# Suggested Questions

***

### 1. What are suggested questions?

Suggested questions are contextual follow-up prompts that appear after the AI responds to a customer. They help guide the conversation by surfacing related topics the customer may not have thought to ask, keeping them engaged with clear next steps.

<figure><img src="/files/xYDCNkNohy4826J7esLD" alt=""><figcaption><p>Suggested questions appear as tappable buttons below the AI's response</p></figcaption></figure>

***

### 2. How suggested questions work

1. A customer sends a message in the chat widget.
2. The AI generates a response.
3. The **Suggested Questions Agent** analyzes the conversation context and generates relevant follow-up questions.
4. The questions are delivered in real time and appear as tappable buttons below the AI's response.
5. When a customer taps a suggested question, it is sent as their next message and the conversation continues.

{% hint style="info" %}
Suggested questions share the same space as [icebreakers](/docs/features/chat-widget/icebreakers.md). When icebreakers are available, they take priority.
{% endhint %}

***

### 3. Enable the Suggested Questions Agent

The suggested questions feature is powered by a dedicated built-in agent. To enable it:

1. Log in to the **Alhena Dashboard**.
2. Navigate to **AI Settings > Agents**.
3. Find the **Suggested Questions** agent card.
4. Toggle the agent to **Enabled**.

The agent does not require any tools or additional integrations to be configured. Once enabled, it will automatically start generating suggested questions for conversations on your website chat widget.

{% hint style="info" %}
The Suggested Questions Agent does not support custom tools. Its behavior can be customized using [Guidelines](/docs/ai-configuration/tuning/guidelines.md).
{% endhint %}

***

### 4. Customize the appearance

You can style the suggested questions to match your website's brand. These settings are part of the [widget customization](/docs/features/chat-widget/customization.md) options. To access them:

1. Navigate to **Integrations > Website > Configure Settings**.
2. Scroll down and expand the **Suggested Questions Settings** accordion.

The following options are available:

| Setting              | Description                                         | Default              |
| -------------------- | --------------------------------------------------- | -------------------- |
| **Background Color** | Background color of the question buttons            | `#EDF3F8`            |
| **Text Color**       | Text color for the question labels                  | `#293037`            |
| **AI Icon**          | Custom icon displayed alongside each question       | Default sparkle icon |
| **Border Radius**    | Corner rounding of the question buttons (in pixels) | `32`                 |

The font size and line height are inherited from the **Message Font Size** and **Message Line Height** settings in the Widget Style section.

A live preview appears on the right side of the settings panel so you can see your changes in real time before saving.

{% hint style="warning" %}
These styling settings only apply to suggested questions. [Icebreakers](/docs/features/chat-widget/icebreakers.md) have their own separate styling configured on the Icebreakers page.
{% endhint %}

### 5. Saving & going live

Style changes are saved when you click **Save** in the widget settings panel. The Suggested Questions Agent starts generating questions immediately after being enabled — no additional setup is required.

Refresh your website in an incognito window to verify the updated styles.


---

# 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://alhena.gitbook.io/docs/features/chat-widget/suggested-questions.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.