Use Forms

Create a New Form

1. In CXone, click the app selector and select Bot Builder.

2. Click the bot you want to work with.
3. Click Dialogues in the left icon menu.
4. In the right pane, click Forms and then click New Form.
5. Enter a name for your new form and press Enter.
6. Under Requested Slots, click Add Slot.
7. Select the Slot from the drop-down, then enter the Question the bot should ask the customer to get the correct information. For example, if your Slot is Name, your Question could be What is your name?
   View image

   
8. Repeat the previous two steps for any additional slots you want to add to the form.

Activate a Form

You need to include a form in a story Used to train bot for interaction handling based on intent and context or rule Used to define bot's response to messages that don't change with context. to describe when the bot should run the form. When the story or rule is triggered, the form will activate and the bot will start to ask the questions.

1. In CXone, click the app selector and select Bot Builder.

2. Click the bot you want to work with.
3. Click Dialogues in the left icon menu.
4. Add a new story or rule. In this example, the name could be Address Change.
5. Enter the message a customer may send. In this example, it could be I need to change my address.

   The bot attempts to assign an intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. If the intent is correct, click Confirm. Otherwise, select the correct intent from the list. If the intent you need does not exist, type an intent name into the search field and click Create intent. This creates a new intent based on this message. You can add more examples to the intent later.

6. Hover over the plus sign until it changes to a bot icon, click the Forms tab, and then click the Activate action.
   View image

   
7. In the bot response, click the drop-down to select a form.
   View image

   

Submit a Form

A form is automatically submitted once all required slots are filled. However, your bot will continue to listen for the next user message, rather than automatically acknowledge that the form was submitted. This can leave the customer wondering whether their submission was successful. For a better customer experience, you can use a rule Used to define bot's response to messages that don't change with context. or story Used to train bot for interaction handling based on intent and context to define what the bot should do after a form is submitted.

Any slots collected from the customer can be used as variables to show the bot has collected the data. To use a variable, enclose the name of the entity Keyword or phrase defined in your company profile in Interaction Analytics. Related to an entity type. Can include variants. in curly brackets.

1. In CXone, click the app selector and select Bot Builder.

2. Click the bot you want to work with.
3. Click Dialogues in the left icon menu.
4. Add a new story or rule. In this example, the name could be Submit Address Change.
5. Click Add condition, then click Active Form. Click the drop-down to select a form. This ensures that the rule only runs if the specified form is active.
6. Hover over the plus sign until it changes to a bot icon, click the Forms tab, and then click the Submit action.
   View image

   
7. In the bot response, click the drop-down to select a form.
8. Add a message from your bot letting the customer know their submission was successful.
   View image

   

Cancel a Form

A customer may change their mind in the middle of filling out a form and decide not to complete it. This can turn into a delicate situation with a customer, so defining a way for your bot to handle this gracefully is a good idea.

1. In CXone, click the app selector and select Bot Builder.

2. Click the bot you want to work with.
3. Click Dialogues in the left icon menu.
4. Click the Rules tab.
5. Click New rule.
6. Enter a name for the rule. In this example, the name could be Cancel Address Change.
7. Click Add condition, then click Active Form. Click the drop-down to select a form. This ensures that the rule only runs if the specified form is active.
8. Enter the message a customer may send. In this example, it could be Nevermind.

   The bot attempts to assign an intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. If the intent is correct, click Confirm. Otherwise, select the correct intent from the list. If the intent you need does not exist, type an intent name into the search field and click Create intent. This creates a new intent based on this message. You can add more examples to the intent later.

9. Hover over the plus sign until it changes to a bot icon, click the Forms tab, and then click the Cancel action.
   View image

   
10. Add a message from your bot letting the customer know their request was cancelled.
    View image

    

Interruptions

Once a bot starts asking form questions, it will keep doing so until all the slots in the form are filled and is not able to process other things. Customers do not always answer all of a form's questions from start to finish. They may ask questions, change their mind, or otherwise change the subject in the middle of the form. These are called interruptions. To handle situations like this, you can write rules or stories that include common interruptions.

An interruption with a recognized intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish triggers one of the following behaviors:

• If the recognized intent is in a rule Used to define bot's response to messages that don't change with context., the bot responds to an interrupted message based on the rule design. The bot then returns to the form loop.
• If the recognized intent is in a story Used to train bot for interaction handling based on intent and context, the bot response may vary based on the story design. Once the intent is fulfilled, the bot returns to the form loop.
• If the recognized intent has low confidence, the bot responds with the NLU fallback phrase, then continues in the form loop.