The AI-powered code editor Cursor has launched a new ‘Agent’ feature, positioning it as a direct competitor to established tools like Anthropic’s Claude Code and OpenAI’s Codex. This feature allows the AI to autonomously execute complex, multi-step coding tasks based on high-level user instructions, such as adding a new feature or debugging an issue. The launch highlights the intensifying competition in the AI-assisted development space, where the goal is to reduce developer workload by automating larger portions of the coding process. The article details the functionality of Cursor’s Agent and discusses the broader industry trend toward more autonomous coding assistants. Read the full article at https://www.wired.com/story/cusor-launches-coding-agent-openai-anthropic/