Creating a dialog

Condition artifacts

You can use one or more of the following artifacts in any combination to define a condition:

• Context variable: The node is used if the context variable expression that you specify is true. Use the syntax, $variable_name:value or $variable_name == 'value'.

  For node conditions, this artifact type is typically used with an AND or OR operator and another condition value. That's because something in the user input must trigger the node; the context variable value being matched alone is not enough to trigger it. If the user input object sets the context variable value somehow, for example, then the node is triggered.

  Do not define a node condition based on the value of a context variable in the same dialog node in which you set the context variable value.

  For response conditions, this artifact type can be used alone. You can change the response based on a specific context variable value. For example, $city:Boston checks whether the $city context variable contains the value, Boston. If so, the response is returned.

  For more information about context variables, see Context variables.

• Entity: The node is used when any value or synonym for the entity is recognized in the user input. Use the syntax, @entity_name. For example, @city checks whether any of the city names that are defined for the @city entity were detected in the user input. If so, the node or response is processed.

  Consider creating a peer node to handle the case where none of the entity's values or synonyms are recognized.

  For more information about entities, see Defining entities.

• Entity value: The node is used if the entity value is detected in the user input. Use the syntax, @entity_name:value and specify a defined value for the entity, not a synonym. For example: @city:Boston checks whether the specific city name, Boston, was detected in the user input.

  If you check for the presence of the entity, without specifying a particular value for it, in a peer node, be sure to position this node (which checks for a particular entity value) before the peer node that checks only for the presence of the entity. Otherwise, this node will never be evaluated.

  If the entity is a pattern entity with capture groups, then you can check for a certain group value match. For example, you can use the syntax: @us_phone.groups[1] == '617' See Storing and recognizing pattern entity groups in input for more information.

• Intent: The simplest condition is a single intent. The node is used if, after your assistant's natural language processing evaluates the user's input, it determines that the purpose of the user's input maps to the pre-defined intent. Use the syntax, #intent_name. For example, #weather checks if the user input is asking for a weather forecast. If so, the node with the #weather intent condition is processed.

  For more information about intents, see Defining intents.

• Special condition: Conditions that are provided with the product that you can use to perform common dialog functions. See the Special conditions table in the next section for details.

Special conditions

Condition syntax details

Use one of these syntax options to create valid expressions in conditions:

• Shorthand notations to refer to intents, entities, and context variables. See Accessing and evaluating objects.

• Spring Expression (SpEL) language, which is an expression language that supports querying and manipulating an object graph at run time. See Spring Expression Language (SpEL) language for more information.

You can use regular expressions to check for values to condition against. To find a matching string, for example, you can use the String.find method. See Methods for more details.

Simple text response

If you want to provide a text response, simply enter the text that you want your assistant to display to the user.

To include a context variable value in the response, use the syntax $variable_name to specify it. See Context variables for more information. For example, if you know that the $user context variable is set to the current user's name before a node is processed, then you can refer to it in the text response of the node like this:

Hello $user

If the current user's name is Norman, then the response that is displayed to Norman is Hello Norman.

If you include one of these special characters in a text response, escape it by adding a backslash (\) in front of it. If you are using the JSON editor, you need to use two backslashes to escape (\\). Escaping the character prevents your assistant from misinterpreting it as being one of the following artifact types:

The built-in integrations support the following Markdown syntax elements:

If you don't code a link when you specify a phone number in a text response, it is not converted to a telephone link anywhere except in a web chat integration that is accessed from a mobile device.

The "Try it out" pane does not support Markdown syntax currently. For testing purposes, you can use the assistant Preview to see how the Markdown syntax is rendered.

The "Try it out" pane, assistant Preview, and web chat integration support HTML syntax. The Slack and Facebook integrations do not.

Hi.
How are you today?

Rich responses

You can return responses with multimedia or interactive elements such as images or clickable buttons to simplify the interaction model of your application and enhance the user experience.

In addition to the default response type of Text, for which you specify the text to return to the user as a response, the following response types are supported:

• Connect to human agent: The dialog calls a service that you designate, typically a service that manages human agent support ticket queues, to transfer the conversation to a person. You can optionally include a message that summarizes the user's issue to be provided to the human agent.

• Channel transfer: The dialog requests that the conversation be transferred to a different channel (for example, from the Slack integration to the web chat integration).

