Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore
Novo Nordisk's Manufacturing Technology team within the Tablet area team built a process-intelligence assistant on Amazon Bedrock AgentCore, using a GraphRAG architecture that pairs a knowledge graph in Amazon Neptune with hybrid search in Amazon OpenSearch Serverless to turn millions of controlled manufacturing documents into grounded, cited answers.
Novo Nordisk, a leading global pharmaceutical company, manufactures medicines for chronic diseases like diabetes and obesity and ships them to patients worldwide. Their manufacturing network must follow strict quality requirements, with every relevant process step documented, controlled, and validated. The Manufacturing Technology team at Novo Nordisk, responsible for tablet area processes, faces significant challenges in managing a large portfolio of controlled documents across multiple divisions and product programs.
These challenges include frequent document updates, complex approval workflows, and difficulty tracking document status. To address these issues, the team developed an intelligent support system using agentic AI on AWS. This system aims to reduce lead times, enhance documentation visibility, and make crucial manufacturing knowledge more accessible.
The solution employs a GraphRAG architecture, integrating a knowledge graph on Amazon Neptune with a hybrid search index on Amazon OpenSearch Serverless. A reasoning layer powered by Amazon Bedrock AgentCore handles the retrieval and response process, ensuring answers are grounded in approved sources and clarify when relevant content is unavailable.
This architecture enables subject-matter experts to complete tasks that previously took hours or days within minutes, significantly improving decision-making speed and patient care.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.