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

# How SUZUNA Works

SUZUNA connects Telegram, a wallet-specific AI agent, BNB Chain data, and the AI Analysis Layer into a single conversational workflow.

### From a wallet address to an understandable answer

SUZUNA is built around a simple data flow. Telegram provides the interface, the SUZUNA agent provides the wallet-specific context, BNB Chain provides the underlying on-chain data, and the AI Analysis Layer turns relevant activity into a natural-language response.

**Telegram → SUZUNA Agent → BNB Chain Data → AI Analysis Layer → Telegram Response**

#### 01. Start

The user opens the **SUZUNA Telegram Bot** and selects **Deploy Agent**.

The bot requests a public BNB Chain wallet address. No private keys, wallet credentials, or transaction signatures are required.

#### 02. Create the Agent

SUZUNA creates an individual agent associated with the submitted wallet address.

Agent creation takes place off-chain. Deploying an agent does not require a blockchain transaction or gas fee.

Each agent represents one BNB Chain wallet.

#### 03. Retrieve Relevant Data

When the user asks a question, SUZUNA identifies the wallet information required to answer it and retrieves the relevant BNB Chain data.

Depending on the question, this can include balances, transactions, token transfers, contract interactions, and historical activity.

SUZUNA retrieves information when needed rather than maintaining a permanent copy of the complete blockchain history for every wallet.

#### 04. Analyze

The relevant data is passed to the **AI Analysis Layer**.

The AI layer interprets the underlying blockchain activity in the context of the user's question and produces an explanation that is easier to understand than raw transaction records.

#### 05. Respond

The resulting explanation is returned to the user through Telegram.

The conversation can continue with additional questions about the same wallet, allowing the user to explore its activity through natural language.

#### A Read-Only Architecture

SUZUNA operates as a read-only intelligence layer.

The agent can analyze publicly available wallet activity, but it does not have authority over the wallet. It cannot sign transactions, transfer assets, execute trades, or access private keys.

This separation keeps the agent focused on its intended role:

**retrieve → analyze → explain**


---

# 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://suzuna.gitbook.io/whitepaper/how-suzuna-works.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.