• Image: Embeds an image into the response. The source image file must be hosted somewhere and have a URL that you can use to reference it. It cannot be a file that is stored in a directory that is not publicly accessible.

• Video: Embeds a video player into the response. The source video must be hosted somewhere, either as a playable video on a supported video streaming service or as a video file with a URL that you can use to reference it. It cannot be a file that is stored in a directory that is not publicly accessible.

• Audio: Embeds an audio clip into the response. The source audio file must be hosted somewhere and have a URL that you can use to reference it. It cannot be a file that is stored in a directory that is not publicly accessible.

• iframe: Embeds content from an external website, such as a form or other interactive component, directly within the chat. The source content must be publicly accessible using HTTP, and must be embeddable as an HTML iframe element.

• Option: Adds a list of one or more options. When a user clicks one of the options, an associated user input value is sent to your assistant. How options are rendered can differ depending on the number of options and where you deploy the dialog.

• Pause: Forces the application to wait for a specified number of milliseconds before continuing with processing. You can choose to show an indicator that the assistant is working on typing a response. Use this response type if you need to perform an action that might take some time.

• Search skill: Searches an external data source for relevant information to return to the user. The data source that is searched is a Discovery service data collection that you configure when you add a search skill to the assistant that uses this dialog skill.

  This response type is available only to users of paid plans.

• User-defined: If you use the JSON editor to define the response, you can create your own user-defined response type. For more information, see Defining responses using the JSON editor.

Different integrations have different capabilities for displaying rich responses. If you want to define different responses that are customized for different channels, you can do so by editing the response using the JSON editor. For more information, see Targeting specific integrations.

To add a rich response, complete the following steps:

1. Click the dropdown menu in the Assistant responds field to choose a response type, and then provide any required information.

   For more information, see the following sections:

   • Connect to human agent

   • Channel transfer

   • Image

   • Option

   • Pause

   • Search skill

     This response type is only visible to users of paid plans.

   • Text

2. To add another response type to the current response, click Add response type.

   You might want to add multiple response types to a single response to provide a richer answer to a user query. For example, if a user asks for store locations, you could show a map and display a button for each store location that the user can click to get address details. To build that type of response, you can use a combination of image, options, and text response types. Another example is using a text response type before a pause response type so you can warn users before pausing the dialog.

   You cannot add more than 5 response types to a single response. This means that if you define three conditioned responses for a dialog node, each conditioned response can have no more than 5 response types added to it.

   You cannot add more than one Connect to human agent or more than one Search skill response type to a single dialog node.

   Do not add more than one option response type to a single dialog node because both lists are displayed at once, but the customer can choose an option from only one of them.

3. If you added more than one response type, you can click the Move up or down arrows to arrange the response types in the order you want your assistant to process them.

Adding a Connect to human agent response type

If your client application is able to transfer a conversation to a person, such as a customer support agent, then you can add a Connect to human agent response type to initiate the transfer. Some of the built-in integrations, such as web chat and Intercom, support making transfers to service desk agents. If you are using a custom application, you must program the application to recognize when this response type is triggered.

If you want to take advantage of the containment metric to track your assistant's success rate, add this response type to your dialog or use an alternate method to identify when customers are directed to outside support. For more information, see Measuring containment.

To add a Connect to human agent response type, complete the following steps:

1. From the dialog node where you want to add the response type, click the dropdown menu in the Assistant responds field, and then choose Connect to human agent.

2. Optional. Add a message to share with the human agent to whom the conversation is transferred in the Message to human agent field.

3. Add a message to show to the customer to explain that they are being transferred.

   You can add a message to show when agents are available and a message to show when agents are unavailable. Each message can be up to 320 characters in length.

   Web chat built-in service desk integrations only: The text you add to the Response when agents are online and Response when no agents are online fields is used for transfers in web chat version 3 and later. If you don't add your own messages, the hint text (the grayed out text that is displayed as the example messages) is used.

   If you use this response type in multiple nodes and want to use the same custom text each time, but don't want to have to edit each node individually, you can change the default text that is used by the web chat. To change the default messages, edit the language source file. Look for the default_agent_availableMessage and default_agent_unavailableMessage values. For more information about how to change web chat text, see Languages.

4. Optional: If the channel where you deploy the assistant is integrated with a service desk, you can add initial routing information to pass with the transfer request.

   • Pick the integration type from the Service desk routing field.

   • Add routing information that is meaningful to the service desk you are using.

