Activate an input guardrail to enforce one content policy for your Optimizely Opal instance. The instance-level input guardrail applies to the requests Opal handles directly. To screen a specialized agent, assign a per-agent guardrail instead.
Prerequisites
The guardrail must already exist and have a trained model with the status Ready. To create and train one, see Create and train an input guardrail.
Activate the guardrail
To activate a guardrail for your instance, complete the following steps:
-
Go to Settings > Chat > Active Input Guardrail.
-
Select the trained guardrail from the Active Input Guardrail drop-down list.
-
Select the version from the Version drop-down list. Only versions with the status Ready display in this list.
The guardrail takes effect immediately for all requests across your Opal instance.
Only one guardrail is active per instance at a time. Activating a new guardrail replaces the previously active one. To deactivate all guardrails, clear the selection in the Active Input Guardrail drop-down list.
Related documentation
Learn more about input guardrails in the following articles:
Article is closed for comments.