# Context Engine The Context Engine serves as Toggle’s perception system. It processes text, metadata, browsing activity, behavioral cues and communication trails, turning these signals into structured meaning. This processing pipeline produces a semantic structure called the Context Object. The object functions as a living map of the user’s digital workspace. It updates continuously as the user reads, writes, researches or switches tasks, allowing Toggle to maintain awareness of how different pieces of information relate to each other. The Context Engine uses a combination of symbolic parsing and embedding-based interpretation. Each element in the structure represents a meaningful unit such as a goal, a document, a topic or a time reference. By updating relationships between these elements in real time, the engine allows Toggle to understand what the user is doing and how their work is evolving. --- # 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://toggle.gitbook.io/togglex/oldgitbook-below/architecture-overview/context-engine.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.