Icite targets knowledge graphs to give AI agents the context needed for autonomous security workflows

Enterprise knowledge graphs are emerging as a key foundation for organizations, giving AI systems the context needed to make better decisions. As cybersecurity teams modernize operations, combining graph data with real-time identity intelligence is helping reduce false positives and enable more autonomous security workflows.

AI agents are only as successful as the data, memory and context they’re given, which means a graph-based knowledge layer is crucial. Rather than pointing agents at raw data, there’s a need for deterministic data they can traverse deliberately with guardrails to avoid hallucinations, according to Wes Mullins (pictured), founder and chief executive officer of Icite Inc.

“That is really the core of what the Icite product does, because of that ability to have the knowledge layer, have our agents traverse it,” Mullins said. “We consume all of our customers’ data, but we normalize it. We massage it in our format that we want, and that’s how our agents are able to do it.”

Mullins spoke with theCUBE’s John Furrier at the Neo4j GraphTalk event, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed the role of enterprise knowledge graphs and graph-based knowledge layers in improving AI agent performance, while using identity intelligence to deliver more accurate cybersecurity detection and investigations. (* Disclosure below.)

Enterprise knowledge graphs and identity data

The more identity data organizations can bring together, the more complete and accurate their knowledge graph becomes. That broader context makes it easier to detect insider threats and spot unusual behavior, Mullins noted.

“You can see the patterns, especially when, if a company has a mature group structure, policies, procedures, who goes in what groups, titles. You build these profiles,” Mullins said. “It’s like you’re a CIA person profiling someone. You can build these profiles for HR versus R&D versus networking. Spotting deviations in that becomes a lot easier the more you have to build that baseline.”

Icite also uses the knowledge graph to power its AI-assisted investigation workflows, where agents surface connections across identity data automatically rather than waiting for a human analyst to notice them. That automation is what allows the team to move from reactive to proactive security operations, Mullins noted.

“We can start autonomously going out and doing work for the security team,” Mullins said. “That’s really the goal. Let the agents handle the routine traversal so your analysts can focus on the decisions that actually require human judgment.”

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.)

Photo: SiliconANGLE