{"id":245508,"date":"2026-10-16T13:05:55","date_gmt":"2026-10-16T18:05:55","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2026\/10\/stanford-cs146s-how-always-on-agents-work"},"modified":"2026-10-16T13:05:55","modified_gmt":"2026-10-16T18:05:55","slug":"stanford-cs146s-how-always-on-agents-work","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2026\/10\/stanford-cs146s-how-always-on-agents-work","title":{"rendered":"Stanford CS146S: How always-on agents work"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/L1OBRtfPS34?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>How do always-on AI agents actually work\u2014and what makes them capable of handling tasks even when you\u2019re not actively prompting them?<\/p>\n<p>In a lecture for Stanford\u2019s CS146S course, Lee Robinson, formerly of Vercel and Cursor and now part of SpaceX\u2019s AI team, explains the engineering behind Grok Bot and the emerging architecture of persistent, proactive AI agents.<\/p>\n<p>The 45-minute lecture covers:<\/p>\n<p>\u2192 What changed in models to make always-on agents possible.<br \/> \u2192 The architecture behind persistent agents.<br \/> \u2192 Harness engineering: the systems that enable models to use tools and take action.<br \/> \u2192 Context engineering for long-running tasks.<br \/> \u2192 Where agent architectures are headed next.<\/p>\n<p>The central insight: An AI agent is more than a model. Its ability to work autonomously over extended periods depends on the surrounding infrastructure\u2014tool use, memory, context management, and the harness that coordinates its actions.<\/p>\n<p>A useful look at the engineering required to move beyond conversational AI toward agents that can work continuously, respond to events, and manage complex tasks over time.<\/p>\n<div class=\"more-link-wrapper\"> <a class=\"more-link\" href=\"https:\/\/lifeboat.com\/blog\/2026\/10\/stanford-cs146s-how-always-on-agents-work\">Continue reading \u201cStanford CS146S: How always-on agents work\u201d | &gt;<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"<p>How do always-on AI agents actually work\u2014and what makes them capable of handling tasks even when you\u2019re not actively prompting them? In a lecture for Stanford\u2019s CS146S course, Lee Robinson, formerly of Vercel and Cursor and now part of SpaceX\u2019s AI team, explains the engineering behind Grok Bot and the emerging architecture of persistent, proactive [\u2026]<\/p>\n","protected":false},"author":709,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6,1514],"tags":[],"class_list":["post-245508","post","type-post","status-publish","format-standard","hentry","category-robotics-ai","category-space-travel"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/245508","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/709"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=245508"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/245508\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=245508"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=245508"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=245508"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}