# Search ## Helio's Search Algorithm ### Core Feature Helio's main feature consists of its search algorithm, which utilizes an optimized graph structure to efficiently store and process connections between data. All user graphs are stored in our database, and are used as data points for training our model. ### Data Processing & Pattern Recognition The idea is that because all data is on-chain, we are able to determine patterns and preemptively act on them. With optimized processing, even CEX data can be associated back to specific wallets, as data patterns are exposable in any scheme. ### Algorithm Implementation Our algorithm runs on a heuristic style DFS search, where more promising paths are explored and unpromising paths are discarded. What is considered an unpromising path is continuously iterated upon. ### Technical Rationale Because of the limits of accessing on chain data, a heuristic style search is necessary to limit the time complexity and augment the speed of the algorithm. ### Future Development Of course, we can't fully reveal our secret sauce, but just know, this is the worst our algorithm will ever be. --- # 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://helio.gitbook.io/helio/inner-workings/quickstart.md?ask= ``` 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.