Use the Fallbacks settings to define how your chatbot handles unexpected behaviour such as questions it can't match, unexpected attachments, and repeated responses.
Fallback settings are versioned
When you make changes to your chatbot's Fallback settings, these changes are stored in the chatbot version. Changes here will not be applied until they are published.
To open the Fallbacks settings:
- Select your team, and the chatbot you want to edit.
- Open the Manage section of the left navigation and click Settings.
- Click Fallbacks.
Remember to save your changes
Save your changes before you navigate away using the Save button at the bottom of the screen.
If the user types a response that does not match any of your questions, select which passage the chatbot should use to respond.
Catch-All - Unexpected Attachments
You can configure a separate Catch-All passage to use if the user sends an unexpected attachment such as an image, sticker, or other file. For example, you may want to display a different message when the user sends an attachment, or use a script to interpret the sticker or file and direct the chatbot to another passage.
This applies to all conversations
The same Unexpected Attachments Catch-All response is used in any conversation when a user uploads an unexpected attachment. This can't be set at a per-conversation level.
Catch-All - Long Text Inputs
Long replies from a user can be difficult to match to the correct question. Rather than using the standard Catch-All passage response, it can be helpful to guide the user to try a shorter reply.
Before you turn this setting on...
Turning on the Long Text Inputs Catch-All will mean any typed reply above your word limit will automatically go to the Long Text Inputs Catch-All passage, even if it would have otherwise matched with a question, or you have specified a different Catch-All response for the conversation.
If you want to treat replies over a certain length differently:
- Turn this setting on.
- Type the number of words the chatbot should consider to be a long reply.
- Select which passage the chatbot should use to respond when the user types a long reply.
You can specify a Catch-All response that is used only when the user is in a specific conversation flow. If the conversation Catch-All is enabled, it takes precedence over the chatbot's default Catch-All. You can specify a Conversation Catch-All for as many different conversations as you need to.
Catch-Alls with multi-level conversation context
If you set a Conversation Catch-All for a parent conversation, that Catch-All response does not apply to child conversations within the parent conversation. You must specify a Conversation Catch-All for any conversation where you do not want the default Catch-All used.
If the user types a response that does not match a question while they are within this conversation flow, select the passage the chatbot should use to respond.
To set a Conversation Catch-All:
- Make sure Conversation Catch-All is selected.
- Select the conversation you want to specify a different Catch-All response for.
- Select the passage to use as the Catch-All response.
- Click Save.
Where are my changes?
Because these settings impact individual conversations, per-conversation Catch-All updates are displayed in your version history as conversation changes. These changes will appear in the draft stage in Versions upon save.
Sometimes a user types a reply that matches a question the chatbot has already answered, and the user receives the same passage again. In some conversations, this is to be expected: a package-tracking chatbot might be asked where a package is several times, and identical replies won't seem out of place. But for conversations where the user does not expect the same response again, it can frustrate the user.
The Intellimem feature steps in when the chatbot would have otherwise repeated its response and sends a different response so the conversation feels more natural. You can use these responses to guide the user into rephrasing their question, or asking to talk to a human.
Intellimem (per Conversation)
You can configure this at the chatbot level if most of your conversations should not repeat responses. If some of your conversations should repeat responses but others shouldn't, or you want to send different passages in different conversations, you can configure Intellimem per-conversation. Intellimem will use the conversation-specific setting when in conversations you've specified, and the default setting otherwise.
Intelliment and multi-level conversations:
If you set a Intellimem for a parent conversation, that same Intellimem setting also applies to any child conversations within the parent conversation. You can specify a different Intellimem for the child conversations if required.
|When first repeat, use||Select the passage to send the first time a passage would have been repeated.|
|Any subsequent repeat, use||Select the passage to send after the first repeat.|
|Advanced||Select whether to use Intellimem for all matched questions, or only when the Catch-All response is being triggered.|
|Intellimem Expiry Period||Allow the original passage to be sent again after this many minutes.|
Where are my changes?
Because these settings impact individual conversations, per-conversation Intellimem updates are displayed in your version history as conversation changes. These changes will appear in the draft stage in Versions upon save.