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.
First seen by Oriel on .
AI summary
Novo Nordisk built an agentic GraphRAG assistant on AWS that helps manufacturing experts find and update governed process documentation with scoped, cited answers in minutes.
- Amazon Neptune models process hierarchies, sites, products, equipment, and document relationships, while Amazon OpenSearch Serverless provides hybrid semantic and lexical retrieval.
- Amazon Bedrock AgentCore coordinates Strands Agents SDK runtimes powered by Anthropic Claude models, with ingestion orchestrated through AWS Step Functions, AWS Lambda, and Amazon Bedrock Data Automation.
- Guided mode clarifies site, product generation, equipment, or other scope using graph-grounded options before retrieval, reducing ambiguous or out-of-scope answers.
- The system prioritizes approved, effective, latest applicable documents, tracks indexed content explicitly, cites sources, preserves requirement strength, and flags missing material for review.
- Across a vault of roughly four million documents, SMEs reduced work that previously took hours or days to minutes, including searching, updating, and adapting documents.
#graphrag #amazon bedrock #knowledge graphs #pharmaceutical manufacturing
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 9189364d4fda8ced7c7c27d0b70ec7adb9ac5ce3 | https://aws.amazon.com/blogs/machine-learning/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore/ Read discussion |