Defining success per workflow before costing anything is the step that makes this usable, since a RAG grounded-answer bar and a coding-agent passing-tests bar produce completely different denominators. Retry and fallback rate belong in the numerator exactly as you have them, because a silent fallback is where the bill grows without anyone noticing. Are you attributing human-review cost back to the specific model that triggered the review, or averaging it across the workflow?