 This paper presents a proof of concept fine-grained mobile AR city GML based pose tracking system aimed at enhancing typical workflows in planning, execution and operation processes in civil engineering and city planning by simplifying planning processes and optimizing communication between decision makers. The system estimates poses by combining 3D city GML data with information derived from 2D camera images and an inertial measurement unit and is fully self-sufficient and operates without external infrastructure. The results of the evaluation show that city GML and low cost off-the-shelf mobile devices, such as smartphones, already provide performant and accurate mobile pose tracking for AR in civil engineering and city planning. This article was offered by ChristofBlood and George Blankenbach.