Google Antigravity: Agent-assisted development

-

Google Antigravity is a new agentic development platform that Google announced on November 18, 2025, alongside the launch of Gemini 3. Here are the key details:

What It Is

Antigravity is an AI-powered integrated development environment designed for prioritizing AI agents platform for software development. It's built on a fork of Visual Studio Code but fundamentally reimagines how developers interact with AI coding tools.

Key Features

Agent-First Design: Unlike traditional coding assistants that act as sidebar chatbots, Antigravity gives agents their own dedicated space to work and allows us to deploy agents that autonomously plan, execute, and verify complex tasks across the editor, terminal, and browser.

Two Interface Modes:

  • The Editor View provides a traditional AI-powered IDE experience with tab completions and inline commands
  • The Agent Manager acts as "Mission Control," allowing us to spawn, monitor, and manage multiple agents working on different tasks simultaneously

Antigravity treats learning as a core primitive, allowing agents to save useful context and code snippets to a knowledge base to improve future tasks.

While it comes with generous rate limits on Gemini 3 Pro, it also offers full support for Anthropic's Claude Sonnet 4.5 and OpenAI's GPT-OSS.

Getting Started

1. Installation & Setup

Download Google Antigravity from the official website and select the installer according to the machine specifications.

After installation:

  • Launch the application
  • Sign in with the personal Gmail account (it's free during preview)
  • Choose Agent-assisted development (recommended) - this keeps us in the loop for approvals
  • Set Terminal execution to Auto for routine commands
  • Select the editor preferences (theme, fonts, etc.)

2. Open a Workspace

Open a local folder by clicking on the button and selecting a folder to start with - this is the project directory, just like in VS Code.

Article content

Simple Example: Building a Basic Web App

Let's say we want to build a simple Train lookup app.

1) Give the Agent a Clear Prompt

Provide a detailed prompt to the agent, outlining the application's required functionality, technologies, and specifications.

Example: Build me a Train lookup Next.js web app where users can enter a Train number and see departure time, arrival time, and status. Use Tailwind CSS for styling and create a clean, modern interface.

2) Review the Implementation Plan

The agent generates an Implementation Plan that details its research and what specific changes it intends to make to the codebase before it starts implementation. We should review and approve this plan before changes are applied.

We'll see:

  • Task List: What the agent plans to do
  • Implementation Plan: File-by-file changes
  • Research artifacts for API documentation or design decisions

Article content

3) Monitor Progress

The agent will:

  • Create project files automatically
  • Install dependencies via terminal
  • Write code across multiple files
  • Test the app in the built-in browser

We can watch the "Thinking" process in real-time to see what it's doing.

Article content

4) Test & Iterate

The agent can test the app in the browser using the Antigravity extension. Here is a sample screenshot on how the browser is controlled by Antigravity - Agent Manager after opening the browser session with a simple train search.

Article content

5) Commit the Code

Use the Generate a commit message button, which uses the conversation history and files to create a contextual commit message.

Final confirmation from the Agent Manager snapshot after successful implementation of Train Lookup app using Node.JS

Article content

Popular posts from this blog

Connecting Claude to Pega Infinity 25.1.3 via MCP — Step-by-Step

-
Image
Enable AI-powered access to your Pega Investigative Case Management data directly from Claude prompts using the Model Context Protocol (MCP) and OAuth 2.0. What is MCP and why connect Pega to Claude? The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude securely call tools and read data from external systems — all from a natural-language prompt. Think of it as a universal adapter between your enterprise systems and AI. Pega Infinity V25.1.3 ships with a first-class MCP service built on its existing REST framework. Once enabled, Claude can: Query and summarize investigative cases without switching apps Retrieve assignment details and case status on demand Trigger Pega workflows from conversational prompts Version requirement: This guide is based on Pega Infinity V25.1.3 (Community Edition) with the Rule-Service-MCP rule type. Earlier versions may not include native MCP support. Architecture overview The connection uses three layers: Claude as the AI c...
Read more

itextpdf API to generate PDF doc from an image file using Pega PE

-
Image
Probably some of the techies might have an idea on an opensource called " itextpdf " (earlier name is lowagie ) to convert an image file(png,jpeg,jpg,tiff,gif etc.) to a PDF file. It is very simple to use this API in Pega function to build the logic using java code. Moreover, this API comes in one single jar file and we need to import it in Pega before we start using it.  I see the conversion comes good in PDF file but not sure if any limitations of this API in terms of conversion is like formatting, font, images etc. So far so good and may be we can keep this API as one of our solutions while working on the requirements accordingly.  Heard that same API can be used to convert the text file to PDF but I didn't explore on it. Those who are interested to work on text -> PDF can take a look at the documentation. Don't hesitate to contact me offline for any further discussion in this context :) :) Prerequisites for doing this exercise: 1) itextpdf 5.4.0 jar file 2) Peg...
Read more

Understanding of Hugging Face platform for AI/ML platform

-
Image
Hugging Face is a platform that provides tools and libraries for natural language processing (NLP), machine learning, and artificial intelligence. It is known for its Transformers   library, which offers pre-trained models for tasks such as text classification, translation, question answering, and more. Hugging Face also hosts a model hub where users can share and discover pre-trained models. Hugging Face is useful in various domains, including: Natural language processing (NLP): Provides tools and pre-trained models for tasks like text classification, translation, sentiment analysis, and question answering. Machine learning research: Offers state-of-the-art models and datasets for researchers to experiment and innovate. Data science and analytics: Helps data scientists analyze and interpret large volumes of text data. AI application development: Enables developers to build AI-powered applications with ease using pre-trained models and APIs. A very simple exercise using the google...
Read more