- “The AI does not respond on its own, it only offers me a suggestion”
- “What does the green box in the chat mean?”
How the Confidence Level decides whether the AI sends a response on its own or proposes it as a suggestion, how to recognize the two cases in the chat, and how to use, modify, or analyze a suggestion.
How it works
- “The AI hands over the chat to me even if the answer is in the Knowledge Base”
- “What does the yellow box in the conversation mean?”
What Human Escalation is, how to recognize it in the chat, why the AI might hand over a conversation even when the information is in the Knowledge Base, and what you can check to reduce unnecessary escalations.
How it works
- “The AI responds with old information even though I updated the Knowledge Base”
- “Where do I write that the AI must escalate refund requests to me?”
Difference between Knowledge Base, Instructions, and Topics: where to write facts, behavioral rules, and fixed responses, and why a Topic takes precedence over the Knowledge Base.
How it works