Shawn Wang: belief

Transcript context

…I don't know either. Like I think like there's... I think about it as like a prompt registry and you store them and you A-B test them and you do that. LangSmith, I feel like doesn't quite go there yet. Yeah. It's obviously the next step. Yeah, we'll probably go. And yeah, we'll do more of that because I think that's definitely part of the application of a chain or agent is you start with a default one, then you improve it over time. And like, I think a lot of the main new thing that we're dealing with here is like language models. And the main new way to control language models is prompts. And so like a lot of the chains and agents are powered by this combination of like prompt language model and then some output parser or something doing something with the output. And so like, yeah, we want to make that core thing as good as possible. And so we'll do stuff all around that for sure.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.