After completing the prerequisite steps, you should have an Airlines knowledge base powered by the LP_Airline domain intents, as well as two bots that are connected to agents. We can now move our focus to Conversation Assist to configure its capabilities.
Step 5: Configure the bots for Conversation Assist
From the Conversational AI dashboard of applications, click Conversation Assist.
If it's your first time accessing Conversation Assist, you might see a window that introduces you to the application. Just click Get started in the window, and then click Got it at the next prompt. You'll be on the Recommendation Sources page at this point, which is good.
If necessary, click Recommendation Sources at the top of the page, and then select the Bots tab.
Click over on the right. This syncs with Conversation Builder and shows you the available bots.
Any bots that are connected to active agent connectors should now be visible here.
Recommendations are tied to skills, so you must assign skills to the bots before the bots can be offered to human agents during conversations.
Earlier, you assigned an "Agent" skill to the logged-in human agent; this is what needs to be assigned for these two bots to be recommended.
- Assign the "Agent" skill to the Seating Bot:
- Beside the bot, click the (Manage source) icon.
In the Manage recommendation source dialog, change the Status value to "ON," enter a description for the bot, and add the "Agent" skill.
- Click Save.
- Repeat the process for the previous step to change the status of the Booking Bot, enter its description, and assign the "Agent" skill to it.
Step 6: Configure the KB for Conversation Assist
Still on the Recommendation Sources page, select the Knowledge Bases tab.
Follow the steps that you used for the bots: First click to sync with KnowledgeAI. Then change the Status of the Airline FAQ knowledge base (KB) to "ON," and assign the "Agent" skill it.
For the purpose of this tutorial, we're relying on the default values for several settings, e.g., the Max # of recommendations to offer at any one time.
Customize your POC: If you built out additional resources in previous steps, make sure to turn on those resources too. Depending on the number of resources, it might be useful to increase the number of recommendations that you display to your agents when they are in a conversation.
Step 7: Create the Web messaging engagement
Updates to the Conversation Assist configuration can take up to 20 minutes to be reflected in conversations. While waiting for these changes to take effect, create a web messaging engagement that connects to the “Agent” skill.
- Back in the Conversational Cloud, select the Manage campaigns and engagements icon from the left-side menu.
- From the Campaign Builder portal, click + Add campaign in the lower-left corner.
- Give the campaign the name "Conversation Assist Testing," and under Campaign goal, select the default “Interact with consumers.”
- Click the + Add engagement link, and then select "Web" as the engagement source.
- In the Engagement template gallery, accept the default value, and click Next.
In the Engagement settings, under Routing, route to the specific skill "Agent."
It is important that this engagement is routing to the "Agent" skill that has been assigned to the human agent. As the Conversation Assist settings have been configured to recommend bots and answers to this particular skill, skipping this important step will result in recommendations not being sent.
- Click Next, and continue through the workflow, accepting the default values. When you’ve reached the last option, "Behavioral targeting library," click Done in the lower-right corner.
Back on the "Conversation Assist Testing" page, confirm that the skill being routed to is "Agent." If so, select the orange Publish button in the upper-right corner. Once published, there will be a visible Running icon to the right of the engagement.
Continue on to the next step in the tutorial.