Case Study: a U.S. healthcare provider cuts QA costs by 70% with StackAI

How a US healthcare provider automated phone calls QA with AI

A US healthcare provider faced the challenge of a slow and costly manual process for quality assessment (QA) of its call center phone calls. They partnered with Stack.ai to automate this process using a no-code, HIPAA-compliant AI assistant built with speech-to-text technology and large language models (LLMs).

The solution from Stack.ai utilized the Deepgram Nova 2 Medical model for transcription and Anthropic’s Claude 3.5 Sonnet to evaluate calls against specific QA criteria. This implementation resulted in a 70% reduction in QA costs, a 10% improvement in customer satisfaction, and an 80% reduction in AI build costs for the healthcare provider.