Evidence

Inhabited architecture, in three proofs.

Every replay below is rendered from recorded simulation. Each trajectory and conversation shown actually occurred in the run, and each case is labelled with what it proves.

Case 01A / B

Two plans, one brief. Two full days, inhabited.

Corridor type vs cluster type · one full day each · separate runs

Two plans drawn for the same brief — a corridor type and a cluster type — each inhabited for a full day. What differs is where people gather, where they talk, where they linger. The two panels are separate runs; each source and engine generation is printed under the frame. Provided as a fixed rendered video for control and confidentiality.

×11.5
Spontaneous lounge activation, B over A
First-generation engine · controlled re-run pending

Open detailed analysis (A/B) →

Case 02Measured · replay in preparation

A real building, at real scale

Three levels of a real building, each room shaded by time spent

A building that exists, entered as its own IFC model — one hundred and three rooms over three levels, at true scale. Each room is shaded by how long it was actually occupied; rooms left uncoloured recorded no use at all. Circulation is drawn but not ranked. The rendered replay of the full day follows once format alignment is complete.

Same run · four conversations placed where they happened · translated, otherwise unedited

Open detailed analysis →

Case 03Reproducibility

The published run, played back in full

M1 original replay · Paper 1 result data · first-generation engine
Loading 3D replay…
Thirty-six inhabitants living a full day. This plays back the exact result data of Paper 1, on the first-generation engine it was published with — so anyone can watch the published findings with their own eyes. Open it full-window →

Open detailed analysis →

Free period — the glazed commons

Nobody was sent here. This is where the day put them.

The same hour, one floor up

The classroom floor at the busiest talking hour of the run.

How a topic spreads across groups, day 2
Fig. 01 — How a topic spreads

Day 2 of a three-day run: each arrow is one person carrying the same topic to a new conversation.

Density of one day of movement over the classroom floor, with conversation points
Fig. 02 — Where the floor wears

One day on the classroom floor, shaded by how often it was walked. Routed on the walkable grid, so no path crosses a wall.

Conversations per room inside one cluster, with the classroom that recorded none
Fig. 03 — Where talk settles, and where it never arrives

One cluster of the upper floor. Circle area is the number of conversations recorded in that room; the brick core is the share that crossed a class. Ninety-three conversations gathered in four rooms — and one classroom recorded none at all.

Interactive viewer access is part of a platform analysis. The replays here are for viewing only.
Bring us the model you are still deciding on.
Interactive viewer access is part of a platform analysis
Request an analysis