United Airlines currently spends significant analyst hours manually compiling weekly management presentation decks from disparate Jira tickets and Confluence logs, leading to inconsistencies and data omissions. We developed an end-to-end AI-driven workflow, using data extraction pipelines and multimodal transformer models fine-tuned on six months of historical decks and project logs, to automate slide structure and styling. The prototype achieved a 60% reduction in deck preparation time while ensuring formatting accuracy and KPI compliance, enabling teams to redirect effort to strategic analysis.
Watch the team present this project at 05:11 in the session recording here.
Keywords: Multimodal transformer, Jira/Confluence data, automated QA layer, enterprise API integration, slide-structure generation, AI Agents, model context protocol (MCP), vision language model, airline
Faculty Advisor
Dr. Justin Kurland is Vice President, Tech Fellow in the Engineering Division at Goldman Sachs. Justin’s 20+ years in data and analytics include a senior lectureship in the Department of Computer Science at the University of Waikato, 50+ peer-reviewed publications, and numerous open-source contributions in Machine Learning and Times Series forecasting. With degrees from Rutgers University, Boston University, and University College London, Justin also has extensive data science consulting experience working with organizations like Microsoft and the UK Home Office.