Reference guides for the maps apps an AI agent can work with: every endpoint, the permission each one needs, and how to give agents safe, governed access.
The Google Maps API is how an app or AI agent works with Google's geospatial data: turning an address into coordinates, finding nearby places, computing a route between two points, or looking up the time zone at a location.
The Mapbox API is how an app or AI agent works with location data: turning an address into coordinates, calculating a driving route, rendering a static map image, or managing styles, datasets, and uploaded tilesets.
A maps API is how an app or AI agent turns addresses into locations and works with geographic data. The two platforms here, Google Maps and Mapbox, provide geocoding, directions, places, and map imagery, and their APIs let an agent look up an address, calculate a route, or find nearby places.
Maps access is mostly read access to location data, and it is billed per request, so an access key’s main concerns are cost and which services it can call. Access runs on an access key, often restricted to particular services and capped with a usage limit. A governed layer lets an agent that geocodes addresses call only that service with a key that cannot run up unrelated map costs.
Bollard AI sits between a team's AI agents and the apps it runs on. Grant each agent exactly the access it needs, read or write, app by app, and every call is checked and logged.