Features and integrations
Guardrails
Learn how to use guardrails preventing harmful, inappropriate, or unintended outputs
Guardrails on Bolna playground
Adding Guardrails
Adding your own Guardrail
1
Name
Give your config an identifiable name
2
Response
This is the action or message that gets triggered when any unwanted or inappropriate phrases or sentences are detected.
3
Threshold
This is the level or limit that determines when the system should react to unwanted words or phrases.
If the threshold is set low, the system will react to even slightly inappropriate language. If it’s set higher, only more severe cases will trigger a response.
4
Utterences
These are the unwanted or inappropriate utterences which you want to guard.
Was this page helpful?