> For the complete documentation index, see [llms.txt](https://help.guestreply.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.guestreply.ai/readme/best-practises/test-your-ai-agent-regularly.md).

# Test Your AI Agent Regularly

Regular testing your AI Agent is crucial to ensure it provides accurate answers, maintains your brand voice, and handles various guest scenarios effectively. The AI Agent Simulator provides a secure testing environment where you can validate responses without affecting real guest conversations.

**Test after every Knowledge Base update** to verify the AI Agent interprets and uses new information correctly.

#### How to Test Your AI Agent

1. Navigate to [**AI Agent → Try**](https://app.guestreply.ai/ai-sandbox)
2. Select a testing scenario based on your testing objectives:

**`Lead simulation`** – Evaluates responses to potential guest inquiries (availability, pricing, amenities)

![Test Lead Simulation](https://2876699998-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FpPCRbMD6qrwDHChBDXHZ%2Fuploads%2Fgit-blob-1ccbdf5543632170d6b229ce6f087fb65d88d6bc%2FAI-try-LEAD-GUEST.png?alt=media)

**`Guest simulation`** – Tests responses for confirmed reservations (check-in, access codes, local recommendations)

![Test Guest Simulation](https://2876699998-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FpPCRbMD6qrwDHChBDXHZ%2Fuploads%2Fgit-blob-d2d21e4f9881fb93d17cea6cab0bd574b2aa5d16%2Fai-agent-guest-simulation.png?alt=media)

3. Click **`Start simulation`** to begin testing AI responses

#### **Best Practises:**

1. **Test after every update -** Verify AI Agent responses whenever you add or modify Knowledge Base information
2. **Use realistic questions** – Ask questions your guests ask in actual conversations
3. **Test both scenarios** – Run Lead and Guest simulations to cover all interaction types
4. **Resolve gaps immediately** – If the AI Agent can't answer, add missing information to the Knowledge Base right away and re-test
5. **Test edge cases** – Ask unusual or complex questions to ensure comprehensive coverage

#### Next Steps

1. For detailed step-by-step instructions on using the AI Agent Simulator, read our complete testing guide [here](/readme/user-manual/ai-agent/ai-agent-sandbox.md).
2. Schedule regular testing


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.guestreply.ai/readme/best-practises/test-your-ai-agent-regularly.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.