> 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/suzuna.md).

# SUZUNA

### A personal intelligence layer for your wallet

SUZUNA is a **Telegram-native AI wallet agent** that gives users a conversational way to understand the activity of a public BNB Chain wallet.

A SUZUNA agent represents a specific wallet. When an agent is deployed, the user provides a public BNB Chain wallet address and the agent is associated with that address. The agent does not control the wallet, hold assets, sign transactions, or perform actions on behalf of the wallet.

Its role is to **observe, interpret, and explain**.

#### Wallet Data

When a user asks a question, SUZUNA retrieves the relevant information available from BNB Chain for that wallet.

The supported data includes:

* BNB balance
* Token balances
* Incoming transactions
* Outgoing transactions
* Token transfers
* Contract interactions
* Transaction history

SUZUNA does not need to permanently store the complete blockchain history of every wallet. Relevant blockchain data can be retrieved when required to answer a user's query.

#### AI Analysis

Raw blockchain records provide facts, but those records do not always provide context that is easy for a person to understand.

SUZUNA's **AI Analysis Layer** processes the relevant wallet activity and converts it into a natural-language explanation.

The objective is not to replace the underlying blockchain data. It is to provide a more accessible interpretation of that data.

For example, instead of requiring a user to manually inspect multiple transactions, SUZUNA can analyze the relevant activity and answer questions about what changed, which assets moved, or what transactions occurred during a particular period.

#### Agent Interaction

The agent is accessed through the **SUZUNA Telegram Bot**.

A typical interaction is:

**User asks a question → Agent retrieves relevant BNB Chain data → AI Analysis Layer interprets the data → Agent returns the response in Telegram**

The user can continue asking follow-up questions about the same wallet, allowing the interaction to remain conversational rather than requiring a new manual investigation for every question.

#### What SUZUNA Does Not Do

SUZUNA is designed as an **information and analysis layer** for wallet activity.

The agent does not:

* Execute trades
* Transfer assets
* Sign blockchain transactions
* Manage funds
* Perform copy trading
* Provide portfolio management
* Require wallet ownership signatures

The initial product has one defined purpose:

**Help users understand what is happening with a BNB Chain wallet through a personal AI agent.**


---

# 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/suzuna.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.
