Agentic AI Coding with Google Jules

Picture by Writer

# Introduction

 
When you’ve got been writing code up to now couple of months, I’m fairly certain you have to have seen a shift. AI is not one thing that simply suggests snippets; it has gone past that, it’s beginning to act. Builders are shifting from assistive instruments like Copilot to agentic techniques that perceive a objective, plan a sequence of steps, and execute them on their very own.

Google Jules sits on the entrance of that curve. It’s not a chat assistant that lives in your IDE; it’s a totally asynchronous coding agent. You inform it what you need mounted, up to date, or examined, and it does the work remotely, from cloning your repo, modifying code in a safe cloud VM, working checks, and opening a pull request for assessment.

The distinction is refined however profound: Jules doesn’t wait so that you can kind. It acts independently, guided by your intent and the context of your codebase. It reads your documentation, runs builds, exhibits its plan earlier than touching something, and even explains every change in a diff view. Whilst you deal with structure or design, Jules quietly handles the upkeep duties that devour most of a developer’s day, reminiscent of model bumps, flaky checks, forgotten docstrings, and low-impact bugs.

# What Makes Jules Totally different?

 
Most AI coding instruments nonetheless dwell inside your editor. They autocomplete capabilities, recommend patches, or refactor small snippets whilst you supervise line by line. Jules doesn’t do this. It strikes the complete workflow exterior your native atmosphere and runs it asynchronously within the cloud.

Once you assign Jules a process, let’s say, “Improve the app to Subsequent.js 15 and migrate to the app listing,” it doesn’t simply predict. It pulls your repository from GitHub, units up a digital machine, installs dependencies, writes and checks the adjustments, and presents a plan and diff earlier than making any adjustments to your essential department.

That end-to-end workflow is what makes Jules completely different from suggestion-based assistants like Copilot or Cody. It’s not serving to you write code quicker; it’s serving to you end work you’d moderately not do in any respect.

The platform is constructed round 4 core concepts:

• GitHub-Native Integration — Jules works by way of points, branches, and pull requests like a teammate. You possibly can even assign it duties immediately by including the jules label to a problem.
• Cloud Execution Setting — Each process runs in a clear Ubuntu VM with Node.js, Python, Go, Rust, Java, and Docker preinstalled. No native setup, no dependency drift.
• Clear Reasoning — Jules exhibits you its plan, explains every step, and generates diffs earlier than merging. You see precisely what it’s pondering.
• Asynchronous Autonomy — As soon as began, Jules retains working even should you shut the browser. You get notified when it’s accomplished.

# The Jules Structure

 
Jules is a workflow system wrapped round a big language mannequin, Gemini 2.5 Professional,  and a cloud-based execution layer. It combines structured automation with agent reasoning, which means each step (plan, edit, check, PR) is observable, traceable, and reversible.

Picture by Writer

Right here’s the way it truly works behind the scenes:

• Job Initialization: Once you describe a process (“Add integration checks for auth.js”), Jules creates a session linked to your GitHub repo and department. It fetches the repository metadata and atmosphere hints from recordsdata like README.md or AGENTS.md.
• Setting Setup: Jules spins up a short-lived Ubuntu digital machine within the cloud. It installs your dependencies routinely or runs your setup script — npm set up, pytest, make construct, no matter you outline. The whole lot runs in isolation, so your repo stays secure.
• Reasoning and Planning: Utilizing Gemini 2.5 Professional, Jules analyzes the codebase and your immediate to provide a plan: which recordsdata to switch, which capabilities to the touch, and which checks to create. It presents this plan for assessment earlier than executing. You possibly can edit or approve it immediately within the interface.
• Code Technology and Testing: As soon as accredited, Jules executes every step contained in the VM. It writes or modifies code, runs the check suite, validates the output, and logs each lead to an exercise feed. That is the place you may watch Jules “suppose aloud” — explaining why it modified every file.
• Diff and Assessment: Each edit comes with a Git diff. You possibly can develop it, assessment the patch, and obtain or copy snippets. Jules explains every change in pure language and sometimes hyperlinks it again to the plan step that precipitated it.
• Commit and PR Creation: Lastly, Jules pushes the up to date department to GitHub and opens a pull request, the place you (or your CI pipeline) can assessment and merge. You keep the proprietor of the repo — Jules solely commits as an assistant.

