%20Agents%20in%20Production%20-%20Banner.png)
Customer Experience (CX) Agents in Production: Lessons from Lyft, Vodafone, and LATAM Airlines
Lyft, Vodafone, and LATAM Airlines are leveraging AI-powered CX agents to enhance customer support through self-service platforms and structured workflows. Lyft’s AI Assist handles over 270,000 interactions with a 65% deflection rate and 35% AI resolution rate, while Vodafone’s Super TOBi and Super Agent achieve high accuracy and resolution rates in customer and internal support. LATAM’s Concierge agent has a 95% success rate in resolving travel-related queries. Lyft employs continuous testing and iteration, using LangGraph and LangSmith for agent development, with a focus on domain-specific evaluation criteria. Vodafone’s system integrates operational knowledge into a living graph, enabling real-time diagnostics and policy-compliant guidance
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