Credits: Vensu
This course provides an in-depth exploration of “agentic” AI pipelines, emphasizing the integration of automated tools for urban data acquisition, analysis, and visualization. It is designed to equip students with both the theoretical foundations and practical skills necessary to harness emerging AI-driven technologies in urban planning and design. Throughout the course, participants will interrogate how autonomous agents – ranging from LLM-based conversational systems to generative image models – can be orchestrated into cohesive workflows that not only address current urban challenges but also inspire speculative design innovations.
By the end of the course, students will have designed, implemented, and refined their own agentic AI pipelines. The final integrated project will serve as both a proof of concept and a platform for critical debate, showcasing each student’s ability to synthesize data acquisition, processing, and visualization into a coherent investigative practice. This hands-on, project-centered approach ensures that graduates are well-prepared to navigate and shape the evolving landscape of urban design through advanced computational methods.
By the end of this course, students will be able to:
Manage Computational Constraints
Navigate hardware limitations using local GPUs or cloud services (RunPod), understanding trade-offs in cost and performance.
Safety Perception in Jakarta Why Simulate Perception in Urban Spaces? In the realm of smart city design and urban analytics, one of the most nuanced yet underexplored datasets is perceived safety. This perception isn’t easily quantifiable, yet it critically influences how public spaces are used, trusted, or avoided. Traditional surveys are the go-to method for … Read more
Project Introduction Urban environments are constantly evolving, shaped by the movement of people, the flow of traffic, and the presence of infrastructure. Yet, understanding these patterns at the street level — especially across an entire neighborhood — can be difficult, time-consuming, and highly subjective. In this project, we present a computer vision–based visual audit of … Read more
As part of our ongoing analysis of Quito’s public transportation, we approximated an analysis of the on-the-ground perspective of traveling through the city on the public buses and then analyzed the attributes of different bus stops through machine learning. We began by creating a trajectory that would be a plausible representation of how a woman … Read more
Abstract Building upon the knowledge acquired in the Agent-Based Design & Machine Learning course, we developed a bot designed to collect data from the population of Rundu, the city we are focusing on for our project within the Vulnerability Studio: Computer-Aided Mobility Justice. We face the challenge of accessing qualitative insights that could help us … Read more
