Knowledge graphs deliver the real-time context enterprises need to make AI explainable
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…
As AI adoption ramps up, enterprises are realizing knowledge graphs are crucial for turning fragmented data into real-time, usable context for AI agents. Intuit Inc., known for its open-source commitment, has harnessed this technology to build a security data platform. Chad Cloes, a staff software engineer at Intuit, explained that graphs help contextualize data and make it easier to monetize and democratize.
At Intuit, the graph layer provides the contextual information necessary to feed large language models. During the Neo4j GraphTalk event, Cloes discussed how the graph technology at Intuit enables security operations, compliance, and real-time context by connecting siloed security tools and data lakes without relying on complex SQL joins.
By automating relationships, they reduced mean time to remediate (MTTR) from days to seconds. Intuit now utilizes a GraphQL API on top of its graph platform to power Model Context Protocol servers that developers can query using natural language. The choice of database is less important than the discipline of building the graph, Cloes emphasized.
Regardless of the underlying database, the key is to contextualize and leverage the data effectively, whether it's ChatGPT today or Amazon Bedrock tomorrow.
Written by urgent.news from SiliconANGLE's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
