Jules 是什么?
Jules is Google's autonomous coding agent, built around working asynchronously: you hand it a coding task, it works on it in the background — planning, writing code, and testing — while you continue with other work, rather than requiring you to sit and supervise each step in real time the way many chat-based coding assistants do.
It launched as a Google Labs experiment in December 2024, entered beta at Google I/O in May 2025, and exited beta in August 2025, making it one of the more mature entries in Google's fast-growing agentic coding lineup alongside Antigravity and Gemini Code Assist. Jules is positioned specifically for well-defined, delegable tasks — bug fixes, small features, refactors — that don't need constant back-and-forth.
Jules doesn't have a standalone subscription — pricing is bundled into Google's AI plans. The free Introductory tier includes 15 daily tasks with 3 concurrent tasks. Google AI Pro ($19.99/month) raises that to 100 daily tasks and 15 concurrent, and Google AI Ultra ($124.99/month for this tier) allows 300 daily tasks and 60 concurrent — useful context since a single task that needs a plan revision can count as two tasks against your limit.
Jules 的核心功能
- Asynchronous task execution: Works on a coding task in the background while you continue other work.
- Concurrent task handling: Runs multiple tasks in parallel, with limits scaling by plan tier.
- Bundled into Google AI plans: No separate subscription — access scales with your existing Google AI Pro/Ultra plan.
- Mature, out-of-beta agent: Exited beta in August 2025 after roughly eight months of public testing.
Jules 的使用场景
- Delegate a well-defined bug fix or small feature to work on in the background
- Run multiple independent coding tasks concurrently without babysitting each one
- Hand off a refactor task while focusing on higher-priority work yourself