By all accounts, ClassPass should have been drowning. As the global fitness platform scaled to 2,500 cities across five continents, the volume of customer support tickets exploded. Members were booking, canceling, disputing, and rescheduling classes around the clock.
Instead of imploding, ClassPass implemented a solution that is rare for a consumer-facing company. Unlike many firms aiming for full automation, ClassPass has not replaced all human support agents with AI. While the chatbot efficiently filters customer conversations, a little less than half still require escalation to human agents—who remain a vital part of the support experience. This isn’t a limited pilot or a narrow use case, but rather a scaled hybrid model where AI plays a significant role in first-line support. Roughly 2.5 million customer conversations later, satisfaction scores have remained steady and ClassPass now operates a chat-first, 24/7 support system with improved efficiency.
Decagon, a YC-backed startup, made a compelling case with its approach. What set Decagon apart from traditional AI support tools was its focus on Agent Operating Procedures (AOPs). Unlike many chatbot platforms that rely on rigid decision trees or complex, opaque large language models (LLMs), Decagon’s system was built on clear, programmable workflows. These workflows allowed companies like ClassPass to refine and control their support automation process over time, ensuring a solution tailored to their specific needs.
