LangChain outlines Rippling AI architecture built on Deep Agents and LangSmith

Rippling AI's architecture is built on Deep Agents and LangSmith, according to LangChain. The setup utilizes a supervisor agent coordinating 5 to 7 specialized subagents.

LangSmith handles tracing, evaluations, and production monitoring for the system, as detailed in LangChain's [case study](https://www.langchain.com/blog/how-rippling-went-ai-native-across-every-product-in-6-months-with-deep-agents-and-langsmith) on Rippling.