# Professional Knowledge Management

When enterprises implement knowledge management, they often face limitations with existing knowledge management systems that only support keyword-based searches. This approach not only has limited semantic understanding but also frequently produces imprecise search results, making it difficult to meet the vast and diverse knowledge needs of enterprises. Now, you can leverage MaiAgent to create a dedicated internal AI knowledge assistant, achieving smarter and more convenient knowledge management!

## Application Scenario: Building a Maritime Industry Professional Knowledge AI Q\&A Assistant

Suppose you are a supply chain management specialist at a maritime company who needs to regularly read journals and reports to stay informed about the latest maritime trends, which serve as crucial references for business operations and decision-making. However, with rapidly changing international situations and constantly evolving industry knowledge, the massive and scattered information often makes it difficult to grasp key points in a timely manner. In this case, you can use MaiAgent to create a dedicated internal AI Q\&A assistant that not only quickly locates, understands, and internalizes key knowledge to help you stay current with trends but also facilitates knowledge circulation and work efficiency across all staff, enhancing your company's adaptability and competitiveness in a volatile market.

## Application Process

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

Fill in 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, if there are no special requirements, you can choose "General Mode" to meet this application scenario. The role instruction reference is as follows:

```
# Role
You are an internal maritime knowledge Q&A assistant for the shipping company

# Output Format
Please use the example format below to respond with the three most relevant knowledge items.

<example>
The question you mentioned is related to the following content:

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

# Output Restrictions
- Please respond in Traditional Chinese
- For technical terms, use Taiwan terminology, for example, the Chinese term "集裝箱" should be changed to "貨櫃"
- Prioritize more recent data as reference material
- Do not answer information outside the scope of the knowledge base
- Answer based on knowledge base data; if unable to answer, respond with the text in the <example> below

<example>
We apologize, but the current knowledge base does not contain the information you requested
```

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

Permission settings: assign roles and click Save

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

### 2. Upload Knowledge Base

Here, we use publicly available data from the UNCTAD 2024 Review of Maritime Transport and CR Technical Bulletin as examples for knowledge base reference sources.

This uses two publicly available data sources—the UNCTAD 2024 Review of Maritime Transport and the CR Classification Society CR Technical Bulletin—as reference materials for knowledge base construction.

<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. AI Assistant Deployment and Application

When you need to understand maritime-related issues, you can now directly ask questions through the AI assistant Q\&A interface! For example, if your supervisor assigns you to write an analysis report on the Panama Canal, you simply need to ask the AI assistant to instantly obtain relevant information without having to search through documents one by one, improving report production efficiency!

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


---

# 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.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/application/km/internalkm.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.