Continuous Delivery 2.0

Sep 1, 2025 · Artificial Intelligence

How Spotify Uses Multi‑Model Voting to Give GenAI a Trustworthy Confidence Score

Spotify’s finance engineering team tackled the challenge of reliable GenAI outputs for invoice parsing by testing three confidence‑scoring methods, discarding two, and refining a multi‑model voting approach with weighted votes, calibration, and practical implementation details for high‑risk, SOX‑compliant scenarios.