TechPrufer
Get started
Google
Google logoGoogle · Feature trail

Full-Stack Development Environment

8 posts · Aug 2023 – Jun 2026

What this trail covers

The Full-Stack Development Environment feature thread continues to evolve with advancements in AI-assisted development workflows and cross-platform capabilities. Project IDX offers an AI-powered cloud workspace supporting various frameworks and languages. This post details the integration of VS Code with Gemini Enterprise Agent Platform Workbench, enabling users to manage code and cloud-based notebooks in a single interface, streamlining the ML lifecycle by eliminating context switching and allo. This post announces the general availability of AI-first Google Colab, integrating agentic capabilities for the entire ML lifecycle, including autonomous data cleaning, feature analysis, model training, evaluation, and smarter debugging with AI-suggested fixes. It also highlights effortless code transformation via natural language descriptions and the Next-Generation Data Science Agent for autonomous analytical workflows.

All Google trails
  1. ML Development in VS Code with Google Cloud Power: Workbench Extension Now Available- Google Developers BlogIntroduces the Google Cloud Workbench Notebooks extension for VS Code, allowing users to connect their local IDE to managed cloud environments (Gemini Enterprise Agent Platform Workbench) for ML development. This enables running notebooks directly on Workbench instances, leveraging high-performance compute without leaving VS Code. The extension is open-sourced.
  2. Introducing Finish Changes and Outlines, now available in Gemini Code Assist extensions on IntelliJ and VS Code- Google Developers BlogIntroduces 'Finish Changes' and 'Outlines' features for Gemini Code Assist extensions in IntelliJ and VS Code. 'Finish Changes' allows AI-driven code completion and refactoring based on in-progress code, pseudocode, comments, and patterns, with context from open files. 'Outlines' generates inline code summaries within the editor and a synchronized sidebar for improved code comprehension and navigation. Both features leverage Gemini 3.0 and aim to reduce developer friction and ramp-up time.
  3. What's new in Gemini Code Assist- Google Developers BlogThis post announces the general availability of Gemini Code Assist's Agent Mode in VS Code and IntelliJ, detailing its capabilities for multi-step task completion, code refactoring, and collaborative AI-assisted development. It highlights improvements in VS Code, such as inline diffs, persistent chat history, and real-time shell command output. For IntelliJ, it notes the availability of Agent Mode on the Stable release and the introduction of 'thinking tokens'. The post also covers general IDE improvements like stopping chat responses and the general availability of previously previewed features. Finally, it details updates to the Gemini CLI, including the launch of Gemini CLI GitHub Actions for automated repository tasks and deeper VS Code integration with context-aware workflows and native in-editor diffing.
  4. Supercharge your notebooks: The new AI-first Google Colab is now available to everyone- Google Developers BlogIntroduces the general availability of AI-first Google Colab, integrating agentic capabilities for the entire ML lifecycle, including autonomous data cleaning, feature analysis, model training, evaluation, and smarter debugging with AI-suggested fixes. It also highlights effortless code transformation via natural language descriptions and the Next-Generation Data Science Agent for autonomous analytical workflows.
  5. Build Go applications using Project IDX and the Gemini API- Google Developers BlogThis post details how to set up a Go development environment within Project IDX, including customizing the environment with Nix to add the Go package and Go extension. It demonstrates writing a basic 'Hello, World!' Go server application and configuring a web preview within IDX to test the server. Additionally, it highlights the availability of Go backend server templates and a Go and Gemini template for building LLM applications, emphasizing the integration with the Gemini API.
  7. How We Built It: The I/O Crossword- Google Developers BlogThis post details the technical implementation of the I/O Crossword game, highlighting the use of Flutter for the UI, including the InteractiveViewer widget and compilation to WebAssembly for performance. It showcases Firebase services for hosting, real-time data storage (Firestore), authentication (anonymous auth, App Check), and backend logic (Cloud Functions for Firebase). The Gemini API and Firebase Genkit are used for AI-powered hint generation, with Gemini 1.5 Flash providing yes/no answers based on context. Dart Frog and Cloud Run are employed for the backend setup, managing API calls and database interactions, with Dart Frog ensuring code sharing between frontend and backend and preventing cheating.
  8. Start Building with Project IDX Today- Google Developers BlogProject IDX is now in beta, removing the waitlist and offering up to 5 workspaces for Google Developer Program members. Gemini integration is improved with better code completion and contextual chat. Slash commands and experimental interactive chat with Gemini are introduced for automating tasks and code edits. New integrations with Gemini API, Firebase Hosting, Google Maps Platform APIs, and Cloud Run are available. Experimental support for Chrome DevTools Console and Lighthouse is embedded for debugging. New templates include Google Maps Platform + Gemini, Google Maps Platform + React, Firebase Data Connect (private preview), and Firebase Genkit. 'Open in IDX' buttons are being added to Google developer docs and codelabs.
  9. Build with Gemini models in Project IDX- Google Developers BlogThis post details the integration of Gemini models into Project IDX, enhancing its AI-powered features. It introduces inline AI assistance for real-time error correction, code suggestions, and auto-completion within any file, and demonstrates its use for tasks like adding authenticated API endpoints, refactoring code, and writing unit tests. Additionally, it announces a new Gemini API template that simplifies building AI-powered features into applications using the Gemini Pro model, with support for multimodal inputs and integration with frameworks like LangChain. A sample recipe builder application showcases the template's capabilities.
  10. Introducing Android emulators, iOS simulators, and other product updates from Project IDX- Google Developers BlogIntroduces the integration of iOS Simulator and Android Emulator directly within the Project IDX browser-based workspace, enabling in-place development, testing, and debugging of Flutter and web applications. Adds new templates for Astro, Go, Python/Flask, Qwik, Lit, Preact, Solid.js, and Node.js. Enhances Nix for workspace customization, file editing with syntax highlighting and error detection, and environment rebuilds. Adds features for auto-detecting network ports, running command-line tools directly, and enabling Docker. Expands AI capabilities to 15 new regions.
  11. Full-stack development in Project IDX- Google Developers BlogThis post details how Project IDX simplifies full-stack development in a browser-based environment by addressing developer authentication, frontend-backend communication, and hermetic testing. It explains how service accounts enable authenticated preview environments, how to configure port communication using Nix and environment variables, and demonstrates making authenticated AJAX requests with credentials. It also introduces temporary access tokens for server-side testing with tools like cURL and Postman, and highlights the integration of Firebase Local Emulator Suite for hermetic testing within the IDX workspace.
  12. Introducing Project IDX, An Experiment to Improve Full-stack, Multiplatform App Development- Google Developers BlogIntroduces Project IDX, a new browser-based development experience built on Google Cloud and powered by Codey AI. It offers a Linux VM workspace, import from GitHub, templates for popular frameworks (Angular, Flutter, Next.js, React, Svelte, Vue, JS, Dart, Python, Go), in-browser web preview, Android emulator, and iOS simulator. AI features include code completion, chatbot, and contextual actions. Integrates with Firebase Hosting for deployment.