{"id":81612,"date":"2026-06-22T11:22:13","date_gmt":"2026-06-22T11:22:13","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/81612\/"},"modified":"2026-06-22T11:22:13","modified_gmt":"2026-06-22T11:22:13","slug":"ai-to-manage-ai-claude-creator-says-prompt-engineering-is-ending-too-just-like-software-engineering-reveals-whats-next","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/81612\/","title":{"rendered":"AI to manage AI? Claude creator says prompt engineering is ending too, just like software engineering. Reveals what&#8217;s next"},"content":{"rendered":"<p>The AI world may already be moving on from <a ref=\"dofollow\" data-ga-onclick=\"Inarticle articleshow link click#News#href\" href=\"https:\/\/m.economictimes.com\/topic\/prompt-engineering\" target=\"_blank\" rel=\"nofollow noopener\">prompt engineering<\/a>.<\/p>\n<p>Just months after claiming that &#8220;<a data-ga-onclick=\"Inarticle articleshow link click#News#href\" target=\"_blank\" href=\"https:\/\/m.economictimes.com\/definition\/software-engineering\" rel=\"nofollow noopener\">software engineering<\/a> is dead,&#8221; Anthropic co-founder and Claude Code creator <a ref=\"dofollow\" data-ga-onclick=\"Inarticle articleshow link click#News#href\" href=\"https:\/\/m.economictimes.com\/topic\/boris-cherny\" target=\"_blank\" rel=\"nofollow noopener\">Boris Cherny<\/a> has a new prediction: humans won&#8217;t be writing prompts for AI much longer.<br \/>Instead, he says the future belongs to &#8220;<a ref=\"dofollow\" data-ga-onclick=\"Inarticle articleshow link click#News#href\" href=\"https:\/\/m.economictimes.com\/topic\/loop-engineering\" target=\"_blank\" rel=\"nofollow noopener\">loop engineering<\/a>&#8221; \u2014 a new approach where <a ref=\"dofollow\" data-ga-onclick=\"Inarticle articleshow link click#News#href\" href=\"https:\/\/m.economictimes.com\/topic\/ai-agents\" target=\"_blank\" rel=\"nofollow noopener\">AI agents<\/a> write, refine, and manage prompts on their own while humans simply define the goal.<\/p>\n<p>&#8220;It&#8217;s an agent that prompts Claude. I don&#8217;t write the prompt anymore. Claude writes the prompt,&#8221; Cherny recently told Business Insider.<\/p>\n<p>In other words, AI is starting to manage AI.<\/p>\n<p><img decoding=\"async\" alt=\"ET logo\" src=\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/04\/118783427.cms.png\" width=\"90%\"\/>Live Events<br \/>So what exactly is a loop?<br \/>Think of a loop as a self-running AI workflow.<br \/>Instead of feeding an AI model one instruction after another, users can give it a broad objective and let it keep working until the task is complete.A command such as &#8220;\/goal&#8221; can tell an AI system to continue solving a problem, checking its work, creating new prompts, and improving results without needing constant human guidance.<\/p>\n<p>The idea is catching on fast among AI insiders.<\/p>\n<p>Peter Steinberger, creator of OpenClaw, says developers should stop obsessing over prompts and start building systems that generate prompts automatically.<\/p>\n<p>&#8220;You shouldn&#8217;t be prompting coding agents anymore. You should be designing loops that prompt your agents,&#8221; he said.<\/p>\n<p>Google Cloud executive Addy Osmani agrees. According to him, effective loops combine automation, plugins, connectors, worktrees, skills, and specialized sub-agents working together.<\/p>\n<p>AI agents are becoming co-workers<br \/>The biggest shift may be how people think about AI.<\/p>\n<p>Instead of using AI like a tool, experts increasingly suggest treating it like an employee.<\/p>\n<p>Claire Vo, founder of ChatPRD, says users should imagine they are onboarding a new hire.<\/p>\n<p>&#8220;This is the time for the manager. You are designing a job,&#8221; she explained.<\/p>\n<p>In these systems, one AI agent might write code, another could review it for bugs, while a third manages documentation or deployment.<\/p>\n<p>The human&#8217;s role? Supervision.<\/p>\n<p>There&#8217;s a catch: AI workers aren&#8217;t cheap<br \/>While loop engineering promises less work for humans, it can mean bigger AI bills.<\/p>\n<p>Every agent consumes tokens, and running multiple agents simultaneously can become expensive quickly.<\/p>\n<p>Steinberger recommends scheduling agents to work hourly or daily instead of constantly running in the background. Osmani also warns that companies should only deploy additional sub-agents when the benefits justify the cost.<\/p>\n<p>In short, the <a ref=\"dofollow\" data-ga-onclick=\"Inarticle articleshow link click#News#href\" href=\"https:\/\/m.economictimes.com\/topic\/ai-workforce\" target=\"_blank\" rel=\"nofollow noopener\">AI workforce<\/a> may need a budget just like a human one.<\/p>\n<p>Boris Cherny is also tired of the term &#8216;vibe coding&#8217;<\/p>\n<p>Cherny has another complaint: the phrase &#8220;vibe coding.&#8221;<\/p>\n<p>The term, coined by OpenAI co-founder Andrej Karpathy in 2025, became one of the hottest buzzwords in tech and was widely used to describe AI-assisted programming.<\/p>\n<p>But Cherny says the label no longer fits.<\/p>\n<p>Today&#8217;s AI coding tools are generating millions of lines of production software and helping create billion-dollar businesses. Calling that &#8220;vibe coding,&#8221; he argues, seriously understates what&#8217;s happening.<\/p>\n<p>He even asked Claude to suggest alternatives.<\/p>\n<p>One option was &#8220;agentic engineering&#8221; \u2014 another term linked to Karpathy \u2014 but Cherny isn&#8217;t sold on it.<\/p>\n<p>For now, he&#8217;s crowdsourcing ideas and inviting people to suggest better names.<\/p>\n<p>One thing, however, seems increasingly clear: prompt engineering may already be yesterday&#8217;s skill.<\/p>\n<p>The next big thing in AI could be learning how to manage teams of autonomous digital workers that manage themselves.<\/p>\n","protected":false},"excerpt":{"rendered":"The AI world may already be moving on from prompt engineering. Just months after claiming that &#8220;software engineering&hellip;\n","protected":false},"author":2,"featured_media":81613,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[405,25088,3766,53,3154,8515,182,44481,37389,11207,424,44480,44479],"class_list":["post-81612","post","type-post","status-publish","format-standard","has-post-thumbnail","category-anthropic","tag-ai-agents","tag-ai-management","tag-ai-workforce","tag-anthropic","tag-anthropic-claude","tag-boris-cherny","tag-claude","tag-future-software-jobs","tag-loop-engineering","tag-prompt-engineering","tag-software-engineering","tag-techie-ai-jobs","tag-techie-jobs-future"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/81612","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=81612"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/81612\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/81613"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=81612"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=81612"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=81612"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}