How to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit

Voice agents feel broken when measured on the wrong latency metrics. This gives concrete targets (about 1.5 s total, 500 to 600 ms to feel human) and a way to benchmark your own stack with simulated callers.

• benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.

• videoHow to Write Your First AI Eval - SallyAnn DeLucia, Arize AI
• videoBuild Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind
• videoHow to Build an AI Code Review Agent - Daksh Gupta, Greptile
• videoCan Your AI Analyst Keep a Secret? - Aaron Linsky, Bridgewater & Nikhil Benesch, turbopuffer

• videoLatency Is a Budget. Humanlike Is the Goal. — Jesse Hall, LiveKitAI Engineer
• videoRealtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAIAI Engineer
• articleBuilding production voice agents: latency, WebRTC and turn detectionAndrew Ng

Checking sign-in…

Loading comments…