How Lyft Built a Self-Serve AI Agent Platform with LangGraph and LangSmith
Lyft implemented a multi-agent system using LangGraph and LangSmith, enabling non-technical users to develop customer support agents through prompts and configuration, reducing reliance on MLEs. The platform uses LangGraph to route requests across specialized subagents, with safety checks, state management, and handoffs integrated into the flow, and emphasizes evaluation, monitoring, and prompt discipline. Agent development time has decreased from 6 months to 2 weeks, and coverage has expanded to multiple issue types, with quality metrics like hallucination and contradiction rates improving by 20%. The system supports self-serve configurable agents and a prompt validation pipeline, enhancing operational efficiency and AI resolution rates.
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