Since 2022, Nava has partnered with the New Jersey Department of Labor & Workforce Development (NJDOL) to build a modern, flexible, and resilient end-to-end unemployment insurance (UI) system. We’re helping NJDOL replace their legacy mainframe with a modern, cloud-based system to improve systemwide performance, reliability, and observability. Initial technical discovery requires interviews with subject matter experts and manual code reviews to confirm the current system’s functions. We’re working with NJDOL to evaluate whether AI-powered tools can streamline this process.
We helped NJDOL conduct a two-week pilot to evaluate how Amazon Web Services’ Transform, an agentic service, could speed up the process of technical discovery for four code modules. We developed a methodology for evaluating the tool, measuring how long engineers and SMEs took to understand a module and comparing it to time spent on the manual process.
After the pilot, the team had plain-language summaries for each code module that included important pieces of business logic. Reviewers can access this information without having to return to the raw code, an important aspect to helping reduce time spent on technical discovery. Transform also produced maps to show the relationships between programs and data, illustrating how the modules rely on each other to function. Finally, NJDOL used Transform’s analysis to derive test cases with the new code. Overall, using Transform reduced the time software engineers and reviewers needed to understand the modules by an average of 30%.
Most importantly, Transform provided a more comprehensive understanding of the legacy system by identifying code dependencies, business rules, and integration points. This foundation helps NJDOL accelerate the process of analyzing and documenting the legacy codebase and designing the replacement solution.
To learn more, read the full case study.
