BotMan AI Taps Knowledge Graphs to Decode Legacy Systems for Modernization
BotMan AI's founder explains how knowledge graphs provide AI agents with the business context needed to autonomously rebuild aging applications rather than simply translating their code.
Modernizing legacy systems demands more than translating old code into new languages. It requires grasping how an application's components, data structures and business logic interconnect before attempting a rebuild.
BotMan AI has built an AI-driven migration pipeline that constructs knowledge graphs mapping an application's dependencies, business logic and data models. This contextual foundation allows AI agents to comprehend the systems they are reconstructing, according to Alejandro D'Andrea, the company's founder and chief technology officer.
Intelligence is not the problem anymore. 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.
Alejandro D'Andrea, founder and CTO of BotMan AI
D'Andrea discussed his approach during an interview with theCUBE Research's John Furrier as part of theCUBE + NYSE Wired: AI Luminaries interview series, broadcast on theCUBE, SiliconANGLE Media's livestreaming platform.
Knowledge graphs in legacy system transformation
BotMan AI deploys knowledge graphs to capture how an application's pieces and business rules relate to each other, D'Andrea explained. Rather than simply converting legacy code into a modern programming language, the company's strategy involves rearchitecting the entire system.
It's basically migrating from an old code base — Delphi, Visual Basic, Oracle Forms — and rewriting that same system into a new architecture. 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.
Alejandro D'Andrea
Beyond the mechanics of code migration, knowledge graphs serve another purpose: they furnish AI agents with reusable business context. When relationships are established as information enters a system, subsequent queries require less exploratory work, D'Andrea noted.
He illustrated this with an example: "You get, let's say, a legal document. At that point, when you get it, you can create all the relationships 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 any agent, when you assign a task, will know automatically from the graph that all that information also might be relevant."
Anchoring unstructured information to identifiable entities gives agents an additional mechanism for recovering business context. A person, project or product can serve as a bridge connecting otherwise isolated messages and documents.
https://www.youtube.com/embed/BwxFXh0RVc0?feature=oembed
One of the things that worked for us in terms of processing all this unstructured information … is link[ing] them through entities. 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.
Alejandro D'Andrea