# Tower AI Assistant

#### What Is the AI Assistant?

Tower's AI assistant is a conversational interface built directly into the trading platform. It connects to on-chain data and translates it into plain-language insights. Instead of deciphering raw blockchain data manually, users can simply ask.

<figure><img src="/files/vzcQyDmZ9SkpBW6wY2pA" alt=""><figcaption></figcaption></figure>

#### What Tower AI Does

The AI assistant helps with:

* **Portfolio Analysis:** Users can ask about current holdings, token allocations, and how their portfolio has changed over time. Example: *"What is my current portfolio breakdown?"*
* **Trade Executions:** Users can make swaps by simply telling the AI to do so. Example: *"swap 10$ usdc to eurc".* (Tower AI does not have access to private keys, trades are signed and confirmed by users).
* **Trade Explanations:** The assistant provides clear explanations of past trades, including the route taken, the price received, and how it compared to market rates. Example: *"Explain my last swap"*
* **Performance Insights:** Users can understand how their trading activity has performed, whether execution has been consistently good and how much has been saved by using Tower. Example: *"How has my trading performance been this week?"*

{% hint style="info" %}
The AI reads publicly available on-chain data. It does not have access to private keys, cannot sign transactions, and cannot move funds. Any swap made by the AI is signed by the User
{% endhint %}


---

# Agent Instructions: 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:

```
GET https://tower-exchange.gitbook.io/tower-exchange/getting-started/tower-ai-assistant.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
