Harrison Chase Explains Why General Agent Memory Fails
Harrison Chase explains why LangChain shuttered its commercial agent memory tool and why continual learning belongs in an outer loop.
10+ hours of podcasts, in 5 minutes.
LangChain co-founder and CEO Harrison Chase joins Harry Stebbings to unpack the engineering challenges of building reliable AI agents and managing enterprise agent infrastructure. Chase discusses why model routing belongs in the agent harness rather than API gateways, the unsolved architecture of agent memory, and how LangChain managed to cut its internal coding agent expenses despite skyrocketing token consumption.
Harrison Chase explains why LangChain shuttered its commercial agent memory tool and why continual learning belongs in an outer loop.
LangChain CEO Harrison Chase explains why surviving AI developer tools requires deleting features every six months as foundation models improve.
LangChain spent 30% of engineering payroll on coding tools until Harrison Chase built a 3-step playbook to stop runaway agent bills.
10+ hours of podcasts, distilled into one 5-minute read. Free, every Sunday.
For now, every subscriber gets both newsletters. No spam. Unsubscribe with one click.