> 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/en/build/agent/explain.md).

# AI Assistant Features

## Purpose and Use Cases of AI Assistants <a href="#ai-agent-purpose-and-use" id="ai-agent-purpose-and-use"></a>

AI assistants can be widely applied across diverse industries and use cases, helping enterprises automate repetitive tasks and improve operational efficiency, allowing teams to focus on high-value work and core strengths.

Below are common examples of AI assistant applications in enterprise workflows:

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-bf43aacb68fe112214ee71f970e0a230ef416879%2F%E6%88%AA%E5%9C%96%202025-04-22%20%E4%B8%8B%E5%8D%882.46.51.png?alt=media" alt=""><figcaption></figcaption></figure>

AI assistants can be applied across various industries, leveraging intelligent automation and real-time interaction to help enterprises optimize processes, improve service quality, and enhance user experience. The following table lists common AI assistant use cases by industry for reference.

<table><thead><tr><th width="214.15234375">Industry</th><th>Use Cases</th></tr></thead><tbody><tr><td>E-commerce &#x26; Retail</td><td>Intelligent customer service, product recommendations, return process handling</td></tr><tr><td>Finance &#x26; Insurance</td><td>Policy inquiries, financial planning recommendations, risk Q&#x26;A</td></tr><tr><td>Education</td><td>Course teaching assistant, learning diagnostics, language practice</td></tr><tr><td>Healthcare</td><td>Health consultations, appointment scheduling, patient education support</td></tr><tr><td>Government</td><td>Public service inquiries, policy Q&#x26;A, public feedback</td></tr><tr><td>Manufacturing</td><td>Internal knowledge management, maintenance operation guides</td></tr><tr><td>Travel &#x26; Tourism</td><td>Itinerary recommendations, guided tours, real-time Q&#x26;A support</td></tr></tbody></table>

## Four Stages of MaiAgent AI Assistant Setup <a href="#maiagent-ai-agent-setup-four-stages" id="maiagent-ai-agent-setup-four-stages"></a>

The MaiAgent AI assistant setup process consists of four stages. Below is a brief description of the goals and features for each stage. Complete step-by-step instructions are provided in the following sections.

### 1. Create a New AI Assistant <a href="#create-new-ai-agent" id="create-new-ai-agent"></a>

Customize the AI assistant to your needs: select an appropriate language model, connect a knowledge base for RAG (Retrieval-Augmented Generation) in <mark style="color:blue;">Knowledge Base Settings</mark>, and define the assistant’s role and tasks to build an intelligent assistant suited to your business.

On the AI assistant’s <mark style="color:blue;">Settings</mark> page, the left menu groups options under <mark style="color:blue;">Basic</mark>, <mark style="color:blue;">Knowledge & Data</mark>, <mark style="color:blue;">Capability Extensions</mark>, <mark style="color:blue;">Interface & Experience</mark>, and <mark style="color:blue;">Management & Advanced</mark>. These include <mark style="color:blue;">Basic Settings</mark>, <mark style="color:blue;">Response Mode Settings</mark>, <mark style="color:blue;">Knowledge Base Settings</mark>, and <mark style="color:blue;">Permission Settings</mark>.

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-ea27e7a463185fe624aec017f06797d609848339%2Fai-agent-settings-nav.png?alt=media" alt="AI assistant Settings page with Settings, Usage Analytics, Conversation Platforms, API Integration, and Webhook tabs at the top and grouped settings on the left"><figcaption><p>AI assistant Settings page and groups in the left menu</p></figcaption></figure>

### 2. Provide Reference Materials for the AI Assistant <a href="#provide-ai-agent-reference-materials" id="provide-ai-agent-reference-materials"></a>

Build a solid knowledge foundation for the AI assistant by configuring a <mark style="color:blue;">Knowledge Base</mark>, creating <mark style="color:blue;">FAQ</mark> entries in it, or using a <mark style="color:blue;">Crawler</mark> to import webpages. This further improves the accuracy and usefulness of responses.

### 3. Launch the AI Assistant <a href="#launch-ai-agent" id="launch-ai-agent"></a>

Decide whether to make the AI assistant publicly available or restrict it to internal use. The <mark style="color:blue;">Conversation Platforms</mark> tab offers three built-in entry points: <mark style="color:blue;">Web Widget</mark> (public, with embed code for your company website), <mark style="color:blue;">Internal Chat</mark> (internal), and <mark style="color:blue;">API</mark>. To serve customers through LINE, Messenger, or other channels, click <mark style="color:blue;">Connect Channel</mark> to integrate with your existing platforms.

<figure><img src="https://1360999650-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F6v6TNkkOQVfRYfcNirHL%2Fuploads%2Fgit-blob-3fb5cd9ff7ebdb63393f641081d57eb020ec18ca%2Fai-agent-platforms-tab.png?alt=media" alt="Conversation Platforms tab showing the built-in Web Widget, Internal Chat, and API channels and a Connect Channel button"><figcaption><p>Built-in channels and Connect Channel on the Conversation Platforms tab</p></figcaption></figure>

### 4. Track AI Assistant Performance <a href="#track-ai-agent-performance" id="track-ai-agent-performance"></a>

Use <mark style="color:blue;">All Conversations</mark>, the AI assistant’s <mark style="color:blue;">Usage Analytics</mark> (including monitoring metrics such as response quality scores), and <mark style="color:blue;">Webhook</mark> to track performance and guide ongoing improvements to the assistant and user experience.

Before you start building an AI assistant, consider reading these helpful articles!

{% hint style="info" %}
🗣️[How to Choose an LLM (Large Language Model)?](https://docs.maiagent.ai/tech/quickstart/llm)
{% endhint %}

{% hint style="info" %}
🔎[What is RAG (Retrieval-Augmented Generation)?](https://docs.maiagent.ai/tech/quickstart/rag)
{% endhint %}

{% hint style="info" %}
👨‍👩‍👧‍👦[What Are Role Instructions?](https://docs.maiagent.ai/tech/ai-agents/system-prompt)
{% endhint %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.maiagent.ai/maiagent-user-guide/en/build/agent/explain.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.