Creator of Anthropic's Claude Code wants you to stop micromanaging your AI
Boris Cherny, creator of Anthropic's Claude Code, advises users to stop micromanaging AI models with overly specific, step-by-step instructions. He suggests that modern models perform better when given clear outcomes and guardrails, allowing the AI to determine the execution path.
Why it matters
As AI capabilities evolve, this shift in prompting strategy highlights the changing relationship between human users and autonomous agents, moving from manual control to goal-oriented management.
Boris Cherny, creator of Anthropic's Claude Code, said newer models can handle higher-level tasks than users think. Jason Henry/Bloomberg via Getty Images Claude Code creator Boris Cherny said users are underestimating the capabilities of newer models. He advised users to stop giving a model overly specific instructions and let it "cook." Cherny said some prompting habits could be obsolete as models continue to improve. If AI users are the new bosses and agents are the new employees, then the creator of Anthropic's popular coding agent has a piece of evergreen management advice: Stop micromanaging your AI. Boris Cherny, the creator of Anthropic's Claude Code , said at a Y Combinator event on Saturday that one common mistake he sees from Claude users is giving overly detailed, step-by-step instructions because they underestimate the tasks a model can handle.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in