The complete system runs asynchronously. You possibly can shut your laptop computer, get espresso, or work on one other department whereas Jules finishes a construct or check run. When it’s accomplished, it sends a browser notification or updates the UI.

# Getting Began with Jules

 
Jules is designed to really feel easy from the primary click on. You don’t want to put in or configure something; it runs totally within the cloud, with GitHub because the entry level. Right here’s what the everyday onboarding movement appears to be like like.

// 1. Log in and Hook up with GitHub

Go to jules.google and check in along with your Google account. After accepting the privateness discover, you’ll be prompted to attach your GitHub account. Jules solely works with repositories you explicitly grant entry to, so you may select to attach all or just some tasks.

As soon as related, you’ll see your repositories listed in a selector. Select one, and Jules will routinely detect its branches, README, and construct context.

Picture by Writer

// 2. Write a Clear Job Immediate

On the coronary heart of Jules is the immediate field, which is the place you describe what you need accomplished. You possibly can kind plain English directions like:

Add a check for parseQueryString() in utils.js

To assign a process immediately from GitHub, merely add the label ‘jules‘ to a problem. Jules will decide it up routinely, generate a plan, and begin getting ready a VM.

You possibly can even connect photos (reminiscent of UI mockups or bug screenshots) to offer extra context. Jules makes use of these as visible hints, not as property to decide to your repo.

// 3. Assessment the Plan

Earlier than any code is written, Jules exhibits you its reasoning, a structured breakdown of the steps it intends to take. You possibly can develop every step, go away feedback, or request changes immediately within the chat. When you approve the plan, Jules begins executing inside a contemporary digital machine.

Picture by Writer

// 4. Watch Jules Work

Within the exercise feed, you’ll see dwell logs of what Jules is doing,  putting in dependencies, modifying recordsdata, working checks, or producing diffs. You possibly can step away; it’s asynchronous by design.

 
When it’s accomplished, you’ll get a abstract displaying:

• Recordsdata modified
• Complete runtime
• Strains of code added or modified
• Department created with commit message

Picture by Writer

From there, you may click on Publish PR, and Jules will open a GitHub pull request with their adjustments already pushed. You possibly can then assessment and merge the PR as soon as you might be glad with it. 

# The Jules CLI

 
Whereas the online app provides you a visible dashboard, the Jules Instruments CLI brings the identical energy on to your terminal. It’s light-weight and integrates easily into your on a regular basis developer workflows. You should use it to begin duties, verify progress, or pull outcomes with out ever leaving your editor or CI/CD pipeline.

// 1. Set up and Login

Jules Instruments is accessible by way of npm. Set up it globally with:

npm set up -g @google/jules

After set up, log in along with your Google account:

A browser window will open for authentication, and as soon as confirmed, you’ll have full entry to your Jules classes.

// 2. Checking Repositories and Periods

The CLI enables you to view all related GitHub repositories and energetic classes.

# Record related repos
jules distant listing --repo

# Record energetic or previous classes
jules distant listing --session

This mirrors what you’d see on the Jules dashboard, however in terminal type, helpful for automated checks or when engaged on a headless server.

// 3. Making a New Session

Beginning a brand new coding process is simply as easy:

jules distant new --repo . --session "Add TypeScript definitions to utils/"

This command tells Jules to fetch the present repository, spin up a safe cloud VM, and start planning. You’ll get a session ID in return, which you need to use to observe or pull adjustments later.

// 4. Pulling Outcomes Again

As soon as Jules finishes a process and creates a pull request, you may carry the ensuing adjustments again to your native atmosphere:

jules distant pull --session 123456

That is helpful for CI techniques or groups that need to assessment adjustments offline earlier than merging.

