customer_support · healthcare · workflow
Amazon Pharmacy builds HIPAA-compliant LLM chatbot for customer care agents using Amazon SageMaker
Customer care agents at Amazon Pharmacy struggled to quickly find precise pharmacy information due to the diversity, volume, and complexity of healthcare processes, slowing down patient service.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Patient contacts via chat
A patient contacts Amazon Pharmacy customer care via chat.
Tools used
Amazon SageMakerAmazon SageMaker JumpStartAWS FargateAmazon S3FAISSAmazon OpenSearch ServiceAmazon ECSAWS CloudFormation
Outcome
Amazon Pharmacy deployed a HIPAA-compliant RAG-based chatbot enabling agents to assist patients more quickly with precise answers, while SageMaker JumpStart cut months of model development work.
Results
Time savedcut months of work
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
agent assistchatbotknowledge searchragknowledge basehuman review describednamed customerproduction runtime claimedsource backedtools describedworkflow describedhealthcareemployee productivitytime savedtechnical build writeupcall center aicustomer supportai draft human approvalrag answering