Users occasionally ask questions outside the agent’s scope. The business wants a polite message, optional suggested topics, and an escalation path — not a silent failure. Which system capability should you customize?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Fallback is the agent's polite "I didn't catch that" moment — customize it with help, suggestions, and a path to a human instead of leaving users in dead air.
Full explanation below image
Full Explanation
System topics include Greeting/Conversation Start, Fallback, Escalate, End of Conversation, and others. Fallback handles cases where intent matching fails.
Option A is correct. Customizing Fallback provides controlled UX for unknown intents.
Option B is wrong; Conversation Start is for session beginning, not ongoing unknown intents.
Option C is wrong; End of Conversation is for closing, not matching failures.
Option D is wrong and harms user experience and supportability.
Exam tip: Map unknown intent → Fallback; explicit human request → Escalate topic; low confidence may also route to escalate depending on configuration.