{"slug": "head-of-anthropics-claude-code-says-prompt-engineering-not-that-important", "title": "Head Of Anthropic’s Claude Code Says Prompt Engineering Not That Important", "summary": "Boris Cherny, head of Anthropic's Claude Code, said prompt engineering is largely not important and that users should focus on giving Claude hard tasks and enabling verification. In an interview with Y Combinator's Diana Hu, Cherny demonstrated that a simple prompt asking Claude to rewrite the Electron desktop app in Swift succeeded without complex instructions. He advised users to unfollow AI influencers and instead let the model work autonomously.", "body_md": "Y Combinator’s Diana Hu recently interviewed Boris Cherny, the creator and head of Claude Code at Anthropic. Cherny said that Claude Code is more capable than is commonly understood, saying that prompt engineering is largely not important. Given that Claude doesn’t require “overthinking,” he suggested Claude Code users would be better off unfollowing AI influencers on Twitter and LinkedIn.\n\n## Prompt Engineering Is Less Relevant Today\n\nOne point that Cherny was excited about is that Claude Code is highly capable and does not require meticulous prompts. He gave the example of an experiment that went viral internally in which an engineer gave Claude access to OpenCV (Open Source Computer Vision Library), an open-source library of several thousand real-time vision algorithms for processing images and machine learning. Then it was asked to draw images, and it did, a capability that was completely unexpected.\n\nThe point of the anecdote was to drive home the message that Claude Code has capabilities that far outstrip the need for “prompt engineering.” Diana Hu asked about model elicitation, which is the process of unlocking hidden capabilities in AI models.\n\n*Diana Hu asked:*\n\n“And the big area of research for this is basically model elicitation, right? Becoming really good at figuring out all these capabilities and asking the model to do the right thing, right?\n\nHow do people get better at that? And effectively, how do people get better at prompt engineering? Do people still need to do a lot of prompt engineering or is that changing as well?\n\nTell us about where this is going.”\n\nOne of the things Cherny kept repeating is that it’s useful to give Claude Code tasks that are hard to do and that go beyond your expectations of what Claude is capable of, which was the point of the OpenCV anecdote.\n\n*Cherny answered:*\n\n“Yeah, I remember like a year ago, one of the most popular job openings was prompt engineer. And then it kind of changed and then I think it became like context engineer. So there’s these kind of waves of it, I think these will kind of like come and go.\n\nI think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard? And then how do you make it possible for Claude to verify its work along the way?\n\nAnd the verification, I think, is probably the single most important thing that people do not get right, largely.”\n\nAt this point, Cherny described giving Claude Tag (Claude working as an agent within Slack) access to a Mac virtual machine and then gave it a complex programming task. He asked it to rewrite the Claude desktop app, transforming it from the open-source Electron framework to the native Apple programming language Swift. Cherny used a simple, direct prompt that did not overthink the instructions or constraints.\n\n*Here’s his description of the task and the prompt:*\n\n“And then I was like, OK, now what I want you to do is I want you to rewrite the Electron app in Swift. I want you to run the Electron app in the Mac virtual machine, screenshot it, and then look pixel by pixel, compare it to the Swift version.\n\nDon’t stop until you’re done.\n\n…So this is really one of those examples where the model can do it today, you just have to let it do it, and you don’t need the fancy stuff.\n\nYou don’t need /goal, you don’t need /loop. These help. But really all you need is give the model the task, give it a way to verify the output of its work so it doesn’t get stuck, and it’ll just go.\n\n…And actually, in this case, Claude also decided to live blog it. So what it did is it created a Slack channel internally, and it started just posting screenshots every few minutes of its progress.”\n\n## How Claude Code Users Can Become More Expert\n\nThe interviewer, Diana Hu, expressed astonishment that a complex programming task could be accomplished with a simple prompt. She next asked how Anthropic Claude Code users can become more expert with Claude Code. Cherny’s answer said that prompting Claude Code has to be done “empirically,” which means through experience and observing how things work out.\n\n*She asked:*\n\n“What is separating the people here that can become the top 1% Claude users? How can people learn to use Claude like Boris?”\n\n*Cherny replied:*\n\n“Maybe like, don’t listen to the LinkedIn influencers. Don’t listen to, don’t read Twitter.\n\nThis is the thing about the model is I think everyone’s looking for like the one weird trick to do it. That doesn’t exist, there’s nothing like that.\n\nThe way the model works is you have to approach it empirically. You have to give it a task that’s too hard.\n\nYou have to give it the tools to verify the work, like you would yourself, like you would if you were doing the task.\n\nYou have to see where it struggles, and then you have to fix that, either with better prompting or with a skill, or if the model is missing context, give it an MCP so it can pull in the context that it needs. That’s kind of it.”\n\n## Over-Specifying Is Self-Defeating\n\nThe interviewer, Hu, remarked that it sounded simple. Cherny replied that he thinks that “people tend to overthink it a little bit.” His point was that over-specifying is not necessary with today’s Claude Code.\n\n*He continued:*\n\n“I think people tend to over-engineer. Because I think, in a lot of ways, when we built systems in the past, that’s the way you had to do it.\n\nSo when I look at engineers that have been coding for a long time, for years or for decades, this is a really, really common failure mode, is trying to over-specify, and it’s trying to be overly specific, and get the model to do the task exactly the way that you would have done it.\n\nAnd that’s just not the way the model works.\n\nBut I think a lot of people are unlearning this, and it’s a journey to unlearn it. It’s a journey to kind of figure out how do you treat this thing like you would a coworker.\n\nI think that’s the level of intelligence that it’s at now.”\n\n## Takeaways\n\n- Prompt engineering matters less than giving Claude clear instructions and ways to verify its work.\n- Claude has advanced to the point where many “prompt engineering” tricks are no longer necessary.\n- Claude Code is capable of more than many users realize.\n- Challenge Claude Code with harder tasks.\n- Giving things a try and seeing how they work out can be useful.\n- Don’t overthink prompts.\n\n### Watch Boris Cherny’s Interview:\n\n*Featured Image by Shutterstock/RixAiArt*", "url": "https://wpnews.pro/news/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important", "canonical_source": "https://www.searchenginejournal.com/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important/584286/", "published_at": "2026-07-30 12:30:07+00:00", "updated_at": "2026-07-30 12:33:30.122981+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-tools", "ai-agents"], "entities": ["Anthropic", "Claude Code", "Boris Cherny", "Diana Hu", "Y Combinator", "OpenCV", "Slack", "Swift"], "alternates": {"html": "https://wpnews.pro/news/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important", "markdown": "https://wpnews.pro/news/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important.md", "text": "https://wpnews.pro/news/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important.txt", "jsonld": "https://wpnews.pro/news/head-of-anthropics-claude-code-says-prompt-engineering-not-that-important.jsonld"}}