# Prompting Prompts are the requests you send to a language model like ChatGPT that tells the system to return a response. Prompts can be a singular request or a combination of requests. The first request in a prompt is called the root request. In this section we discuss prompting in detail to provide a good foundation in applying processes from the various GDF knowledge areas to your prompts. The Prompting section consists of the following key concepts: * [Prompt Patterns](/gdf-full-stack-engineering/prompting/prompt-patterns.md) * [Prompt Context](/gdf-full-stack-engineering/prompting/prompt-context.md) * [Prompt Stores](/gdf-full-stack-engineering/prompting/prompt-stores.md) * [Prompt Operators](/gdf-full-stack-engineering/prompting/prompt-operators.md) * [Prompt Chaining](/gdf-full-stack-engineering/prompting/prompt-chaining.md) --- # 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.gdf.ai/gdf-full-stack-engineering/prompting.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.