What we actually mean by spatial intelligence
It is a phrase that gets used loosely across our industry. Here is what it means on our platform, and just as importantly, what it deliberately does not mean.
Every software category eventually collects a phrase that gets stretched to cover too much. In the built environment right now, that phrase is "digital twin", and the one we use, "spatial intelligence", is at risk of the same fate. So before this blog goes any further, it is worth being precise about what we mean by it, because the definition is doing real work.
Three layers, not one product
OnXR is built from three things working together over the same 3D model of a building or site, not three separate tools bolted on afterwards. The first is capture: a photoreal 3D twin, built from a scan of the real space, accurate enough to measure against. The second is detection: software that finds and tags the things in that twin that matter to whoever is looking at it, a fire door, a damp patch, a piece of plant. The third is live data: sensor readings and inspection history overlaid on the exact surface they relate to, so the twin keeps describing the building as it is now, not as it was on the day of the scan.
None of the three is optional. A photoreal twin with no live data is a nice picture that goes stale the day after capture. Live sensor data with no spatial model is a dashboard, and most buildings already have one of those gathering dust. Spatial intelligence is what you get when all three are the same system.
What it is not
A game engine dressed up for business. There is no avatar, no headset requirement, and nobody on a client team needs to learn to fly through a virtual world to get value from it.
A one off scan. A static point cloud from a single visit answers "what did this look like once", which is a different, much smaller question.
A replacement for the people who run the building. It is a shared, accurate reference the team works from, not a system that removes the judgement of a site manager or a surveyor.
Why we lead with the boundaries: a platform that promises everything ends up trusted for nothing. We would rather a prospective client understand exactly what the twin does and does not do before the first demonstration, than discover the gap after they have signed.
The rest of this series works through each of those three layers in turn, starting with capture and the reason we build on 3D Gaussian Splatting rather than the point clouds most of the industry still uses. Read the next post.
See the platform on your own building
The clearest way to understand spatial intelligence is to look at a twin of a space you already know. We run short, no obligation discovery calls for teams in construction, facilities management, insurance, security and defence.
Book a discovery call