If you aim for one of the easiest solutions for your chatbot project, the Basic Support Bot is the right choice.
To access the Template, please click here and select the Basic Support Bot Template in the Template overview on top of the Bot List page you will land on (above the fold).
The bot will help solve specific problems, and by incorporating end user input such as contextual information, it guides the end user to or through a process. Here is an overview of its capabilities:
- Smart assistant by answering FAQs
- Understanding end users' needs with the help of NLU,
- Linking to human support.
- Integrations to third-party systems to provide the bot with additional information.
In this article, we will cover the following:
- Different Color Framings
- KPI Tag Indications
- Selected Module Configurations
- Global Connections Configuration
Different Color Framings
On the bot building canvas, you can find several Modules in different color framings. Each color stands for a specific Module category or group. The overview of the color framing can be found on the left sidebar. From here, you can manage the visibility of selected groups.
|Start||Introduction to the conversation with the bot.|
|Fallback||Modules that are triggered whenever the bot cannot understand the end user's input. Read this article for more explanation: Fallback module|
|Exit||Any Module that relates to the end of a specific conversation|
|Handover||Linking to human support by, among others, triggering a transfer to live chat, by sending an email notification, or by creating a support ticket.|
|Send Message||Module category that closely relates to Handover. The modules provide an information collection flow to gather all important input, before sending out a message to your organization's service team.|
|Domains||Modules that will contain the content that is specific to your organization. It is separated into three different Domains 1, 2, and 3, as we believe that you will have more than one group of topics that you would like the bot to cover and relay answers to.|
|Technical issue||Conversational flow that serves to understand any technical problems the chatbot visitor might face.|
To check if the Webhooks have been executed correctly, we recommend you insert "Real Fallbacks". Read the article "Real Fallback" for Webhook Failure to learn more.
KPI Tag Indications
You can find Key Performance Indicator (KPI) tags assigned to specific Modules.
- Webhook KPI tag: Indicates in which Module a Webhook must be implemented in Module Connections.
- Start KPI tag: Shows the Starting Module. It is important that the checkbox "Make bot start message" is ticked in this Module's Message tab.
- Handover KPI tag: Points to Modules in which a transfer to a real person happens. This transfer can either be connected to live chat or create a message to be received by human agents.
- Fallback KPI tag: Marks Fallback Modules triggered whenever the bot does not understand the end user's input.
- KPI tag 4: Set for Module categories that contain organization-specific content. You may cluster this content following the Domains you have defined for your bot.
- KPI tag 5: Find out how many visits lead to a feedback rating
- KPI tag 6: Analyse how many users rated an answer as helpful (positive feedback)
- KPI tag 7: Analyse how many users rated an answer as not helpful (negative feedback)
We can now take a closer look at some Module configurations.
Selected Module Configurations
To ease your platform navigation, use Control+F (or Command+F on the Mac) and look for the specific Module titles as listed below.
|Starting Module||Note that next to saying hi to chatbot visitors, the Starting Module also sets expectations right. The bot informs the chatbot visitor about the fact that simple and short visitor messages are preferred.|
|Call to action to ask a question.||
The chatbot visitor is asked to phrase the request or question. Note that a feature called variation is used here, as the chatbot visitor is likely to come back to this Module. By using the variation feature, you give the bot answers a more human touch.
As this Module is also triggered after providing a helpful answer, it is valuable to separate it from the Starting Module.
Note how the end users' input to the question is saved as a value for the custom variable searchQuery in the Module's Connection tab. This variable appears three times as the end user might have more than one query.
The module connections are configured as such that the bot would check if a value for searchQuery already exists, and if so, save it as searchQuery2 and searchQuery3 accordingly.
|"Okay" to call to action.||Bear in mind that in human conversations, people often confirm what has been said previously. In this case, after the call to action to ask a question, your bot must be ready to interpret a confirmation from the chatbot visitor.|
|"Hello" to call to action.||Somehow comparable to the Module "Yes" to call to action, prepare your bot to answer a "hi" from the chatbot visitor as a response to the welcome message of the chatbot.|
|Fallback 1/3, 2/3, and 3/3||
Note that the Fallback Modules are not showing a dotted line in between. The reason for the missing line is that each Fallback Module is connected with the following one by being part of the previous Module's Fallback:
Looking at each Fallback Modules Connections will make this configuration clearer.
|Evaluation after given answer: Was it helpful?||
This Module provides you with insights into the quality of your chatbot's answers.
You may include this Module into the conversational flow after any content-rich bot answer, which is why this Module is a predecessor of the Modules below the Categories. Remember that the Categories contain content specific to your organization.
|"No": Answer was helpful||
Presumably, you like to know why a chatbot visitor has rated an answer as unhelpful. Accordingly, you ask the end user for more feedback, offer a transfer to human support, or leave it up to the end user to leave the chat.
By apologizing and creating easy next action options, you can sustain an engaging user journey and raise the understanding of the chatbot visitor.
Note the line [customVariable key=userName fallback="for that information"] in the bot message.
Here, you use the custom variable userName, that you have previously collected in Module "Collect name".
If the bot could not collect the end user's name, the fallback "for that information" would apply.
For example, the end user is called "Max":
If not end user name is provided (fallback):
Bot: "Thanks for that information."
|Do you have another question?||
If an answer was marked as helpful, the user is asked to phrase another question. Whatever this question is, it can be useful to save the input in a variable.
Lastly, check out the Global Connections of this Template.
Global Connections Configuration
If you are in doubt about the general functionality of Global Connections, learn more about it in this article: Basic Insights on Global Connections
Note that in the Support Bot Template, Module Connections are preferred over Global Connections. This means that Global Connections are trigger if not Module Connection applies to the specific end user's or system (in case of third-party integrations) input.
The Basic Support Bot will understand the following Intents at any point of the conversation if Global Connections are not deactivated (Global Connections are deactivated for any Module that starts with "Collect"):
- "Speak to a Human"
- "Waiting on email" (Group Technical issue)
- "System down" (Group Technical issue)
- "Login issue" (Group Technical issue)
- "Error messages" (Group Technical issue)