Question

Updated in 2026.3

Description

A Question Node is used to ask a question that requests specific information from the user. When the Node is triggered, the Entrypoint shifts to this Node so that the conversation continues only after the user answers. Also, a new Input object is generated. When a user input is received, it’s scored based on natural language understanding (NLU). If an attached Flow has an Intent that scores higher than Intents in the current Flow, the attached Flow is executed. The Intent scoring occurs before validation of the Question Node is completed. After the AI Agent asks a question and the user answers, the answer is validated according to its type. If it passes, the answer is valid and stored, and the conversation continues.

Question Nodes and Intent Execution

Question Nodes, by default, are triggered repeatedly until a valid answer is provided. To avoid this behavior, you can use an Optional Question or change the Intent Execution setting.

Parameters

Question Types

Question Nodes have a selection of types that determine the validation used before a conversation continues.

Type	Expected user input to answer question	Example
Text	Any text input.
Yes / No	A positive or negative response.
Intent	One of the trained Intents must be identified from the user’s response.
Slot	A System Slot or Lexicon Slot must be detected within the user’s response. The slot is defined by name.
Date	Any date (system-defined).
Number	Any number (system-defined).
Temperature	Any temperature (system-defined).
Age	Any age (system-defined).
Duration	Any time duration (system-defined).
Email	Any email address (system-defined).
Money	Any amount of money (system-defined). The input needs to include a number and a currency: Number — if the number has decimals, they need to be separated by the respective separator of the conversation’s language. For example, separate decimals with a period for English and with a comma for German. Currency — it is accepted as a symbol or written out, and can be written before or after the number.	`1,300 dollars`, `111.21 USD` (English), `USD 75`, `43 $`, `$ 11`, `300 euros`, `300 Euro`, `150,00 EUR` (German), `150.00 EUR` (English), `EUR 28`, `1900 €`, `€ 200`
URL	Any reference/address to a resource on the Internet, for example, `http://example.com`.
Percentage	Any percentage (system-defined).
Regex	Any custom data format defined by a regex expression must be detected in the user’s response. The regular expression must start with `/` and end with `/g`. For example, `/^1\d{7}$/g`.
Data	Any data (input.data) input.
xApp	Any xApp input.
Custom	Any input.
Pattern: License Plate (DE)	A pattern for the German vehicle registration plate. This license plate is a unique alphanumeric identification tag displayed on a vehicle. It consists of letters, numbers, and sometimes special characters, for example, `ö`, `ä`, or `ü`. License plates serve as a means of identifying and registering vehicles, providing important information such as vehicle ownership, registration details, and compliance with legal requirements.	`M-345`, `x1Y2Z3`, `D 12345C`
Pattern: IBAN	A pattern for the International Bank Account Number (IBAN).	`DE12345678901234567890`
Pattern: Bank Identifier Code (BIC)	A pattern for the Bank Identifier Code (BIC).	`DEUTDEFF500`
Pattern: Social Security Number (US)	A pattern for the US Social Security Number.	`123-45-6789`
Pattern: IP Address (IPv4)	A pattern for the IPv4 address.	`192.168.1.1`
Pattern: Phone Number	A pattern for the phone number.	`+49 0000000000`, `49 0000000000`, `+490000000000`, `(555) 000-000`
Pattern: Credit Card	A pattern for the bank card.	`4111111111111111`
LLM-extracted Entity	Utilizes a chosen LLM to extract entities, such as product codes, booking codes, and customer IDs, from a given string. Go to the LLM Entity Extraction Options.

All data formats supported by the Cognigy NLU for system slot mapping are listed on the Slot Mapping page.

Channels and Output Types

Question Node output types carry the same functionality as the Say Node.

If you select the Date as a Question Type, the Question Node automatically renders a datepicker if the channel supports it. Refer to Datepicker for more information.

LLM Entity Extraction Options

This section appears if you’ve selected the LLM-extracted Entity question type.Before using this Question type, set the LLM provider in the Settings. You can configure the Node to either use the default model defined in the Settings or choose a specific configured LLM.

