> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/km/faq.md).

# How to Create FAQ

## How to Upload FAQ <a href="#how-to-upload-faq" id="how-to-upload-faq"></a>

### Select Knowledge Base <a href="#select-knowledge-base" id="select-knowledge-base"></a>

Go to the left sidebar "<mark style="color:blue;">AI Features</mark>" → "<mark style="color:blue;">Knowledge Base</mark>", and click on the knowledge base where you want to create FAQ (if you haven't created one yet, please refer to [How to Create a Knowledge Base: Basic Settings](/maiagent-user-guide/maiagent-user-guide-en/km/km-basic-settings.md)).

### Add Q\&A Content <a href="#add-qa-content" id="add-qa-content"></a>

1. Enter the knowledge base page, select the "<mark style="color:blue;">FAQ</mark>" tab, and click the "<mark style="color:blue;">+Create FAQ</mark>" blue button in the upper right corner to start adding Q\&A content.

<figure><img src="/files/YOZ8PTT27wlsEpAdrefD" alt=""><figcaption></figcaption></figure>

2. Create FAQ

The FAQ editor supports multiple answer formats:

* Basic text formatting (bold, underline, italic, etc.)
* Equations
* Source code (HTML, XML)
* Embedded links (videos, websites)
  * Videos provide reference links for users (the AI assistant cannot read video content yet)

<div><figure><img src="/files/KnAV5b8oLSAMB3xxaNqC" alt=""><figcaption></figcaption></figure> <figure><img src="/files/tDhazrvwFp4DTE4WBs2K" alt=""><figcaption><p>Answer format illustration</p></figcaption></figure></div>

This allows you to use multiple formats to clearly highlight key points in your answers and ensure the information is complete.

Taking e-commerce payment methods as an example, you can add the following question to explain online payment methods:

<figure><img src="/files/7NnBYiRSiNZQXoBC9elg" alt=""><figcaption></figcaption></figure>

After creation, you can click preview to confirm the answer content:

<div><figure><img src="/files/nnxL6yMIbmXSYBrDCYzk" alt=""><figcaption></figcaption></figure> <figure><img src="/files/kjrkTPAlKAt3B9442Kz5" alt=""><figcaption></figcaption></figure></div>

After adding, click "<mark style="color:blue;">Confirm</mark>" to complete the FAQ creation. The AI assistant will then be able to reference your provided answers when responding:

<figure><img src="/files/5abHWtQsxsckEnIwUdv0" alt=""><figcaption></figcaption></figure>

When customers ask questions related to online payment methods, the LLM will respond based on the FAQ content:

<figure><img src="/files/MmDs7s2QRdKW4ro6Q62b" alt=""><figcaption></figcaption></figure>

This way, you can restrict the AI assistant's response scope and prevent it from providing incorrect or non-compliant answers.

## Other Use Cases <a href="#other-use-cases" id="other-use-cases"></a>

### Product Operation Guidance Q\&A <a href="#product-operation-qa" id="product-operation-qa"></a>

Using **MaiAgent platform usage** as an example, suppose you need to help new users understand how to get started with the MaiAgent system. You can add the following Q\&A in the FAQ section:

**Question:** What should I do if I don't know how to use MaiAgent?

{% hint style="info" %}
When the answer is too long, you can click preview to confirm the full content
{% endhint %}

<div><figure><img src="/files/a8NDpidMYpMTT8Ch3F8R" alt=""><figcaption></figcaption></figure> <figure><img src="/files/ow6lBBPMcGKwr0TZNeED" alt=""><figcaption><p>Answer preview screen</p></figcaption></figure></div>

The AI assistant will explain MaiAgent's available resources and getting started steps based on your provided answer, and provide the links in your answer for users to reference:

***

### Knowledge Introduction <a href="#knowledge-introduction" id="knowledge-introduction"></a>

Using **LLM technology introduction** as an example, suppose you run a technology education platform and need to explain what Large Language Models (LLM) are to the general public. You can add the following Q\&A in the FAQ section:

**Question:** What is the working principle of LLM?

{% hint style="info" %}
You can enter video links within the answer
{% endhint %}

<div><figure><img src="/files/4Cb8F3ZYaySUCuZP8lPo" alt=""><figcaption><p>Click Insert/Edit Media</p></figcaption></figure> <figure><img src="/files/U0H1KKbUFVLaZKNxtnYb" alt=""><figcaption><p>Link input illustration</p></figcaption></figure></div>

<figure><img src="/files/tIpnTiZjotYjRILr0x06" alt=""><figcaption><p>Media insertion preview</p></figcaption></figure>

The AI assistant will respond based on the answer you set, and provide the video reference link for users to access:

<figure><img src="/files/lfXQOY5669act5xBdtU5" alt=""><figcaption></figcaption></figure>

***

## FAQ Management and Maintenance Tips <a href="#faq-maintenance-tips" id="faq-maintenance-tips"></a>

**Content Timeliness Management**

* **Event information updates**: Remove or update related content immediately after promotions or limited-time offers end
* **Policy synchronization**: When company policies (such as return/exchange conditions, terms of service) change, ensure FAQ content is updated accordingly
* **Product information maintenance**: New product launches, specification changes, discontinued products, and other information should be reflected in related Q\&A promptly

**Data-Driven Optimization**

* **Answer quality improvement**: Optimize answer content for high-frequency questions by providing more detailed and practical information
* **Gap analysis**: Discover common questions not covered by FAQ through customer feedback and customer service records

**Quality Control Mechanisms**

* **Content accuracy checks**: Regularly verify that links, contact information, and technical data in FAQ are correct
* **Tone consistency**: Ensure all FAQ content aligns with brand tone and communication style
* **Multi-language version synchronization**: If multi-language support is needed, ensure all language versions are kept in sync

{% hint style="info" %}
You can check the hit count of FAQ entries to identify the most frequently asked question categories and update them regularly.

For hit count details, please see: [Search Testing](/maiagent-user-guide/maiagent-user-guide-en/km/test-search-result.md)
{% endhint %}

<figure><img src="/files/X5bZewuAEgZglSU720Qa" alt=""><figcaption></figcaption></figure>

This management mechanism ensures the AI assistant always provides accurate, timely, and user-relevant responses, enhancing the overall customer service experience.


---

# 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://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/km/faq.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.