Articles

In this post, I walk you through how to build a simple prompt tracker, using a combination of Python and Colab, Gemini, BigQuery, and Data Studio. We will make requests using the API as opposed to browser interaction, but this will allow you to get your hands dirty and see what outputs entail. It will also process the unfriendly redirect URLs that the Gemini API includes in its citation data, translating it to the final real URLs, as well as include query fan out data.

Learn how to extract passages from your content based on how closely related they are to queries you input. You can use this as a simple way to begin optimizing your content for SEO and GEO.

Learn how to transform representative grounding queries into a list of probable fan out queries by vectorizing your real-world keyword data and comparing the grounding queries to them.

Learn how to track organic search traffic from Google AI Overviews and Google AI Mode without relying on URL fragments.

This is a follow-up from the post yesterday, and also a beginner’s starting point to learning how to make your BWT AI performance export data

Updated April 27, 2026 Yes, the title is terrible. But the content of this post is well worth it. Not so long ago, Bing Webmaster

You read that title correctly. You can do some form of server log file analysis on a Squarespace website, even though you cannot readily find the logs. Surprised?