Google makes Jules, its AI coding agent, generally available
Google has transitioned Jules from Google Labs beta to full public release. Powered by Gemini 2.5 Pro, Jules runs asynchronously in a cloud VM to read, test, improve, and visualize code with minimal developer oversight. The launch adds a free tier alongside paid “Pro” and “Ultra” plans and introduces a critic capability that flags issues before changes are submitted.
Google debuted Jules in December 2024 as an experimental agent within Google Labs, later opening it to public beta in May 2025. Following months of beta testing that generated thousands of tasks and more than 140,000 code improvements, the company has now promoted Jules to general availability. The update includes a redesigned interface, bug fixes, GitHub Issues integration, and multimodal output support.
Jules runs in a secure Google Cloud virtual machine, cloning a user’s repository and performing tasks such as writing tests, fixing bugs, updating dependencies, and summarizing changes with audio changelogs. Its asynchronous design allows developers to start tasks and continue other work without monitoring execution in real time.
Pricing is structured into three tiers: a free tier with 15 tasks per day and three concurrent jobs, a Pro tier with roughly five times those limits, and an Ultra tier with up to twenty times the capacity. All tiers use Gemini 2.5 Pro.
The critic-augmented generation feature reviews Jules’s proposed changes before submission and flags issues from logic errors to inefficiencies, allowing the agent to replan or revise before completing the task. Google positions Jules as part of its broader strategy to embed task-oriented AI agents into everyday workflows across technical and non-technical domains.
Pure Neo Signal:
We love
and you too
If you like what we do, please share it on your social media and feel free to buy us a coffee.
