ElevenLabs runs its own support on ElevenAgents, resolving 22,000 tickets monthly
The interesting detail is the build method: existing SOPs converted into agent steps, rather than prompt engineering from scratch, is a pattern most support teams can replicate with their own documentation. It is a concrete reference for operations and automation leads evaluating voice AI agents, showing measured results on real ticket volume instead of demos. Compare it against hiring seasonal support staff or deploying chatbot vendors like Intercom's Fin.
ElevenLabs uses its own ElevenAgents platform to handle its customer support, resolving over 22,000 tickets per month and cutting response time from hours to 60 seconds. The team converted existing standard operating procedures for refunds, billing changes, and voice clone questions into step-by-step workflows the agent follows. The agent can retrieve customer information, read text, screenshots, and PDFs, reply in the customer's language, take actions, and hand off to human staff when needed. ElevenLabs published a blog post explaining how it built the system.
We run our own customer support on ElevenAgents. It’s resolved over 22,000 tickets a month and cut our response time down from hours to 60 seconds. Our support team already had standard operating procedures for every major kind of ticket, like refunds, billing changes, and voice clone questions. We turned each one into a set of steps the agent follows. The agent can also look up what it needs about a customer, read text, screenshots, and PDFs, reply in the customer's language, take actions, and hand off to our team when a person is needed. Read how we built it: elevenlabs.io/blog/how-we-so… Your browser does not support the video tag. 🔗 View on Twitter 💬 6 🔄 2 ❤️ 30 👀 2164 📊 9 ⚡
