Home · Strong theory
Empty-Home Water Sentinel
In an empty house, it sees a leak growing inside a wall.
The physics is solid; our own validation is scheduled.
How it works
Water changes how WiFi passes through a wall far more than almost anything else. As a leak spreads, signals crossing that wall slow down and weaken in one spot that keeps growing. The change stays in one place and only grows — nothing else in an empty house behaves like that.
In the physics: Water has eps_r~80 vs ~2 for dry drywall/wood; even a few percent moisture gain in a wall cavity measurably increases dielectric constant and loss along paths traversing it — shortening apparent electrical delay, attenuating specific CIR taps, and shifting the reconstructed eps_r field in that voxel. The change is spatially localized and monotonic, unlike occupancy clutter.
See it work
This is real pipeline output for Home, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
Own-hardware: controlled wetting of a drywall test wall (measured gravimetric moisture) over 21 days inside a mesh, correlate reconstructed eps_r drift with moisture content; compare against commercial moisture meter ground truth.
Who it is for
"Your empty ski house texts you about the leak in week one, not the $80k mold claim in month three." For second-home owners, rental managers, and home insurers.
runtime Runs today in LatentField 2.0 as presence
The matching solution
Complete first-room estimateHome Presence & Intrusion2 nodes · ~$90 parts · 45 min Request kit, subscribe, or set up →Compatible DIY hardware options
45 min · intermediate
60 min · intermediate