> 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/agent-builder/agent.md).

# Agent (AI Assistant)

## What Is This? <a href="#what-is-this" id="what-is-this"></a>

An Agent is an AI conversational persona you build on MaiAgent. Each Agent is an independent chatbot with its own identity, personality, knowledge, and capabilities.

Think of an Agent as a new employee — you need to tell it:

* **Who you are** (System Prompt)
* **What you know** (Knowledge Base, Database)
* **What you can do** (Tools, Skills)

Once configured, the Agent can serve users across various conversation platforms.

## Core Concepts <a href="#core-concepts" id="core-concepts"></a>

### Large Language Model (LLM) <a href="#language-model-llm" id="language-model-llm"></a>

The Agent's comprehension and response capabilities come from the underlying Large Language Model (LLM). Think of the LLM as the Agent's "brainpower" — different models vary in comprehension, response quality, speed, and cost.

When creating an Agent, you can choose the model that best fits your scenario. MaiAgent supports multiple models, including Claude, GPT, and more — you don't need to manage the models yourself; the platform handles it for you.

> **Quick guide**: For precise responses and complex reasoning, choose a more powerful model. For high-frequency simple Q\&A or cost control, choose a faster and lighter model.

### System Prompt <a href="#system-prompt" id="system-prompt"></a>

The system prompt defines how the Agent behaves. For example:

* "You are a friendly customer service representative. Respond in Traditional Chinese with a professional yet approachable tone."
* "You are a financial analysis assistant. Only answer finance-related questions. If data is uncertain, clearly state so."

A well-crafted system prompt significantly improves the Agent's response quality.

### Response Mode <a href="#response-mode" id="response-mode"></a>

MaiAgent offers two response modes:

* **Chat Mode**: Suitable for general Q\&A, responds directly using Knowledge Base content
* **Agent Mode**: Suitable for scenarios requiring multi-step reasoning, where the Agent decides what data to look up and which tools to use

### Memory <a href="#memory" id="memory"></a>

Agents have memory capabilities:

* **Conversation Memory**: Remembers what was discussed earlier within the same conversation
* **Long-Term Memory**: Retains important information across conversations, so you don't need to reintroduce yourself every time

> **Advanced note**: The memory feature allows the Agent to maintain contextual coherence across multiple conversation turns and recall past conversations through vector retrieval. You can adjust related parameters in the Agent's "Memory Settings."

## What Do I Need to Do? <a href="#what-do-i-need-to-do" id="what-do-i-need-to-do"></a>

1. **Create an Agent** — Give it a name and choose a language model
2. **Write a System Prompt** — Define the Agent's role and response style
3. **Attach Capabilities** — Connect a Knowledge Base, Tools, Skills (as needed)
4. **Test Conversations** — Test the results in the built-in chat window
5. **Connect a Platform and Go Live** — Deploy to Web Chat, LINE, or other conversation platforms

## Further Reading <a href="#further-reading" id="further-reading"></a>

* [AI Assistant Features](/maiagent-user-guide/maiagent-user-guide-en/build/explain.md)
* [Create an AI Assistant](/maiagent-user-guide/maiagent-user-guide-en/build/setup.md)
* [System Prompt Design Guide](/maiagent-user-guide/maiagent-user-guide-en/build/system-prompt.md)
* [Add a System Prompt to Your AI Assistant](/maiagent-user-guide/maiagent-user-guide-en/build/add-system-prompt.md)


---

# 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/agent-builder/agent.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.