FAQ
Frequently asked questions related to NLX
Applications
Can I design and test conversations before selecting an NLP integration (AI engine)?
Designing a conversation flow and setting up resources to be used within a flow may be done without an NLP in your workspace. However, to test flows within the available sandbox test, an NLP must be integrated, as each build uses an AI engine (NLP). If you haven’t connected a third-party NLP yet, you can use the built-in NLX engine to build and test.
How do I publish my application and make it available outside of the NLX platform?
Publish your application by creating a build and then deploying it. Deploying pushes that build to your selected delivery channels (like the API channel, telephony, SMS, or a CCaaS integration) so it’s accessible outside NLX. If you want an instant shareable experience without installing it into your own site yet, you can also enable Touchpoint Hosting during deployment to generate a conversational.app URL you can open or send to others for testing and review
How do I take an application offline?
Select a deployed build. From there, choose the Deployment tab in the modal. Scroll to the bottom, and choose Delete deployment. This will take the application out of a deployed state. You may re-deploy the same build or create a new build and deploy to make your application available again.
My build failed. What do I do?
NLX runs through all flows of your application to confirm it will work properly before you deploy it to the world. For a failed build, select the build to view a report of detected errors to address.
Flows
What's the difference between multiple messages and message variations?
Multiple messages on the same node are displayed or read off in succession and in the order they're arranged. This primarily allows you to break up large paragraphs of text in chat channels so they appear as individual chat bubbles.
Message variations provide a bank of message options for the NLX NLU to select randomly when a user hits that node in the conversation. This is especially useful if the same node has a chance to be reached twice in a single session. Please note that message variations do not get translated if deploying your application in multiple languages.
How do I change the inflection or get advanced control on how my conversational AI sounds?
When drafting messages for voice channels, you may use SSML tags (Speech Synthesis Markup Language) supported by your NLP. Inserting SSML into your messages can control volume, pitch, pauses, emphases, breathing, and more.
For Amazon Lex, check their supported SSML guide here.
Why do I need to give an attached slot a name?
Whether custom or built-in, slots are available for use in a flow once attached, and they can be attached multiple times to the same flow (e.g., an NLX.Country slot attached twice for a step that collects an international departure location and another for an arrival location). Because AI models reference these names when resolving a user parameter or routing users according to their preferences, the slot names must be unique and distinguished from others. Therefore, the name you give your slot is the name that will appear when referencing it in your flow.
Why can't I rename my flow?
The name given to each flow is used when constructing a build of your application and will break an application in production, if renamed. Instead, you may duplicate the flow and provide a new name.
Slots
Can I reuse a custom slot across multiple flows?
Absolutely. In order to use a slot with any flow in your workspace, it must first be attached. From there, you may decide how it's used in NLP training phrases and/or the flow as well as determine the path that continues forward from each selected value on a User choice node.
Should I use a built-in slot type or custom slot?
Several built-in slots are provided in NLX that capture common values that would otherwise be painstaking to recreate: list of countries, time, dates, common first names, etc.
Create custom slots if built-in types don't exist and when you want to provide fixed and fairly limited choices that users select from or would normally use to clarify a preference: Yes/No, reason for cancellation, t-shirt size, etc.
For values that may change regularly or are massive in scale (e.g., showtimes, available hotel rooms, grocery store inventory, etc.) create a Data request integration instead.
Why do I need to attach a slot to a flow?
Since slots can be used in training phrases or within a flow when users make selections on User choice nodes or Generative Journey nodes, the slot's values then become part of the data that trains the NLP to understand valid or invalid user inputs.
Voice+
What happens when a Voice+ script's SMS is accessed by a messaging app that's not a mobile device?
Voice+ scripts continue to work as designed, regardless of the device used to open and navigate through the SMS link. Conversational AI will continue to be synced and will read aloud all steps through the user's mobile device as they view their weblink on their desktop, phone, smart watch, or tablet.
Last updated