My ship gate came back 0 for 14, three passes, zero variance. The thresholds existed only as text inside a prompt, and the LLM reading them could not do arithmetic.
Grid search across 16 RAG configurations reveals embedding model selection drives 26% more retrieval quality than chunk tuning.
My first LLM judge had a 0% failure rate. That meant it was useless. This is the story of calibrating it to actually catch failures, and building a correction loop that took synthetic data failures from 36 to zero.