Cursor, a popular AI-powered code editor, has launched a new ‘Agent’ experience designed to compete directly with established coding assistants like Anthropic’s Claude Code and OpenAI’s Codex. The new feature aims to provide a more autonomous and integrated coding workflow within the editor itself. It allows developers to describe a task in natural language, and the AI agent will plan and execute the necessary code changes across multiple files, while explaining its reasoning. This positions Cursor as a more proactive tool compared to traditional code-completion models, focusing on complex, multi-step development tasks. The launch highlights the intensifying competition in the AI-assisted programming space as companies seek to build the most effective and intuitive tools for developers. For the full details, read the article at https://www.wired.com/story/cusor-launches-coding-agent-openai-anthropic/