Setup
Can I use the same agent group or profile in multiple add-ons within a rule?
Yes. But keep in mind that the order of the add-ons matters: At runtime, the add-ons are evaluated in order, and the first one that’s matched is executed.
How are a rule’s add-ons evaluated?
In a rule, the add-on completes the rule’s definition. Think of it as the rule’s “predicate.”
Adds-on are evaluated in the order listed in the rule, and the first one that’s matched is executed. So it’s important to order the add-ons as you require.
Add-on evaluation works as follows:
-
During the conversation, get some necessary data about the conversation:
a. What’s the skill assigned to the conversation? Retrieve this.
b. Which agent groups and profiles, if any, are assigned to the agent? Retrieve these.
c. Are in-conversation or on-demand recommendations needed? If the agent just entered a message in the On-Demand Recommendations widget, consider it a request for the latter. Otherwise, consider it a request for the former. -
Use the data retrieved in steps 1 - 3 to find a matching knowledge base rule and add-on, if any; retrieve the first match. Also find a matching bot rule and add-on, if any; retrieve the first match.
Once add-on evaluation is done, the retrieved rules are executed: Their add-ons are used to retrieve answers or bots. Finally, the “candidate” answers and/or bots are used to determine which recommendations to offer to the agent. Learn more about how recommendations are offered.
Can I turn off all recommendations?
Yes, you can turn off recommendations for your account. To do this:
- Access Conversation Assist.
- Click Settings from the menu at the top.
- Under General, click Suspend.
Agent experience
Why aren’t my knowledge base answers formatted?
Currently, only hyperlinks are supported.
Agent feedback (thumbs up, thumbs down)
Is the feedback of my agents captured in the reports that are available for download?
Yes! Learn about agent feedback reports.
Agents can provide feedback on bot/answer recommendations by clicking “thumbs up” or “thumbs down” on the recommendation. They can also edit recommended answers and send the edited answers to consumers. Do these actions influence what recommendations are subsequently offered?
No, not at this time.
In the case of recommended answers, does editing the answer before sending it, or clicking “thumbs up” or “thumbs down” on the recommended answer influence the knowledge base in KnowledgeAI?
No, not at this time.
Is agent feedback used to enhance the underlying recommendation engine?
No, not at this time.
Metrics and reporting
On the Home page, in the Recommendations widget, the Summary data does not align with the graph data. Why is this?
There’s a bug in the Summary information in this widget. It should show the number of used recommendations “over” the number of offered recommendations, where the latter (the denominator) reflects the recommendations that were and weren’t used.
Currently, the denominator is incorrect. It reflects only the recommendations that weren’t used.