Thanks for writing this up, @DouglasGarcia. The split you draw, "AI is best for text and profiles; use standard SQL for numbers and dates," was interesting enough that I ran an experiment on it.I built customer, order and ticket tables with Databrick...
Hey @SumeshKashyap Thanks for writing this up, and for the question at the end. I found it interesting enough that I ran an experiment on it.I set up bike, walk or wait inputs like the ones your agent gets back from its tools (16 scenarios over six H...
@ShenXu : I found this really interesting so did a bit of experimentation. My lab notes and a test notebook are available at https://medium.com/lab-notes/unity-catalog-functions-kept-ai-agents-from-acting-on-stale-memory-7d63e15f992b
Hey @Andrewww , I know your post was from a few months ago. But as I was testing out a use case, I came across your question and put together an experiment. Would love to hear where you ended up with your Genie agents.Experiment writeup is at https:/...
Hey @Khasim_1, this was an interesting one and I wanted to experiment a bit. I put this together if it helps - https://medium.com/lab-notes/three-lakeflow-quarantine-designs-tested-and-the-one-condition-every-queue-needs-1bea1c1588ff
