Our few-shot examples came from the eval set. The 0.94 was fiction.

TL;DR. Our ticket-routing eval scored 0.94 for five weeks. The number was manufactured. We had built a dynamic few-shot selector that retrieved the eight nearest labeled examples for each input, and we built its index out of the same labeled_tickets.jsonl the eval set was sampled from. So for every eval case, the nearest neighbor in that index was the eval case itself, gold label attached, pasted into the prompt directly above the question we were about to ask. The model was not answering. It…