Generative Engine Optimization with Python

Chapter 2. Topic Research

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].

The goal of this chapter is to identify the topics that will help a website maximize its visibility in AI search.

Topics from a Generative Engine Optimization (GEO) perspective are defined as individual content themes realized as website articles that each have their own URL.

One of the biggest challenges is determining which topics an organization should select to cover, create and publish, in order for their website content to be visible for their targeted prompts in Large Language Models (LLMs) driven AI search.

The Importance of Topic Coverage

Like search engines, a website will be considered more authoritative by LLMs if they have wider topic coverage for related prompts.

Search engines are still important because AI search platforms are highly reliant on search engine results to help check the outputs of the native LLM results before generating an answer to a user’s prompt.

Consider websites A and B from the same industry. Website A covers 100 topics while B ...