people · May 17, 2026
LangChain Launches SmithDB and LangSmith Engine at Interrupt 2026
Share the canonical public link.
LangChain shipped SmithDB and LangSmith Engine at Interrupt 2026 on May 13-14 in San Francisco. SmithDB serves as the dedicated data layer for agent observability while LangSmith Engine automatically detects production failures, diagnoses root causes against live codebases, and proposes fixes. The releases closed the full ADLC loop for agents with managed deployment and UI. Harrison Chase, Co-Founder and CEO of LangChain, announced LangChain Labs as an applied research effort into continual learning for agents using signals from Agent Traces, Environments, and Production Systems.
Below validation threshold — auto-passed without scoring