Parameter	Type	Description
Large Language Model	Select	Select a model or use the default one.
Entity Name	CognigyScript	The name of the entity to extract. For example, `customerID`.
Entity Description	CognigyScript	A sentence which describes the entity. For example, `An alphanumeric string of 6 characters, e.g. ABC123 or 32G5FD`.
Example Input	Text	Examples of text inputs. For example, `My ID is AB54EE, is that ok?`, `That would be ah bee see double 4 three`, `I guess it's 49 A B 8 K`.
Extracted Entity	CognigyScript	Examples of extracted entities. For example, `AB54EE`, `ABC443`, `49AB8K`.
Additional Validation	CognigyScript	User input must meet this extra validation criteria, in addition to the built-in field validation, for example, Email, to be considered valid.

Alternatively, you can add input examples in the Use JSON Editor code field. For example:

{
  "My ID is AB54EE, is that ok?": "AB54EE",
  "That would be ah bee see double 4 three": "ABC443",
  "I guess it's 49 A B 8 K": "49AB8K"
}

Advanced

Parameter	Type	Description
Temperature	Indicator	The appropriate sampling temperature for the model. Higher values mean the model takes more risks.
Timeout	Number	The maximum amount of milliseconds to wait for a response from the LLM provider.

Reprompt Options

Reprompt messages are automatically triggered if the question is not answered correctly, such as when the expected type of input is not provided or a validation does not return true.Reprompt Methods

Simple Text
Channel Message
LLM Prompt
Execute Flow and Return

Outputs a simple text message to the user.

Parameter	Type	Description
Reprompt Message	CognigyScript	The message to output if the given answer is invalid. For example, `Not sure I understood this correctly`.

Outputs a comprehensive, channel-specific message to the user. This message includes rich-media, for example, images or audio. You can define distinct messages for each channel, such as Webchat, Voice Gateway, WhatsApp, and others.

Parameter	Type	Description
Reprompt Message	Channel	The channel for which you want to configure the repromt message. You can select multiple channels.
Output Type	Select	The format of the content that delivers through the selected channel. Depending on the selected channel, a list of possible output types suitable for that channel is presented. All channels support the text type, but support for other types may vary.

Runs an LLM prompt and outputs the result in the format of a text message to the user. Before using this Node, configure a model in the LLM settings.

Parameter	Type	Description
Large Language Model	Select	The channel for which you want to configure the repromt message. You can select multiple channels.
LLM Instructions	CognigyScript	The input or command, such as a prompt or system message, that is given to the Language Model to generate an output.
Transcript Turns	Slider	The number of conversation turns to include in the LLM chat completion request. By default, the value is `3`.
Stream Reprompt to Output	Toggle	Streams the result directly into the output. This means that the model provides prompts directly into the conversation chat, as soon as a Stream Buffer Flush Token is matched, and you don’t need to use the LLM Prompt Result token and Say Node. Note that streaming may not be supported by all Cognigy LLM Prompt Node providers, such as Google¹.

Executes a specific Flow and returns to the question afterward.

Parameter	Type	Description
Select Flow	Select	The Flow that is executed as the reprompt message.
Select Node	Select	The Node from which the Flow should be executed as the reprompt message.
Parse Intents	Toggle	This setting determines whether the system should parse Intents separately in the executed Flow. By default, this setting is enabled.
Parse Slots	Toggle	This setting determines whether the system should parse Slots separately in the executed Flow. By default, this setting is enabled.
Absorb Context	Toggle	This setting determines whether the system should absorb the executed Flow’s Context into the current Context. By default, this setting is disabled.

Repeat QuestionRepeats a question if a user gives an invalid answer. By default, this setting is enabled.Reprompt ConditionOptionally, you can add a CognigyScript condition to determine whether a reprompt message is shown.Skip on IntentSkips the reprompt if an Intent was found in the input.

