StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure

TL;DR

StreetDesignAI is an interactive AI system that helps cycling infrastructure designers consider diverse cyclist perspectives by surfacing conflicts and enabling iterative, multi-persona evaluation in real street contexts.

Contribution

The paper introduces StreetDesignAI, a novel AI-powered tool that facilitates multi-persona evaluation and conflict surfacing to improve cycling infrastructure design.

Findings

Structured multi-perspective feedback enhances understanding of cyclist needs.

Designers feel more confident and satisfied using StreetDesignAI.

Explicit conflict surfacing shifts design focus to deliberate trade-off reasoning.

Abstract

Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how different cyclists experience the same street environment. We investigate how persona-based evaluation can support cycling infrastructure design by making experiential conflicts explicit during the design process. Informed by a formative study with 12 domain experts and crowdsourced bikeability assessments from 427 cyclists, we present StreetDesignAI, an interactive system that enables designers to (1) ground evaluation in real street context through imagery and map data, (2) receive parallel feedback from simulated cyclist personas spanning confident to cautious users, and (3) iteratively modify designs while the system surfaces conflicts across perspectives. A within-subjects study with 26 transportation professionals comparing StreetDesignAI against a general-purpose AI chatbot demonstrates that structured multi-perspective feedback significantly Broaden designers' understanding of various cyclists' perspectives, ability to identify diverse persona needs, and confidence in translating those needs into design decisions. Participants also reported significantly higher overall satisfaction and stronger intention to use the system in professional practice. Qualitative findings further illuminate how explicit conflict surfacing transforms design exploration from single-perspective optimization toward deliberate trade-off reasoning. We discuss implications for AI-assisted tools that scaffold persona-aware design through disagreement as an interaction primitive.