Boris Cherny, co-founder of Anthropic and creator of Claude Code, has shifted his stance, now stating that the era of manually writing AI prompts is ending and that the future lies in loop engineering, a system where AI agents generate and refine prompts themselves. Cherny explained, “It’s an agent that prompts Claude. I don’t write the prompt anymore. Claude writes the prompt, and now I’m talking to that new Claude that is coordinating.” Other AI leaders echo this shift: Peter Steinberger, creator of OpenClaw at OpenAI, told users, “You shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents,” while Addy Osmani, director at Google Cloud, described loops as requiring five components: automations, worktrees, skills, plugins and connectors, and sub-agents. Claire Vo, founder of ChatPRD, explained, “This is the time for the manager. You are designing a job.” While loops reduce human effort, they raise concerns about token budgets, with Steinberger advising longer intervals to reduce costs and Osmani cautioning that sub-agents should only be used when a second opinion is worth the expense. Separately, Cherny told Business Insider that “vibe coding”—coined by OpenAI co-founder Andrej Karpathy in early 2025 and named word of the year by Collins Online Dictionary in November—is starting to grate on him, as he believes “vibe