AWS · Cloud service
Amazon Bedrock with OrchestrAI
Catalog exported 2026-09-02
Use Amazon Bedrock from chat: list models, invoke Claude or Llama, and build and query RAG knowledge bases.
OrchestrAI exposes 4 Bedrock operations: 3 are low-risk (read-only or low-impact), and 1 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
Data and ML teams use OrchestrAI to check which foundation models are available in a region, send a prompt to a model such as Claude or Titan, and set up a knowledge base for retrieval-augmented generation that they can then query in the same session. Listing, invoking, and querying are all low risk, and creating a knowledge base waits for your confirmation. There is no operation for attaching a data source to a knowledge base or triggering an ingestion sync, so populating one is still done through the console.
Every Bedrock operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Invoke Bedrock Model |
Invoke foundation model (Claude, Llama, Titan) | Low risk | No |
List Bedrock Models |
List available foundation models in AWS Bedrock | Low risk | No |
Query Bedrock Knowledge Base |
Query knowledge base for RAG | Low risk | No |
Create Bedrock Knowledge Base |
Create RAG knowledge base | Creates resources | 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 foundation models available in Bedrock in us-east-1
- Invoke Claude on Bedrock with this support ticket and summarize it in three bullet points
- Query the product-docs knowledge base for our refund policy on annual plans
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 create a Bedrock knowledge base?
- Yes, and the create operation is medium risk with confirmation, so you review the plan first. Data source attachment and ingestion are not covered, so you add documents in the console.
- Which models can OrchestrAI invoke through Amazon Bedrock?
- Any foundation model your account has access to, including Claude, Llama, and Titan. Invocation is rated low risk.
- Which Bedrock operations need an extra approval step?
- One operation carries a step-level approval gate on top of plan confirmation: Create Bedrock Knowledge Base. 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.