The forecast, risk, and read layer
The number, not the loop.
Forge is what a trader betting on energy or AI-infrastructure strain actually wants: the number, not the loop. Telemetry through Echo, the read and the calibrated call.
Stands alone. Sellable on its own.
What you get
Read the operation. Project it forward. Call the breach.
Telemetry
What Forge reads
Vector Processing
The read, projected forward
Baros
The strain state
Echo
The call
Our wins
Four arenas, each calibrated in its own domain. Every figure is from a preregistered test, fit on train and scored on an untouched test set, with the pass condition written before the data was opened.
Hospital admissions
+10.6–19.9%
floor skill over the baseline it is forbidden to lose to
Brier 0.041–0.047 vs 0.067
NHS · 137 trusts · daily
Power grid
+30.4–61.0%
floor skill over persistence at the measured lag
Brier 0.005–0.030 vs 0.033
EIA-930 · 37 balancing authorities · hourly
Grid, five-minute
+9.5–19.7%
held all the way down to a five-minute grain
Brier 0.005–0.014 vs 0.046
NYISO · 11 zones · 1.77M ticks
Production compute
+12.0–21.5%
on a real production trace, in the arena we predicted would fit
Brier 0.031–0.035 vs 0.049
Azure Functions · 300-function cohort · 5-min
Coming · Praxis, the NexOS API
Some buyers want the number, not the instrument.
Praxis is the developer's bench: Forge's calibrated breach-risk read, served over HTTP into your own system, with the calibration and the preregistration travelling alongside every score. One endpoint, one arena to start, and arenas open only in the order they earn it.
In build. There is no key to issue today.
Forge is where most operations start.
It stands on its own. When you want the move, the approval, and the loop that closes on recurring failures, Radar sits on top of it.