[{"@context":"https:\/\/schema.org\/","@type":"BlogPosting","@id":"https:\/\/blog.terabox.com\/insights\/future-of-ai-agents-harrison-chase-langchain#BlogPosting","mainEntityOfPage":"https:\/\/blog.terabox.com\/insights\/future-of-ai-agents-harrison-chase-langchain","headline":"Future of AI Agents: Harrison Chase on LangChain & LangGraph","name":"Future of AI Agents: Harrison Chase on LangChain & LangGraph","description":"\ud83d\udcfa Today’s recommended deep-dive video: https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY Beyond the Chatbot: Harrison Chase on the Architecture of Autonomous AgentsDefining the Agentic SpectrumThe Rise of Cognitive ArchitecturesUX and the Human-in-the-LoopTesting and ObservabilityKey TakeawaysQ&A Beyond the Chatbot: Harrison Chase on the Architecture of Autonomous... ","datePublished":"2026-08-14","dateModified":"2026-08-14","author":{"@type":"Person","@id":"https:\/\/blog.terabox.com\/author\/flextech-admin\/#Person","name":"flextech-admin","url":"https:\/\/blog.terabox.com\/author\/flextech-admin\/","image":{"@type":"ImageObject","@id":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","url":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","height":96,"width":96}},"publisher":{"@type":"Organization","name":"terabox","logo":{"@type":"ImageObject","@id":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","url":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","width":900,"height":900}},"image":{"@type":"ImageObject","@id":"https:\/\/img.youtube.com\/vi\/6XZLoW0-mPY\/maxresdefault.jpg","url":"https:\/\/img.youtube.com\/vi\/6XZLoW0-mPY\/maxresdefault.jpg","height":"","width":""},"url":"https:\/\/blog.terabox.com\/insights\/future-of-ai-agents-harrison-chase-langchain","video":{"@context":"http:\/\/schema.org\/","@type":"VideoObject","@id":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY#VideoObject","contentUrl":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY","name":"LangChain\u2019s Harrison Chase on Building the Orchestration Layer for AI Agents | Training Data","description":"Last year, AutoGPT and Baby AGI captured our imaginations\u2014agents quickly became the buzzword of the day\u2026and then things went quiet. AutoGPT and Baby AGI may have marked a peak in the hype cycle, but this year has seen a wave of agentic breakouts on the product side, from Klarna\u2019s customer support AI to Cognition\u2019s Devin, etc.\n\nHarrison Chase of LangChain is focused on enabling the orchestration layer for agents. In this conversation, he explains what\u2019s changed that\u2019s allowing agents to improve performance and find traction. \n\nHarrison shares what he\u2019s optimistic about, where he sees promise for agents vs. what he thinks will be trained into models themselves, and discusses novel kinds of UX that he imagines might transform how we experience agents in the future.     \n\n(01:21) What are agents? \n(05:00) What is LangChain\u2019s role in the agent ecosystem?\n(11:13) What is a cognitive architecture? \n(13:20) Is bespoke and hard coded the way the world is going, or a stop gap?\n(18:48) Focus on what makes your beer taste better\n(20:37) So what? \n(22:20) Where are agents getting traction?\n(25:35) Reflection, chain of thought, other techniques?\n(30:42) UX can influence the effectiveness of the architecture\n(35:30) What\u2019s out of scope?\n(38:04) Fine tuning vs prompting?\n(42:17) Existing observability tools for LLMs vs needing a new architecture\/approach\n(45:38) Lightning round\n\nHosted by: Sonya Huang and Pat Grady, Sequoia Capital\n\nRead the Transcript: https:\/\/seq.vc\/TDHC\nRead the Inference Essay: https:\/\/seq.vc\/TDHCIA","thumbnailUrl":["https:\/\/i.ytimg.com\/vi\/6XZLoW0-mPY\/default.jpg","https:\/\/i.ytimg.com\/vi\/6XZLoW0-mPY\/mqdefault.jpg","https:\/\/i.ytimg.com\/vi\/6XZLoW0-mPY\/hqdefault.jpg","https:\/\/i.ytimg.com\/vi\/6XZLoW0-mPY\/sddefault.jpg","https:\/\/i.ytimg.com\/vi\/6XZLoW0-mPY\/maxresdefault.jpg"],"uploadDate":"2024-06-18T11:00:04+00:00","duration":"PT49M51S","embedUrl":"https:\/\/www.youtube.com\/embed\/6XZLoW0-mPY","publisher":{"@type":"Organization","@id":"https:\/\/www.youtube.com\/channel\/UCWrF0oN6unbXrWsTN7RctTw#Organization","url":"https:\/\/www.youtube.com\/channel\/UCWrF0oN6unbXrWsTN7RctTw","name":"Sequoia Capital","description":"Sequoia helps daring founders build legendary companies from idea to IPO and beyond. We aim to be the first true believers in tomorrow\u2019s most consequential companies. We partner with a few outliers each year and go all-in, providing them with the hands-on help required at every stage of the company building journey. Our expertise comes from nearly 50 years of working with legendary founders like Steve Jobs, Elon Musk, Larry Page, Jan Koum, Brian Chesky, Tony Xu, Lin Qiao, Eric Yuan, Christina Cacioppo, and Patrick Collison. In aggregate, Sequoia-backed companies account for more than 30% of NASDAQ's total value. The vast majority of the money we invest has been on behalf of nonprofits and schools like the Ford Foundation, Mayo Clinic and MIT, which means most of the returns we generate benefit these great causes.\n\n","logo":{"url":"https:\/\/yt3.ggpht.com\/uCN-D7KzMQY-Ti-xTsNAwilXVFFMYjEBRju_mXrR22HUYxJZjVZgP_SnamO9KbPo2XN-nE3O-A=s800-c-k-c0x00ffffff-no-rj","width":800,"height":800,"@type":"ImageObject","@id":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY#VideoObject_publisher_logo_ImageObject"}},"potentialAction":{"@type":"SeekToAction","@id":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY#VideoObject_potentialAction","target":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY&t={seek_to_second_number}","startOffset-input":"required name=seek_to_second_number"},"interactionStatistic":[[{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY#VideoObject_interactionStatistic_WatchAction","interactionType":{"@type":"WatchAction"},"userInteractionCount":17886}],{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=6XZLoW0-mPY#VideoObject_interactionStatistic_LikeAction","interactionType":{"@type":"LikeAction"},"userInteractionCount":395}]},"about":["\u300eEnglish\u300f","Insights"],"wordCount":1435},{"@context":"https:\/\/schema.org\/","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Insights","item":"https:\/\/blog.terabox.com\/insights\/#breadcrumbitem"},{"@type":"ListItem","position":2,"name":"Future of AI Agents: Harrison Chase on LangChain & LangGraph","item":"https:\/\/blog.terabox.com\/insights\/future-of-ai-agents-harrison-chase-langchain#breadcrumbitem"}]}]