# Reasoning Core The Reasoning Core is the analytical center of Toggle. It transforms contextual information into structured understanding, identifies priorities and interprets the implications of the user’s activity. **The core performs three categories of reasoning:** * **Semantic reasoning**, which interprets intent, relevance and conceptual relationships. * **Temporal reasoning**, which evaluates sequence, timing and priority. * **Reflective reasoning**, which considers uncertainty, risk and alternative paths. To achieve this, the Reasoning Core uses a coordinated ensemble of language models trained for different purposes. One model focuses on structural parsing, another on semantic interpretation and another on inference. A coordination layer ensures consistency across all outputs. Each reasoning step is logged inside Toggle’s introspection system, which allows users and auditors to review how the system arrived at a given interpretation or recommendation. --- # 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/reasoning-core.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.