Result Storage

Question results are always stored in input.result.If Store Result in Context is enabled, the Question Result is also stored in the Context object.If Store Result to Contact Profile is enabled, the Question Result is also stored in the Profile object.

Escalation - Intents

Allows the conversation to break out of the Question Node if a specified Intent was found.

Parameter	Type	Description
Escalation Action	Selector	Defines what happens when a question step escalates. Select one of the following options: No Escalation – no action is taken. This option is selected by default. Output Message – sends a message and behaves the same as a Say Node. Skip Question – skips the question and stores a value under the `result` in the Input object. Go To Node – jumps to a specific Node and continues from there and behaves as a Go To Node. Execute Flow and Return – executes a Flow Node and then returns to the question step and behaves as an Execute Flow Node. Handover to Human Agent – hands the conversation over to a human agent and behaves the same as a Handover to Human Agent Node.
Send Queue Event	Toggle	Sends an event to the Flow when the handover is queued.
Send Active Event	Toggle	Sends an event to the Flow when the handover becomes active.

Escalation Action: Output Message

Parameter	Type	Description
Valid Intents	List	A list of Intents that can trigger the escalation. Press Enter to add each Intent. Only Intents included in this list will be considered for escalation.
Intent Score Threshold	Number	The minimum confidence score an Intent must have to trigger the escalation. If the detected Intent’s score is below this threshold, the escalation will not occur.
Escalation Message	Text	The message the AI Agent sends when the wrong answer count is reached. Supports CognigyScript and Tokens.
Output Type	Toggle	Defines how the escalation message is sent. For example, Text will render the message as plain text in the channel, supporting emojis, HTML formatting, or CognigyScript.
Linear	Toggle	Controls whether multiple escalation messages are shown in a specific order (linearly) or randomly. If enabled, messages appear in the defined sequence.
Loop	Toggle	Works with Linear. If Loop is enabled, the sequence starts over after the last message. If disabled, the last message repeats after reaching the end.
Data	JSON	Additional data to send with the escalation message. For example, `{ "type": "escalation" }`.
Prevent Reprompt Message Once	Toggle	If enabled, the escalation message will only be triggered once per conversation, preventing repeated escalation messages.

Escalation Action: Skip Question

Parameter	Type	Description
Valid Intents	List	A list of Intents that can trigger the escalation. Press Enter to add each Intent. Only Intents included in this list will be considered for escalation.
Intent Score Threshold	Number	The minimum confidence score an Intent must have to trigger the escalation. If the detected Intent’s score is below this threshold, the escalation will not occur.

Escalation Action: Go To Node

Parameter	Type	Description
Valid Intents	List	A list of Intents that can trigger the escalation. Press Enter to add each Intent. Only Intents included in this list will be considered for escalation.
Intent Score Threshold	Number	The minimum confidence score an Intent must have to trigger the escalation. If the detected Intent’s score is below this threshold, the escalation will not occur.
Select Flow	Flow ID	Select the Flow to switch to when the escalation triggers. Use Manual Input to enter the Flow ID directly, or click the target Flow icon to select.
Select Node	Node ID	Select the Node to switch to when the escalation triggers. The Node must be an Entrypoint. Use Manual Input to enter the Node ID directly.
GoTo Execution Mode	Selector	Determines the behavior when switching to the selected Node/Flow: Go to Node and continue – the conversation immediately continues in the target Node or Flow using the current input. You can override the text or data using Optional Injected Text or Optional Injected Data. Go to Node and Wait for input – the conversation switches to the target Node/Flow but pauses, waiting for the user to provide input before continuing. Useful when you want the escalation to prompt the user.
Optional Injected Text	Text	When the escalation triggers, you can overwrite the text sent with this field. If left empty, the default text from Escalation Message is used.
Optional Injected Data	JSON	When the escalation triggers, you can overwrite the data sent with this field. If left empty, the default data is used.