     Service desk routing options

     Service desk type	Routing information	Description
     Salesforce	Button ID	Specify a valid button ID from your Salesforce deployment. For more information, see Adding routing logic for Salesforce transfers.
     Zendesk	Department	Specify a valid department name from your Zendesk account. For more information, see Adding routing logic for Zendesk transfers.

The dialog transfer does not occur when you test dialog nodes with this response type in the "Try it out" pane of the dialog skill. You must access a node that uses this response type from the Preview button for the assistant to see how your users will experience it.

Adding a Channel transfer response type

If your assistant uses multiple integrations to support different channels for interaction with users, there might be some situations when a customer begins a conversation in one channel but then needs to transfer to a different channel.

The most common such situation is transferring a conversation to the web chat integration, in order to take advantage of web chat features such as service desk integration.

Currently, the web chat is the only supported target for a channel transfer.

Only the following integrations can initiate a channel transfer: - Slack - Facebook Messenger - WhatsApp

Other integrations ignore the Channel transfer response type.

To add a Channel transfer response type, complete the following steps:

1. From the dialog node where you want to add the response type, click the dropdown menu in the Assistant responds field, and then choose Channel transfer.

2. Optional. In the Message before link to web chat field, edit the introductory message to display to the user (in the originating channel) before the link that initiates the transfer. By default, this message is OK, click this link for additional help. Chat will continue on a new web page.

3. In the URL to web chat field, type the URL for your website where the web chat widget is embedded.

In the integration that processes the Channel transfer response, the introductory message is displayed, followed by a link to the URL you specify. The user must then click the link to initiate the transfer.

When a conversation is transferred from one channel to another, the session history and context are preserved, so the destination channel can continue the conversation from where it left off. Note that the message output that contains the Channel transfer response is processed first by the channel that initiates the transfer, and then by the target channel. If the output contains multiple responses (perhaps using different response types), these will be processed by both channels (before and after the transfer). If you want to target individual responses to specific channels, you can do so by editing the response using the JSON editor. For more information, see Targeting specific integrations.

Adding an Image response type

Sometimes a picture is worth a thousand words. Include images in your response to do things like illustrate a concept, show off merchandise for sale, or maybe to show a map of your store location.

To add an Image response type, complete the following steps:

1. Choose Image.

2. Add the full URL to the hosted image file into the Image source field.

   The image must be in .jpg, .gif, or .png format. The image file must be stored in a location that is publicly addressable by an https: URL.

   For example: https://www.example.com/assets/common/logo.png.

   If you want to display an image title and description above the embedded image in the response, then add them in the fields provided.

   To access an image that is stored in IBM Cloud® Object Storage, enable public access to the individual image storage object, and then reference it by specifying the image source with syntax like this: https://s3.eu.cloud-object-storage.appdomain.cloud/your-bucket-name/image-name.png.

   Some integration channels ignore titles or descriptions.

Adding a Video response type

Include videos in your response to share how-to demonstrations, promotional clips, and so forth. In the web chat, a video response renders as an embedded video player.

To add a Video response type, complete the following steps:

1. Choose Video.

2. Add the full URL to the hosted video into the Video source field:

   • To link directly to a video file, specify the URL to a file in any standard format such as MPEG or AVI. In the web chat, the linked video will render as an embedded video player.

     HLS (.m3u8) and DASH (MPD) streaming videos are not supported.

   • To link to a video hosted on a supported video hosting service, specify the URL to the video. In the web chat, the linked video will render using the embeddable player for the hosting service.

     Specify the URL you would use to view the video in your browser (for example, https://www.youtube.com/watch?v=52bpMKVigGU). You do not need to convert the URL to an embeddable form; the web chat will do this automatically.

     You can embed videos hosted on the following services:

     • YouTube
     • Facebook
     • Vimeo
     • Twitch
     • Streamable
     • Wistia
     • Vidyard

   If you want to display a video title and description above the embedded video in the response, then add them in the fields provided.

   Some integration channels ignore titles or descriptions.

   If you want to scale the video to a specific display size, specify a number in the Base height field.

3. The Video response type is supported in the web chat, Facebook, WhatsApp, Slack, and SMS integrations.

Adding an Audio response type

Include audio clips in your response to share spoken-word or other audible content. In the web chat, a video response renders as an embedded video player. In the phone integration, an audio response plays over the phone.

