# Passing Custom Data to an LLM In some cases, you might want to ask ChatGPT to review a specific set of data before giving its response. This is useful if you want ChatGPT to search through your database or a spreadsheet before picking a relevant response. You could even access a list of Slack Channels in a Google Spreadsheet and then ask ChatGPT to recommend Slack Channels based on an introduction. In this video, you’ll see how you can do this. {% embed url="" %} --- # 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://docs.pixiebrix.com/developing-mods/developer-concepts/using-bricks/bricks-for-ai/passing-custom-data-to-an-llm.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.