{"slug": "creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai", "title": "Creator of Anthropic's Claude Code wants you to stop micromanaging your AI", "summary": "Boris Cherny, the creator of Anthropic's Claude Code, said at a Y Combinator event on Saturday that users should stop giving overly detailed, step-by-step instructions to AI agents. Cherny advised describing the task, setting guardrails, and defining success, then letting the model work independently, noting that modern models can handle more autonomy than users assume. He estimated that dozens or hundreds of useful AI abilities remain undiscovered.", "body_md": "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.\n\nBoris Cherny, the creator of [Anthropic's Claude Code](https://www.businessinsider.com/anthropic-improve-claude-code-snorkel-data-training-contractors-2026-6), 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.\n\n\"They're like, 'I want you to do this, but I want you to do it in this way, this way, this way. You must do one, then two, then three, then four,'\" Cherny said. \"For modern models, that's actually really not the way to do it.\"\n\nInstead, Cherny said users should be specific about the outcome while giving the model more freedom to decide how to get there. He recommended describing the task, setting the guardrails, and defining what a successful completion looks like.\n\n\"Then just go let the model cook and come back in a little bit,\" he said. \"I think it'll surprise you.\"\n\nCherny's advice reflects how quickly AI models can improve, potentially rendering older prompting habits obsolete. Cherny said his approach may not have worked six months ago, but it does with today's more capable models.\n\nGoogle Brain cofounder Andrew Ng shared a similar idea last year, calling it \"[lazy prompting\"](https://www.businessinsider.com/andrew-ng-lazy-ai-prompts-vibe-coding-2025-4) — when users provide minimal instructions as models get smarter.\n\n\"We add details to the prompt only when they are needed,\" Ng said.\n\nCherny said Anthropic employees are also finding new capabilities as they experiment with the company's models. He estimated that there are probably dozens, if not hundreds, of useful abilities that have yet to be discovered.\n\nSo, AI power users: Don't repeat the same mistakes [bad managers make](https://www.businessinsider.com/types-toxic-bad-bosses-what-to-do-2025-3). You could be getting in your AI's way.\n\n*Have a tip? Contact this reporter via email at *__lloydlee@businessinsider.com__* or Signal at lloydlee.71. Use a personal email address, a nonwork WiFi network, and a nonwork device; here's our *__guide to sharing information securely__*.*", "url": "https://wpnews.pro/news/creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai", "canonical_source": "https://www.businessinsider.com/anthropic-claude-code-prompting-tips-boris-cherny-micromanaging-ai-2026-7", "published_at": "2026-07-27 22:08:02+00:00", "updated_at": "2026-07-27 22:28:12.359727+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-products", "large-language-models"], "entities": ["Boris Cherny", "Anthropic", "Claude Code", "Y Combinator", "Andrew Ng", "Google Brain"], "alternates": {"html": "https://wpnews.pro/news/creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai", "markdown": "https://wpnews.pro/news/creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai.md", "text": "https://wpnews.pro/news/creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai.txt", "jsonld": "https://wpnews.pro/news/creator-of-anthropic-s-claude-code-wants-you-to-stop-micromanaging-your-ai.jsonld"}}