
How a chemical engineer built an agentic manufacturing troubleshooting assistant
Notes de l’épisode
In this episode, I sit down with Scott Duncan, a chemical engineer who built an agentic manufacturing troubleshooting assistant – without any coding background. We dive into the real-world challenges of process manufacturing and how AI is transforming the way plant issues are solved. Scott shares his journey from hands-on troubleshooting to leveraging large language models, knowledge graphs, and real-time data for smarter, faster problem-solving. We also debate the future of domain expertise in an AI-driven world and what it means for education and workforce development. Join me as we explore the potential – and the limitations – of AI in reshaping the future of industrial operations.
NXAI Claude Codehttps://www.anthropic.com/news/claude-3-opus-sonnet-haiku
MATLABhttps://www.mathworks.com/products/matlab.html
OPC Foundation OPC UAhttps://opcfoundation.org/about/opc-technologies/opc-ua/
PI Systemhttps://www.aveva.com/en/products/pi-system/
RAG (Retrieval-Augmented Generation)https://en.wikipedia.org/wiki/Retrieval-augmented_generation
Knowledge Graph MCP Server