Custom

Learn to set up your conversational AI application with NLX in minutes

What's a Custom application?

A Custom application is a build-your-own experience powered by the flows you design and attach to your app that contain all the logic, prompts, and pathways that are tailored to your goals. It can be deployed across multiple channels (chat, voice/phone, SMS) and offers advanced controls, including supported languages and configurable confidence thresholds with your NLP provider for intent recognition and flow invocation.

Create a custom app

  • Select Applications in your workspace menu > Choose New application

  • Click Blank application from the available options > Choose Custom

  • Provide a name for your application > Click Create application

Configuration

The Configuration tab allows you to provide the necessary NLP engine, flows, and communication method for your application.

Configuration tab of custom application
1

AI Engine

  • An AI engine helps disambiguate human speech for language understanding and intent recognition and also help construct construct a package of your application whenever a new build is made. Select the engine in the Provider dropdown. You may choose the built-in NLX model or select a managed NLP provider you previously integrated into your workspace

    • Optional

      • Enable NLX Boost: Enhances the performance of your engine with generative AI intent classification

        • Allow NLX Boost to override the NLP: Enabling this relies on NLX's built-in generative AI to detect user intent (based on your routing data) and route to a flow accordingly, regardless of the AI engine's detected match

2

Delivery

  • Channels are the modes through which users interface with your application. Each new custom application you create in your workspace comes with a prebuilt API channel for easy installation on web or mobile frontend services.

  • + Add channel: Select one or more channels from the list where you want your application deployed

    • Channel name: Defaults to the chosen channel type, but you may overwrite with a custom name

    • Integration: For channels requiring a one-time workspace integration, select from applicable integration(s) created

    • Custom conversation timeout: Customize the timeout period (in minutes) for a conversation session to end on the selected channel

    • Escalation: If any escalation channels have been created in your workspace, they will be listed here for selection

    Remaining fields are specific to the channel type selected. See list of channels for complete instructions

3

Functionality

  • Custom applications are defined by the flows they're comprised of. Here, you'll attach the workflows that your application will have access to and will follow.

    • + Add flow: Choose one or more flows created in your workspace

  • Click Save

Default behavior

Default behaviors control which flows the app triggers in key moments, including how it greets users, handles unknown inputs, and responds to errors.

For each behavior, you can choose between Quick reply or Flow:

  • Quick reply: Enter at least one phrase the AI will say, or add more for variety. Best used for prototyping

  • Flow: Point to a workflow from your attached flows to handle the situation

NLX includes starter quick replies, but we recommend creating flows for required defaults (Welcome, Fallback, and Unknown) for better control and consistency:

Required behaviors for an application

  • Welcome: What your application follows when a conversation session is initialized

  • Fallback: What your application follows during timeouts, integration failures, and exceeding the number of permitted incomprehension events

  • Unknown: What your application follows when incomprehension occurs (inability to understand the user's response). You may assign a Knowledge base from your workspace to the Unknown default; this allows your application to check the knowledge repository for a response to a common question without the need for a dedicated intent flow.

Optional defaults

  • Help: When a user expresses they are in an emergency situation

  • Frustration: When a user expresses frustration

  • Escalation: When an escalation process is triggered

  • Repeat: When a user requests the last message be repeated

  • Resume: When a user requests a pause before continuing the conversation

Deployment

The Deployment tab allows you to construct a build that is the package of the application's flows, channel(s), and settings in the state they exist at the time the build is created. You may then deploy a successful build to make it live or roll back to a previous deployment.

1

Build

  • Click Deployment tab > Select Create build

  • Review Validation check for critical errors or detected UX issues in custom flows. Before each new build initiates, a validation check is run to provide a preview of potential errors that may cause failed builds. Detected issues are listed with descriptions and potential solutions

  • You may provide a Description of notable build edits as a changelog

  • Click Create build

You may now test your newest build in your workspace using any of the test chats.

Experiencing a Failed build? Select the Details link next to the build status to expand information on what caused the failure.

2

Deploy

Delivery channels provide the frontend interface and determine how users experience your app. Deploying a build pushes your updates to those connected channels, effectively making your app live outside of your NLX workspace.

