# AI Agent

## What is a reactive AI agent?

A reactive AI agent can be configured to respond to inbound messages by assuming predefined roles such as lead acquisition, shop assistant, customer support, or a custom role tailored to your needs. By carefully setting up the agent's profile, providing comprehensive guidelines, and enriching its knowledge base and manuals, it becomes highly capable of handling common, repetitive inquiries. Furthermore, it can even manage complex data-interaction tasks, thereby significantly boosting the efficiency of your customer service operations.

<figure><img src="https://3466127247-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSIAnjLP6KQY5rvyuaq5K%2Fuploads%2FgaP9DfjS3EnbD4vGXVEV%2FMy_Photor_1760424882818.jpg?alt=media&#x26;token=2d99c573-a402-4805-8cd7-0e9a8f45a0d3" alt=""><figcaption></figcaption></figure>

## How to configure AI tailored for business

### General

General settings for the reactive AI agent.

#### [Profile](https://helpdocs.ycloud.com/help-center/chatbot/ai-profile)

Setup the personality and the conversation rules of Chatbot to meet the requirements of customized brand services.&#x20;

In Profile, you can set the avatar, name of the reactive AI agent and choose the role for it:

* Lead acquisition: A lead acquisition agent can help you with automatically capturing and qualifying potential customer information through conversational AI. By providing 24/7 instant responses and reducing manual effort, it increases conversion rates, improves lead quality, and ensures no opportunity is missed.
* Shop assistant: An AI-powered shop assistant robot enhances the retail experience by guiding customers to their desired products instantly. It can answer questions about features, availability, pricing, and promotions. By understanding customer needs, it provides personalized recommendations, suggests complementary items.
* Customer service: A customer service robot provides instant, 24/7 automated support to resolve common inquiries and issues. It handles frequent tasks like tracking orders, processing returns, answering FAQs, and troubleshooting basic problems. By using AI to understand customer intent, it offers immediate solutions or efficiently escalates complex cases to human agents with full context.
* Custom agent: Customize the role of the AI agent according to your business needs.

### Knowledge

The Knowledge of AI, add the knowledge you think AI needs to learn and understand, as the material library for AI's answers.

#### [Knowledge base](https://helpdocs.ycloud.com/help-center/chatbot/ai-knowledge-base)

Enable the AI to learn knowledge, to enhance the ability of AI to answer customer questions, it is recommended to provide relevant knowledge for these unresolved queries, allowing your team to focus on business growth.

#### [Suggestions](https://helpdocs.ycloud.com/help-center/chatbot/ai-suggestions)

To enhance AI's ability to answer customer questions, it is advisable to provide relevant knowledge for these unaddressed queries.

### Manuals

#### [Flows](https://helpdocs.ycloud.com/help-center/chatbot/create-a-flow)

Build flows of Chatbot in a visual editor and let it interact with customers on WhatsApp.

#### [Skills](https://helpdocs.ycloud.com/help-center/chatbot/ai-skills)

Break down the process into steps and help AI learn how to manage complex tasks.

<figure><img src="https://ycloudteam.feishu.cn/space/api/box/stream/download/asynccode/?code=M2IxN2Q4NGU5NTRjMzYxNjkzMGY0M2QzYjhiNzFiNDhfUzZkRmsxY1lYMkh0cW9sVlVFZ2FUTEdhcUdsdHkzQjBfVG9rZW46T3hyZWIzd2NWbzk3TGN4UnozVWNCVDRsbmZjXzE3Mzk0MjYwNzY6MTczOTQyOTY3Nl9WNA" 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://helpdocs.ycloud.com/help-center/chatbot/reactive-ai-agent.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.