# Build on MapsIndoors with LLMs Large Language Models (LLMs) process plain text formats more effectively than web-based formats like HTML and CSS. To optimize our documentation for LLMs, you can append specific suffixes that transform the content into LLM-friendly formats such as plain text or markdown. LLM-optimized documentation ensures that AI systems like ChatGPT, Claude, Cursor, and Copilot can retrieve and provide accurate, contextual responses about your product or API. ## Markdown Add `.md` to the URL to serve the page as a markdown file. The markdown file will be much easier for your chosen LLM to work with, than directly linking to the URL of our documentation.\ \ Example:

You can also quickly access both the markdown file and open it directly in ChatGPT or Claude from this dropdown.

## llms.txt `llms.txt` is a proposed standard for making web content available in text-based formats that are easier for LLMs to process. The `llms.txt` file contains an index of all the page URLs and titles of our documentation. You can find that here: . You can also fetch the full content of our documentation in one file that can be passed to LLMs as context. That is available here: . --- # 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.mapsindoors.com/other/build-on-mapsindoors-with-llms.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.