SMU Data Science Review


Abstract. “Growth strategies that are purpose-led, customer-centric, experience-driven, data/AI-enabled, and technology-scaled require new mindsets…” (Cornfield, 2021). What can we take from this? Business growth and customer experience are inextricably tied together. Therefore, thriving, as an organization, is dependent on reimagining enterprise operations through modern, scalable data and AI technologies. Our study aims to enhance support operations with emerging AI capabilities, including OpenAI’s LLM models, built on self-attention mechanism transformer architecture, and tailored for business needs through prompt engineering. Our research uses Markov Decision Process and the Q-learning algorithm to evaluate synthetically created support incidents. Through this set of methods, our study seeks to determine the optimal policy to apply for each incident, including demarcating low-cost self-service approaches, in which an agent leverages AI tools to support a support ticket resolution process versus following a traditional, resource-driven approach wherein higher-level expertise intervention and escalation is required. Our research also explores different aspects of AI model development and performance, including grounding data for content relevance, breadth of user intent, and the quality of user prompts, aspects which are fundamentally enabled through prompt engineering methods. Ultimately, in this analysis, we aim to elevate the support experience for Microsoft customers, reducing support staff burnout, while providing a blueprint for other businesses to improve support operation costs, and thereby, their bottom lines.

Creative Commons License

Creative Commons Attribution-Noncommercial 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License