Escalation Action: Execute Flow and Return

Parameter	Type	Description
Valid Intents	List	A list of Intents that can trigger the escalation. Press Enter to add each Intent. Only Intents included in this list will be considered for escalation.
Intent Score Threshold	Number	The minimum confidence score an Intent must have to trigger the escalation. If the detected Intent’s score is below this threshold, the escalation will not occur.
Select Flow	Flow ID	Select the Flow to switch to when the escalation triggers. Use Manual Input to enter the Flow ID directly.
Select Node	Node ID	Select the Node to switch to when the escalation triggers. The Node must be an Entrypoint. Use Manual Input to enter the Node ID directly.

Escalation Action: Handover to Human Agent

Parameter	Type	Description
Valid Intents	List	A list of Intents that can trigger the escalation. Press Enter to add each Intent. Only Intents included in this list will be considered for escalation.
Intent Score Threshold	Number	The minimum confidence score an Intent must have to trigger the escalation. If the detected Intent’s score is below this threshold, the escalation will not occur.
Handover Accepted Message	CognigyScript	The message that is displayed to the user when the handover request is accepted. It confirms to the user that a human agent will take over the conversation, providing reassurance that their issue is being handled.
Repeat Handover Accepted Message	Toggle	Repeatedly outputs the Handover Accepted Message if the user sends additional messages while waiting in the queue. This parameter the user informed and reassured during the wait. The parameter is activated by default.
Cancel Intent	CognigyScript	Specifies the Intent that a user can trigger to cancel a handover request. This parameter allows users to regain control of the conversation if they change their mind or no longer want to wait for a human agent.
Cancel Button Text	CognigyScript	Provides the text for a quick-reply button that users can click to cancel the handover. This parameter is an alternative to triggering the cancel Intent manually, offering a more robust option to stop the handover process.
Flow Continuation	Selector	Determines where the conversation resumes after the handover is completed. Select one of the following options: At current AgentInject Entrypoint – Start again where the handover began. Below this Node – Continue with the next step in the chat.
Send resolve event to Virtual Agent	Toggle	Sends an event to the AI Agent when the human agent resolves the conversation. This parameter allows the AI Agent to respond appropriately, update conversation status, or trigger additional automated processes after the human interaction. The parameter is deactivated by default.
Handover Provider	Selector	The provider that will handle the handover. By default, Legacy Mode is selected, using endpoint settings defined in Deploy > Endpoints. Alternatively, you can migrate to a provider from the Handover Providers interface or create a new provider from scratch.
Additional Category IDs	CognigyScript	The IDs for for the RingCentral Engage handover provider to allow you to categorize or route conversations according to custom categories. This parameter that the handover is directed to the appropriate team or workflow.
Live Agent Inbox Id	CognigyScript	The inbox ID used to route the conversation to the human agent. This ID must match the inbox configured in the Live Agent system to ensure messages are delivered correctly.
Live Agent – Allow reply as user	Toggle	Lets human agents respond on behalf of the end user in the chat interface. This parameter is useful for scenarios where a human agent needs to simulate user actions or correct information during the conversation. The parameter is deactivated by default.
Chatwoot Inbox Id	CognigyScript	The ID for routing the conversation to a Chatwoot inbox. This ensures proper delivery and handling within Chatwoot’s system.
Salesforce Send Transcript As First Message	Toggle	Sends the conversation transcript to Salesforce as the first message when handover begins. If the transcript is long, it is split into multiple messages. This parameter helps human agents have context at the start of the interaction. The parameter is deactivated by default.
Salesforce Prechat Entities	JSON	Refers to structured key-value data used for routing, automation, or passing contextual information to Salesforce flows. These are often used internally by Salesforce to map chat data to variables in Omni-Channel or automation logic.
Salesforce Prechat Details	JSON	Refers to user-facing or pre-filled field data in Salesforce chat forms, for example, name, email, issue type. This data is used to pre-populate fields the agent sees when the conversation starts.
Language	CognigyScript	Defines the languages for the conversation. This ensures the user is connected to agents who can communicate effectively in the chosen language.
Skills	CognigyScript	Specifies the skills required to handle the conversation. Agents are filtered based on these skills, ensuring users are connected to qualified personnel for their issue.
Priority	CognigyScript	Sets the priority of the conversation. Higher-priority conversations may be routed faster or treated with urgency in the contact center.
Custom Attributes	JSON	Adds additional key-value metadata to provide context or support custom routing and reporting. These attributes can include any relevant information about the user, conversation, or business context.
8x8 Channel Id	CognigyScript	Specifies the ID of the 8x8 chat channel used for handover. Links the conversation to the correct channel.
8x8 Queue Id	CognigyScript	Identifies the queue in 8x8 where the conversation should be routed.
8x8 JSON Properties	JSON	Allows sending additional custom JSON properties to 8x8 for configuration, routing, or passing extra metadata.
Only escalate once	Toggle	Ensures that a conversation is handed over only once. Prevents repeated escalations for the same issue to avoid confusion or redundant agent interactions.
Enable User Connects Message	Toggle	Notifies human agents when a user reconnects to the chat. This parameter ensures agents are aware of returning users and can continue the conversation seamlessly.
Enable User Disconnects Message	Toggle	Notifies human agents when a user leaves or closes the chat. This parameter helps maintain awareness of user engagement and session status.
Maximum Queue Position	CognigyScript	Sets the threshold for the maximum queue position. If this threshold is reached, the alternative text is sent. This parameter appears if Alternative Update is selected.
Maximum Estimated Wait Time	CognigyScript	Defines the maximum estimated wait time in milliseconds. If this duration is exceeded, the alternative text is sent. This parameter appears if Alternative Update is selected.
Alternative Text	CognigyScript	The message sent to the user when the maximum queue position or wait time threshold is reached. This ensures users are informed and reduces frustration while waiting for an human agent.

