RELEASE · COMPANIES · #3687
Novo Nordisk builds GraphRAG manufacturing assistant using Amazon Bedrock AgentCore
Novo Nordisk’s Manufacturing Technology team built an AI process-intelligence assistant on AWS that combines a knowledge graph in Amazon Neptune with hybrid semantic/exact-match search in Amazon OpenSearch Serverless and an agent reasoning layer running on Amazon Bedrock AgentCore. The GraphRAG system is designed to deliver grounded, cited answers about controlled manufacturing documents and relationships, improving visibility and helping subject-matter experts complete tasks that previously took hours or days in minutes.
KEY POINTS
- Novo Nordisk’s Manufacturing Technology team built an AI process-intelligence assistant on AWS that combines a knowledge graph in Amazon Neptune with hybrid semantic/exact-match search in Amazon OpenSearch Serverless and an agent reasoning layer running on Amazon Bedrock AgentCore.
- The GraphRAG system is designed to deliver grounded, cited answers about controlled manufacturing documents and relationships, improving visibility and helping subject-matter experts complete tasks that previously took hours or days in minutes.
- Demonstrates a production application of agentic AI and GraphRAG in a highly regulated pharmaceutical environment to improve traceability, reduce lead times, and reduce reliance on tribal knowledge.
WHY IT MATTERS
Demonstrates a production application of agentic AI and GraphRAG in a highly regulated pharmaceutical environment to improve traceability, reduce lead times, and reduce reliance on tribal knowledge.
SOURCES & TIMELINE
1Novo Nordisk (Novo) is one of the world’s leading global pharmaceutical companies, manufacturing medicines for chronic diseases such as diabetes and obesity, and delivering them to patients across many countries. Behind every product lies a manufacturing network that adheres to strict quality requirements. Every quality-relevant process step must be described, controlled, and validated through formal documentation. K…
This post was co-written with Ashwin Srinivasan, Nishan Das and Karthik Baile from MoEngage. A marketing or product team member planning a weekend flash sale often opens three tools before writing a single line of copy. First they open the analytics dashboard to see what worked last time, then the content library to find the right tone, and then the campaign builder to build the campaign itself. Repeat that across e…