> For the complete documentation index, see [llms.txt](https://kizunai.gitbook.io/kizuna-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://kizunai.gitbook.io/kizuna-docs/06.-kizuna-agent.md).

# 06. KIZUNA Agent

## KIZUNA Agent

### An AI Built Around the Project

KIZUNA is designed as a project-specific AI community manager.

Instead of providing generic answers across unrelated topics, a KIZUNA agent is created for a specific project and connected to that project's identity, context, and trusted knowledge.

The agent becomes a dedicated AI layer for the project's community.

### Project Identity

Every project has its own identity.

Its products, terminology, documentation, community, and information are unique.

When a project creates a KIZUNA agent, it provides the identity and context needed to represent that project.

The exact configuration options available when creating an agent are:

**\[NEEDS CONFIRMATION]**

The principle is straightforward:

**ONE PROJECT → ONE PROJECT-SPECIFIC KIZUNA EXPERIENCE**

### Context Matters

A community question is not always just a general question.

The answer can depend on the specific project being discussed.

KIZUNA is designed to use the project's connected knowledge and context when responding to community questions.

This allows the agent to focus on information that is relevant to the project and its community.

### The Agent and Its Knowledge

The KIZUNA agent works together with the project's knowledge layer.

The project provides trusted information.

The knowledge layer connects that information to KIZUNA.

The agent uses the connected project context when interacting with the community.

The relationship is:

**PROJECT IDENTITY**

*

**PROJECT KNOWLEDGE**

↓

**KIZUNA AGENT**

↓

**COMMUNITY**

### A Dedicated Community Manager

KIZUNA is positioned as an AI community manager, not simply an AI chatbot.

Its purpose is to help the community access project information through conversation.

Community members can ask questions directly in Telegram without needing to leave the community to search through different project resources.

The agent is designed to remain available for community interaction without requiring a team member to answer every question manually.

### Project-Specific, Not Generic

The difference can be summarized simply:

**GENERIC AI**

Designed to answer broad questions across many subjects.

**KIZUNA**

Designed around one project's identity, context, and knowledge.

This project-specific approach is central to KIZUNA's product direction.

### The KIZUNA Agent Model

The complete model can be represented as:

**CREATE**

Create the agent for the project.

↓

**IDENTITY**

Give the agent the project's identity and context.

↓

**KNOWLEDGE**

Connect the project's trusted information.

↓

**COMMUNITY**

Bring the agent into Telegram.

↓

**SUPPORT**

Let the community interact with the project-specific AI.

KIZUNA turns project knowledge into an active AI community layer.

**YOUR PROJECT.**\
**YOUR KNOWLEDGE.**\
**YOUR KIZUNA.**


---

# 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://kizunai.gitbook.io/kizuna-docs/06.-kizuna-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.