Attach slots
Learn to attach slots for use in training phrases or conversation flows in your NLX workspace
What's the Attached slots tab?
Slots help capture parameters from user responses and are deemed required bits of information for completing a process outlined in an intent.
The majority of user turns in an intent workflow are likely to be made up of User choice nodes that capture and resolve these slot values while the AI assistant is guiding a user through a self-service task.
If a user wants to book a stay at your resort, you would use slots to resolve the preferred room type, check-in date, check-out date, number of guests, name of guest, and so on.
Slots must always be attached to an intent to be used within that intent's training data and/or the intent's conversation flow(s).
Custom or built-in
You may use either custom slots (containing custom values), or built-in slot types:
Custom
Custom slots have values that are small in range, are customizable to your business, and may be visible choices for use in chat. Custom slots are created within your workspace using the Slots resource
Examples:
Yes / No (boolean)
Small / Medium / Large
I want to signup / I want something else
Built-in
Built-in slots have standardized slot values that may be large or infinite in range or abstract. Built-in slots are accessible when attaching a slot to your intent
NLX.Country
When the user input will be any country.
NLX.Date
When the user input will use words to represent a date. Converts words to standard ISO-8601 format. Recognizes words such as "now" or "today" to mean the complete date of the current day. Input such as "this week" or "next week" will map to the first day of the week. ISO-8601 format begins its week on Monday and ends on Sunday. Input such as "next month" maps to the last day of the following month
NLX.Duration
When the user input will use words to represent duration. Converts words to standard format
NLX.Email
When the user input will use words and characters to represent an email address. Supports additional characters such as underscores, hyphens, periods, and plus signs
NLX.FirstName
When the user input will use a word to represent a first name
NLX.LastName
When the user input will use a word to represent a last name
NLX.Number
When the user input will use numeric words. Converts words to digits
NLX.Ordinal
When the user input will use ordinal words (e.g., first or 1st) to represent ordinal position
NLX.AlphaNumeric
When the user input will be a combination of letters and numbers
NLX.PhoneNumber
When the user input will use numeric words to represent a phone number. Converts them to a numeric string
NLX.Text
When the user input will consist of any words or characters
NLX.Time
When the user input will use words to represent time. Converts them to standard time format
NLX.Url
When the user input will use words to represent a URL. Converts them to standard URL format
NLX.City
When the user input will be any global city
NLX.USCity
When the user input will be a United States city
NLX.USState
When the user input will be a United States state
Attach a slot
Click Attached slots tab of intent > Select + Attach new slot
Choose a slot source from the dropdown (organized by Custom then Built-in types)
Provide a name for the slot to be referenced when using in an intent's training date or conversation flow
Click Save
Optional: Request, invalid, and example phrases
Expand a slot to access adding Request phrases or Invalid phrases:
For better UX, it's recommended that User choice nodes and fail state messaging with Basic nodes be used to collect preferred slot values rather than employing the Request phrases or Invalid phrases feature.
Request phrases: What you'd like your bot to say to prompt the user to provide slot choice (if not using the User choice node in your conversation flow to collect a value)
Invalid phrases: What you'd like your bot to say when the user selection is invalid
Examples: Add sample phrases that users may provide (e.g., for the built-in
NLX.Time
slot, you might add "7 pm," "7:00pm" or "7 in the evening" as examples for use with the Generative Journey node).Enter as many variations as you like. Your bot selects from them randomly
Optional: Sensitive setting
There may be cases where a user's selection may reveal personally identifiable information (PII). For user privacy, you can enable the Sensitive setting so user input for this slot is not stored in conversation logs.
By default, the Sensitive toggle is disabled.
Last updated