How AI Responses Are Generated
For every incoming guest message, Cendra’s AI:- Identifies the guest — matches to a reservation via phone number or email
- Retrieves context — pulls property details, house rules, amenities, and past conversation history
- Checks rules — applies AI Rules, escalation conditions, and label restrictions
- Generates response — composes a reply using your knowledge, tone, and style
- Routes appropriately — sends automatically (autopilot), queues for review (semi-auto), or suggests (manual)
Response Quality Controls
| Control | How it works |
|---|---|
| Knowledge base | AI only references information you’ve provided — no external assumptions |
| AI Rules | Guardrails prevent unwanted responses (no financial commitments, no refund promises) |
| Tone settings | Responses match your configured communication style |
| Language matching | AI responds in the guest’s language by default |
| Escalation rules | Complex or sensitive topics are routed to humans |
Teaching the AI
When the AI generates an incorrect or suboptimal response:- Edit the response directly in the inbox before sending
- The AI learns from your edit and adjusts for similar future questions
- Add missing knowledge if the AI didn’t have the information it needed
- Set a new rule if the AI’s behavior needs a persistent change
Response Modes
| Mode | Behavior | Control level |
|---|---|---|
| Autopilot | AI sends responses automatically | Low oversight, high efficiency |
| Semi-automated | AI drafts responses, you approve before sending | Medium oversight |
| Manual | AI suggests responses, you edit and send | Full oversight |