Pedestrian routing is important in a multitude of public spaces, especially those characterized by a large number of newcomers. Their needs may be diverse, with priority for the shortest path, the less crowded or the less polluted one, the accessibility for reduced mobility, or the sheltering from unfavorable weather conditions. Hence, typical graph-based routing must be enriched to support multiple policies, at the choice of each person. The paper proposes a systemic approach and a set of services for orientation and accessibility, which are both community-driven and data-driven, for correctly perceiving the routing necessities and the surrounding situation. The response time to a pathfinding query depends on the types of policies applied and not only on their number, because each of them contributes to the customization of the weighted graph, although it refers to the same physical space traversed by pedestrians. The paper also presents results of loading tests for up to 5000 Virtual Users, inspired from real-life requirements and executed on a graph that models a real building in our university; different policies are applied to assess performance metrics, with simulated community feedback and sensor data.