In business and academic settings, presentation slides reflect the individual
preferences of their authors. Even when presenting the same content to the same
audience, authors vary in their preferred level of detail, organization, and style. Current
slide generation systems overlook these preferences and produce generic presentations
that require extensive revision. We address this limitation with SlideSuite, a multi-agent
LLM pipeline that (1) distills an author’s preferences from prior slide decks and (2) uses
the resulting profile to transform a written document into personalized presentations.
LLM evaluators show that SlideSuite improves both overall quality and personalization
without sacrificing readability or completeness.
Watch the team present this project at 00:28:46 in the session recording here.
Keywords: slide generation, multi-agent systems, personalization, large language
models, prompt optimization, LLM as judge
Faculty Advisor
Ashish Pujari is a Data and AI consultant, practitioner, and educator with over 20 years of experience in in machine learning, big data, and cloud computing. He has led large global technology and data science teams and consulted for Fortune 500 companies in banking, finance, healthcare, insurance, and manufacturing.
As a Principal ML/AI Architect at AWS, Ashish provides strategic guidance to enterprise customers on leveraging the cloud for AI and Machine Learning. Prior to joining Amazon, he served in various technology leadership roles at Credera, GLG, IRI, and Pegasystems. Ashish holds a Master of Science in Analytics from the University of Chicago and BS in Electrical Engineering from the National Institute of Technology, Rourkela.