placemy.cloud
Savings evidence

Five workloads. Measured. Published.

Before placemy was a product, the engine inside it was a dissertation project. These are the five test cases from that evaluation, reproduced without rounding and without cherry-picking. Your workloads will look different — every cloud estate does — but the technique that produced these numbers is the same one running inside the CLI today.

Dissertation evaluation

Five real workloads, measured savings

CaseWorkloadCurrentBefore / moRecommendationAfter / moSaving
TC-01
Over-provisioned t3.micro (idle, 0.07% avg CPU)
AWS t3.micro, eu-west-2
AWS t3.micro
eu-west-2
$8.61
AWS t4g.nano
EU (Stockholm)
$3.1463.6%
TC-02
Under-provisioned B1s (22% avg, 94% peak CPU)
Azure Standard_B1s, northeurope
Azure Standard_B1s
northeurope
$8.25
Azure B2pts v2
swedencentral
$6.2823.9%
TC-03
Idle B1s (0.4% avg CPU, 25.7% peak)
Azure Standard_B1s, italynorth
Azure Standard_B1s
italynorth
$8.76
AWS t4g.nano
EU (Stockholm)
$3.1464.2%
TC-04
Residency-constrained t3.micro (Ireland)
AWS t3.micro, eu-west-1
AWS t3.micro
eu-west-1
$8.32
AWS t4g.micro
EU (Stockholm)
$6.2824.6%
TC-05
Stable web B2s (13.7% avg, spiky pattern)
Azure Standard_B2s, switzerlandnorth
Azure Standard_B2s
switzerlandnorth
$38.54
AWS t4g.small
EU (Stockholm)
$12.5667.4%

Real workloads on real AWS and Azure accounts in EU regions, scanned with the same pipeline shipping in placemy today. Published in the 2025 MSc dissertation (L00162129). On-demand pricing; your results will vary by workload pattern.

What the numbers cover

Each test case is a real workload scanned before any placemy recommendation was applied (the “Before” column) and re-scanned after applying the highest-confidence recommendations (the “After” column). We did not apply every recommendation — only the ones the engine flagged with high confidence and low blast radius. The delta is the monthly saving, not a projection.

What the numbers don't cover

Implementation time, engineering review, regression testing. The savings figures are the ceiling of what the placemy engine surfaces — the floor depends on how your team chooses to act on the report. We think that's the honest way to talk about it.

Peer-reviewed methodology

The multi-cloud right-sizing methodology behind these results is being presented as an IEEE paper at the 2026 IEEE International Conference in Bristol, UK (September 2026). The paper covers the P95-based sizing algorithm, cross-cloud candidate filtering, and the evaluation methodology used to produce the figures above.