Abstract
There is a lack of research on how users of Large Language Model (LLM) engines actually come up with explanations of their findings in a specific social and organizational context. The issue of LLM explainability is highly relevant in the context of Competitive Intelligence (CI) practices. The objective of this article is to explore how the challenge of dealing with explainability in using LLM tools affects the process and the quality of LLM-driven CI practices and describes a case of using an LLM engine (Perplexity AI) to enhance the CI practices of a small Canadian company. The article emphasizes the need to consider explanation in Generative AI and LLMs as both a construct and an outcome of a socially situated participatory process that incorporates the complex multifaceted relationships between the AI tool, its developers, its users/analysts and their clients. It offers a case study of adopting a digital transformation framework to design a set of prompts enabling comprehensive CI information gathering relevant to the context of a real-life business.

This publication has 11 references indexed in Scilit: