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

# AI Agent (Bro Chat)

Conversational AI assistant powered by Grok and OpenAi

**Bro Chat** is NadoBro's conversational layer (the part you talk to). Ask questions in plain English or Local Languages, get live market context, sentiment, X (Twitter) alpha, and finance-aware reasoning. 

#### What Bro Chat can do

* **Live prices** for every Nado perp and spot product.
* **Sentiment & Fear & Greed Index** with source citations.
* **X (Twitter) search** for project- and token-specific alpha.
* **Funding & market structure** — current funding, basis, recent moves.
* **Strategy recommendations** — DMind's finance-native signal scoring suggests strategies that fit the current regime.
* **Finance-aware Q\&A** — explain what a perp is, what funding does, how Delta Neutral works.
* **Source-freshness tracking** — every provider-backed answer is stamped with how recent the data is, so you know when an answer is from a cached snapshot or a live pull.

#### Knowledge Sources

| Source                  | Data                                                                                                        |
| ----------------------- | ----------------------------------------------------------------------------------------------------------- |
| **Nado Knowledge Base** | Nado ecosystem docs, protocol details, trading rules                                                        |
| **CoinMarketCap**       | Prices, market cap, volume, token info                                                                      |
| **Fear & Greed Index**  | Current market sentiment score (0-100)                                                                      |
| **X Search**            | Real-time tweets, alpha, community sentiment                                                                |
| **DMind**               | The finance expert layer. Used for finance-native structuring, signal scoring, and strategy recommendations |

**Example Conversation**

```
You: What's the current price of BTC?
Bro: BTC is trading at $74,250 — up 2.3% in the last 24h. 
     Fear & Greed Index is at 72 (Greed). Looking bullish, bro! 🟢

You: Search X for ETH alpha
Bro: Here's what I found trending on X about ETH:
     • @whale_alert: Large ETH transfer from exchange to cold storage
     • @CryptoAnalyst: ETH forming a bull flag on the 4H chart
     • @DeFiPulse: ETH TVL up 5% this week...
```

#### Chat History

Bro Chat retains your last **12 messages** for **30 minutes**. This allows for context-aware, multi-turn conversations. After 30 minutes of inactivity, the chat history resets.

{% hint style="info" icon="lightbulb" %} <sup>**Tip: Ask NadoBro anything — "What's the sentiment on ETH?", "Search X for BTC alpha", or "What's the Fear & Greed Index?" The AI is there to help you make informed trading decisions.**</sup>
{% endhint %}


---

# 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://nadobro.gitbook.io/docs/core-features/markdown.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.