Spaces

A space is a 3D version of a real place, such as a museum floor, a store, or a worksite. Its semantic layer names what is there: rooms, zones, objects, landmarks, and routes.

Agents use a space to know where they are and what is around them. They get short facts from it, such as which room the visitor is in, which object the camera recognized, or the way to the next exhibit.

Create and edit a space

Open Spaces and choose New space. Start from scratch, or import a semantic layer from a JSON file. (Creating a space from video is coming later.)

Open a space to work on it in the space editor: rename it, look around, and edit the semantic layer. You can also ask Builder to look at the space and change what is placed in it.

Use a space in an agent

The Spaces section of the agent's configuration lists its spaces. With a space, an agent can search objects, read their descriptions, and ask for routes.

Each space there has a Recognition checkbox and a recognition connection. Recognition lets the agent identify objects through the camera; turning it off keeps the other space tools. Set up connections in the space editor.

Share a space link

A space link pasted into Slack, iMessage, WhatsApp, or X shows a card with the space's name and a picture. Anyone with the link can see that much without signing in; everything else stays private.

See also: Spatial Intelligence Engine, Simulations

Technical

• The editor opens at /org/<organization id>/spaces/<space id>. Change spaces only through the editor or the space tools, never by editing their files.
• How well an agent finds its way depends on the space's landmarks, camera calibration, and room plans.
• The link card picture is the thumbnail the editor saves while someone works in the space; a space nobody has opened shows the default cover. Set WORLDAGENTS_SPACE_LINK_PREVIEWS to off to turn link cards off on a server.