Title:

AI Assistant for Home Gas and Oil Company

Poster

Preview Converted Images may contain errors

Abstract

Palmer Oil and Gas serves thousands of customers who need fast digital services, yet current systems lack conversational information access. To address this, our team developed a secure, scalable AI chatbot to modernize Palmer’s customer support. The system leverages Azure OpenAI's GPT-5-Mini for natural language processing, coupled with a custom .NET Model Context Protocol (MCP) server. This MCP server acts as a secure middle layer, proxying requests between the AI model and Palmer's live Azure APIs without exposing sensitive resources directly to the LLM. Throughout our work on this project, we successfully established the end-to-end pipeline, enabling the chatbot to securely retrieve live fuel inventory data using structured tool calls and allowing the user to conversationally receive important data. Validated through integration and unit testing, our product demonstrates reliable data retrieval and architectural viability. Ultimately, this solution will reduce IT and general support demands by allowing customers to seamlessly query usage, manage billing, and access account details, positioning Palmer at the forefront of the customer experience

Authors

First Name Last Name
Jacob Musgrave
Jackson Haubert
Kyle Goodwin
Christian Cunio
Jacob Chapman
Ryan McCarthy

Advisors:

Full Name
David Benedetto

File Count: 1


Leave a comment

Comments are viewable only by submitter



Submission Details

Conference URC
Event Interdisciplinary Science and Engineering (ISE)
Department Computer Science (ISE)
Group Computer Science- Systems / Infrastructure
Added April 20, 2026, 1:49 p.m.
Updated April 20, 2026, 1:49 p.m.
See More Department Presentations Here