LangChain’s Harrison Chase on Building the Orchestration Layer for AI Agents | Training Data

[@ololandai]

Great discussion! We are leveraging LangGraph to implement congintive architecture of agentic state machine and already seeing phenomenal improvements in the quality of the output. Really appreciate what both Harrison at LangChain and the team at Sequoia are doing for AI developer community!

[@nachoeigu]

Great interview, good job!

[@mussen1876]

Always great to hear from Harrison. Thanks for a great video.

[@WenRolland]

Love the idea of cognitive architecture. Very interesting, thanks. Very helpful to plan.

[@levelupai]

Thanks for a great discussion!

[@fintech1378]

awesome, the UI/UX described here is definitely the future of agents, there will be humans in the loop but its more for 'assistant' instead of co-pilot, this will help in the five nines

[@ozgurgulerx]

It would be great to dive deeper into the "cognitive architectures" Harrison is referring to "Planning step and reflection Loop or like tree of thoughts or something like this"...

[@humanish_ai]

37:33 very interesting

[@rajs3181]

My view is the concepts of Agents, Tools etc will be part of a enhanced RPA process and can be incorporated as another capability within a RPA tool. I dont see why this has to be a standalone concept and needs a seperate set of tools and techniques. Definitely LLM is transformative but not concepts like Agents and Tools.

[@arsalonamini]

nice

[@JoaquinTorroba]

👏

[@todd-alex]

OpenAI does not recognize any of all of the work we put into OpenAI Labs from 2015 leading up to University and beyond.