Magalix AI predicts changes in workloads to make pods, and the cluster ready for those changes. See how containers should be scaled based on the expected use of memory, CPU, and network I/O.
When the autopilot feature is turned on, Magalix will apply pods and nodes scalability decisions according to pre-defined business rules.
Because it is hard to correlate all performance and capacity factors at the same time, Magalix monitors and generates recommendations with all layers and expected workloads in mind.
Our AI layer uses sophisticated algorithms to understand how pods, containers, and nodes will behave under different workloads. It is a multistage pipeline that mimics the human-driven process of understanding and
Magalix captures use patterns and creates predictions for resource consumption, automatically calibrating when needed.
Our AI intuitively scales up to meet workload
Monitoring thousands of data points, Magalix builds container profiles that help understand performance under different workloads.
“The value of AI and what Magalix has done is really taking this human judgement and automate it in a way that it’s more proactive than reactive.”
GM - Microsoft
“Over-provisioning is not going to be solved by human powered optimization. Machine learning will identify areas of deficiencies and help companies save money.
Partner — 500Startups
“We were very impressed with the technical competence and the white glove treatment we received so far.”
CTO — Medstreaming