BotMan AI leverages knowledge graphs for legacy modernization

Legacy modernization requires understanding how an application’s code, data, and business rules fit together before rebuilding.

BotMan AI uses an AI-powered migration pipeline that maps an application’s dependencies, business logic and data models into a knowledge graph. According to Alejandro D’Andrea (pictured), founder and chief technology officer of BotMan, this context helps agents interpret the system they are rebuilding.

“Intelligence is no longer the problem,” he said. “The problem is the context. You have to explain to the agent everything he needs to understand.” [how] complete a specific task. What if you didn’t have to explain this? What if it already knew everything you know? That’s the key now.”

D’Andrea spoke to theCUBE Research John Furrier for theCUBE + NYSE Wired: AI lights Interview series on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how knowledge graphs support the modernization of legacy systems and provide reusable business context to AI agents. (*Disclosure below.)

How knowledge graphs support the modernization of legacy systems

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

“Basically it’s about migrating from an old code base – Delphi, Visual Basic, Oracle Forms – and rewriting the same system into a new architecture,” he explained. “It’s about redesigning the whole thing. We take the whole thing in at once and migrate it completely autonomously. Diagrams play a big role in this.”

Beyond code migration, knowledge graphs can provide reusable context for AI agents. According to D’Andrea, mapping relationships as information is entered into the system can reduce the investigative effort required for subsequent queries.

“You get, let’s say, a legal document,” he gave as an example. “At that point, when you get it, you can make all the connections to other documents. You can say, ‘This relates to this particular project and this particular loss and this particular lawsuit.’ And you do that once. Then, when you assign a task, each agent automatically knows from the graph that all of that information may also be relevant.”

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

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

Here’s the full video interview, part of SiliconANGLE and theCUBE’s coverage theCUBE + NYSE Wired: AI lights Interview series:

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

Photo: SiliconANGLE