An Illustrated Guide to AI Agents

Chapter 5. Tool Usage, Learning, and Protocols

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 5th 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].

The tool module is such an interesting module for augmenting your LLM and generating autonomous behavior in agents. By themselves, regular LLMs are nothing more than functions that take in some text and output some text. Although that creates interesting chatbots, they cannot yet interact with their environment. Tools, in the form of functions and APIs, allow LLMs to step into the real world and interact with any system exposed to the LLM, ranging from codebases and internal tools to online databases and even home assistants.

A key trait that defines an agent is its ability to autonomously search for, select, and utilize tools, allowing it to interact with and influence its environment. With enough capabilities, agents can even create their own set of tools to use. Generally, tools allow an LLM to take action and interact with the external environment or extract data and use external applications (see Figure 5-1). The benefit of tools is not contained ...