Ground Agent AI Knowledge Graphs at Raymond James

Knowledge graphs are becoming a critical layer of context and reasoning for agent AI, helping companies connect data and ground agents in key areas of business expertise.

For diversified financial services companies like Raymond James Financial Inc., graph technologies have become an important part of developing a trustworthy infrastructure to support AI. According to Jeff Griffith (pictured left), vice president of AI engineering and data science at Raymond James, the technology has been particularly helpful in developing unique solutions.

“Using something like a data graph allows us to harness the power of AI in a dynamic way,” Griffith said. “People already know how to get the things they get every day. But if you want to transcend those realms or do something unique, that’s a huge value.”

Griffith spoke with John Furrier, Executive Analyst at theCUBE Research, at the recent GraphSummit event during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. He was joined by Naveen Mahankali (right), vice president of technology at Raymond James, and they discussed how knowledge graphs and AI are changing the business landscape. (*Disclosure below.)

Knowledge graphs for data reliability

As a Neo4j customer, Raymond James uses graph technologies that give developers the ability to represent the relationships, dependencies, and business context that AI applications need to reason effectively. Accuracy is a critical requirement in the financial world, and Raymond James uses its knowledge graph to help agents work with data from trusted systems and evaluate results against established sources.

“We have golden sources, we have systems that we can rely on today, and we are able to create using agents and compare what we create against the golden sources,” Mahankali told theCUBE. “Even if we get the data from different sources, the knowledge graph is in Neo4j and we do evaluations against the gold sources and make sure they are 100% accurate before launch.”

Raymond James’ work with AI is driving new efficiencies within the organization. Looking forward, Mahankali sees opportunities for AI to reduce the amount of time and effort financial advisors spend gathering information for clients.

“One of the things we’re trying to do is have AI query the data dynamically so that our financial advisors can get what they want without clicking on screens and without looking at a fixed dashboard,” he said. “They can do more analysis than just looking at the data they already see in other applications. They can do product analysis and compare how accounts are balanced and things like that by asking a question.”

The implementation of AI agents is also transforming everyday processes at Raymond James itself. In January, the company launched Raimond, its proprietary digital AI operations agent.

“We have an AI assistant… it has gained wide acceptance and is getting smarter,” Griffith said. “That’s part of the core evolution of our engineering work. We’re changing the way people work, how everyone works with a desktop that gives people the best AI tools to move from doing all menial tasks to managing agents who do those tasks. In terms of skills and what we’re looking for, it’s shifting from people who can do tasks to people who have the drive to solve a meaningful problem.”

Here’s the full video interview, part of SiliconANGLE and theCUBE’s coverage of GraphSummit:

(*Disclosure: TheCUBE is a paid media partner for GraphSummit. Neither Neo4j, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over theCUBE or SiliconANGLE content.)

Photo: SiliconANGLE