent-first IDE that the Google DeepMind team has been building, and honestly? It’s completely ruined "normal" coding for me.

We talk a lot about AI in development, but most of the time this just ends up being a chat box in the browser. Antigravity is different - it's built on an "agent-first" architecture (shoutout to the Windsurf team who brought this idea to life!). The idea is that the AI shouldn’t just suggest code; it should be an autonomous partner that can navigate the terminal, the editor, and even a live browser to get things done. We're even starting to incorporate many of these agentic features into AI Studio's Build feature!

I wanted to share two specific features that have become absolute game-changers for my daily workflow.

QA testing and documentation on auto-pilot

If you're like me, the most exhausting part of any sprint isn't the code - it’s the housekeeping. You know the drill: you finish a feature, then you have to spend hours taking screenshots and writing detailed how-to guides for the quality assurance team and for users. It's incredibly important, but also tedious, work.

In Antigravity, I’ve started using the Browser Subagent (powered by Gemini 2.5 Computer Use) to handle this. I can literally just say: "Go to this staging site, identify five core user journeys, and make a tutorial for all of them."

The agent doesn't just "guess." It explores the DOM, interacts with elements, and records its progress. But the "secret sauce" is the Artifacts System. Instead of a wall of text, the agent produces a Walkthrough Artifact - which is a structured, human-readable document complete with verification results, detailed steps expressed as text, and screenshots.

Because Antigravity supports asynchronous feedback, I can hop into that Implementation Plan or Walkthrough and leave Google Docs-style comments directly on the text or screenshots - there's no black box. The agent reads my feedback in real-time and adjusts its next steps without me having to restart the whole task.

Toolkit for Antigravity extension

If you’re pushing the limits of agentic coding, you’re likely bouncing between models. I usually have Gemini 3 Pro handling complex architectural planning while Gemini 3 Flash handles the high-velocity subtasks.

Keeping track of your quota (token consumption) across Google AI Studio, Anthropic's models (Opus, Sonnet), and OpenAI's models is usually a nightmare. Luckily, a community member built an incredible open-source extension called Toolkit for Antigravity (you can find it on the OpenVSX marketplace).

It adds these sleek Semi-Arc Gauges to your sidebar that show:

• Real-time Quota Tracking: Hour-by-hour stats for Gemini, Claude 4.5, and the OpenAI GPT models.
• Cache Management: A one-click way to browse and purge conversation caches when things get a bit "loopy."
• Privacy First: It’s 100% local with no telemetry, which is a must for those of us working in enterprise repos.

Shifting to "Manager View"

The biggest mental shift with Antigravity is moving from the Editor View to the Manager View. In the Editor, you’re writing code; in the Manager, you’re an architect overseeing multiple agents working in parallel.

Whether you’re refactoring a legacy auth module or having an agent vibe code a new frontend from scratch, the goal is to keep you building without distractions. Antigravity handles the terminal commands, the dependency installs, and the UI verification so you can focus on what you're building instead how.

So anyhow, I’m curious - what’s the one part of your development workflow you wish you could just hand off to an agent today? For me, one of the top instances was definitely the "screenshotting for tutorials", and I’m never going back.

Catch you in the comments! ✌️