PerfectScale now recognizes HPA triggers that target a single container, keeping right-sizing recommendations accurate for workloads using container-scoped autoscaling. Recommendations apply only to the container the HPA watches, preventing over- or under-sized suggestions. Podfit and Zoom-In now distinguish pod-level from container-level triggers, so the data you see matches how your autoscaler actually behaves.

A clearer menu that shows the full PerfectScale feature set, with organization and cluster pages in separate sections and quick access to any cluster.

PerfectScale now shows cluster costs, pod waste, and potential savings in EUR, GBP, JPY, ILS, CHF, and more.

PerfectScale now flags containers whose CPU allocations keep climbing without resolving resource pressure, a sign of a workload problem rather than real demand. Automation pauses further CPU increases once your configured thresholds are reached. Set daily and weekly increase limits in your automation YAML to keep rightsizing safe and predictable.

Unevictable pods block node scale-down and drain, quietly limiting cluster elasticity and savings. Now visible and fixable via API.

Make full use of resources in namespaces governed by ResourceQuotas

Public API for node utilization, efficiency data, and infrastructure optimization insights

Find every Java workload in a cluster in one click, no labels required

Numbers across PerfectScale now display the way your country writes them.

Find and fix the configurations blocking node scale-down.

PerfectScale by DoiT now delivers actionable recommendations to improve your Karpenter NodePool configuration, fully aligning it with how your workloads actually run.

PerfectScale now provides visibility into GPU memory utilization, removing a blind spot and helping you run AI/ML workloads with confidence.

Reduce maintenance overhead and keep your agents always up to date with the PerfectScale Operator — a Kubernetes operator that manages installation and upgrades of all PerfectScale components.

See exactly which pods are keeping your nodes alive and blocking scale-down. The new Unevictable Pods view in PerfectScale InfraFit highlights these workloads across any node group, with per-node resource breakdowns for CPU, memory, and GPU. Pair it with node recommendations to improve bin-packing, get more out of Karpenter or Cluster Autoscaler, and lower your Kubernetes spend.

Users could specify "period" query parameter to scope down time window for workloads and their cost analysis data

Understand why memory recommendations are set where they are — now with a toggleable Max Memory metric line and OOM kill event markers directly on the ZoomIn chart.

Enable and manage Kubernetes workload automation directly from the PerfectScale web interface

We've updated workload automation status model and improved related user experience.

Optimization policies can now be managed directly via Kubernetes Custom Resources — alongside or instead of the UI — giving teams full GitOps-style control over how PerfectScale recommends resources across every level of the cluster hierarchy.

We've shipped a major upgrade to node recommendations in PerfectScale for K8s — moving from a single "best pick" to a multi-suggestion experience that gives users real choice over their infrastructure.