Why does no one measure prompt velocity

by thepaulthomson on 9/21/2023, 4:09:22 PM with 11 comments

  • by killaJ on 9/21/2023, 4:23:16 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 9/21/2023, 4:31:22 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 9/21/2023, 4:23:57 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 9/21/2023, 4:12:08 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 9/21/2023, 4:23:06 PM

    What’s LangSmith's revenue model?