As AI adoption accelerates and language models become commodities, enterprises are discovering that knowledge graphs provide the critical layer for turning scattered data into usable, real-time context for AI agents.
That shift is playing out inside large end-user organizations already running graph technology in production. Intuit Inc., known for its active role in open-source communities, including the Linux Foundation, has built its security data platform around graph technology to solve exactly this problem, according to Chad Cloes (pictured), staff software engineer at Intuit.
“I think graphs already were very relevant from a, ‘How do I make my data valuable? How do I make it useful? How do I monetize and/or democratize that data?'” Cloes said. “We have found at Intuit that the graph layer gives that contextualization — it’s a byproduct. The byproduct of it is you can hand all that context that you’ve built with the graph to your LLM.”
Cloes spoke with theCUBE’s John Furrier at the Neo4j GraphTalk event, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how knowledge graphs power security operations, compliance and real-time context at Intuit. (* Disclosure below.)
Knowledge graphs turn security data silos into real-time context
Intuit’s Security Knowledge and Insights Platform team built its system to connect siloed security tools and data lakes without relying on sprawling SQL joins, replacing manual lookups with automated, queryable relationships, Cloes noted.
“One of the main tenets of what we attempt to do is we attempt to drive down MTTR, which is meantime to remediate,” he said. “When we started, it would take days to do analysis on how things were connected. You have to log into seven different things. You had to have three different people with different credentials. Once you start drawing that data in and connecting it in a way that’s relevant, you again democratize the data such that it takes it from days to seconds.”
That foundation has since become the backbone for Intuit’s AI tooling, with the team building a GraphQL API on top of its graph platform to power Model Context Protocol servers that developers query in natural language. The underlying database choice matters less than the discipline of building it, Cloes noted.
“Frankly, I don’t even care who wins because I’m going to be pulling data into a graph, making it relevant and real for me,” Cloes said. “It’s going to be ChatGPT today. It’s going to be Amazon Bedrock tomorrow. It’s going to be whatever. It doesn’t really matter because I’m going to be able to contextualize and use it in the most important way.”
Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the Neo4j GraphTalk event:
(* Disclosure: TheCUBE is a paid media partner for the Neo4j GraphTalk event. Neither Neo4j, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)