Every claim traces to a measurement.
The numbers on our homepage are not marketing copy — they are experimental results. This page is the methodology.
Chaos-validated blast radius
We do not simulate failure — we cause it. On an instrumented multi-node cluster, workloads were killed one at a time and the measured downstream impact was compared to what Iverson predicted beforehand. Result: Spearman rank correlation of 0.98 between predicted and measured blast radius, with recall 1.0 — no failure our model called dangerous turned out benign, and none it called safe took anything down.
Root-cause diagnosis, ground-truth tested
Faults were injected into a 12-service production-shaped estate — crashed dependencies, misconfigured probes, broken external endpoints — and the diagnosis engine was asked to find them cold. It identified the seeded root cause correctly in every test case, separating true roots from collateral damage using failure-onset ordering and shared-dependency inference.
CEI: the Criticality-Entropy Index
CEI scores how dangerous each dependency concentration is by combining graph centrality (how many things need this), dependency entropy (how concentrated the need is), and operational risk signals. It is the number that says which service is quietly becoming the single point of failure nobody chose. Patent pending, USPTO App. No. 19/641,446, with additional filings in preparation covering blast-radius computation and related components.
Risk in dollars, not adjectives
Structural risk is priced by Monte-Carlo availability modeling against your downtime cost rate. Every recommendation carries its net annual benefit: risk reduction minus the cost of the change. High, medium, and low are not numbers; dollars per year are.