# deepcat Made with ChatGPT o1-preview. Am registering that I've learned what I needed to learn from this level of language, and it feels like it's suitable to transition. [AI-first coding is very different than AI-assisted coding.](/2024/11/12/a-future-of-ai-code.md) :) I have an [opportunity to change](/2024/11/08.md#theres-an-opportunity-here-for-me-to-change-and-im-feeling-it-out). Anyway, this script is good for starting with a single markdown file from a GitBook-backed repository, and printing out that file *and all of its references, recursively* so that you can hand a piece of content to an AI model with all its relevant context. {% 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://www.isaacbowen.com/2024/11/11/deepcat.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.