by killaJ on 9/21/23, 4:23 PM
Been messing with LangSmith playground recently. Pains me to say but it’s actually been a pretty good experience so far.
by finnlobsien1 on 9/21/23, 4:31 PM
super interesting how it makes "decisions", but nice that they let you tie user feedback directly into LLM refinement, otherwise would be hard to make that info useful
by fwesss on 9/21/23, 4:23 PM
I'm curious about LangSmith's 'dynamic datasets'. How does it ensure data integrity, especially when rapidly iterating on AI models?
by dazzeloid on 9/21/23, 4:12 PM
Love the concept of prompt velocity. Although it doesn't capture the initial quality of the prompt or whether the changes are effective.
by casstang on 9/21/23, 4:23 PM
What’s LangSmith's revenue model?