Federator.ai acquires operational data collected by monitoring services. As long as those monitoring services provide enough operational data (at least a month is recommended), Federator.ai can produce its predictions within a few hours.
The longer the monitoring services feed data to our machine learning-based algorithms, the more accurate the result of predictions can be presented by Federator.ai.

Federator.ai utilizes a machine learning algorithm to build different featured models mirroring real operations, aka Digital Twins.
With the help of AI, hundreds of the features in the application workloads can be rapidly identified and inducted to fit models so that the predictions Federator.ai provides can be fast but reliable.

Federator.ai uses an AI algorithm to predict and recommend the right amount of resource usage for containers, namespaces, and clusters. In many cases, Federator.ai’s recommendations lead up to 70% of cost savings.
Since the usage of resources can be precisely predicted, you can also take advantage of the cost comparisons with different public clouds, so that the opportunities for potential savings in the future can be captured.

1. Auto resource provisioning to adjust the right amount of resource usage for containers and namespaces.
2. Prediction-based HPA that automatically scales containers based on predicted workloads.
3. Application-aware scaling for Kafka consumer and Web Services using NGINX ingress controller.

Yes, Federator.ai provides resource predictions/recommendations and cost analysis for the VMware VM cluster and AWS VM Cluster.

Yes, Federator.ai can be integrated with Gitlab and Terraform when deploying applications to Kubernetes clusters.