Advancing Industrial Efficiency: Conversational Agents and Low-Code Automation for Organizational Transformation

Diogo Teixeira Pires

Key information

Authors:

Diogo Teixeira Pires (Diogo Teixeira Pires)

Supervisors:

Paulo Miguel Nogueira Peças (Paulo Miguel Nogueira Peças)

Published in

November 26, 2025

Abstract

This dissertation investigates the deployment of Artificial Intelligence (AI) tools as catalysts for enhancing organizational efficiency and fostering entrepreneurial opportunities within industrial maintenance contexts. The research focuses on the integration of conversational AI agents, specifically Chatbots powered by Generative AI technologies, within Microsoft’s Power Platform to automate and optimize repetitive workflows. Recognizing the challenges posed by traditional manual processes in large-scale operations, this dissertation uses a case study methodology underpinned by Multi-Criteria Decision Analysis to design, develop and evaluate two AI agents: ManuBot and MailBot. Quantitative performance metrics underscore substantial reductions in task completion times and error rates, while qualitative insights reveal elevated user satisfaction and operational planning. The research further addresses the technological challenges and organizational considerations related to deploying low-code AI automation solutions in industrial settings. This dissertation contributes actionable knowledge on scaling Chatbot adoption and embedding AI driven workflows to drive digital transformation and sustained productivity gains. Recommendations emphasize the advancement of context-aware agent capabilities and the expansion of AI solutions tailored to domain-specific decision support.