# Crawling At any time, you can request a crawl of your website or FAQ documents. We will load the information gained from the crawl into your AI agent, so that it will retrieve the most relevant piece of content to refer to when the GPT-3 fallback is used to answer a random utterance from a caller. For example, if a caller asks "How much does Simple Phones cost?" and the website was not crawled, the AI agent will just provide the general prompt about Simple Phones to GPT-3 (the one that was written when the agent was created) and so it will probably give an inaccurate answer. To fix this, once information from the website is loaded in, GPT-3 will automatically be prompted with the section of the website related to pricing, using a semantic search of the entire knowledge base, so it will give a much more accurate answer, in a comparable amount of time. --- # 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://help.simplephones.ai/basics/crawling.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.