Build an AI Agent (From Scratch)

2 The brain of AI agents: LLMs

This chapter covers

• Selecting the right LLM for agent development
• Using LLM APIs with LiteLLM
• Using prompt engineering for agents
• Experiencing LLM limitations through the GAIA benchmark

Throughout this book, we’ll build a research agent—a system that can interpret requests such as “survey recent work on X” and “extract key findings from these PDFs,” gather information from multiple sources, and synthesize findings into comprehensive answers. At the heart of this agent is the large language model (LLM), which serves as its decision-making brain. But before we can build an effective agent, we have to answer some fundamental questions. Which LLM should we use, and how do we communicate with it programmatically? ...