Finally got around to setting up prompts, evals, and datasets in Arize Phoenix today with a small sample of 24 Jev calls. More disagreement than I was expecting! I am planning to expand this and get some labeled data for a small classification model with multiple heads. Will update with that later!
I'm going with Sol 6.1 for the automatic daily eval for now. Will do more spot checks later.
Top comments (0)