Customs digitalisation single-window systems, pre-arrival processing, and automated risk management is widely promoted as a means of compressing the variability of border-clearance time. Drawing on classical inventory theory, we ask how that variance compression affects a firm’s optimal safety stock. Using a discrete-event simulation of a continuous-review (Q, r) replenishment system with skewed (lognormal) clearance times, and isolating the variance channel through a mean-preserving compression, we find that the inventory benefit of digitalisation is strongly regime-dependent. Above a cycle-service-level threshold (≈0.68 in our base case), variance compression reduces required safety stock substantially by roughly two-thirds at very high service levels. Below the threshold across the 50–70% band where most firms operate the benefit vanishes and reverses: variance compression raises the required buffer. The widely assumed inventory dividend of customs digitalisation thus accrues mainly to high-service-level firms. This regime-heterogeneity also offers a mechanism reconciling the operations prediction with the null clearance-uncertainty effect reported in aggregate trade data. The result speaks directly to the conference theme of moving “from data to policy”: the operational returns to a border-digitalisation policy depend on the service-level profile of the importing firm population.