✨Generative Journey

From start to finish, set up a flow using Generative Journey in minutes with NLX

Checklist

You'll complete the following to successfully launch a workflow powered by Generative Journey:

You may add the following to an existing voice or chat application in your workspace, if desired.

Pre-setup: Integration

Est. time to complete: ~5 minutes

A one-time integration of a Natural Language Processing (NLP) engine must be completed in your workspace:

Step 1: Create an intent & workflow

Est. time to complete: ~3 minutes

Begin by identifying the tasks your conversational AI application will automate and organize them into individual topics called intents.

Each intent is invoked when your chosen AI model matches a user's query ("I want to order room service") to an intent you've created (OrderRoomService). This match is done based on the training data you provide for your AI model.

  • Select Intents from workspace menu > Choose New intent

  • Enter a descriptive name (no spaces or special characters) > Select Save

  • Click + Add new training phrase > Create 5 phrases that users might say to invoke the intent

  • Select Attached slots > Attach custom and/or built-in slots that will be resolved in your workflow

  • Click Save

  • Select + Add flow > Click Create flow

  • On the canvas builder, add nodes by right-clicking & choosing New node (see available node types)

  • Connect first node to Start node > Connect sequential nodes via node edges or stacking

  • Add bot messages to nodes by selecting + Add message on a node's side panel

  • Click Save

Repeat for any additional intents your application will help automate.

Step 2: Add Generative Journey

Est. time to complete: ~10 minutes

A Generative Journey node uses NLX's native LLM to help collect required parameters (slots) from customers in order to complete a necessary process in a workflow.

  • Place a Generative Journey node on the canvas > Using the node's side panel, assign NLX as the integration

  • Provide a succinct prompt to the LLM on what workflow the task is part of, the end goal of the task, specific messaging or branding requirements (if any), and things to avoid (if any)

  • Assign all Required slots needed to complete the task

  • Expand and adjust Generative Journey's Settings, if needed

  • Link from the node's Success edge to the next node in the flow

  • Click Save

Step 3: Set up application & deploy

Est. time to complete: ~5 minutes

Now you'll create the conversational AI application will interface with. This step involves attaching all intent workflows you want your application to access, defining flows to handle certain behaviors, setting up the channel(s) your application supports, and deploying your application.

  • Select Applications from workspace menu > Choose New application

  • Enter a descriptive name > Click Save

  • Select Default behavior tab of application > Assign flows to handle any behaviors, including Welcome

  • Select Channels tab of application > Create one or more communication channels your application will support

  • Click Deployment tab of application > Select Create or Review & build

  • Wait for validation to complete > Select Create build*

  • When satisfied with a successful build, click Deploy

Optional: Use modalities

Est. time to complete: ~8 minutes

Modalities allow for information to be transmitted to a user that goes beyond a standard assistant message. Images, audio, structured text, haptic signals, videos, and more can be modalities you may want to provide users during conversation with your conversational AI application.

Set up modality:

  • Select Settings from workspace menu > Choose Modalities tab

  • Click + Add modality > Click <> Auto-generate schema

  • Enter schema > Select Set schema

  • Click Create modality

Use modality:

  • Select an intent flow

  • Choose a node on your canvas to support your modality

  • On the node's side panel, choose Add functionality > Select Modalities

  • Locate the modality you created and switch the Enable toggle on

  • Enter all payload details into applicable fields > Click Save

Be sure to create a new build and deploy your application to experience changes.

Last updated