How Rippling built production AI in 6 months with Deep Agents and LangSmith
Rippling transformed its AI layer into a fully agent-based system using Deep Agents and LangSmith, enabling complex cross-domain reasoning. The architecture leveraged LangChain's composable agents and a shared observability layer, with a supervisor agent coordinating multiple specialized subagents. The system managed a massive ontology with overlapping domains, using dynamic skill injection and re-rankers to reduce context size and improve efficiency. LangSmith supported production debugging and evaluation, enabling collaboration and continuous quality assurance through a self-healing loop and trace store. The system, now in production with millions of users, was built in six months, integrating Deep Agents from the start and ensuring LLM-friendly reasoning and code execution.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents