Generative Journey
From start to finish, set up a flow using Generative Journey with NLX
Last updated
From start to finish, set up a flow using Generative Journey with NLX
Last updated
Generative Journey is a node type used when constructing a flow that allows you to employ a large language model (LLM) to facilitate the process of collecting necessary parameters (slots) from a user to complete a task (e.g., collecting preferences for booking a hotel, placing an order, etc.). This both allows for multiple slots to be collected by a single node in your flow and provides greater flexibility for a user to give information in a less rigid, more natural way.
Want to see it in action? Explore a few conversations powered by Generative Journey.
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.
Est. time to complete: ~5 minutes
A one-time integration of a Natural Language Processing (NLP) engine must be completed in your workspace:
Est. time to complete: ~5 minutes
Begin by identifying the tasks your conversational AI application will automate and organize them into individual topics handled by a flow. Determine the sequence of steps and messaging that the conversational application follows to assist a user with the task. The conversation workflow is assembled in an intent's Canvas builder with a pattern of nodes similar to a flow diagram.
Each flow is invoked when your chosen AI model identifies customer intent from a user's query ("I want to order room service") and matches it to a flow you've created (OrderRoomService). This match is done based on the training data you provide for your AI model.
Select Flows from workspace menu > Choose New flow
Enter a descriptive name (no spaces or special characters) > Select Save
Complete Flow setup by attaching training data and attaching slots
Add nodes by right-clicking on the Canvas & choosing New node (see available node types)
Connect first node to Start node > Connect sequential nodes via node edges or stacking
Add conversational AI messages to nodes by selecting + Add message on a node's side panel
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 flow 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
Repeat for any additional flows your application will help automate.
Est. time to complete: ~5 minutes
Now you'll create the conversational AI application users will interface with. This step involves attaching all flows you want your application to access, defining flows to handle certain behaviors, setting up the channel(s) your application supports, and deploying.
Select Applications from workspace menu > Choose New application
Enter a descriptive name > Click Save
Click Flows tab of application > Select Attach flows > Attach one or more flows created to make available to your application > Click Attach selected then Save
Select Default behaviors tab of application > Assign any attached flows to the application's behaviors > Click Save
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
Est. time to complete: ~8 minutes
Modalities allow for information to be transmitted to a user that goes beyond a standard 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 Resources from workspace menu > Choose Modalities
Click New modality > Click <> Auto-generate schema
Enter schema > Select Set schema
Click Create modality
Use modality:
Select a 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.
Looking for more? See Flows
*After a build status appears as Built, you may use the Test feature to test the conversation with your application using the latest build.
Looking for help with channel setup? See Manage channels
Need to troubleshoot your build? See how to troubleshoot build errors
Looking for more? See Modalities or check our REST API instructions