Pratim Bhosale

Localized reading

오늘 @typesafeai Jev와 함께 놀면서 주로 도구 호출에 대해 무엇을 하는지 이해했습니다. LLM이 무엇을 해야할지 결정하는 대신 그 부분을 Jev로 대체했습니다. 제가 배운 것은 우리가 만들 수 있다는 것입니다 ...

Original post / EN

Played around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the end user. TLDR is to understand more about how voice agents can run decisions on partials instead of waiting for the end of the turn, with lower costs.