AI Reverse Engineering Tool

Development teams working on modernization efforts often face major setbacks trying to understand legacy systems. The complexity of outdated code and unclear business logic can lead to long timelines, bloated teams, and poor user outcomes.

As Principal UX Designer, I led the end-to-end design process. This included recruiting participants, conducting user research, facilitating strategy workshops, and synthesizing insights to guide the product vision. I also designed the concept in Figma, tested it with users, and collaborated closely with developers to build a high-fidelity prototype through to final release.

We created an AI-powered platform that helps developers quickly import legacy codebases, visualize system architecture, and better understand business logic. The tool features interactive system diagrams and layered data views that simplify complexity and accelerate onboarding.

The Kickoff

Problem Statement

How might we solve the issues faced by modernization teams with our AI platform?

Define Objectives

Research questions
Research methods
Expected outcomes
Determine personas
Determine stakeholders

Expected Outcomes

Gain process knowledge
Desired features
Past experiences
Create data driven culture
Eliminate manual process

Research Methods

User interviews
Interview analysis
Research papers
Surveys
Usability testing

Target Persona

Emilio Holiday is a senior software engineer, leading a team of developers who are all well versed in modern technologies and expert at writing efficient code.

The company that hired them has a 30 year old mainframe system that needs to modernize so they can continue to provide the same services to their clients without disruption.

Research

Research Methods

15 mainframe developer interviews
8 mainframe research papers
3 surveys to mainframe teams

Key Research Findings

Due to security risks, companies are preferring to keep sensitive data on their mainframes and modernize systems into the cloud like analytics and reporting.
Attempting large scale migration without fully understanding workload interdependencies or time and budget needs has led many to underestimate the impact of modernization and project failure.
Legacy applications are not designed to support continuous delivery, as some components within these applications create obstacles - or friction points - that negatively impact business operations.
Poor coordination between product and modernization teams - and lack of engagement with business leaders - will undermine continuous modernization efforts.
Main reasons to spend money on a modernization project: license costs, lack of scalability, stability and performance, customer complaints, security issues, industry competition and a desire for greener industry.
Problems faced by modernization teams: dead code, difficult to understand systems and business logic, lack of documentation, outdated processes and tools.
By prioritizing the mainframe developer experience and automating manual activities. organizations can deliver even greater value to their businesses.

Brainstorming

We analyzed the data from the interviews in Dovetail using tags aligned with our script.

Using these insights, the team mapped out the pain points and opportunities in a Miro Experience Map.

Once this was complete, we presented our research to the stakeholders with key findings from the research papers included.

This gave us all we needed to create a concept of our solution.

Screenshot 2025-03-14 at 8.38.36 PM (1).png

Prototype Creation

Based on feedback from the stakeholders, product and development teams, we refined the solution several times and arrived at a high fidelity design using Figma.

This solution provided a means to import a codebase from GitHub and reverse-engineer product requirements from existing code, enabling users to develop a comprehensive understanding of legacy codebases in minutes.

The platform analyzes the codebase and provides the ability to view all the data layers that come along with it, including dependencies, file analysis, business logic, a tech stack analysis users can drill into, and tools to help add comments and development plans while highlighting business logic and including integration with Jira, automated with the help of AI.

Validation

We iterated the design based on our feedback sessions, then prepared our script and prototype for usability testing.

The solution was tested with 10 of the developers from the user interviews.

Feedback was gathered from these which we used to further refine the solution.

Results

The project was met with positive feedback from clients, who’s ideas for a next phase added more value. Our solution provided:

Faster Discovery: AI can analyze the vast amount of data in a legacy codebase and reverse-engineer the system’s original requirements faster than human teams resulting in a 75% faster project completion rate, reducing cost by more than 50%.
Clearer Communication: AI bridges the gap between business and technical teams by serving as a translation layer between org-level and code-level requirements achieving 80% or better accuracy.
Dynamic Distribution: AI can reference requirements at every phase of development, ensuring that the updated system actually solves the problem it’s meant to address.

The Design