Alnylam Transforms Product Complaint Management with Generative AI Using Amazon Bedrock

Alnylam Pharmaceuticals was taking 3-4 days to process drug product quality complaints across time zones, languages, and reporting channels, with manual work to categorize and investigate hundreds of complaints for regulators like the FDA, plus employees spending significant time searching internal documents. Alnylam built two generative AI solutions on Amazon Bedrock: a product-complaint intake/triage system using Anthropic's Claude with Amazon S3 and retrieval-augmented generation, and "AskALNY," a Slack-integrated chatbot used by 2,000+ employees and 1,000+ contractors to retrieve information and summarize documents. Complaint triage time dropped from 3-4 days to hours (near real-time), and information-search time dropped from 15 minutes to 30 seconds. The effort also surfaced 250+ potential AI use cases company-wide, with nine more projects planned.

AWS is Amazon's cloud platform, used across pharma for genomics compute, SageMaker/Bedrock model training, and healthcare-and-life-sciences-specific services like Amazon HealthOmics.

This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.