Build voice agents with visibility into every interaction ✨ Learn how Caroline di Vittorio from LangChain uses the Google ADK, the Gemini Live model, and LangSmith to trace voice agent behavior, inspect tool calls, review interruption events, analyze token costs, and more.

@LangChain Gemini Live API docs:

@LangChain Google ADK docs:

@LangChain LangSmith docs:

@carodivittorio @LangChain Using LangSmith to trace Gemini Live interactions is a massive step forward for debugging real-time audio!🤩

@carodivittorio @LangChain Tracing voice agent behavior is crucial for refining interactions. My agents often reveal unexpected tool use patterns.

@carodivittorio @LangChain Yes, that visibility makes debugging so much easier!

@carodivittorio @LangChain 语音 Agent 最怕的就是中断黑盒

@carodivittorio @LangChain Thank for sharing

@carodivittorio @LangChain Tracing tool calls and interruption events makes voice-agent debugging much more concrete. Visibility is what turns a demo into an engineering workflow.

@carodivittorio @LangChain Tracing tool calls and interruptions is the part builders actually need

@carodivittorio @LangChain こんな技術の進化、実感するよね💡