> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bubblav.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Testing

> Preview and test your chatbot before going live

Before adding the chatbot to your public website, it's important to test its responses and behavior.

## Testing Environments

There are two ways to test your chatbot within the dashboard: the **Design Preview** for visuals and the **Dedicated Test Page** for behavior.

### 1. Design Preview

The **Design** page features a real-time preview of your widget's appearance.

1. Navigate to your website dashboard.
2. Click **Design** in the sidebar.
3. The right side of the screen shows a fully interactive preview.

**Best for:** Checking visual changes like colors, positioning, and welcome messages.

### 2. Dedicated Test Page

For evaluating the chatbot's **intelligence and responses**, use the dedicated Test page.

1. Click **Test** in the sidebar menu.
2. This opens a full-screen chat interface with a **Debug & Improve** side panel.

**Features of the Test Page:**

* **Full-screen chat**: Focus entirely on the conversation without distraction.
* **Debug & Improve panel**: A side panel (desktop only) that shows confidence scores, sources, and improvement tips for each bot response.
* **Confidence monitoring**: Every bot response is analyzed and given a confidence score — helping you quickly spot weak answers.
* **Quick Q\&A creation**: Add Q\&A entries directly from the test page when the bot struggles with a question.
* **Reset Chat**: Start a new conversation by clicking "New Chat".

## Debug & Improve Panel

The **Debug & Improve** side panel (visible on desktop) gives you real-time insight into how the bot answered each question.

### Confidence Scores

After each bot response, the panel displays a confidence indicator:

| Level      | Score     | Meaning                                                                                   |
| ---------- | --------- | ----------------------------------------------------------------------------------------- |
| **High**   | 70%+      | The bot found relevant content and answered confidently.                                  |
| **Medium** | 40–69%    | The bot found some content but may not have fully answered. Consider adding a Q\&A entry. |
| **Low**    | Below 40% | The bot could not find enough information. Adding a Q\&A entry will help.                 |

### Sources

The panel lists the **sources** the bot used to generate its answer. You can click any source to open it and verify the content is accurate and up to date.

### Low-Confidence Alerts

When the bot's confidence drops below 70%, a low-confidence alert appears below the response. On mobile devices, this alert appears inline; on desktop, the side panel highlights the issue.

### Quick Actions

For medium and low-confidence responses, a **"Add Q\&A for this question"** button appears in the panel. Clicking it opens a dialog pre-filled with the question you asked, so you can quickly provide the correct answer.

## What to Test

### Knowledge Accuracy

Ask questions about your business to ensure the AI has learned your content correctly.

* **Product details**: "What is the price of X?"
* **Policies**: "What is your return policy?"
* **Support**: "How do I contact support?"

Use the confidence score and sources in the Debug panel to verify each answer. If the score is low or the sources are wrong, update your content.

### Behavior

Check that the bot adheres to your settings:

* Does it use the correct tone?
* Does it escalate to human support when needed?
* Does it capture lead information?

### Debugging

If the bot says "I don't know" or gives wrong information:

1. Check the **confidence score** and **sources** in the Debug panel to understand why.
2. Add missing information to the **Knowledge Base**.
3. Use the **"Add Q\&A"** button in the panel to provide a direct answer for that specific question.
4. Use the **Q\&A** section or resolve **Content Gaps** for broader improvements.

## Best Practices

To learn how to get the most out of testing and continuous improvement, check out our [Best Practices](/user-guide/best-practices) guide which covers the full cycle of crawling, testing, adding knowledge, and monitoring.