  • Click Deploy option next to the successful build

    • Optional:

      • Deployment languages: Select the languages to include in the deployment, if multiple are available

      • Hosting: Host your application as a Touchpoint app via the conversational.app domain. Ideal for previewing its final look during development and sharing your app externally with collaborators. Enable the Hosting option to configure the URL (e.g., mybusiness.conversational.app)

  • Click Create deployment

Once a build is made, flows can be further edited without affecting a deployed application. Only deploying a new build will impact live applications.

Only one build can be deployed at a time and deploying any build deactivates the previous one. You can freely alternate between newer and older builds using Rollback or Deploy.

3

Install

  • Click deployed build > Choose Deployment tab in modal

  • Access Setup instructions for each delivery channel or MCP Client

Want to take your app offline? Click the deployed build > Select Deployment tab in modal > Scroll to Danger zone and click Delete deployment. The app stays offline until you redeploy.

Once you deploy a build, you can use your application outside the NLX workspace in two ways:

  1. Delivery channel: Interact with the app through the channel where it’s installed (e.g., web chat via API channel, voice, SMS)

  2. Touchpoint (hosted chat): Open the hosting URL from the deployment details to chat with the app. Hosting must be enabled when you deploy

Custom app settings

General

AI settings

  • Input a brief description of the application for Model Context Protocol (MCP) Clients to reference

Automated tests (enterprise only)

  • See the Automated tests setup for advanced configuration

Advanced

  • Child-directed: For applications subject to COPPA. Utterance information will not be stored if enabled

  • Autocorrection: For supported NLPs, spell correction will be applied towards written user responses

  • Repeat on incomprehension: If a user's response is unclear, the application will repeat its last message to the user

  • NLP confidence threshold: When an utterance is at or above this value, your application assumes it matched to a flow with certainty

  • Negative sentiment threshold: The flow assigned to the Frustration default will be triggered when negative sentiment is detected above this threshold by the NLP (e.g., profanity, sarcasm, etc.)

  • Incomprehension count: Define the number of sequential utterances that the application asks for clarity on before an escalation or Unknown flow is triggered

  • Conversation timeout (min): Sets the timeout period for all channels on your application. If a timeout was also configured for a channel when managing channels, that channel's setting will take precedence over the application's setting

  • Default project ID: Default Project ID when using Google's Dialogflow NLP

Languages (check the list of supported languages in your workspace)

  • Choose which languages your application supports when in production. Though the flows attached to your application may be set up and developed in several languages, your application ultimately decides which to provide when released.

  • Expand either Main language or any Supported language to view advanced settings:

    • Use native NLP: Sends a user's utterance to the NLP directly without translation

    • Region: Global is chosen by default but may be toggled to EU for compliance and performance when using Dialogflow's NLP

    • Dialogflow project ID: If using Dialogflow's NLP, enter the project ID generated on the application's deployment tab

    • Amazon Lex Voice: If using Amazon's Lex NLP for voice channels, select the conversational AI voice to be used. You may listen to the selection of Amazon Polly voices here

When an application is created, it also inherits the list of workspace languages that have been pushed to all resources. Under Main language, the default language is English (US), while Supported languages lists any additional workspace languages applied via Translations.

Need to adjust languages and translations at the workspace level? See Translations.

As some voice channels leverage NLP models to convert audio inputs to text, check your NLP provider's supported languages for phone-enabled applications deployed with NLX.

Amazon Lex V2

Google Dialogflow

Inworld voice personas are language specific. Check their TTS page for details.

Lifecycle (enterprise only)

  • Choose any Lifecycle hook (enterprise only) created within your workspace that enables your application to retrieve and use content from external resources or trigger an external operation during specific points within the application's conversation session. The following are all lifecycle types available to configure on your application:

    • Conversation start: Triggers when a conversation session starts

    • Conversation end: Triggers when a conversation session ends/times out

    • Escalation: Triggers when an Escalate node is hit and the agent escalation transfer initiates

    • Message received: Triggers whenever a user submits a message (utterance)

    • State modification: Triggers when a node is hit that includes State modifications applied to one or more Data requests where the Stream state modification setting is also enabled

Danger

  • Should you want to delete an application that's no longer in production, you may do so through the application setting's Danger zone

Deleting an application does not delete the resources attached to your application, but the deletion of your application does wipe all custom settings configured for communication channels you may have set up for the application or any automated tests.

Last updated