NetSuite + governed AI agents
NetSuite tends to be the system of record nobody wants touched by automation. Scoped, reviewed, approval-gated access is the version of AI access an ERP owner will actually sign off on.
Connecting NetSuite
| Definition | Import the SuiteTalk REST record specification for the record types you want reachable. |
|---|---|
| Credential | Token-based authentication. Store the consumer and token pair in your vault under one reference. |
| Stored as | A secret:// reference to your own vault. FlozentAi never holds the value. |
Actions teams usually publish
Action names are yours to choose during review — these are the shapes most teams end up with. Anything that writes is confirmation-gated unless you deliberately publish it otherwise.
| Action | Kind | What it does |
|---|---|---|
customer.get | Read | Read a customer record. |
salesorder.list | Read | List sales orders by status. |
salesorder.update | Write | Amend an order after approval. |
What people build with it
- Order-status answers inside a customer-facing assistant, scoped to that customer’s tenant.
- An internal agent that prepares order amendments for an operations lead to approve.
There is no field in the console that accepts a token or a password. You store the secret in your vault and give FlozentAi a reference; the runtime resolves it inside the execution layer, after the policy decision.
NetSuite questions
Can we start read-only?
Yes, and this is the integration where you should. Publish the read actions, run them for a few weeks, and look at the traces before publishing anything that writes.
Use cases that involve NetSuite
Connect NetSuite the governed way.
Import the specification, review what it found, and publish only what you want reachable.