An Illustrated Guide to AI Agents

Chapter 2. Large Language Models

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 2nd chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

As we saw in Chapter 1, the LLM powers agents to go from observations to actions. In Figure 2-1, we can see this general workflow. Here, we color-code the areas where the agent interacts with the user (on the left) and where the agent interacts with the environment (on the right).

Figure 2-1. The agent acts as a bridge between user and environment

Let’s take a simple example to unroll the loop we see in the figure. The example is a simple information-seeking agent trying to answer a question for a user using a web search tool. In Figure 2-2, we can see that interaction:

1. The user asks the agent a question.

2. The agent uses a web search tool, effectively pulling in information from the environment.

3. The retrieved information is presented to the agent, which decides that it now has enough information to answer the user’s question.

4. The agent prints out its ...