To add an Audio response type, complete the following steps:

1. Choose Audio.

2. Add the full URL to the hosted audio clip into the Audio source field:

   • To link directly to an audio file, specify the URL to a file in any standard format such as MP3 or WAV. In the web chat, the linked audio clip will render as an embedded audio player.

   • To link to an audio clip on a supported audio hosting service, specify the URL to the audio clip. In the web chat, the linked audio clip will render using the embeddable player for the hosting service.

     Specify the URL you would use to access the audio file in your browser (for example, https://soundcloud.com/ibmresearch/fallen-star-amped). You do not need to convert the URL to an embeddable form; the web chat will do this automatically.

     You can embed audio hosted on the following services:

     • SoundCloud
     • Mixcloud

   If you want to display a title and description above the embedded audio player in the response, then add them in the fields provided.

   Some integration channels ignore titles or descriptions.

   If you want the audio clip to loop indefinitely, select On in the Loop field. For example, you might want to use this option to play music while a user waits on the phone. (By default, the audio plays only once and then stops.)

   The Loop option is currently supported only by the phone integration. This option has no effect if you are using the web chat integration or any other channel.

3. The Audio response type is supported in the web chat, Facebook, WhatsApp, Slack, SMS, and phone integrations.

Adding an iframe response type

Include iframes in your response to embed content from another website directly inside the chat window as an HTML iframe element. An iframe response is useful if you want to enable customers to perform some interaction with an external service without leaving the chat. For example, you might use an iframe response to display the following within the web chat:

• An interactive map on Google Maps
• A survey using SurveyMonkey
• A form for making reservations through OpenTable
• A scheduling form using Calendly

In the web chat, an iframe response renders as a preview card that describes the embedded content. Customers can click this card to display the frame and interact with the content.

To add an iframe response type, complete the following steps:

1. Choose iframe.

2. Add the full URL to the external content in the iframe source field.

   The URL must specify content that is embeddable in an HTML iframe element. Different sites have varying restrictions for embedding content, and different processes for generating embeddable URLs. An embeddable URL is one that can be specified as the value of the src attribute of the iframe element.

   For example, to embed an interactive map using Google Maps, you can use the Google Maps Embed API. (For more information, see The Maps Embed API overview.) Other sites have different processes for creating embeddable content.

   For technical details about using Content-Security-Policy: frame-src to allow embedding of your website content, see CSP: frame-src.

3. Optionally add a descriptive title in the Title field.

   In the web chat, this title will be displayed in the preview card before the customer clicks to render the external content. (If you do not specify a title, the web chat will attempt to retrieve metadata from the specified URL and display the title of the content as specified at the source.)

4. The iframe response type is supported in the web chat and Facebook integrations.

In the "Try it out" pane, the iframe is rendered immediately, without the preview card. To see how the web chat renders your response, use the assistant Preview page.

Adding an Option response type

Add an option response type when you want to give the customer a set of options to choose from. For example, you can construct a response like this:

Most integrations display the options as buttons if there are only a few items (4 or fewer, for example).

Otherwise, the options are displayed as a list.

To add an Option response type, complete the following steps:

1. From the dialog node where you want to add the response type, click the dropdown menu in the Assistant responds field, and then choose Option.

2. Click Add option.

3. In the List label field, enter the option to display in the list.

   The label must be less than 2,048 characters in length.

4. In the corresponding Value field, enter the user input to pass to your assistant when this option is selected.

   The value must be less than 2,048 characters in length.

   For Slack integrations where the options are displayed as a list, each value must be 75 characters or less in length.

   Specify a value that you know will trigger the correct intent when it is submitted. For example, it might be a user example from the training data for the intent.

5. Repeat the previous steps to add more options to the list.

   You can add up to 20 options.

6. Add a list introduction in the Title field. The title can ask the user to pick from the list of options.

   Some integration channels do not display the title.

7. Optionally, add additional information in the Description field. If specified, the description is displayed after the title and before the option list.

   Some integration channels do not display the description.

8. Optional: If you want to indicate a preference for how the options are displayed, as buttons or in a list, you can add a preference property for the response.

   To do so, open the JSON editor for the response, and then add a preference name and value pair before the response_type name and value pair. You can set the preference to dropdown or button.

