> 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/08.-product-architecture.md).

# 08. Product Architecture

## Product Architecture

### Overview

KIZUNA connects a project's knowledge with an AI community manager and brings that experience into Telegram.

The architecture can be understood through four primary layers:

**PROJECT KNOWLEDGE**

↓

**KIZUNA**

↓

**TELEGRAM**

↓

**COMMUNITY**

Each layer has a clear role in the overall product.

### 01 — Project Knowledge

The project provides its trusted information through sources such as:

* Website
* GitBook
* Documentation
* FAQs
* Trusted project resources

This information forms the foundation of the KIZUNA experience.

### 02 — KIZUNA Layer

The connected project knowledge is used by the KIZUNA agent to provide project-specific community support.

KIZUNA combines the project's identity, context, and connected knowledge into a dedicated AI community manager.

The exact internal AI and retrieval architecture is:

**\[NEEDS CONFIRMATION]**

### 03 — Telegram Layer

KIZUNA is designed to operate within the project's Telegram community.

Community members interact with the agent directly through Telegram and ask questions about the project.

The exact Telegram API and integration architecture is:

**\[NEEDS CONFIRMATION]**

### 04 — Community Layer

The final layer is the community itself.

Members ask questions and receive responses based on the project's connected knowledge.

The complete product flow is:

**PROJECT**

↓

**KNOWLEDGE**

↓

**KIZUNA**

↓

**TELEGRAM**

↓

**COMMUNITY**

### Backend Infrastructure

KIZUNA's current backend infrastructure uses:

**Supabase**

Supabase is planned for project data storage.

**Railway**

Railway is planned to run and deploy the backend.

The exact backend framework, database schema, API structure, authentication system, queue architecture, and other infrastructure details are:

**\[NEEDS CONFIRMATION]**

### Architecture Principle

KIZUNA is designed around a simple architectural principle:

**KEEP THE PROJECT KNOWLEDGE AT THE CENTER.**

The project provides the source information.

KIZUNA turns that information into an AI-powered community experience.

Telegram provides the environment where that experience reaches the community.

This creates a direct path from project knowledge to community interaction.

### High-Level System

```
┌─────────────────────────────┐
│      PROJECT KNOWLEDGE      │
│                             │
│ Website · GitBook · Docs    │
│ FAQs · Trusted Resources    │
└──────────────┬──────────────┘
               ↓
┌─────────────────────────────┐
│        KIZUNA AGENT         │
│                             │
│ Project Identity + Context  │
│ + Connected Knowledge       │
└──────────────┬──────────────┘
               ↓
┌─────────────────────────────┐
│          TELEGRAM           │
│                             │
│     Community Interaction   │
└──────────────┬──────────────┘
               ↓
┌─────────────────────────────┐
│          COMMUNITY          │
│                             │
│       Questions & Answers   │
└─────────────────────────────┘
```


---

# 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/08.-product-architecture.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.