If the user types a response that does not match any of your questions, use a Catch-all to select which passage the chatbot should use to respond. There are a few specific scenarios you can configure separately:
- Catch-all for unexpected new users
- Catch-all for unexpected attachments
- Catch-all for long responses
- Catch-all within specific conversations
- Catch-all for specific languages
Catch-all settings are versioned: these changes are stored in the chatbot version, and will not be applied until they are published.
Catch-alls are configured in your chatbot's Fallback settings. 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.
Catch-All - Unexpected Interaction From New User
Sometimes a new user may start an interaction with your chatbot in a way you didn't plan for. To make sure all new users receive the same welcome experience with your chatbot, you can configure a specific Catch-All passage for unexpected new users. This passage is sent when a chatbot receives an interaction from a new user that it hasn't sent the first passage to.
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.
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.
The same Long Text Inputs Catch-All response is used in any conversation when a user sends a response longer than you specify. This can't be set at a per-conversation level.
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.
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.
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.
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.
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.
You can specify a Catch-All response that is sent when the user's response does not match any questions in your chatbot but does match a language supported in your NLP settings.
You don't need to specify the languages in a particular order; your chatbot's natural language processing AI will determine the best match from the languages in your NLP Settings. If you have a language configured in your NLP Settings that does not have a language-specific catch-all configured, then your normal conversation or default catch-all settings will be used instead.
To add a Language-specific Catch-all:
- Make sure the language you want to add a catch-all for is configured in your NLP Settings.
English is always configured by default in your NLP Settings.
- In your Fallbacks Settings, make sure Language-Specific Catch-All is selected.
- Click + Language.
- Select the language you want to create a catch-all for.
- Select the conversation and passage that should be sent when the chatbot detects that language but can't match it to an existing question.
The same Language-specific Catch-All response is used for each specified language throughout your chatbot and cannot be configured per-conversation. If your chatbot user sends an extremely long message in a language that you have configured a catch-all for (other than English), the language-specific catch-all will be sent instead of the long-text catch-all.
You should create a separate passage for each language you specify, to give your chatbot user the best experience.
Article is closed for comments.