Automating Consultation? Urban Planners and Chatbot-Based AI-Mediated Participation

Source abstract

This study reports findings of a two-year embedded case study in which planners integrated a WhatsApp-based large language model (LLM) chatbot into a regional strategic planning process. Across two deployments in the Sabana Occidente region of Bogotá, Colombia, the chatbot facilitated 273 citizen-to-AI interactions covering visioning, project exploration, and voting. Drawing on semi-structured interviews with planners, the study examines planners’ expectations, experiences, and criteria for evaluating chatbot-mediated engagement. The planners reported that the chatbot reduced participation barriers but raised concerns about misinformation and shallow depth of deliberation. The chatbot expanded access and supported prioritization, yet remained closer to consultation than deliberation. Democratic value depended primarily on governance arrangements—validation, accountable summarization, and traceability—rather than interface novelty.