This webinar sets the scene by outlining the real challenges manufacturers face because of messy data. When data lacks structure and context, it becomes difficult to understand process risks like bottlenecks, quality issues, and lost time.

We then walk through practical methods for bringing this data together and adding meaning using knowledge graphs and large language models (LLMs). Rather than relying on manual data modelling, we’ll show how LLMs can be used to accelerate the creation of knowledge graphs by extracting structure and relationships from existing data. From there, we’ll cover different techniques for retrieving information from these graphs, focusing on how to surface the right context for a given question or use case.

Finally, we’ll close with a real-world deployment using our product Anvil, covering the original challenge, the approach taken, and the resulting outcome.

By attending this webinar:
Attendees will learn to focus on mapping relationships and meaning across existing data using knowledge graphs. Attendees will also see how LLMs can be used to build and maintain these knowledge graphs, not just query them.