How One Team Built Automated LLM Evaluation That Catches 92% of Hallucinations

A development team discovered critical gaps in their AI quality process after deploying a RAG-based customer support assistant that served hallucinated responses to over 500 users before detection. The failures included fabricated billing policies and rate-limit figures pulled from a competitor's documentation, exposing the team's reliance on informal, manual testing. In response, they built a production-grade evaluation pipeline integrating a suite of automated judges covering faithfulness, instruction-following, JSON schema validation, and domain accuracy. The system is designed to run within CI/CD workflows, blocking code merges that degrade response quality and enabling rapid regression detection. The team published their architecture and code patterns to help other engineers move from subjective review toward measurable, automated LLM quality assurance.