> For the complete documentation index, see [llms.txt](https://fortuna-finance-1.gitbook.io/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://fortuna-finance-1.gitbook.io/documentation/a.i-yield-aggregator/how-does-it-work.md). # How does it work ? #### How does the AI choose the pool with the highest probability of generating yield ? * **Monitoring and Selection Process** : The AI model continuously monitors a predefi ned array of pools, focusing on identifying those with the top APYs. This process is not about gambling on a single pool; instead, it's about systematically scanning for the best yield opportunities at any given moment. * **Top Performing Pools Analysis** : After identifying the top performers, typically the top three pools with similar APYs, the AI model proceeds to a deeper analysis. This involves estimating the costs, fees,checking the minimum lock-up period (if any) and calculating the potential outcomes associated with investing in each of these pools. * **Decision-Making Criteria** : If the initial analysis doesn't yield a clear winner (by at least 20% yield difference), the AI models - Naive Bayes Classifi er and k-Nearest Neighbours - are deployed to assess which pool has the lowest risk of asset price drop. This assessment is crucial as even a high APY can be offset by a signifi cant drop in the reward asset value, leading to impermanent loss. * **Risk Mitigation Strategy** : By employing this method, our AI Aggregator aims to choose the most optimal pool, balancing high yield potential with minimal risk. The focus is not solely on the highest immediate return but on sustaining yield optimization over time, minimizing risks such as asset price volatility. --- # 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://fortuna-finance-1.gitbook.io/documentation/a.i-yield-aggregator/how-does-it-work.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.