Strategy for Work Reduction: Creating Automated AI Hack Life with Agentic AI to Promote Information Literacy

Abstract

     This study aimed to develop a prototype automated system for creating and managing AI Hack Life content by integrating Agentic AI with the n8n platform to enhance operational efficiency and reduce staff workload, and to use the program as an informal learning resource for promoting AI literacy. A comparative process-level approach was employed within the frameworks of Lean Thinking and Time and Motion Study. Actual operational time data from the traditional production process were used as the baseline and compared with the mean processing times obtained from trials of the developed prototype process. A two-member development team worked collaboratively and conducted 10 trials for each of five processes: content preparation, audio recording or synthesis, audio editing and enhancement, cover image creation, and cross-platform distribution.
    The findings showed that the process under the developed prototype system reduced the total production lead time from 360 minutes to 39 minutes, representing an 89.17% reduction. The findings demonstrated the potential of Agentic AI and automated workflows to improve process efficiency by reducing repetitive tasks, waiting time, and staff technical workload. However, the system had limitations regarding the naturalness of Text-to-Speech output, particularly in conveying emotion, pronunciation, and speech rhythm, as well as the risk of factual inaccuracies in Generative AI–generated content. In addition, Khon Kaen University Library produced and published 18 AI Hack Life podcast episodes and accompanying articles, which received a total of 2,471 views in less than two months, reflecting initial audience reach and interest in AI-related content. Nevertheless, the number of views alone cannot directly demonstrate an increase in users’ knowledge or AI literacy.
     In conclusion, integrating Agentic AI with the n8n platform can support improvements in media production efficiency and reduce technical workload. The comparison in this study reflects process-level performance rather than individual staff performance. An appropriate operational model should therefore emphasize human–AI collaboration, in which AI supports technical and systematic tasks, while library staff remain responsible for fact-checking, content curation, quality assurance, learning experience design, and the preservation of organizational identity. Such collaboration can support the development of information service innovations that are efficient, trustworthy, and sustainable.