SpheriCity is an expert-grounded conversational prototype designed to support trustworthy knowledge sensemaking from sustainability reports. City-level circularity assessment reports contain rich information about materials, infrastructure, and policy interventions; however, their length and heterogeneous structure complicate cross-document synthesis and comparison for practitioners and researchers in circular economy initiatives. While large language models (LLM) promise faster knowledge access and synthesis, their opaque reasoning, hallucinations, and lack of source transparency introduce risks for trust and interpretability, necessitating verification in high-stakes sustainability contexts.
SpheriCity addresses these challenges through a provenance-first conversational agent that emphasizes evidence traceability, structured synthesis, and interaction scaffolds to support exploratory querying and cross-document synthesis across sustainability reports. We conducted a formative expert review with six sustainability experts using representative queries spanning cross-city comparisons, policy summarization, and recommendation-oriented tasks. Experts evaluated responses across dimensions and provided qualitative reflections on the system's usefulness for sustainability knowledge work.
Our results reveal that transparent sourcing, contextual explanation, interpretability, and alignment with expert workflow strongly shape expert trust and judgments of system usefulness. This work contributes (1) a conversational prototype for sustainability knowledge sensemaking, (2) an expert-grounded evaluation framework for assessing AI responses in high-stakes knowledge domains, and (3) design insights into how provenance, uncertainty communication, and integration in workflow influence expert users' trust in AI assistance for sustainability decision support.
Blogger's Review: SpheriCity demonstrates how enhancing evidence traceability and contextual explanation can elevate trust in AI within sustainability domains. This project not only provides robust support for AI applications in complex knowledge areas but also offers significant design references for future research. Its focus on interpretability and transparency in high-stakes environments is particularly noteworthy and deserves further exploration.