> For the complete documentation index, see [llms.txt](https://docs.quadratichq.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.quadratichq.com/quadratic-ai/ai-memory-and-context.md). # AI memory & context ## AI memory & context Quadratic AI can remember durable context between chats so you don't repeat yourself. Memory lives at three levels: personal, team, and connection. ### Personal memory **Settings > AI** holds your personal memory — preferences and facts included in every chat you start. For example: "I prefer charts with a dark theme" or "Fiscal year starts in February." You can edit it directly, and the AI may propose updates as it learns your preferences. Version history lets you review and roll back changes. ### Team memory Your team settings hold shared context for everyone on the team: business definitions, naming conventions, metric formulas, and domain knowledge. Team editors can update it. Example: "ARR is calculated from the `subscriptions` table excluding trials. Our customer IDs look like CUST-XXXX." ### Connection context Each database connection can carry its own context — schema quirks, which tables matter, what joins to use. The AI reads it whenever it writes SQL against that connection. ### How the AI uses memory Memory is automatically included in AI chats. The AI can also update memory itself when you tell it something worth remembering ("remember that we report revenue in EUR") — updates are versioned, so you can always see what changed and revert. {% hint style="info" %} You can disable prompt storage entirely from your team's Settings page — see AI security. {% endhint %} --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.quadratichq.com/quadratic-ai/ai-memory-and-context.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.