UPDATED 15:46 EST / NOVEMBER 16 2026.
In a recent development, AI agents need more than enterprise data to be effective; they also need the business context that data lives in. Knowledge graphs could consolidate the enterprise context currently fed to different AI agents into a single knowledge layer.
According to recent reports, developers are already providing AI agents with business context through prompts. But without a central source of truth, they must repeat that work every time they build a latest agent, rather than drawing on a shared knowledge layer, according to Jesús Barrasa (pictured), 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 stated 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.”.
During interviews at GraphSummit, theCUBE Research’s John Furrier spoke with industry experts from Collibra BV, Blitzy Inc., Raymond James Financial Inc., and Qiagen N.V., among others. They discussed how knowledge graphs can ground AI agents in shared, traceable enterprise knowledge to improve explainability, enable safer coding at scale, support drug discovery and transform business operations. (* Disclosure below.).
Here’s theCUBE’s complete video interview with Jesús Barrasa:.
Governance is a key question for enterprise AI deployments. How do you ensure AI agents behave appropriately as they become more autonomous? Judgment calls that used to be made by people now need to be made by agents in seconds, requiring a shift toward runtime governance, according to Felix Van de Maele, chief executive officer and co-founder of Collibra BV.
Recent findings suggest that collibra has introduced several capabilities – Live Map, Maestro, Guardian Agents and Agent Contracts – built on Neo4j’s graph database. Together, they form a control system that helps businesses make sure their AI agents use the right information and follow the rules.
In a recent development, “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.”.
In a recent development, other solutions, such as Agent Contracts, focus on enforcing boundaries around AI agents’ behavior. They monitor agents’ actions and block those that violate predefined rules, helping prevent unauthorized actions, according to Van de Maele.
Here’s theCUBE’s complete video interview with Felix Van de Maele:.
Changing one small piece of software can unexpectedly break something somewhere else. For Blitzy Inc., which runs thousands of AI coding agents at once to help businesses make large-scale system changes, a knowledge graph can map dependencies and the risks of change within a system.
According to recent reports, A knowledge graph gives agents the context they need to make changes safely without being overwhelmed by millions of lines of code, according to Neeraj Deshmukh, director of engineering at Blitzy. The manufacturer also uses human-approved action plans and automated testing to keep the coding process on track.
“On top of that, we have agents who are watching other agents to make sure that they abide by the spec, the blueprint that we had created and approved by the human in the loop,” Deshmukh told theCUBE. “That ensures that there is no drift or hallucination.”.
Here’s theCUBE’s complete video interview with Neeraj Deshmukh:.
A knowledge graph helps Raymond James Financial Inc. put AI agents to work on data from established sources, according to Naveen Mahankali, vice president of technology at Raymond James.
It has been revealed that 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,” he told theCUBE. “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 exploring how AI agents can help financial advisors serve clients more efficiently. The firm has already rolled out Raimond, its proprietary AI assistant, explained Jeff Griffith, vice president of AI engineering and data science at Raymond James, who joined Mahankali during the interview.
Sources indicate that “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.”.
Here’s theCUBE’s complete video interview with Jeff Griffith and Naveen Mahankali:.
Catch up on theCUBE’s complete video coverage of GraphSummit:.
(* Disclosure: TheCUBE is a paid media partner for GraphSummit. Sponsors of theCUBE’s event coverage do not have editorial control over content on theCUBE or SiliconANGLE.).
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
Exclusive: Envoy targets defense contractors and semiconductor fabs with Visitors Critical.
Spara's Scout AI assistant acts on sales opportunities before reps know to look.
Semperis updates Lightning identity security platform to defend against AI agent attacks.
Exclusive: Cogent Security's DefenseOS adds policies and automations for AI agents.
SiMa.ai's Palette 3.0 runs many AI models on one chip and lifts throughput up to 3.5 times.
Three insights you might have missed from theCUBE’s coverage of Dell’s “AI Leadership Symposium”.
Exclusive: Envoy targets defense contractors and semiconductor fabs with Visitors Critical.
SECURITY - BY DUNCAN RILEY . 1 HOUR AGO.
Spara's Scout AI assistant acts on sales opportunities before reps know to look.
In a recent development, APPS - BY DUNCAN RILEY . 1 HOUR AGO.
Semperis updates Lightning identity security platform to defend against AI agent attacks.
Recent findings suggest that SECURITY - BY DUNCAN RILEY . 1 HOUR AGO.
Exclusive: Cogent Security's DefenseOS adds policies and automations for AI agents.
Industry observers note that SECURITY - BY DUNCAN RILEY . 1 HOUR AGO.
SiMa.ai's Palette 3.0 runs many AI models on one chip and lifts throughput up to 3.5 times.
It has been revealed that INFRA - BY DUNCAN RILEY . 1 HOUR AGO.
Three insights you might have missed from theCUBE’s coverage of Dell’s “AI Leadership Symposium”.
AI - BY VICTORIA GAYTON . 1 HOUR AGO.