AI Business

Knowledge Graphs Emerge as Critical Infrastructure for Enterprise AI Agents

Enterprise AI agents require more than raw data to function effectively—they need business context and governance frameworks. Knowledge graphs are positioning themselves as a central layer to provide consistency, explainability and safety across autonomous AI deployments.

·4 min read
Three insights you might have missed from theCUBE’s coverage of GraphSummit 2026
Three insights you might have missed from theCUBE’s coverage of GraphSummit 2026

Effective AI agents in enterprise settings depend on access to business context alongside data. Knowledge graphs offer a way to consolidate the contextual information that currently gets distributed across multiple AI agents into a unified knowledge layer.

Today, developers manually inject business context into AI agents through prompts. This approach forces teams to recreate that context work each time they deploy a new agent, rather than leveraging a shared foundation. According to Jesús Barrasa, field chief technology officer of gen AI at Neo4j Inc., "This knowledge layer, this idea of capturing your enterprise knowledge and using it as the context engine for your agents, not only gives you the consistency … it gives you the explainability," he said during an exclusive broadcast on theCUBE, SiliconANGLE Media's livestreaming studio. "That's the source of my data. These are the elements that I use to produce the answer."

At GraphSummit, theCUBE Research's John Furrier conducted interviews with industry leaders from Collibra BV, Blitzy Inc., Raymond James Financial Inc., and Qiagen N.V., among others. These conversations explored how knowledge graphs can anchor AI agents in shared, auditable enterprise knowledge to enhance explainability, enable secure coding at scale, accelerate drug discovery and reshape how organizations operate.

https://www.youtube.com/embed/CJlkmav-r5k?feature=oembed

Runtime Governance Keeps Autonomous Agents Accountable

Governance presents a critical challenge as AI agents gain autonomy in enterprise environments. Decisions that previously required human judgment must now be made by agents within seconds, necessitating a transition to runtime governance approaches, according to Felix Van de Maele, chief executive officer and co-founder of Collibra BV.

Collibra has rolled out multiple capabilities—Live Map, Maestro, Guardian Agents and Agent Contracts—all built atop Neo4j's graph database infrastructure. These components work together as a control mechanism to ensure AI agents access appropriate information and adhere to organizational policies.

"The challenge is: how do you govern at the speed of AI, which is different than the way we had to govern five years ago?" Van de Maele told theCUBE. "Maestro gives our customers the ability to build these governance steward agents that automate up to 80% of the governance work. You're able to govern quickly and efficiently enough to keep up with the demands of new AI workloads."

https://www.youtube.com/embed/FdtCk9IbVxQ?feature=oembed

Tools like Agent Contracts take a different approach by establishing guardrails around what agents can do. These systems track agent actions and prevent those that breach established rules, mitigating the risk of unauthorized operations.

Knowledge Graphs Enable Safe, Accurate AI-Driven Code Changes

Minor modifications to software can trigger unexpected failures elsewhere in a system. For Blitzy Inc., which operates thousands of AI coding agents simultaneously to facilitate large-scale infrastructure modifications, knowledge graphs provide a way to visualize system dependencies and assess change-related risks.

A knowledge graph supplies agents with the contextual information needed to execute changes safely without being buried under millions of lines of code, according to Neeraj Deshmukh, director of engineering at Blitzy. The organization complements this with human-reviewed action plans and automated testing protocols to maintain quality throughout the coding workflow.

https://www.youtube.com/embed/j8P2nLXLldI?feature=oembed

"On top of that, we have agents who are watching other agents to make sure that they abide by the spec, the plan that we had created and approved by the human in the loop," Deshmukh told theCUBE. "That ensures that there is no drift or hallucination."

Financial Services Firms Use Knowledge Graphs to Validate AI Reliability

Knowledge graphs allow Raymond James Financial Inc. to deploy AI agents against data originating from trusted, established sources. According to Naveen Mahankali, vice president of technology at Raymond James, "We have golden sources; we have systems that we can rely on today, and we're able to use agents to build and compare what we are building against the golden sources. With the knowledge graph, even when we pull the data from different sources, it sits in the Neo4j, and we run evals compared to the golden sources and make sure they're 100% accurate before launching."

Raymond James is also investigating how AI agents can enhance the efficiency of financial advisors serving clients. The firm has already deployed Raimond, its proprietary AI assistant, as explained by Jeff Griffith, vice president of AI engineering and data science at Raymond James, who participated alongside Mahankali.

https://www.youtube.com/embed/8OgyswtEyho?feature=oembed

https://www.youtube.com/embed/videoseries?list=PLHBeVIUN0Be0

"We have an AI assistant … it's gotten huge adoption, and it's just going to get smarter," Griffith said. "That's part of the core evolution of what we're doing in terms of engineering. We're changing how people — how everyone — works with a desktop that gives people the best AI tools to move from doing all the menial tasks to managing agents that are doing those tasks. In terms of skills and what we are looking for, it is shifting just from people who can do tasks to people who have a drive to solve a meaningful problem."