   {
     "output": {
       "generic": [
         {
           "title": "Insurance types",
           "options": [
             {
               "label": "Boat",
               "value": {
                 "input": {
                   "text": "I want to buy boat insurance."
                 }
               }
             },
             {
               "label": "Car",
               "value": {
                 "input": {
                   "text": "I want to buy car insurance."
                 }
               }
             },
             {
               "label": "House",
               "value": {
                 "input": {
                   "text": "I want to buy house insurance."
                 }
               }
             }
           ],
           "preference": "dropdown", //add this name and value pair 
           "description": "Which of these items do you want to insure?",
           "response_type": "option"
         }
       ]
     }
   }
   

   When you define an options list with only 3 items, the options are typically displayed as buttons. When you add a preference property that indicates dropdown as the preference, for example, you can see in the "Try it out" pane that the list is displayed as a drop-down list instead.

   

   Some integration types, such as the web chat, reflect your preference. Other integration types, such as Slack, do not reflect your preference when they render the options.

Do not add more than one option response type to a single dialog node because both lists are displayed at once, but the customer can choose an option from only one of them.

If you need to be able to populate the list of options with different values based on some other factors, you can design a dynamic options list. For more information, see the How to Dynamically Add Response Options to Dialog Nodes blog post.

Adding a Pause response type

Add a pause response type to give the assistant time to respond. For example, you might add a pause response type to a node that calls a webhook. The pause indicates that the assistant is working on an answer, which gives the assistant time to make the webhook call and get a response. Then, you can jump to a child node to show the result.

To add a Pause response type, complete the following steps:

1. From the dialog node where you want to add the response type, click the dropdown menu in the Assistant responds field, and then choose Pause.

2. Add the length of time for the pause to last as a number of milliseconds (ms) to the Duration field.

   The value cannot exceed 10,000 ms. Users are typically willing to wait about 8 seconds (8,000 ms) for someone to enter a response. To prevent a typing indicator from being displayed during the pause, choose Off.

   Add another response type, such as a text response type, after the pause to clearly denote that the pause is over.

This response type does not render in the "Try it out" pane. You must access a node that uses this response type from a test deployment to see how your users will experience it.

Adding a Search skill response type

If you have existing customer-facing material, such as an FAQ, a product catalog, or sales material that can answer questions that customers often ask, put that information to use. You can trigger a search of the existing material in real time to get the latest and most up-to-date answer for your customers.

To use the search skill response type, you must create a search skill and add it to the same assistant that uses this dialog skill. For more information, see Creating a search skill.

To add a Search skill response type, complete the following steps:

1. From the dialog node where you want to add the response type, click the dropdown menu in the Assistant responds field, and then choose Search skill.

   Indicates that you want to search an external data source for a relevant response.

2. To edit the search query to pass to the Discovery service, click Customize, and then fill in the following fields:

   • Query: Optional. You can specify a specific query in natural language to pass to Discovery. If you do not add a query, then the customer's exact input text is passed as the query.

     For example, you can specify What cities do you fly to?. This query value is passed to Discovery as a search query. Discovery uses natural language understanding to understand the query and to find an answer or relevant information about the subject in the data collection that is configured for the search skill.

     You can include specific information provided by the user by referencing entities that were detected in the user's input as part of the query. For example, Tell me about @product. Or you can reference a context variable, such as Do you have flights to $destination?. Just be sure to design your dialog such that the search is not triggered unless any entities or context variables that you reference in the query have been set to valid values.

     This field is equivalent to the Discovery natural_language_query parameter. For more information, see Query parameters.

     • Filter: Optional. Specify a text string that defines information that must be present in any of the search results that are returned.

       • To indicate that you want to return only documents with positive sentiment detected, for example, specify enriched_text.sentiment.document.label:positive.

       • To filter results to includes only documents that the ingestion process identified as containing the entity Boston, MA, specify enriched_text.entities.text:"Boston, MA".

       • To filter results to includes only documents that the ingestion process identified as containing a product name provided by the customer, you can specify enriched_text.entities.text:@product.

       • To filter results to includes only documents that the ingestion process identified as containing a city name that you saved in a context variable named $destination, you can specify enriched_text.entities.text:$destination.

       This field is equivalent to the Discovery filter parameter. For more information, see Query parameters.

     If you add both a query and a filter value, the filter parameter is applied first to filter the data collection documents and cache the results. The query parameter then ranks the cached results.

3. Optional: Change the query type that is used for the search.

   The search skill sends a natural language query to Discovery automatically. If you want to use the Discovery query language instead, you can specify it. To do so, open the JSON editor for the node response.

