Knowledge graphs give AI real-time context, Intuit engineer says
Intuit engineer Chad Cloes says knowledge graphs give AI real-time context, cutting security analysis from days to seconds.
Cloes, who spoke with theCUBE’s John Furrier during an exclusive broadcast, described how Intuit built its Security Knowledge and Insights Platform around graph technology. The system connects siloed security tools and data lakes without relying on sprawling SQL joins, replacing manual lookups with automated, queryable relationships. According to Cloes, one of the main goals is to drive down meantime to remediate, or MTTR. "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," he said. "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."
The graph layer has since become the backbone for Intuit’s AI tooling. The team built a GraphQL API on top of the graph platform to power Model Context Protocol servers that developers query in natural language. According to Cloes, contextualization is a byproduct of the graph. "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," he said. This approach allows the large language model to work with accurate, up-to-date context rather than static or isolated data.
Cloes also downplayed the importance of which AI model or vendor wins, noting that the value lies in the contextual layer. "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," he 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." This vendor-neutral stance highlights how knowledge graphs can future-proof AI investments.
The comments come as enterprises increasingly look to make AI explainable and trustworthy. Knowledge graphs, which organize data into interconnected entities and relationships, are emerging as a practical way to provide the real-time context that AI agents need to produce accurate, defensible results. At Intuit, the security platform has been running in production, demonstrating that graph technology is no longer experimental. Intuit is known for its active role in open-source communities including the Linux Foundation, and its engineers have integrated graph technology deeply into security operations, compliance workflows and real-time data access.
The interview took place at the Neo4j GraphTalk event, where Cloes discussed how knowledge graphs power security operations, compliance and real-time context at Intuit. According to SiliconANGLE, theCUBE, SiliconANGLE Media’s livestreaming studio, covered the event as a paid media partner. The sponsor of the event coverage did not have editorial control over the content on theCUBE or SiliconANGLE.