Escalation - Wrong Answers

Allows the conversation to break out of the Question Node after a number of incorrect answers were provided.

Parameter	Type	Description
Escalation Action	Selector	Defines what happens when a question step escalates. Select one of the following options: No Escalation – no action is taken. This option is selected by default. Output Message – sends a message and behaves the same as a Say Node. Skip Question – skips the question and stores a value under the `result` in the Input object. Go To Node – jumps to a specific Node and continues from there and behaves as a Go To Node. Execute Flow and Return – executes a Flow Node and then returns to the question step and behaves as an Execute Flow Node. Handover to Human Agent – hands the conversation over to a human agent and behaves the same as a Handover to Human Agent Node.
Send Queue Event	Toggle	Sends an event to the Flow when the handover is queued.
Send Active Event	Toggle	Sends an event to the Flow when the handover becomes active.

Escalation Action: Output Message

Parameter	Type	Description
Wrong Answer Count Trigger	Number	The number of incorrect responses a user can give before the escalation message is triggered. For example, if set to `1`, the escalation message will appear after the first wrong answer.
Escalation Message	Text	The message the AI Agent sends when the wrong answer count is reached. Supports CognigyScript and Tokens.
Output Type	Toggle	Defines how the escalation message is sent. For example, Text will render the message as plain text in the channel, supporting emojis, HTML formatting, or CognigyScript.
Linear	Toggle	Controls whether multiple escalation messages are shown in a specific order (linearly) or randomly. If enabled, messages appear in the defined sequence.
Loop	Toggle	Works with Linear. If Loop is enabled, the sequence starts over after the last message. If disabled, the last message repeats after reaching the end.
Data	JSON	Additional data to send with the escalation message. For example, `{ "type": "escalation" }`.
Prevent Reprompt on Escalation	Toggle	If enabled, the escalation message will only be triggered once per conversation, preventing repeated escalation messages.
Only escalate once	Toggle	Ensures that a conversation is handed over only once. Prevents repeated escalations for the same issue to avoid confusion or redundant agent interactions.

