EnsoAI Overview
EnsoAI helps you manage guest messages and inquiries through two distinct modes:
EnsoAI CoPilot – Suggests a reply that you can review, edit, and send manually to the guest.
EnsoAI AutoPilot (currently in beta) – Automatically generates and sends replies to guests without requiring any user interaction.
Both CoPilot and AutoPilot rely on your Knowledge Base to craft accurate responses. Keeping this information up to date ensures that EnsoAI can deliver the best possible answers.
This guide explains how to train EnsoAI to respond to guest questions accurately and consistently—improving both the quality of suggested replies (CoPilot) and automated replies (AutoPilot).
Understanding the EnsoAI Knowledge Base
EnsoAI relies on multiple sources to determine the best response to each guest. Together, these sources make up what’s called the Knowledge Base.
Enso automatically builds the initial Knowledge Base using information from your connected PMS. However, you can further train and refine it through various interactions—ensuring the most accurate and context-aware responses.
To view the current Knowledge Base for each listing, go to EnsoAI → Knowledge Base in your dashboard.
From this page, you can click on any individual listing to view all the information EnsoAI has access to for that specific property.
The more complete and up-to-date your listing and policy content is, the better EnsoAI performs.
The 3 Place to “Train” EnsoAI
From the Inbox (fastest for day-to-day): This option allows you to seamlessly address any issues during live operations and fill in any gaps without having to leave the conversation. You can also access the suggestion bubble in both Inbox and Sandbox. Learn more about this type of training here.
In the Knowledge Base (single-pane view): This is the perfect place to audit coverage, identify any gaps, and gain a better understanding of where information is located and review suggestions. Learn more about the AI Knowledge Base here.
In the Sandbox (bulk “agent” updates & testing): Use this approach to train Knowledge Base in rapid, interactive fashion where you by testing guest questions and making suggestions in a sandbox environment. Learn about our Sandbox here.
Setting Up: What types of content should you add?
The content should be aligned with the typical questions or inquires you get from your guests. This includes:
Facts that drive 80% of questions: check-in details, parking, Wi-Fi, beds/rooms layout, appliances (e.g., rice cooker), A/C and heating, pet policy, trash/recycling day, pool/hot tub rules, house rules.
Operational specifics: SOPs for maintenance/lockouts, after-hours support rules, fee logic, upsell rules.
Room configuration (bedrooms/bathrooms) is supported. If answers differ by listing, add them per property.
See the sections for individual listings within Knowledge Base to identify gaps for each listing.
Improving answers over time (accept vs. edit)
When EnsoAI proposes a Suggested Reply in the Inbox:
Click Reply (without edits) → strong positive signal that the suggestion was correct.
Edit first, then send → the team reviews these to tune accuracy (e.g., signature formatting, phrasing). Edits don’t automatically save as new knowledge yet - use the suggestion bubble if the content itself was wrong or missing.
💡 Why it matters: Your Accept/Edit patterns drive the internal review queue. Once accuracy for a category stays high, we can safely enable AutoPilot for that category.
AutoPilot (Beta)
AutoPilot is currently in beta, however you can start getting ready by keeping the following in mind.
AutoPilot messages rely on a confidence score, which is calculated based on ensuring it has enough knowledge to reply to the guest. Therefore investing in maintaining the Knowledge Base is key.
Safer categories (e.g., short acknowledgements) arrive first; sensitive flows (e.g., pre-check-in with access codes, time-bound upsells) require higher confidence.
💡 How you’ll know you’re ready: Rising acceptance rate of suggested replies (fewer edits) in a category. Your CSM/Enso team monitors this and will advise when to flip AutoPilot on.
FAQs and Feedback
Do you have any more questions or feedback about our AI?
Check out our Frequently Asked Questions page here.
You can also contact our support team at [email protected].