Shahebaz Pathan is a Technical Program and Project Manager based in the Bay Area, California with over eight years of experience leading data-driven digital transformation initiatives across enterprise systems and fuel distribution operations. His work focuses on integrating cloud technologies, artificial intelligence, and automation to improve operational efficiency, forecasting accuracy, and decision-making. He has led the development of enterprise solutions including AI-driven forecasting platforms, automated tax compliance systems, and real-time operational dashboards. One of his notable contributions is the design and deployment of a custom CRM/ERP platform for wholesale fuel distribution that automated dispatch, pricing, billing, and tax workflows; the system later resulted in a patent filed under his name. In addition to his industry work, he has authored research articles and technical publications related to artificial intelligence, data analytics, and enterprise system innovation. Shahebaz holds Master’s degrees, Project Management Professional (PMP), and is currently pursuing the Applied AI & Data Science program through MIT Professional Education. He has been recognized as an Honored Listee in Marquis Who’s Who in America (2025–2029) and was also featured in Forbes India for his professional achievements.

Enhancing CRM Systems with Prompt Engineering: AI-Driven Customer Feedback Intelligence  Customer feedback is a valuable source of insight for improving service quality and maintaining trust in the fuel distribution industry. However, manually analyzing large volumes of customer feedback within Customer Relationship Management (CRM) systems can be time-consuming and inefficient. This study presents an AI-driven enhancement to a patented CRM platform designed for the fuel industry by integrating Large Language Models (LLMs) with prompt engineering techniques to automatically analyze customer feedback. The proposed system classifies feedback into positive, negative, and neutral sentiments and enables faster identification of service issues while supporting automated response generation. Different prompt engineering strategies, including zero-shot, few-shot, and chain-of-thought prompting, are explored to evaluate their effectiveness in sentiment classification. By embedding generative AI capabilities into the CRM platform, the system transforms unstructured feedback into actionable insights, helping fuel distributors improve customer engagement, operational responsiveness, and data-driven decision making.