With the introduction of Gemini 3.5 Flash, Google is setting a new standard in AI development, offering advanced capabilities at a remarkably reduced cost. Complementing this innovation is Antigravity 2.0, designed to facilitate the creation and management of AI agents, empowering developers to tackle their latest projects with enhanced efficiency.
Antigravity 2.0: A Unified AI Coding Platform
Launched last year amidst the vibecoding movement, Antigravity has evolved from a standalone application into a comprehensive platform that integrates AI coding assistance, drawing inspiration from Microsoft’s VS Code. The latest iteration, Antigravity 2.0, emphasizes agent orchestration, allowing developers to deploy multiple agents simultaneously to solve various challenges, thereby accelerating development timelines.
This revamped version introduces seamless integrations with Google AI Studio, Firebase, and Android. Developers can now effortlessly export projects from AI Studio to their local Antigravity application, preserving context for a smooth transition back to agentic development.
For those who prefer to remain within their chosen Integrated Development Environment (IDE), Google is unveiling a new Command Line Interface (CLI) for Antigravity. This tool enables developers to initiate new agents directly from the terminal, streamlining workflows. Notably, the Antigravity CLI will replace the previous Gemini CLI, necessitating a migration of existing workflows to the new system.
Custom Solutions and Enhanced Features
In addition to the CLI, Google is introducing the Antigravity Software Development Kit (SDK), which allows for the creation of custom agents tailored for Gemini. Once developed, these agents can be deployed on the infrastructure that best suits an organization’s needs. To further simplify deployment, a new “Managed Agents” feature within the Gemini API will provide agents with an isolated Linux environment for their operations.
As coding agents typically consume more resources than traditional chat functionalities, developers may find themselves exceeding the limits of the per month Pro plan. To address this, Google is launching a new 0 per month AI Ultra tier, which offers five times the usage limits compared to the Pro plan. As a promotional offer for I/O week, both new and existing AI Ultra subscribers can receive 0 in bonus credits, ensuring uninterrupted workflow even when quotas are reached.
AI Studio: A New Mobile Experience
In a related development, Google is also rolling out a dedicated Android application for AI Studio. While details remain sparse, the app is expected to allow users to verbally or textually input ideas, starting from high-quality example applications. Once completed, users will have the ability to share their creations with friends, adding a social dimension to the development process. Pre-registration for AI Studio is now available on the Play Store.
Your next big idea is just a conversation away.
Inspiration doesn’t wait for you to be at your desk. It strikes on the couch, on the bus, or in the middle of the night. With Google AI Studio, you finally have a way to capture that spark and turn it into something real—right from your phone.
By integrating these tools, Google is empowering developers to harness their creativity from anywhere inspiration strikes. Whether articulating a vision through AI Studio on a mobile device or exporting projects to Antigravity for further development, the workflow transforms app creation into a more manageable project, akin to leading a team of AI agents powered by Gemini.
