Conversation canvas tutorial

Available in Classic and VPC

Create conversation flow with Conversation canvas

Conversation canvas is a feature in CLOVA Chatbot Builder that lets you design conversation flows and create AiCall bots. This document guides you through how to create a basic conversation flow that starts with a welcome message, and create a simple AiCall bot out of it.

Create conversation flow

First, create a basic conversation flow for AiCall.

1. Click Conversation canvas in the menu on the left.
2. Click [+] at the upper left on the canvas. You can see various types of conversation boxes in the dropdown menu.
3. Drag Welcome message to the canvas, and add conversation boxes you want that fit in the conversation flow.
4. Click the connection point at the bottom right of the conversation box where you want to start the connection, then drag the arrow to the box you want to connect.

{height="" width="70%"}
{height="" width="70%"}

• When connecting system response
  

• When connecting context
  

5. You can end the conversation by connecting a Finish call box at the end of the conversation flow.
   

Create an AiCall with conversation canvas 1: Package pickup

You have created a basic conversation flow, now it's time to see how to create an AiCall bot which carries out a service in full. In the first exercise, you will create an AiCall bot that lets a courier company confirm a customer's intent to request a package pickup.

Create welcome message

First, write a welcome message that briefly introduces the courier company to the customer.

1. Click [+], and drag the welcome message box to the canvas.
2. Clicking on that welcome message will cause an editing panel to appear on the right. Fill the system response field with the message "Hello, this is OO Delivery, dedicated to sincere service." After entering this, click [Save].

Create system response

Write a system response asking the customer whether they want a package pickup.

1. Click [+], and drag the system response box to the canvas.
2. Write "Do you want to send a package?" in the answer field of the system response box, and click [Save]. The saved answer will be displayed under the button.
   
3. Connect the welcome message box and the system response box to create a conversation flow. Click System response in the welcome message, and connect it to the system response box by dragging the arrow.
   

Create "Yes" and "No" options with general conversation

Based on whether the customer wants a package pickup, create two conversation flows depending on whether they respond 네 or 아니요.

1. Click [+], and drag a general conversation box to the canvas.

2. In the editing panel, double-click the title, then change the conversation name to 대답_yes.

3. In the question field of the [User utterance] tab, enter 네, and click [Save]. Entering various user utterances helps the model recognize similar utterances.

4. Enter the system response. From the [System response] tab, enter the answer "Items that could be damaged, such as food or home appliances, cannot be shipped by courier. Make sure the contents are general items such as clothing, accessories, or books." After entering this, click [Save]. The answer entered will be displayed under the [Save] button.
   

5. Create the conversation flow for "No" the same way. Drag a General conversation box to the canvas and change the box name to 대답_no.
   In the [User utterance] tab, enter "No" as the question. From the [System response] tab, enter the answer "I see. Thank you for using OO Delivery.

6. Click the output context connection point of the previously created system response box, then drag the arrow to the 대답_yes and 대답_no boxes.
   

Finish call

If the customer does not want a package pickup, end the conversation by connecting a Finish call box.

1. Click [+], and drag the Finish call box to the canvas.
2. In System response of the 대답_no box, click the dot and drag the arrow to connect it to the Finish call box.
   

Save conversation

The conversation content is automatically saved. To save manually, press [Ctrl] + [S] (Windows) or [Command] + [S] (macOS) at the top.

Wrap-up

So far, you have created an AiCall bot that confirms a customer's intent to request a package pickup. The completed conversation flow looks like this. In the next exercise, you will connect conversation groups to create a flow that checks the phone number of a customer who wants a package pickup.

Conversation group

In addition to the basic conversation flow, an AiCall bot may need responses to frequently asked questions such as business hours or parking location, as well as a recovery scenario that returns to the previous flow when a reservation fails.

Managing all scenarios in 1 location makes the conversation flow complex and difficult to edit. Using conversation groups lets you manage conversation flows separately by scenario.

Create conversation group

Create a new conversation group to manage conversation flows by scenario.

