AWS · Cloud service
Amazon Elastic Kubernetes Service with OrchestrAI
Catalog exported 2026-09-02
Provision Amazon EKS from chat: clusters, managed node groups, Fargate profiles, add-ons, and inspection.
OrchestrAI exposes 7 EKS operations: 4 are low-risk (read-only or low-impact), 2 create or modify resources and run only after you confirm the plan, and 1 is destructive and requires a typed risk phrase. 1 of them also carries a step-level approval gate.
What teams use it for
Platform teams use OrchestrAI to create an EKS control plane, add a managed node group on ON_DEMAND or SPOT capacity, define a Fargate profile for serverless pods, install add-ons like VPC CNI and the EBS CSI driver, and describe or list clusters across a region. Deleting a cluster is critical risk and requires a typed risk phrase. Kubernetes version upgrades, node group deletion, and anything at the kubectl level are not covered, so workload changes inside the cluster are handled with your usual tooling.
Every EKS operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Create EKS Add-on |
Install a managed EKS add-on (CoreDNS, kube-proxy, VPC CNI, EBS CSI driver) | Low risk | No |
Create EKS Fargate Profile |
Create an EKS Fargate profile for serverless pod execution without managing worker nodes | Low risk | No |
Describe EKS Cluster |
Get detailed information about an EKS cluster | Low risk | No |
List EKS Clusters |
List all EKS clusters in a region | Low risk | No |
Create EKS Cluster |
Create a new Amazon EKS Kubernetes cluster | Creates resources | No |
Create EKS Managed Node Group |
Create a managed node group for an EKS cluster with configurable instance types, scaling, and capacity type (ON_DEMAND or SPOT) | Creates resources | No |
Delete EKS Cluster |
Delete an Amazon EKS cluster and all associated resources | Destructive | Yes |
Risk tiers come from the catalog: low is read-only or low-impact, medium creates resources and is reversible, high modifies existing resources, destructive may lose data. Every plan that creates or changes resources is shown with its cost estimate and waits for your confirmation. Operations marked with a step-level approval pause again on their own step. Destructive operations require a typed risk phrase.
Prompts that work
- Create an EKS cluster named platform-eks in us-east-1 on Kubernetes 1.31 in the platform-vpc private subnets
- Add a SPOT node group called batch-nodes to platform-eks with m6i.large instances scaling from 1 to 8
- Install the aws-ebs-csi-driver add-on on platform-eks and describe the cluster
Before anything runs
Every mutation shows its plan, cost estimate, and blast radius, then waits for your confirmation. Destructive operations require a typed risk phrase. Credentials are minted per run through OIDC federation and discarded afterward; nothing you create here is invisible later, because every resource lands in the desired-state ledger where drift is detected and can be converged. Details on the security page.
Frequently asked questions
- Can OrchestrAI upgrade an EKS cluster's Kubernetes version?
- No, it creates clusters, node groups, Fargate profiles, and add-ons and can describe or delete clusters, but version upgrades are not available.
- What protection is there when OrchestrAI deletes an EKS cluster?
- Cluster deletion is critical risk. You confirm the plan and type the risk phrase before the cluster and its associated resources are removed.
- Which EKS operations need an extra approval step?
- One operation carries a step-level approval gate on top of plan confirmation: Delete EKS Cluster. It is classed destructive and cannot run without a typed risk phrase.
Other AWS services
Related integrations
Try it on your own account
Connect your cloud read-only and see your resources, drift, and costs before anything runs. $5 minimum to start. Unused credits refunded in your first 14 days.
Unused credits refunded in your first 14 days.