GeoAI Agency Primitives
This work tackles the problem of low productivity translation from AI models to practical GIS work for practitioners, representing a novel method for a known bottleneck rather than incremental progress.
The paper addresses the gap between advanced GeoAI model capabilities and actual productivity gains for GIS practitioners by proposing 9 agency primitives that connect foundation models to real-world GIS workflows, with a benchmark to measure human productivity improvements.
We present ongoing research on agency primitives for GeoAI assistants -- core capabilities that connect Foundation models to the artifact-centric, human-in-the-loop workflows where GIS practitioners actually work. Despite advances in satellite image captioning, visual question answering, and promptable segmentation, these capabilities have not translated into productivity gains for practitioners who spend most of their time producing vector layers, raster maps, and cartographic products. The gap is not model capability alone but the absence of an agency layer that supports iterative collaboration. We propose a vocabulary of $9$ primitives for such a layer -- including navigation, perception, geo-referenced memory, and dual modeling -- along with a benchmark that measures human productivity. Our goal is a vocabulary that makes agentic assistance in GIS implementable, testable, and comparable.