1. To create a new group, click [+] next to the [HOME] tab.
2. Double-click the group name and enter the name you want.
3. Create a conversation flow in each conversation group.
   

Connect conversation groups

If you have created multiple conversation groups, use a conversation link box to connect the conversation flow between groups.

1. Drag a conversation link box to the canvas.
2. Click the conversation group to connect and conversation name.
3. Then, connect the boxes. The location to connect depends on the conversation type selected (e.g., general conversation or system response).
   • Situation 1: If the type of the selected conversation is a general conversation box, click the dot of the output context in the general conversation box, and drag the arrow to connect it to Conversation group 1.
     
   • Situation 2: If the type of the selected conversation is a system response box, click the dot of system response, and drag the arrow to connect it to the Conversation group 1 box.
     
4. If the connection was done right, the connected conversation group will show the link box to another conversation.
   

Create an AiCall with conversation canvas 2: Package pickup

In the first exercise, you confirmed the customer's intent to request a package pickup. In this exercise, you will create a conversation flow that checks the phone number of a customer who wants a package pickup, and manage it by separating it into its own conversation group.

1. Create an AiCall with conversation canvas 1: Add a general conversation popup window to the basic conversation flow created in Package pickup.

2. Change the name of the general conversation to 배송가능물품_확인, enter 네 as the question in the [User input] tab, and click [Save].

3. Select No answer as the response type under the [System response] tab, and then click [Save].
   

4. Click the dot of the output context in the 대답_yes box, and drag the arrow to connect the 배송가능물품_확인 popup window you just created.
   

5. Next, click [+] next to the [HOME] tab menu to create a new group, and change the group name to "Check phone number."
   

6. Drag the system response popup window to the Check phone number group canvas.
   

7. Change the name of the system response popup window to 시스템응답_전화번호. Enter 고객님의 전화번호를 알려주시겠어요? in the response field, and click [Save].

   • The successfully registered answer will be displayed under the button.
     

8. Connect this flow to the conversation flow in HOME. Go back to the [HOME] tab, which has the basic conversation flow, and drag a Conversation link box onto the conversation canvas.
   

9. In the editing panel, select 전화번호 확인 as the conversation group to connect, and then select 시스템응답_전화번호 as the conversation box to connect.
   

10. Click the output context connection point of 배송가능물품_확인 상자, then drag the arrow to the conversation link box.
    

11. The complete flow looks like this.
    

12. To check if the connection has been made successfully, go to the Check phone number tab, which is the connected conversation group, and check if another conversation link box appears in front of the connected conversation box.
    

All steps have been completed. The conversation is automatically saved. If needed, you can save manually using the top menu or the [Ctrl] + [S], [Command] + [S] keys.

Export conversation list

Through exporting and importing the conversation list, you can seamlessly connect the conversation canvas and the chatbot's conversation list. After creating a conversation flow using the conversation canvas, you can export it to the conversation list. Conversely, you can import a conversation from the conversation list into the conversation canvas to check and edit the conversation flow.

1. Click [Export] at the upper right. If an error occurs during an export, a popup window will appear with the error content.
   

2. To see the exported conversations, select Conversation list from the menu on the left. Check that the exported conversation is displayed.
   

FAQ

1. What are export and import?

• Conversations created using the conversation canvas are saved separately, and not synced to the chatbot until you export or import manually.
• When you click Export the conversations created using the conversation canvas will be exported to the chatbot. On the other hand, you can click Import to import conversations created using a chatbot to the conversation canvas.

2. How do I resolve an export failure?

• You cannot export the conversation if you do not enter a phone number in the Forward to a number popup window.
• If the export fails, the cause of failure is displayed in a notification window. Fix the error, and export again.

3. Can I use a chatbot and conversation canvas at the same time?

• You can sync a chatbot and conversation canvas using the export and import features, but caution is required in the following cases.

4. What are the functions of each conversation box?

The functions of each conversation box are as follows.