AI Agent Sandbox
The AI Agent Sandbox is a secure testing environment that enables you to validate your AI Agent's responses to guest inquiries without affecting real conversations, before deploying it to production.
The Sandbox allows you to:
Test AI responses without affecting real guest conversations
Identify missing information in your knowledge base
Validate response quality
How to Test Your AI Agent
Step 1: Navigate to the Sandbox
Go to AI Agent → Try.
Step 2: Select a Testing Scenario
Choose a scenario based on your testing objectives:
Lead simulation — Evaluates responses to potential guest inquiries.
Use this scenario to test how the AI handles pre-booking questions from potential guests. Simulates conversations with leads who are inquiring about availability, pricing, amenities, etc.
Guest simulation — Tests responses for confirmed reservations.
Use this scenario to test how the AI communicates with guests who have active bookings. Simulates conversations about check-in procedures, property access, local recommendations, etc.
Step 3: Start the Simulation
Click Start simulation to begin testing AI responses
Resolve Knowledge Gaps
When the AI Agent cannot provide an adequate response to a question, you'll see a message indicating that the AI doesn't have enough information to answer. This is your opportunity to identify and fill knowledge gaps in your system.
Step 1: Go to the Listing
Click Go to the listing to access the knowledge base.
Step 2: Add a Field
Click Add field to create new knowledge entries.
Step 3: Input the Missing Information
Enter the missing information with detailed descriptions. Be specific and comprehensive to ensure the AI can provide accurate responses in the future.
Step 4: Re-test
Return to the Sandbox and re-test the same question to validate that the AI can now answer correctly
Last updated
Was this helpful?