Escalation Action: Skip Question

Parameter	Type	Description
Wrong Answer Count Trigger	Number	The number of incorrect responses a user can give before the escalation message is triggered. For example, if set to `1`, the escalation message will appear after the first wrong answer.
Only escalate once	Toggle	Ensures that a conversation is handed over only once. Prevents repeated escalations for the same issue to avoid confusion or redundant agent interactions.

Escalation Action: Go To Node

Parameter	Type	Description
Wrong Answer Count Trigger	Number	Set the number of incorrect responses a user can give before the escalation action is triggered. For example, if set to `1`, the escalation will occur after the first wrong answer.
Select Flow	Flow ID	Select the Flow to switch to when the escalation triggers. Use Manual Input to enter the Flow ID directly, or click the target Flow icon to select.
Select Node	Node ID	Select the Node to switch to when the escalation triggers. The Node must be an Entrypoint. Use Manual Input to enter the Node ID directly.
GoTo Execution Mode	Selector	Determines the behavior when switching to the selected Node/Flow: Go to Node and continue – the conversation immediately continues in the target Node or Flow using the current input. You can override the text or data using Optional Injected Text or Optional Injected Data. Go to Node and Wait for input – the conversation switches to the target Node/Flow but pauses, waiting for the user to provide input before continuing. Useful when you want the escalation to prompt the user.
Optional Injected Text	Text	When the escalation triggers, you can overwrite the text sent with this field. If left empty, the default text from Escalation Message is used.
Optional Injected Data	JSON	When the escalation triggers, you can overwrite the data sent with this field. If left empty, the default data is used.
Only escalate once	Toggle	If enabled, the escalation message is triggered only once per conversation, preventing repeated escalation messages.

Escalation Action: Execute Flow and Return

Parameter	Type	Description
Wrong Answer Count Trigger	Number	The number of incorrect responses a user can give before the escalation action is triggered. For example, if set to `1`, the escalation will occur after the first wrong answer.
Select Flow	Flow ID	Select the Flow to switch to when the escalation triggers. Use Manual Input to enter the Flow ID directly.
Select Node	Node ID	Select the Node to switch to when the escalation triggers. The Node must be an Entrypoint. Use Manual Input to enter the Node ID directly.
Only escalate once	Toggle	If enabled, the escalation action is triggered only once per conversation, preventing repeated escalation triggers.

