✨Generative Journey
From start to finish, set up a flow using Generative Journey in minutes with NLX
Last updated
From start to finish, set up a flow using Generative Journey in minutes 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 workflow 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 bot 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: ~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.
🧠 Looking for more? See Construct flows
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
🧠 Looking for more? See Generative Journey node
Est. time to complete: ~5 minutes
Now you'll create the conversational AI application users 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.
Select Bots from workspace menu > Choose New bot
Enter a descriptive name > Click Save
Select Default behavior tab of bot > Assign flows to handle any behaviors, including Welcome
Select Channels tab of bot > Create one or more communication channels your bot will support
Click Deployment tab of bot > Select Create or Review & build
Wait for validation to complete > Select Create build*
When satisfied with a successful build, click Deploy
*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
Est. time to complete: ~8 minutes
Modalities allow for information to be transmitted to a user that goes beyond a standard bot 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 bot to experience changes.
🧠 Looking for more? See Modalities or check our REST API instructions
