Raymond James Deploys Knowledge Graphs to Ground AI Agents in Financial Services

Graph technologies are emerging as a foundational layer for agentic AI systems, enabling large enterprises to weave together data across domains and anchor AI reasoning in established business knowledge. At Raymond James Financial Inc., a diversified financial services company, knowledge graphs have become central to constructing AI infrastructure that meets the accuracy demands of the financial sector.

Jeff Griffith, vice president of AI engineering and data science at Raymond James, explained the strategic value of the approach in remarks at GraphSummit. "Using something like a data graph lets us harness the power of AI in dynamic ways," Griffith said. "People already know how to go get the things that they're getting every day. But it's when you want to cross those domains or do some unique thing that this has a lot of value."

Knowledge graphs for data reliability

Raymond James, a customer of Neo4j, leverages graph technologies to model the relationships, dependencies and business context that AI systems require for sound reasoning. In financial services, where precision is non-negotiable, the company uses its knowledge graph to ensure agents operate with data from authoritative systems and validate outputs against established benchmarks.

Naveen Mahankali, vice president of technology at Raymond James, described the validation process: "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."

The deployment of AI agents is unlocking operational efficiencies across Raymond James. Mahankali identified a near-term opportunity to free financial advisors from routine information gathering. "One of the things we're trying to do is we're letting AI query the data dynamically so that our financial advisors get what they want without clicking on screens and without looking at a fixed dashboard," he explained. "They can do more analysis rather than just looking at the data that they already see in other applications. They can do product analysis versus how accounts are balanced and things like that by asking a question."

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

The shift extends to internal operations. In January, Raymond James introduced Raimond, a proprietary digital AI operations agent designed to handle routine tasks. Griffith noted the tool's rapid uptake: "We have an AI assistant … it's gotten huge adoption, and it's just going to get smarter. 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."