# Part 2: Agent Training ### Training on Knowledge & Data {% embed url="" %} Welcome to the second part of your training: Agent Training. While prompt engineering defines the agent's personality and goals, the agent's knowledge and intelligence come from the data it is trained on. In this section, you will learn how to effectively manage and prepare data to create knowledgeable and accurate AI agents. This section will cover the entire data lifecycle, from preparing raw documents to creating sophisticated, derivative knowledge bases. You will learn the best practices for managing files, the technical aspects of working with vector stores (explained in a non-technical way), and how to use raia Academy to transform documents into AI-ready formats. We will also cover the powerful technique of creating derivative data with Manus to enhance agent performance and the use of AI Agent Packs for modular, reusable training. By the end of this section, you will be able to build and manage a comprehensive and effective knowledge base 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-2-agent-training.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.