Raymond James Turns to Neo4j Knowledge Graphs for AI Accuracy

Knowledge graphs are becoming a critical context and reasoning layer for agentic AI, helping enterprises connect data and ground agents in key areas of business expertise, according to the interview. For a diversified financial services company such as Raymond James, graph technologies have become an important part of developing trustworthy infrastructure to support AI. Griffith said the technology has been particularly helpful in building unique solutions. “Using something like a data graph lets us harness the power of AI in dynamic ways,” he 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.”

As a Neo4j customer, Raymond James uses graph technologies that give developers a way to represent the relationships, dependencies and business context that AI applications need to reason effectively. Accuracy is a critical requirement in the financial world. Mahankali said the company has golden sources, systems it can rely on today, and uses agents to build and compare what it is building against those 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,” Mahankali said.

Raymond James’ work with AI is creating new efficiencies within the organization, according to the executives. Mahankali said one goal is to let AI query data dynamically so financial advisors get what they want without clicking on screens and without looking at a fixed dashboard. Advisors can then do more analysis, including product analysis versus how accounts are balanced, by asking a question, he said.

The implementation of AI agents is also changing everyday processes inside Raymond James. In January, the company launched Raimond, its proprietary digital AI operations agent. Griffith said the company has an AI assistant that has gained huge adoption and will get smarter. He described the engineering evolution as changing how everyone works with a desktop, giving people the best AI tools to move from doing all the menial tasks to managing agents that perform those tasks. In terms of skills, he said the company is shifting from looking for people who can do tasks to people who have a drive to solve a meaningful problem.

TheCUBE is a paid media partner for GraphSummit, according to a disclosure. Neither Neo4j, the sponsor of theCUBE’s event coverage, nor other sponsors had editorial control over content on theCUBE or SiliconANGLE.

Editor's Summary

Raymond James Financial is using Neo4j knowledge graphs to ground AI agents in trusted data and test outputs against golden sources before launch, executives said at GraphSummit. The company launched Raimond, a digital AI operations agent, in January and is exploring dynamic queries that would let financial advisors analyze data without fixed dashboards. The executives said the technology supports accuracy and new efficiencies in financial services.