BotMan AI Uses Knowledge Graphs to Give Agents Context for Legacy Modernization

D’Andrea said legacy modernization requires understanding how an application’s code, data and business rules fit together before rebuilding it. BotMan AI uses an AI-powered migration pipeline that maps an application’s dependencies, business logic and data models in a knowledge graph. That context helps agents interpret the system they are rebuilding, he said.

“Intelligence is not the problem anymore,” D’Andrea said. “The problem is context. You have to explain to the agent everything it needs to understand [how] to do a particular task. What if you didn’t have to explain that? What if it already knew all that you know? That’s the key now.”

According to D’Andrea, BotMan AI uses knowledge graphs to represent how an application’s components and business rules relate to one another. Its approach rebuilds the application’s architecture rather than simply translating old code into a newer language.

“It’s basically migrating from an old code base — Delphi, Visual Basic, Oracle Forms — and rewriting that same system into a new architecture,” he said. “It’s re-architecting the entire thing. We ingest the whole thing at once and we migrate it fully autonomously. That’s where graphs play a big part.”

Beyond code migration, knowledge graphs can provide reusable context for AI agents, D’Andrea said. Mapping relationships when information enters the system can reduce the discovery work needed for subsequent queries.

He gave the example of a legal document. When the document enters the system, relationships can be created to other documents. “You can say, ‘This relates to this particular project and this particular loss and this particular lawsuit,’” D’Andrea said. “And you do that once. Then any agent, when you assign a task, will know automatically from the graph that all that information also might be relevant.”

Connecting unstructured information to recognizable entities gives agents another way to recover business context, according to D’Andrea. A person, project or product can link otherwise separate messages and documents.

“One of the things that worked for us in terms of processing all this unstructured information … is link[ing] them through entities,” he said. “An entity for us will be a person, a project or a product. It will look you up, it will see all the connections that you already have, the projects that you’re working on, the interactions that we had and everything. And then it will figure out where that piece of information … should fit.”

The interview is part of SiliconANGLE’s and theCUBE’s coverage of theCUBE + NYSE Wired: AI Luminaries interview series. TheCUBE is a paid media partner for the series. Neo4j, the sponsor of theCUBE’s event coverage, and other sponsors do not have editorial control over content on theCUBE or SiliconANGLE, according to a disclosure that accompanied the interview.