AWS · Cloud service
Amazon Redshift with OrchestrAI
Catalog exported 2026-09-02
Work with Amazon Redshift from chat: create clusters, list them, run SQL, and fetch query results.
OrchestrAI exposes 4 Redshift operations: 2 are low-risk (read-only or low-impact), and 2 create or modify resources and run only after you confirm the plan. 1 of them also carries a step-level approval gate.
What teams use it for
Analytics teams use OrchestrAI to list Redshift clusters in an account, run a SQL statement against a cluster, retrieve the result set once it completes, and provision a new cluster for a project. Cluster creation is high risk with confirmation, executing a query is medium risk, and listing and fetching results are low risk. There is no operation to pause, resize, snapshot, or delete a cluster, so lifecycle management beyond creation stays in the console.
Every Redshift operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Get Redshift Query Results |
Get Redshift query results | Low risk | No |
List Redshift Clusters |
List Redshift clusters | Low risk | No |
Execute Redshift Query |
Execute SQL query on Redshift | Creates resources | No |
Create Redshift Cluster |
Create Redshift cluster | Modifies existing | 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
- List the Redshift clusters in us-west-2 and their node types
- Run SELECT count(*) FROM sales.orders WHERE order_date >= '2026-08-01' on the analytics-cluster and show the result
- Create a 2-node ra3.xlplus Redshift cluster named reporting-dev in the data-subnet group
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 run SQL on Amazon Redshift?
- Yes, the execute_query operation submits a statement and get_query_results returns the rows. Query execution is medium risk because statements can modify data.
- Can OrchestrAI pause or delete a Redshift cluster?
- No, only creation and listing are covered for cluster lifecycle; pause, resize, and delete are done in the console.
- Which Redshift operations need an extra approval step?
- One operation carries a step-level approval gate on top of plan confirmation: Create Redshift Cluster. None of them is classed destructive.
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.