Optimizing Document Management in Industrial Maintenance through Generative Artificial Intelligence and Prompt Engineering

Abstract

In the context of Industry 4.0, Generative Artificial Intelligence (GAI) has primarily been used to automate operational processes and schedule activities. However, the work order (WO) closure stage is often considered a low-value administrative process, despite its potential as a critical source of unstructured knowledge. This article demonstrates the effective use of GenAI in completing maintenance report documentation for strategic industrial assets. The research proposes a five-stage approach involving case identification, data collection, prompt design, execution using large-language models (LLMs), and technical validation. Two cases reinforces how prompt engineering can extract value from manual records and checklists by transforming fragmented technical descriptions into structured, coherent reports. The results show that GenAI can be used to leverage closure information for feedback in analytical models and data-driven decision-making. By significantly reducing man-hours and improving the quality of historical data, GenAI acts as a key enabler for transitioning to predictive maintenance. In conclusion, integrating GenAI into the document workflow enables the utilization of previously untapped operational knowledge, thereby strengthening industrial reliability.