An Intelly Brain Candy Brief
The biggest challenge in working with with legacy code is understanding what it does.
The original developers may be long gone, and with them any institutional knowledge about the code and application. Sometimes responsibility for maintaining the code is outsourced to consultants, or offshore services companies. Documentation may be scarce, non existent, or not kept up to date.
To help address these challenges, Sage AI Technologies developed a set of gen AI powered tools to analyze legacy code bases, and generate architectural models, documentation, training materials, and recommendations for modernization projects.
The architectural models depict the overall application design and as well as individual components of the application.
The generated documentation is used to train an LLM so it can respond to prompts about the application, including project related aspects such as staffing requirements. AI coding agents work with the trained LLMs using MCP servers.
Sage’s models also generate Behavior Driven Development (BDD) style syntax, which allows developers to tweak the design or add functionality before generating new code.
Training data is kept locally within the organization’s data center, where the LLMs are also hosted. All code remains under an organization’s control.
Sage currently supports Java, C#, Python, COBOL, PL/1, and Basic and is adding support for additional languages.
Copyright © Intellyx BV. Intellyx is an industry analysis and advisory firm focused on enterprise digital transformation. Covering every angle of enterprise IT from mainframes to artificial intelligence, our broad focus across technologies allows business executives and IT professionals to connect the dots among disruptive trends. None of the vendors mentioned in this article is an Intellyx customer. No AI was used to produce this article. To be considered for a Brain Candy article, email us at pr@intellyx.com.