// 5. Launching the TUI

In the event you choose visuals, you may merely kind:

This launches the Terminal Person Interface (TUI), a minimal dashboard that exhibits dwell classes, duties, and their progress, all inside your terminal. It’s the proper mix of automation and visibility.

# Selecting Jules Plans that Match Your Workflow

 
Jules is constructed to scale along with your coding,  from solo debugging to enterprise-level agile improvement. It’s out there in three tiers, every tuned for various workloads, however all powered by the identical Gemini 2.5 Professional mannequin. 

Paid plans are managed by way of Google AI Plans, at present out there just for particular person @gmail.com accounts. Google has confirmed that Workspace and enterprise paths are coming quickly.

When you’ve used your each day quota (measured over a rolling 24-hour interval), you may nonetheless view and handle present classes; nonetheless, you can’t begin new ones till the restrict resets. Jules will show a tooltip or “Improve” immediate when that occurs.

Every plan enforces its personal concurrency restrict, which determines the utmost variety of VMs that may run concurrently. Exceeding it merely queues duties, making certain secure parallel execution with out conflicts.

Each Jules session spins up a safe digital machine with actual compute value. Limits guarantee stability, isolate workloads, and shield repository information from overuse or abuse. In addition they assist Google benchmark efficiency for upcoming multi-agent upgrades.

# Privateness, Safety, and Knowledge Dealing with

 
When an AI system runs your code, belief isn’t non-obligatory; it’s every part. Jules was designed from the bottom up with developer privateness in thoughts. Each repository, process, and atmosphere is dealt with in isolation, and none of your personal information is used for mannequin coaching.

Right here’s what which means in follow:

1. Brief-Lived, Remoted Digital Machines: Every process Jules runs takes place in a brief cloud VM. As soon as the duty completes, whether or not it succeeds or fails, the atmosphere is destroyed. No persistent containers, no shared volumes, and no long-lived processes. This sandbox mannequin protects your repository from leaks or cross-contamination between runs. Each new process begins clear.
2. Express Repository Entry: Jules can solely entry the repositories you authorize by way of GitHub. To cease a repository from working, merely revoke its entry by way of your GitHub software settings.
3. No Coaching on Personal Code: In contrast to some assistants that silently acquire context, Jules doesn’t practice on personal repositories. Your prompts, diffs, and commits are used just for that session’s execution, by no means for enhancing the mannequin. This level is central to Google’s method to agentic techniques: the mannequin might enhance by way of combination studying, however not out of your private or company code.
4. Protected Execution and Dependency Dealing with: All builds occur in a totally sandboxed atmosphere. You possibly can examine each command that runs through the exercise feed or logs. If one thing appears to be like dangerous, you may pause or delete the duty at any time.
5. Clear Logs and Full Auditability: Each motion Jules takes, e.g. plan creation, diff era, testing, commit, or PR, is logged. You possibly can obtain or assessment these logs later for compliance or auditing.

# Wrapping Up

 
Software program improvement is getting into an agentic section, the place AI doesn’t simply help, however participates. Google Jules is without doubt one of the clearest examples of that shift.

It integrates immediately with GitHub, runs duties safely in its personal VM, validates its output by way of checks, and exhibits its reasoning and diffs earlier than merging something. Whether or not you’re fixing a bug, refactoring a characteristic, or cleansing up dependencies, Jules provides you a technique to transfer quicker with out chopping corners.

For groups exploring automation or builders bored with upkeep overhead, that is the place the following era of AI tooling begins. Discover it your self at jules.google and see what it feels wish to code alongside an agent that actually works with you.
 
 

Shittu Olumide is a software program engineer and technical author obsessed with leveraging cutting-edge applied sciences to craft compelling narratives, with a eager eye for element and a knack for simplifying complicated ideas. You can even discover Shittu on Twitter.