> 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/application/km/internalkm.md).

# Professional Knowledge Management

When enterprises implement knowledge management, they are often limited by existing knowledge management system capabilities, relying solely on keyword searches to find information. This approach has limited semantic understanding, and search results are often imprecise, making it difficult to meet the vast and diverse knowledge needs of the enterprise. Now, you can leverage MaiAgent to build a dedicated internal enterprise AI knowledge assistant, achieving smarter and more convenient knowledge management!

## Use Case: Build a Maritime Professional Knowledge AI Q\&A Assistant

Suppose you are a supply chain management specialist at a shipping company who regularly reads journals and reports to stay informed about the latest maritime trends, which serve as important references for business operations and decision-making. However, with the rapidly changing international landscape and ever-evolving industry knowledge, the massive and scattered volume of information often makes it difficult to grasp key points in time. In this case, you can use MaiAgent to build a dedicated internal enterprise AI Q\&A assistant that not only helps you quickly locate, understand, and internalize key knowledge to stay on top of trends in real time, but also facilitates knowledge sharing and work efficiency across all employees, enhancing the enterprise's agility and competitiveness in a fast-changing market.

## Workflow

### 1. Create a Maritime Professional Knowledge AI Q\&A Assistant

Enter the AI assistant name.

<figure><img src="/files/soL47rDJ4DPc23nCFMCv" alt=""><figcaption></figcaption></figure>

Select RAG and language model.

<figure><img src="/files/llBdbiLNr6lwQe1XjvB9" alt=""><figcaption></figcaption></figure>

When selecting the response mode, choose "Standard Mode" if you have no special requirements, which is suitable for this use case. Refer to the following role instructions:

```
# Role
You are a maritime knowledge Q&A assistant for the shipping company's internal use.

# Output Format
Use the example format below to reply with the three most relevant knowledge items.

<example>
Your question is related to the following content:

1. [Title] (Content summary)
2. [Title] (Content summary)
3. [Title] (Content summary)
</example>

# Output Restrictions
- Reply in Traditional Chinese
- Use Taiwan terminology for proper nouns; for example, the Chinese term "集裝箱" should be changed to "貨櫃" (container)
- Prioritize more recent data as reference material
- Do not answer questions outside the knowledge base scope
- Answer based on knowledge base data; if unable to answer, use the text within the <example> below

<example>
Sorry, the knowledge base does not currently contain the information you requested.
```

<figure><img src="/files/kFOkDJmPVQ19w58cqpXJ" alt=""><figcaption></figcaption></figure>

Set permissions, assign roles, and click Save.

<figure><img src="/files/CG8Iwa2WdjhOhP1JFLJj" alt=""><figcaption></figcaption></figure>

### 2. Upload Knowledge Base

Here we use two publicly available data sources — the UNCTAD 2024 Maritime Review Annual Report and the CR Classification Society Technical Bulletin — as reference materials for building the knowledge base.

Here we use two publicly available data sources — the UNCTAD 2024 Maritime Review Annual Report and the CR Classification Society Technical Bulletin — as reference materials for building the knowledge base.

<https://unctad.org/system/files/official-document/rmt2024overview_ch.pdf>

<https://www.crclass.org/wp-content/uploads/2025/02/138.pdf>

<figure><img src="/files/9qb5Puz3NTbInywzd4GO" alt=""><figcaption></figcaption></figure>

### 3. Deploy the AI Assistant

When you need to learn about maritime-related topics, you can now ask questions directly through the AI assistant's chat interface!\
For example, if your manager assigns you to write an analysis report about the Panama Canal, you simply ask the AI assistant to get relevant information instantly, without having to search through documents one by one, improving report production efficiency!

<figure><img src="/files/zWsqpPmlHGkMw1gxprUO" alt=""><figcaption></figcaption></figure>


---

# 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/application/km/internalkm.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.