The Future of Inference Market & Model Routing: Commodity or Increasing in Value? | LangChain CEO
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.
- LangChain shut down its commercial memory offering after discovering generalized context tools fail across different production workloads. Read →
- LangChain treats feature deletion as a core operating rule, discarding tools like custom JSON parsers the moment frontier models ship native function calling. Read →
- LangChain's internal spend on coding tools surged to nearly 30% of engineering salaries before management intervened to control runaway token consumption. Read →