Speaker: Vaishali Dhanoa
Abstract: Autonomous agents powered by Large Language Models are transforming AI, making it essential for the visualization field to embrace agentic frameworks. However, our field’s focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such agentic visualization that preserve human agency while amplifying analytical capabilities. In this talk, we will address these questions by reinterpreting existing visualization systems with semi-automated or fully automatic AI components through an agentic lens. We will then walk through a set of design patterns that emerged from this lens, showing how agent roles, communication, and coordination are already shaping these systems. Finally, we will discuss how these patterns can guide the design of future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.
Bio: I am a PostDoc at Aarhus University, Denmark and a part-time researcher at TU Wien, Vienna. I completed my PhD in October 2024 at Johannes Kepler University (JKU), Linz, Austria, where I focused on making sense of complex spreadsheets and explaining visualization dashboards to users. During my PhD, I also worked at Pro2Future GmbH, collaborating closely with industrial partners to develop visualization dashboards for their data challenges. Prior to academia, I worked as a software developer at Intel GmbH, Linz while pursuing my master’s in Pervasive Computing, at JKU, Linz. My research interests include dashboards, onboarding, data-driven storytelling, developing visualization tools, and recently agent-based visualization systems.
