Cognigy

Cognigy.AI Docs

COGNIGY.AI is the Conversational AI Platform focused on the needs of large enterprises to develop, deploy and run Conversational AI’s on any conversational channel.

Given the arising need of voice interfaces as the most natural way of communicating with brands, Cognigy was founded in 2016 by Sascha Poggemann and Phil Heltewig. Our mission: to enable all devices and applications to intelligently communicate with their users via naturally spoken or written dialogue.

Get Started

Description

A Question Node is used to ask a question that requests specific information from the user.

▶️

Techinar video "Question Nodes"

Watch this Episode of Cognigy Sessions for a technical deep dive

Question Types

Question Nodes have a Type which defined what kind of answer is required from the user before the conversation continues. After a question was asked and the user provided an answer, the answer is validated according to its Type. If it passes, the answer is considered valid, is stored and the conversation continues.

Type

Expected user input to answer question

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 monetary value (system-defined)

URL

Any reference/address to a resource on the Internet e.g. 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

Data

Any data (input.data) input

Custom

Any input

🚧

Regex

Please make sure that your regular expression starts with a / and ends with /g.

Example:

  • /^1\d{​​​​7}​​​​$/g

📘

Supported Data formats for System Defined slots

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.

👍

Date Questions

In case the Question Type Date has been selected, the Question Node will automatically render a Datepicker if the channel permits. Please refer to Datepicker for more information.

Reprompt Options

Reprompt Message

Remprompt Messages are automatically triggered in case the question was not answered correctly (e.g. with the expected type of input or a validaiton didn't return true).

The Remprompt can be configured to automatically re-ask the question.

Reprompt Condition

Optionally a CognigyScript condition can be added which will determine whether the Reprompt Message is shown or not.

Skip on Intent

Skips 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 will also be stored in the Context object.

If Store Result to Contact Profile is enabled, the Question Result will also be stored in the Profile object.

Escalation to Handover

As of Release v4.4.0, we added the option "Handover to Human Agent". Open the Node Editor and you will find this option as an escalation action for "Intents" and "Wrong_Answers" that offers the ability to escalate questions by creating handovers to a real human agent.
When this escalation is hit, the conversation is handed to an agent, who can then help you finish the question step and hand it back.

Escalation on Intent

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

Action

Description

Output Message

Outputs a message (equal to a Say Node)

Skip Question

Skips the Question and enters a specific value into the input.result object.

Go to Node

Goes to a specific Flow Node and continues from there (equal to GoTo Node)

Execute Flow and Return

Goes to a specific Flow Node and returns to the question after (equal to Execute Flow Node)

Handover to Human Agent

The conversation is handed to an agent, who can help you finish the question step and hand it back

Add intents that can trigger the "escalate on intent" function by typing the intent name into the "Valid Intents" field and pressing ENTER on your keyboard. Adjust the dedicated intent score threshold slider to the preferred setting so that the escalation will only occur if one of the listed intents reaches that score.

Escalation on Wrong Answers

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

Action

Description

Output Message

Outputs a message (equal to a Say Node)

Skip Question

Skips the Question and enters a specific value into the input.result object.

Go to Node

Goes to a specific Flow Node and continues from there (equal to GoTo Node)

Execute Flow and Return

Goes to a specific Flow Node and returns to the question after (equal to Execute Flow Node)

Handover to Human Agent

The conversation is handed to an agent, who can help you finish the question step and hand it back

It is possible to prevent reprompts when the escalation is happening.

The option "only escalate once" determines if the escalation only happens once on the threshold or on every input form the threshold on.

Advanced

The Question Node has two advanced settings that can be used.

Store detailed Results

This 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 Input

When enabled, this setting will skip the Question if the answer is already provided in the input text.

Additional Validation

A 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 Location

The location of an answer is determined by default by the question type (e.g. input.slots.EMAIL[0] for Email Questions). This can be overwritten using this setting (e.g., input.slots.EMAIL would store all found email slots). If the result location doesn't return a value (= is falsy), the answer will be considered invalid.

Forget Question Threshold

This 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 will be treated as if the question was hit for the first time and the quesiton will be asked.

🚧

Question Nodes and Intent Execution

Question Nodes - by default - will be triggered again and again until a valid answer has been provided. In order to avoid this, you can opt for an Optional Question or you can change the Intent Execution setting.

👍

Slot Fillers

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

Question Information in Input

When a Question is "active", meaning an answer is being waited for, information about 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.

Updated 3 months ago



Question


Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.