# Chatbot Rules

The rules system provides two types of behavioral controls for your chatbot: General Rules that guide overall behavior, and Search Rules that control which content sources are searched based on the type of question.

***

## General Rules (Chatbot Behavior)

General Rules set behavioral guidelines that your chatbot follows during all conversations.

### Step 1: Access General Rules

Go to chatbots page and click on **"Edit Chatbot"**.

Navigate to the **"General"** settings tab.

Scroll down to the **"Rules"** section.

### Step 2: Add General Rules

You can add up to **10 rules**, with each rule containing up to **500 characters**.

Enter your rules in the text fields provided. Rules are automatically numbered.

Click **"Save"** to apply your rules.

### How General Rules Work

* Rules are integrated into your chatbot's system prompt
* Applied to every conversation response
* Strictly enforced during all interactions

### Example General Rules

```
1. Always respond in a professional tone
2. Never discuss competitor products  
3. Redirect pricing questions to sales team
4. Always mention our 30-day guarantee
5. If unsure, admit uncertainty rather than guess
```

***

## Search Rules (Content Filtering)

{% hint style="info" %}
Search Rules are currently only available for Enterprise users.
{% endhint %}

Search Rules control which content sources are searched based on the type of question being asked, providing more targeted and relevant responses.

### Step 1: Access Search Rules

Go to your chatbot dashboard and click on **"Edit Chatbot"**.

Navigate to the **"Advanced"** settings tab.

Find the **"Search Rules"** section.

### Step 2: Create Search Rules

For each search rule, provide:

1. **Rule Definition**: Define the condition (e.g., "user asks about products")
2. **Example Questions**: Provide sample questions that should match this rule
3. **Counter-Examples**: Add questions that should NOT match this rule
4. **Content Sources**: Select which specific content sources to search for this type of query

Click **"Save"** to apply your search rules.

### How Search Rules Work

1. When a user asks a question, the system evaluates which search rule applies
2. Only the specified content sources for that rule are searched
3. This provides more targeted and relevant responses

### Example Search Rules

**Product Recommendations Rule:**

* **Condition**: User asks about product recommendations
* **Example questions**: "What product do you recommend?", "Which plan is best for me?"
* **Content sources**: Product catalog, pricing pages only

**Technical Support Rule:**

* **Condition**: User needs technical help
* **Example questions**: "How do I install this?", "The app won't start"
* **Content sources**: Technical documentation, troubleshooting guides only

**Billing Questions Rule:**

* **Condition**: User asks about billing or payments
* **Example questions**: "How much does this cost?", "When will I be charged?"
* **Content sources**: Pricing information, billing documentation only

### Best Practices for Rules

**General Rules:**

* Keep rules clear and specific
* Focus on tone, behavior, and response guidelines
* Test rules to ensure they don't conflict with each other

**Search Rules:**

* Create rules for your most common question types
* Provide diverse example questions for better matching
* Ensure content sources are relevant to the rule type
* Review and refine rules based on chatbot performance

***

If you have any more questions, feel free to reach out to us at <mark style="color:purple;">**<support@wonderchat.io>**</mark>


---

# Agent Instructions: 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:

```
GET https://docs.wonderchat.io/setup-guides/setting-up-your-chatbot/how-to-set-up-chatbot-rules.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.