Flow settings
Learn to easily configure settings of your intent and its flow in your NLX workspace
Last updated
Learn to easily configure settings of your intent and its flow in your NLX workspace
Last updated
Each flow created in your NLX workspace has crucial settings for workflow construction, customer intent recognition, and LLM training before building and deploying an application that will use the flow.
A flow's Settings setup provides options for adding advanced AI support, training data, using slot variables, and assigning languages for translation.
Select Flows from workspace menu > Choose New flow option
Provide a name (no spaces or special characters) > Click Create flow > Click Save
To duplicate an existing flow, choose the Settings icon within the flow's Canvas toolbar > Click the Advanced tab > Choose Duplicate flow. As flows cannot be renamed, you may duplicate an existing flow and provide the clone the desired name.
To delete a flow, select the gear icon (Settings) within your flow's Canvas. Choose the Advanced tab > Select Delete flow option and confirm. If the intent flow is attached to an application(s), create a to experience the change.
AI settings is where you can provide necessary data for LLMs to recognize customer intent and invoke the correct flow, or to support integrating your flow as a service with an LLM through .
The AI description field is required for LLMs to understand the purpose and context of a flow so it understands when to invoke the flow.
Select gear icon (Settings) within your flow's toolbar
From the AI settings tab, enter a concise description explaining the purpose of the flow (e.g., Provide a restaurant recommendation) into the AI description field
Training phrases comprise samples of what users might say to your conversational AI application that in turn invokes a flow to satisfy their intent. AI models (NLP and LLM) become trained on these samples to better identify customer intent and invoke the appropriate flow.
For an OrderRoomService flow, training phrases such as 'Order something to eat,’ 'I want room service’ or ‘Can I order food to my room?’ helps AI recognize that similar expressions from a user should invoke that flow.
The minimum number of training phrases recommended is 5, but providing a strong variety of user expressions results in better performance.
Select gear icon (Settings) within your flow's toolbar
Click AI settings tab > Enable Training phrases toggle
Select + Add new training phrase
When done adding phrases, click Save on the Canvas
Optional:
Skip translation (expand a phrase to view setting): Toggled OFF by default. Enable this in multi-language situations where the phrase would not make sense when translated into another language.
Upload/Download: Allows for a JSON or CSV to be ingested or downloaded with training phrase data. Tap the CSV/JSON button beside the Download link to swap formats
Variables required for the flow to work that should be extracted by the LLM in conversation and passed along to NLX are set up first in the flow's Settings.
For example, if a flow is to provide restaurant recommendations to a user, the structured MCP schema could contain the variables cuisine and location that are captured by an LLM and passed along to NLX:
Select gear icon (Settings) within your flow's toolbar
Click AI settings tab > Enable MCP toggle
Provide a unique and concise input name (no spaces or special characters)
Enter the input schema containing necessary variable(s) that will be set and passed along by the LLM interfacing with a user
Expand each property variable defined in your MCP input schema > Expand their settings > Enter a brief description in the property's Description field for the LLM to understand the purpose and context of each (e.g., location property might have the accompanying description for a restaurant recommendation flow: The location where you want to find a restaurant)
Click Save
On any node of the flow, enter an open curly brace { and reference the MCP input variable you want to use as an output in messaging, payload fields, Split node conditions, etc:
If a user wishes to book a stay at your resort, you might use slots to resolve the check-in date, check-out date, number of guests, name of guest, and so on.
Slots must be attached to a flow to be used within its training phrases or within Canvas nodes.
Select gear icon (Settings) within your flow's Canvas toolbar
Click Attached slots tab > Select +Attach new slot
Choose slot(s) from the dropdown (organized by Custom then Built-in types in your workspace)
Provide a name for the slot to be referenced when in use
Click Save
Optional:
Sensitive (expand an attached slot to view setting): Toggled OFF by default. 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 NLX conversation logs
Examples:
Yes / No
Small / Medium / Large
I want to signup / I want something else
Built-in slots have standardized values that may be large or infinite in range or abstract:
NLX.Country
When a user response should be any country
NLX.Date
When a user response 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 a user response should be words that represent duration (e.g., "two days," "30 seconds"). Converts words into numeric duration
NLX.Email
When a user response should involve words and characters to represent an email address. Supports additional characters such as underscores, hyphens, periods, and plus signs
NLX.FirstName
When a user response should use a word to represent a first name
NLX.LastName
When a user response should use a word to represent a last name
NLX.Number
When a user response should only use numeric words. Converts words to digits
NLX.Ordinal
When a user response should use ordinal words (e.g., "first" or "1st") to represent ordinal position
NLX.AlphaNumeric
When a user response may use a combination of letters and numbers
NLX.PhoneNumber
When a user response should use numeric words to represent a phone number. Converts them to a numeric string
NLX.Text
When a user response may consist of any words or characters
NLX.Time
NLX.Url
When a user response should use words to represent a URL. Converts them to standard URL format
NLX.City
When a user response should be any global city
NLX.USCity
When a user response should be a United States city
NLX.USState
When a user response should be a United States state
Languages lists all languages assigned to your flow, allowing for easy management of translations to any messaging contained within the flow and/or training phrases.
Select gear icon (Settings) within your flow's Canvas toolbar
Click Languages tab > Select +Add new language
Choose language(s) from dropdown
Click Save
Select Manage translations next to a supported language
Choose Auto-translate all > Confirm
You may easily restore or view past versions of a saved flow:
Select gear icon (Settings) within your flow's Canvas toolbar
Click Versions tab > Choose version to preview
If assigning a flow to one of the or if a flow is to be invoked through redirect nodes in other flows (not invoked by a user's utterance), keep Training phrases toggle disabled.
Saved changes do not take effect with applications that are already deployed. To experience changes to training data with applications in production, create a .
Enable training: Toggled ON by default. If disabled, prevents users from being routed to the flow via intent recognition. Useful if the situation requires users only be navigated to the flow through deliberate in other flows, or if the flow is set to a on the application. Essentially, this prevents the flow from being invoked by a user
Generate using AI: Quickly generate your training dataset
If you have you'd like to reference in generated training phrases, include them in your sample set first.
Take a deep dive on organizing intent flows and developing training data with .
place an order for room service
would like to order room service
Can I please place an order for room service for my family this evening?
would like a {size} pizza
look up {accountType} account balance
look up savings account balance; look up checking account balance, etc.
Check out our complete guide on setting up .
allows you to expose your NLX workflow(s) to a supported Large Language Model (LLM), allowing the LLM to follow and execute a service or task defined in any flow. In this way, NLX acts as the MCP Server, while the LLM becomes the MCP Client.
Be sure to also include an and turn on the on an application that will use MCP-enabled flow(s).
Slots capture parameters from user responses and are deemed required information for completing a process outlined in a flow. The majority of user nodes in a flow are likely to be made up of or that resolve these parameters while your conversational AI guides a user through a self-service task.
Examples (expand an attached slot to view setting): 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 node)
Custom slots have values that are small in range, are customizable to your use case, and may also be visible choices for user selection in chat (text-based) applications. Custom slots are created within your workspace using the .
When a user response should use words that represent time. Converts them to standard time format. You may use to parse information in flow, if needed
Need a list of available languages? See
When new languages are added via , they may be applied globally to resources in your NLX workspace. However, you may add/remove languages at the flow level to override your workspace's language settings.
