Jules: Google’s Autonomous AI Coder That Works While You Sleep…

Author(s): R. Thompson (PhD)

Originally published on Towards AI.

What Happens When an AI Agent Reads Your Entire Codebase at Once?

Picture giving a coding brief at the end of the workday and waking up to a finished feature, a full test suite, and an annotated pull request. That scene is no longer sci‑fi. It arrived in August 2025 when Google released Jules, an AI agent that goes far beyond autocomplete. Jules runs inside a dedicated Google Cloud virtual machine, picks up an entire GitHub repository, and carries out tasks end‑to‑end without real‑time supervision. Developers hand over the “what,” and Jules handles the “how.”

Jules, Google’s new AI coding agent, operates within a virtual machine to autonomously handle programming tasks from start to finish, freeing developers to focus on higher-level decisions and enhancing productivity across teams. With a unique asynchronous model, it drafts and seeks approval on tasks before executing them, providing detailed pull requests upon completion. This innovative tool not only automates tedious processes such as bug fixes and comprehensive testing but also adapts seamlessly to workflows, emphasizing task delegation and collaboration within development teams.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI