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

# What is Drawi?

Drawi is an **AI-powered Twitter Agent** that organizes **daily, decentralized contests** where users can win **SOL rewards** by posting the best responses to engaging questions.

This system is designed to **maximize engagement**, **reward creativity**, and leverage **provably fair on-chain randomness** for winner selection.

#### **How It Works**

1. **A new contest tweet is posted every 24 hours.**
2. **Users must reply with their best response, like the tweet, and include their SOL wallet address.**
3. **Drawi’s AI analyzes responses in real time, filtering out low-quality or spam submissions.**
4. **The winner is selected by our decentralized agent, ensuring a fully decentralized and fair draw.**
5. **SOL is sent automatically to the winner’s wallet, with all transactions verifiable on-chain.**

This **automated, trustless, and high-engagement** model makes Drawi one of the **most scalable and transparent** Twitter giveaway systems in the Web3 space.

#### Why It Matters

Drawi is not just another Twitter giveaway bot—it’s a **high-tech AI-powered system** that leverages **blockchain transparency and provably fair randomness**. By combining **cutting-edge AI, automation, and decentralized selection**, Drawi ensures a **trustless, scalable, and engaging** Web3 experience.

#### ➡ **Follow. Engage. Win SOL.**


---

# 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://drawi.gitbook.io/drawi/introduction/quickstart.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.