# Product Query Assistant

In enterprise product customer service, facing a large volume of frequent customer inquiries, manual responses not only lead to delays but also cause excessive burden on customer service staff, affecting overall service efficiency. Many repetitive questions occur repeatedly, consuming significant time to handle, making it difficult for teams to focus on more complex customer needs and problem-solving. Additionally, the lack of personalized recommendations based on customer behavior and needs prevents effective improvement of customer satisfaction and user experience, further impacting brand image and business growth.

Now, you can use MaiAgent to build an AI product search assistant for external customer interactions, not only effectively reducing customer service costs but also providing more personalized product recommendations that better meet customer needs, improving service quality and customer satisfaction!

## Application Scenario: Building an External Product Search Assistant for a Computer Brand

Suppose you are a product customer service specialist for a computer brand, facing a large volume of diverse specification inquiries from customers, which often requires spending significant time processing and responding. At this point, you can use MaiAgent to build an AI product search customer service assistant for external enterprise interactions, providing real-time responses that not only significantly improve work efficiency but also effectively reduce customer service burden, allowing you to focus on higher-value customer service work.

## Application Process

### 1. Create an External AI Product Search Assistant

Fill in the AI assistant name

<figure><img src="/files/WySHbDPydBnH4ThijUAM" alt=""><figcaption></figcaption></figure>

Select RAG and language model

<figure><img src="/files/ZcWUcieerWz199EYRuks" alt=""><figcaption></figcaption></figure>

When selecting the response mode, if there are no special requirements, you can choose "General Mode", which will meet this application scenario. The role instruction reference is as follows:

```
# Role
You are the company's external product search assistant

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

<example>
Regarding your question, we recommend the following products:

1. [Product Name] Specifications
2. [Product Name] Specifications
3. [Product Name] Specifications
</example>

# Output Restrictions
- Please respond in Traditional Chinese
- Prioritize newer data as reference material
- Do not answer information outside the knowledge base scope
- Answer based on knowledge base data; if unable to answer, respond with the text in the <example> below

<example>
We apologize, but this question is currently beyond the scope of our response. Please contact human customer service for assistance.
```

<figure><img src="/files/xJ0w6PV3HdgxwPEXBQBX" alt=""><figcaption></figcaption></figure>

### 2. Upload Knowledge Base

Here we use HP's publicly available product catalog as a template for upload

<https://www.hptw-ebrochure.com/hipershop/rwd1185/store/F2/2024-0824_compressed.pdf>

<figure><img src="/files/to7MWxFAziDjClStGDqp" alt=""><figcaption></figcaption></figure>

### 3. Deploy AI Assistant

Now, you can directly embed the AI assistant into your company website, allowing customers to ask questions in real-time through a Q\&A interface, providing more personalized product recommendation options that better meet their needs, improving user experience and satisfaction!

<figure><img src="/files/Z3ifXEWTOaRa7oG3nLSQ" 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/text/productsearch.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.