> For the complete documentation index, see [llms.txt](https://info.xtreamly.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://info.xtreamly.io/project-overview/trading-bot.md). # Trading Bot The Xtreamly bot is comprised of multiple AI-trained (tree-based) long and short biased models combined as a meta model with a focus on having consistent P\&L (both on shorts and long) and improving Sharpe ratio. The model tries to predict the direction of market (long/short) for a specific amount of time ahead. The strategy based on this model is developed following the betting concept (based onthe framework by Dr.De Prado at ) in which each new position is considered a bet with its own stop loss, take profit, and expiry time. The superposition of all the bets reflects the overall bot performance. In developing the model we used both market data from central exchanges as well as leveraging on-chain data, including lending protocols (e.g., AAVE), DeXs (e.g,. Uniswap), and token flows, among others. The frequency of trades can be controlled by adjusting the minimum confidence level required in all the internal models and also the meta model itself, both of which are tree-based. **ENGINEERING THE YIELD** * The system is an engineering tool, not a trading bot. * Yield Focus: The goal is verifiable, positive Net PnL (yield), not speculative gains. * Smartness: A specialized A.I. is trained to maximize risk-adjusted returns (Sharpe). It is programmed to avoid losses, enforcing superior discipline over any human. * Safety: Non-custodial smart contracts protect capital. Leverage is used only for capital efficiency, governed by hard-coded, immutable limits. * Perpetual Action: When no high-conviction trade exists, capital is automatically rotated to a safe, on-chain base yield, ensuring continuous asset work. {% content-ref url="/pages/SKbEpEagjqXTGdRQPYoC" %} [RISK DISCLAIMER & USER RESPONSIBILITY NOTICE](/project-overview/risk-disclaimer-and-user-responsibility-notice.md) {% endcontent-ref %} --- # 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://info.xtreamly.io/project-overview/trading-bot.md?ask=&goal= ``` `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.