Google releases its asynchronous Jules AI agent for coding — how to try it for free

 

Google has entered the AI coding segment with a new tool called Jules. The tool as introduced back in December last year to Google Labs and now its beta version will be available to the public.

the AI coding segment with a new tool called Jules. | Photo Credit: Reuters

Google has entered the AI coding segment with a new tool called Jules. The tool as introduced back in December last year to Google Labs and now its beta version will be available to the public.

Jules can write code, debug and perform tests just like other AI coding assistants.

“It is an asynchronous, agentic coding assistant that integrates directly with your existing repositories. It clones your codebase into a secure Google Cloud virtual machine (VM), understands the full context of your project, and performs tasks like writing tests, building new features, providing audio changelogs and bumping dependency versions,” a blog posted by Google stated.

The tool will compete with existing AI coding agents like Cursor that are popular in the market.

Additionally, Google also launched a new AI tool called Stitch so developers can quickly build UI ideas into app designs. Powered by Gemini 2.5 Pro, the tool is now available on Google Labs.

Users just need to enter text prompts by referencing images which is then converted into UI designs and frontend code in a matter of minutes. The tool allows developers to experiment with different styles and layouts.

Once the UI assets are generated with the front-end code they can be directly added into apps or exported to another design tool to refine further.

What is Jules?

Jules is an asynchronous, agentic coding assistant that integrates directly with your existing repositories. It clones your codebase into a secure Google Cloud virtual machine (VM), understands the full context of your project, and performs tasks such as:

• Writing tests
• Building new features
• Providing audio changelogs
• Fixing bugs
• Bumping dependency versions

Jules operates asynchronously, allowing you to focus on other tasks while it works in the background. Upon completion, it presents its plan, reasoning and a diff of the changes made. Jules is private by default, it doesn’t train on your private code, and your data stays isolated within the execution environment.

Jules updates the codebase to a new version of Node.js

We’re at a turning point: agentic development is shifting from prototype to product and quickly becoming central to how software gets built. Jules uses Gemini 2.5 Pro, giving it access to some of the most advanced coding reasoning available today. Paired with its cloud VM system, it can handle complex, multi-file changes and concurrent tasks with speed and precision.

Here’s a look at what you get with Jules:

• Works on real codebases: Jules doesn’t need a sandbox. It takes the full context of your existing project to reason about changes intelligently.
• Parallel execution: Tasks run inside a cloud VM, enabling concurrent execution. It can handle multiple requests simultaneously.
• Visible workflow: Jules shows you its plan and reasoning before making changes.
• GitHub integration: Jules works where you already do, directly inside your GitHub workflow. No context-switching, no extra setup.
• User steerability: Modify the presented plan before, during, and after execution to maintain control over your code.
• Audio summaries: Jules offers an audio changelog of recent commits, turning your project history into a contextual changelog you can listen to.

Set up your dev environment

Connect to Github and create branch

Prompt a task and approve Jules’ plan

Give feedback as Jules performs tasks

Manage all your Jules tasks from the panel

Jump to position 1Jump to position 2Jump to position 3Jump to position 4Jump to position 5

During this public beta phase, access is free of charge, though usage limits do apply. Details can be found here. We expect to introduce pricing after this beta as the platform matures.

Get started with Jules and explore the documentation.https://jules.google/docs/usage-limits/

Here’s a look at what you get with Jules:

• Works on real codebases: Jules doesn’t need a sandbox. It takes the full context of your existing project to reason about changes intelligently.
• Parallel execution: Tasks run inside a cloud VM, enabling concurrent execution. It can handle multiple requests simultaneously.
• Visible workflow: Jules shows you its plan and reasoning before making changes.
• GitHub integration: Jules works where you already do, directly inside your GitHub workflow. No context-switching, no extra setup.
• User steerability: Modify the presented plan before, during, and after execution to maintain control over your code.
• Audio summaries: Jules offers an audio changelog of recent commits, turning your project history into a contextual changelog you can listen to.

Key Features That Stand Out

Free Access (For Now)

During the beta period, Jules is completely free with generous daily limits:

• 5 daily tasks
• 3 concurrent tasks
• Access to all core features

This is refreshing compared to competitors that put similar capabilities behind expensive paywalls.

 

Internet Access

Unlike OpenAI’s Codex, Jules has internet access.

This is good for tasks involving newer libraries or APIs with evolving documentation.

GitHub Integration

Jules connects directly to your GitHub repositories.

It can read your entire codebase to understand context and automatically create branches with changes.

Virtual Machine Execution

Each task runs in its secure VM where Jules can install dependencies, run tests, and verify its work before submitting changes.

Codecasts

A unique feature called “Codecasts” provides audio summaries of recent repository activity.

Think of them as audio changelogs that help you quickly catch up on project developments.

Real-World Performance

In testing, Jules demonstrated impressive capabilities.

When tasked with upgrading an older Gemini API implementation to the newer unified Google Gemini SDK, Jules:

1. Quickly identified the relevant files
2. Created a sensible implementation plan
3. Made appropriate code changes
4. Added unit tests to verify functionality
5. Created a new branch with all changes

The entire process took only about two minutes, without requiring constant supervision.

The Future of Software Engineering

The rise of asynchronous coding agents like Jules signals a paradigm shift in software development.

These tools don’t replace good engineering practices.

Developers who understand clean code principles, testing strategies, and solid architecture will benefit most.

Rather than threatening developer jobs, these agents appear to be evolving into productivity multipliers that handle routine tasks while letting humans focus on design decisions and complex problem-solving.

Should You Try Jules?

If you’re a developer looking to automate routine coding tasks, Jules is worth exploring.

The learning curve is minimal, especially if you’re already familiar with GitHub.

Most developers will likely see immediate productivity benefits, particularly for tasks like:

• Updating dependencies
• Adding documentation
• Writing unit tests
• Implementing simple features
• Fixing straightforward bugs

Getting Started

Getting started with Jules is simple:

1. Visit jules.google.com
2. Sign in with your Google account
3. Connect your GitHub repositories
4. Create your first task

The five daily free tasks give room to experiment and see if it fits your workflow.

Final Thoughts

While it’s too early to declare any definitive “winners” in the coding agent race, Jules is a good addition to autonomous coding assistants.

I like its combination of asynchronous operation, internet access, and GitHub integration.