If your virtual assistant doesn't recognize the intent of the user, it activates the fallback trigger. You can encounter this in the following cases:
- If the brain recognizes the intent with a confidence level below the threshold you have set.
- If you have not connected the intent to a trigger that matches the dialogs you have already set up. You can do that for intents like
- If the brain does not recognize an appropriate answer to a question (wrong type or entity).
You can also use the fallback as a child node in a dialog. This means that the brain activates this trigger only when it is already inside the dialog of a parent node.
When the fallback is a child node, if the user types something that the brain cannot understand within a dialog, the message it gives the user is different than when the user is not in the dialog.