AI Agent for Wiring Component Intelligence

Abstract

Throughout my OMSCS program at Georgia Tech, I have been developing a software system that automates the creation of wire harness components in computer-aided design (CAD) tools. Traditionally, engineers must manually model these components, which is a time-consuming and error-prone process. My system applies advanced artificial intelligence and data mining techniques learned from multiple Georgia Tech courses to transform this task into an intelligent, automated workflow. This presentation will describe how key courses from the OMSCS program directly influenced the design and development of this solution. It will cover how concepts from Human-Computer Interaction and Knowledge-Based Artificial Intelligence informed a human-centered design approach and how agile development practices supported collaboration and rapid iteration. It will also touch on the entrepreneurial and legal foundations that helped structure the business behind the technology. The resulting application integrates several modern AI models, including Anthropic Claude, Meta’s Segment Anything Model, and semantic search. It functions as an intelligent agent capable of generating validated wire harness CAD parts about thirty times faster than manual methods while maintaining 98.81% accuracy. Attendees will learn how Georgia Tech coursework can be applied to create meaningful, real-world innovations that combine human-centered design, artificial intelligence, and entrepreneurship. This talk aims to inspire students and alumni to see how their academic experiences can lead to impactful technological and professional achievements.