McKinsey Deploys Knowledge Graphs to Give Enterprise AI Systems Business Context

Knowledge graphs function as a bridge between raw enterprise data and the contextual understanding that AI systems require to support decision-making. By mapping relationships between data points, these structures enable AI applications to grasp not just isolated facts but the business logic that connects them.

Most people encounter knowledge graphs regularly without recognizing them, according to James Kaplan, a distinguished partner at McKinsey & Company. "If you're using LinkedIn, if you're using Wikipedia, if you're using any social media, that's a graph," he said. "Many of the social media companies have arrived at this and the power of this technology before the enterprise did. It's much more intuitive than a relational database. We're all used to massive relational databases, which are wonderful if you're processing transactional data, and are much less good at ambiguous or complicated data. It's incredibly insightful to describe a customer or a product or a process or a step in the process in the context of its relationship to other things."

Kaplan shared these insights during an exclusive interview with theCUBE Research's John Furrier as part of the theCUBE + NYSE Wired: AI Luminaries interview series, broadcast on theCUBE, SiliconANGLE Media's livestreaming platform.

Structuring Messy Data Through Knowledge Graphs

AI can transform unstructured information into organized data and business rules suitable for storage within a knowledge graph, Kaplan explained. Historically, this transformation demanded substantial time, expense and manual effort from business analysts or data scientists, often with imperfect results.

"Now, for the first time, we have the ability to interrogate complicated processes and create deterministic business rules programmatically," he said. "We have the capability to interrogate messy, uncorrelated, unstructured data and turn it into structured data, often storing it in a graph. That opens up whole new frontiers."

Organizations should align their use of AI and knowledge graphs with strategic business priorities, Kaplan noted. Different departments may benefit from different applications—customer experience improvements might outweigh productivity gains in some cases.

"What if I pointed these AI improvements at customer experience rather than productivity?" he said. "The richer the interconnections among nodes, the more intelligence you have in the graph and the more things you can determine."

McKinsey's Approach: EcliptOS and Semantic Layers

McKinsey has integrated AI and knowledge graphs into EcliptOS, an AI operating system designed to align executive strategy with operational execution through agentic workflows. The platform incorporates a semantic data layer that structures data and its interconnections to support generative AI applications.

https://www.youtube.com/embed/E6_3KlZwc8M?feature=oembed

"What we in effect created was a graph of databases," Kaplan said. "One of the nice things about graphs is they have more flexible data schemas. It's easier to create a virtual graph that connects many databases. And that to me is incredibly powerful."