Escalation Action: Handover to Human Agent

Parameter	Type	Description
Wrong Answer Count Trigger	Slider	Defines the number of consecutive incorrect answers the AI Agent can give before automatically triggering a handover. This helps ensure users aren’t stuck with repeated wrong responses and are directed to a human agent when necessary.
Handover Accepted Message	CognigyScript	The message that is displayed to the user when the handover request is accepted. It confirms to the user that a human agent will take over the conversation, providing reassurance that their issue is being handled.
Repeat Handover Accepted Message	Toggle	Repeatedly outputs the Handover Accepted Message if the user sends additional messages while waiting in the queue. This parameter the user informed and reassured during the wait. The parameter is activated by default.
Cancel Intent	CognigyScript	Specifies the Intent that a user can trigger to cancel a handover request. This parameter allows users to regain control of the conversation if they change their mind or no longer want to wait for a human agent.
Cancel Button Text	CognigyScript	Provides the text for a quick-reply button that users can click to cancel the handover. This parameter is an alternative to triggering the cancel Intent manually, offering a more robust option to stop the handover process.
Flow Continuation	Selector	Determines where the conversation resumes after the handover is completed. Select one of the following options: At current AgentInject Entrypoint – Start again where the handover began. Below this Node – Continue with the next step in the chat.
Send resolve event to Virtual Agent	Toggle	Sends an event to the AI Agent when the human agent resolves the conversation. This parameter allows the AI Agent to respond appropriately, update conversation status, or trigger additional automated processes after the human interaction. The parameter is deactivated by default.
Handover Provider	Selector	The provider that will handle the handover. By default, Legacy Mode is selected, using endpoint settings defined in Deploy > Endpoints. Alternatively, you can migrate to a provider from the Handover Providers interface or create a new provider from scratch.
Additional Category IDs	CognigyScript	The IDs for for the RingCentral Engage handover provider to allow you to categorize or route conversations according to custom categories. This parameter that the handover is directed to the appropriate team or workflow.
Live Agent Inbox Id	CognigyScript	The inbox ID used to route the conversation to the human agent. This ID must match the inbox configured in the Live Agent system to ensure messages are delivered correctly.
Live Agent – Allow reply as user	Toggle	Lets human agents respond on behalf of the end user in the chat interface. This parameter is useful for scenarios where a human agent needs to simulate user actions or correct information during the conversation. The parameter is deactivated by default.
Chatwoot Inbox Id	CognigyScript	The ID for routing the conversation to a Chatwoot inbox. This ensures proper delivery and handling within Chatwoot’s system.
Salesforce Send Transcript As First Message	Toggle	Sends the conversation transcript to Salesforce as the first message when handover begins. If the transcript is long, it is split into multiple messages. This parameter helps human agents have context at the start of the interaction. The parameter is deactivated by default.
Salesforce Prechat Entities	JSON	Refers to structured key-value data used for routing, automation, or passing contextual information to Salesforce flows. These are often used internally by Salesforce to map chat data to variables in Omni-Channel or automation logic.
Salesforce Prechat Details	JSON	Refers to user-facing or pre-filled field data in Salesforce chat forms, for example, name, email, issue type. This data is used to pre-populate fields the agent sees when the conversation starts.
Language	CognigyScript	Defines the languages for the conversation. This ensures the user is connected to agents who can communicate effectively in the chosen language.
Skills	CognigyScript	Specifies the skills required to handle the conversation. Agents are filtered based on these skills, ensuring users are connected to qualified personnel for their issue.
Priority	CognigyScript	Sets the priority of the conversation. Higher-priority conversations may be routed faster or treated with urgency in the contact center.
Custom Attributes	JSON	Adds additional key-value metadata to provide context or support custom routing and reporting. These attributes can include any relevant information about the user, conversation, or business context.
8x8 Channel Id	CognigyScript	Specifies the ID of the 8x8 chat channel used for handover. Links the conversation to the correct channel.
8x8 Queue Id	CognigyScript	Identifies the queue in 8x8 where the conversation should be routed.
8x8 JSON Properties	JSON	Allows sending additional custom JSON properties to 8x8 for configuration, routing, or passing extra metadata.
Only escalate once	Toggle	Ensures that a conversation is handed over only once. Prevents repeated escalations for the same issue to avoid confusion or redundant agent interactions.
Enable User Connects Message	Toggle	Notifies human agents when a user reconnects to the chat. This parameter ensures agents are aware of returning users and can continue the conversation seamlessly.
Enable User Disconnects Message	Toggle	Notifies human agents when a user leaves or closes the chat. This parameter helps maintain awareness of user engagement and session status.
Maximum Queue Position	CognigyScript	Sets the threshold for the maximum queue position. If this threshold is reached, the alternative text is sent. This parameter appears if Alternative Update is selected.
Maximum Estimated Wait Time	CognigyScript	Defines the maximum estimated wait time in milliseconds. If this duration is exceeded, the alternative text is sent. This parameter appears if Alternative Update is selected.
Alternative Text	CognigyScript	The message sent to the user when the maximum queue position or wait time threshold is reached. This ensures users are informed and reduces frustration while waiting for an human agent.

Reconfirmation Options

Allows for answers to be reconfirmed before continuing. This is especially useful when using voice agents and reconfirming what the agent understood (for example, in Number questions when the user said “my number is three double five triple nine five six eight”). The answer given to the reconfirmation question has to be a yes/no style answer and follows the same rules as a Yes/No Question.Reconfirmation Questions can contain a specific token ANSWER, which is replaced with a short form version of the given answer (for example, “3 EUR” in a Money question). The short form answer is taken from input.activeQuestion.tentativeShortFormAnswer;Reconfirmation Questions can have a specific re-prompt set, which is output before the question if the answer to the question is not of yes/no style.

