Online Archive of University of Virginia Scholarship
Function Calling for LLMs: Using AI to Create Intuitive Experiences for Users at Scale; An Investigation into the “Automation Divide” and the Social Construction of Agentic AI4 views
Author
Ghadge, Amogh, School of Engineering and Applied Science, University of Virginia
Advisors
Jog, Adwait, EN-Comp Science Dept, University of Virginia
JACQUES, RICHARD, EN-Engineering and Society, University of Virginia
Abstract
Autonomous artificial intelligence agents—systems that perceive their environment, reason about goals, and take independent action on a user’s behalf—are rapidly transforming how people interact with software. At the application level, AI agents can simplify a banking interface by translating a customer’s natural language query into structured filter selections, or manage a user’s calendar by chaining tool calls against live device APIs, all without requiring the user to learn a complex interface. These are tools of augmentation: they make an individual more productive without displacing anyone’s labor. Yet the broader trajectory of the agentic AI industry points in a different direction. Technology firms are increasingly building autonomous agents designed not to assist workers but to replace them entirely—automating complex digital workflows end to end, from customer service to creative production. My thesis examines this divergence from both sides. The technical project designed and deployed an AI-powered natural language search system for the Capital One Mobile Banking App as a proof of concept for user-facing augmentation. The STS project investigates why the agentic AI industry is instead being socially constructed around labor displacement, creating a new form of socioeconomic inequality I call the “automation divide.”
Degree
BS (Bachelor of Science)
Keywords
Artificial Intelligence; Large Language Models; Agentic Artificial Intelligence; Automation Divide
Notes
School of Engineering and Applied Science
Bachelor of Science in Computer Science
Technical Advisor: Adwait Jog
STS Advisor: Richard Jacques
Technical Team Members: Amogh Ghadge
Language
English
Rights
All rights reserved by the author (no additional license for public reuse)
Ghadge, Amogh. Function Calling for LLMs: Using AI to Create Intuitive Experiences for Users at Scale; An Investigation into the “Automation Divide” and the Social Construction of Agentic AI. University of Virginia, School of Engineering and Applied Science, BS (Bachelor of Science), 2026-05-09, https://doi.org/10.18130/tqtv-r968.