   Edit the JSON code snippet to replace natural_language with discovery_query_language. For example:

   {
     "output": {
       "generic": [
         {
           "query": "",
           "filter": "enriched_text.sentiment.document.label:positive",
           "query_type": "discovery_query_language",
           "response_type": "search_skill"
         }
       ] 
     }
   }
   

Test this response type from the assistant Preview. You cannot test it from the dialog skill's "Try it out" pane.

Conditional responses

A single dialog node can provide different responses, each one triggered by a different condition. Use this approach to address multiple scenarios in a single node.

The node still has a main condition, which is the condition for using the node and processing the conditions and responses that it contains.

In this example, your assistant uses information that it collected earlier about the user's location to tailor its response, and provide information about the store nearest the user. See Context variables for more information about how to store information collected from the user.

This single node now provides the equivalent function of four separate nodes.

To add conditional responses to a node, complete the following steps:

1. Click Customize, and then set the Multiple conditioned responses switch to On.

   The node response section changes to show a pair of condition and response fields. You can add a condition and a response into them.

2. To customize a response further, click the Edit response icon next to the response.

   You must open the response for editing to complete the following tasks:

   • Update context. To change the value of a context variable when the response is triggered, specify the context value in the context editor. You update context for each individual conditional response; there is no common context editor or JSON editor for all conditional responses.

   • Add rich responses. To add more than one text response or to add response types other than text responses to a single conditional response, you must open the edit response view.

   • Configure a jump. To instruct your assistant to jump to a different node after this conditional response is processed, select Jump to from the And finally section of the response edit view. Identify the node that you want your assistant to process next. See Configuring the Jump to action for more information.

     A Jump to action that is configured for the node is not processed until all of the conditional responses are processed. Therefore, if a conditional response is configured to jump to another node, and the conditional response is triggered, then the jump configured for the node is never processed, and so does not occur.

3. Click Add response to add another conditional response.

The conditions within a node are evaluated in order, just as nodes are. Be sure that your conditional responses are listed in the correct order. If you need to change the order, select a condition and response pair and move it up or down in the list using the arrows that are displayed.

Configuring the Jump to action

If you choose to jump to another node, specify when the target node is processed by choosing one of the following options:

• Condition: If the statement targets the condition section of the selected dialog node, your assistant checks first whether the condition of the targeted node evaluates to true.

  • If the condition evaluates to true, the system processes the target node immediately.

  • If the condition does not evaluate to true, the system moves to the next sibling node of the target node to evaluate its condition, and repeats this process until it finds a dialog node with a condition that evaluates to true.

  • If the system processes all the siblings and none of the conditions evaluate to true, the basic fallback strategy is used, and the dialog evaluates the nodes at the base level of the dialog tree.

  Targeting the condition is useful for chaining the conditions of dialog nodes. For example, you might want to first check whether the input contains an intent, such as #turn_on, and if it does, you might want to check whether the input contains entities, such as @lights, @radio, or @wipers. Chaining conditions helps to structure larger dialog trees.

  Avoid choosing this option when configuring a jump-to from a conditional response that goes to a node situated above the current node in the dialog tree. Otherwise, you can create an infinite loop. If your assistant jumps to the earlier node and checks its condition, it is likely to return false because the same user input is being evaluated that triggered the current node last time through the dialog. Your assistant will go to the next sibling or back to root to check the conditions on those nodes, and will likely end up triggering this node again, which means the process will repeat itself.

• Response: If the statement targets the response section of the selected dialog node, it is run immediately. That is, the system does not evaluate the condition of the selected dialog node; it processes the response of the selected dialog node immediately.

  Targeting the response is useful for chaining several dialog nodes together. The response is processed as if the condition of this dialog node is true. If the selected dialog node has another Jump to action, that action is run immediately, too.

• Wait for user input: Waits for new input from the user, and then begins to process it from the node that you jump to. This option is useful if the source node asks a question, for example, and you want to jump to a separate node to process the user's answer to the question.

Next steps

• Be sure to test your dialog as you build it. For more information, see Testing the dialog.
• For more information about ways to address common use cases, see Dialog building tips.
• For more information about the expression language that you can use to improve your dialog, such as methods that reformat dates or text, see Expression language methods.

You can also use the API to add nodes or otherwise edit a dialog. See Modifying a dialog using the API for more information.