Advanced

Store detailed ResultsThis setting, when enabled, stores a more detailed JSON object under the result property of the input. This is useful in case more information is needed.Skip if Answer in InputWhen enabled, this setting skips the Question if the answer is already provided in the input text.Additional ValidationA CognigyScript condition which must return true in order for the answer to be considered valid. An example would be an additional validation on an Email Question of input.slots.EMAIL[0].endsWith("cognigy.com") which would guarantee that only cognigy.com email addresses pass the validation.Result LocationThe location of an answer is determined by default by the question type (for example, input.slots.EMAIL[0] for Email Questions). This can be overwritten using this setting (for example, input.slots.EMAIL would store all found email slots). If the result location doesn’t return a value (= is falsy), the answer is considered invalid.Forget Question ThresholdThis setting determines how long a user can have been “away” from the Node after the question was initially asked. With the default setting 1 this means that the question has to be answered on the next user input. If a user input comes back to the question at a later stage, it is treated as if the question was hit for the first time and the question is asked.

Handover to Human Agent

Action	Description
Handover Output Destination	Defines how messages are delivered after the handover occurs: User and Agent, Agent Only, or User Only. This option is available only for the Live Agent handover provider.

AI-Enhanced Output

To use AI-enhanced output rephrasing, read the Generative AI article.

Answer Preprocessing

You can use various functions of the Text Cleaner class to preprocess the answer to a question before it is evaluated. This can be helpful, for example, when requesting a name using a text type question or when asking for a part number using a slot question.In addition to the Text Cleaner functions, users have the option to rerun NLU after the cleaning process. This approach allows for tasks such as re-detecting slots or properly filling any remaining slots.

Exclude from Transcript

Excludes the Node output from the conversation transcript. The output remains visible to the end user but isn’t stored in the transcript object or shared with the LLM provider. You can use this parameter to:

Hide sensitive or irrelevant data, such as legal disclaimers, so the model doesn’t see or repeat them.
Prevent the model from copying patterns (called in-context learning) you didn’t want it to learn.

Example

By default, the model model repeats the question style it learned from the AI Agent’s earlier question, even though the end user asked for an answer, not a question.

AI Agent: What is your favorite color? (included in the conversation transcript)
End User: Blue.
Later:
End User: Tell me your favorite food.
AI Agent: What is your favorite food?

By excluding the AI Agent’s earlier question from the transcript, the same conversation looks like this:

AI Agent: What is your favorite color? (included in the conversation transcript)
End User: Blue.
Later:
End User: Tell me your favorite food.
AI Agent: I enjoy pizza.

Use this parameter to maintain confidentiality, for example, prevent sensitive data from reaching the LLM, or to display messages such as legal disclaimers or system notes that shouldn’t affect the AI Agent’s behavior.

Question Information in Input

When a question is active, meaning that the AI Agent is waiting for the answer, information regarding the question is added to the Input object.

"activeQuestion": {
    "nodeId": "18b158bf-71a3-4d4f-a31f-812b1810f8af",
    "type": "yesNo",
    "lastExecutedAt": 2,
    "forgetQuestionThreshold": 1,
    "repromptCount": 1,
    "escalationCount": 0
}

This information can be used to trigger specific actions on escalation or to jump back to the Question Node after an escalation.

Slot Fillers

Questions can be combined with Slot Fillers to create a “Missing Pattern”. This mechanism keeps asking the user for the missing information in a very natural way, until all questions have been answered.

¹: Note that not all LLM models support streaming.

Overview

AI Agents

Human Escalation

Platform Features

For Developers

Administration and Installation

Description

Parameters

Exclude from Transcript

Question Information in Input

Overview

AI Agents

Human Escalation

Platform Features

For Developers

Administration and Installation

​Description

​Parameters

​Exclude from Transcript

​Question Information in Input

Description

Parameters

Exclude from Transcript

Question Information in Input