# Part 1: Prompt Engineering {% embed url="" %} Welcome to the first part of your training: Prompt Engineering. In this section, you will learn the art and science of crafting effective instructions for AI agents. The instructions you write, also known as system prompts, are the single most important factor in determining an agent's behavior, personality, and performance. A well-crafted prompt can mean the difference between an agent that is helpful and accurate, and one that is confused and unreliable. Welcome to the first part of your training: Prompt Engineering. In this section, you will learn the art and science of crafting effective instructions for AI agents. The instructions you write, also known as system prompts, are the single most important factor in determining an agent's behavior, personality, and performance. A well-crafted prompt can mean the difference between an agent that is helpful and accurate, and one that is confused and unreliable. This section will cover everything from the basic anatomy of an instruction to advanced techniques for controlling agent behavior. You will learn how to use AI assistants to help you write prompts, how to create effective routing sections to guide agents to the right knowledge sources, and the best practices that we follow at raiaLabs to ensure consistent quality across all our client deployments. By the end of this section, you will be able to create clear, concise, and effective instructions for any type of AI agent. --- # 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.raiaai.com/ai-training/partner-training/raia-labs-training/part-1-prompt-engineering.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.