<p>Voice agents are moving from “cool demo” to real product infrastructure.</p><p><br></p><p>In this livestream, we’re joined by Ben Cherry of LiveKit to break down what it actually takes to build real-time AI agents that can listen, respond, interrupt, call tools, and work in production.</p><p><br></p><p>LiveKit is an open source framework and developer platform for building voice, video, and physical AI agents in production.</p><p><br></p><p>We’ll talk through the stack behind real-time AI experiences, then build and test a live demo together on The Neuron.</p><p><br></p><p>In this live demo, we’ll cover:</p><p><br></p><p>🎙️ How LiveKit helps developers build voice, video, and physical AI agents</p><p>⚡ What makes real-time agents different from normal chatbots</p><p>🧠 How voice agents handle latency, interruptions, speech, and tool calls</p><p>🛠️ Why production-ready AI agents are much harder than a weekend demo</p><p>🚀 What builders should know before shipping voice AI to real users</p><p><br></p><p>And yes, we’re doing a live demo, which means there is at least a small chance the agent talks back at exactly the wrong time. Perfect television.</p><p><br></p><p>Guest: Ben Cherry, LiveKit</p><p>LiveKit: https://livekit.com/</p><p>Ben on LinkedIn: https://www.linkedin.com/in/bcherry-product-engineer</p><p>Ben on GitHub: https://github.com/bcherry</p><p><br></p><p>Subscribe to The Neuron for clear, useful AI news, demos, and explainers for people trying to understand where this tech is actually going.</p><p><br></p><p>https://www.theneuron.ai/</p>