Track chatgpt ai rankings over time - how?

The trick is keeping everything identical between checks. Same list of prompts, same wording, a temporary chat each time so memory and personalisation don't creep in, and the same day each month. Log it in a sheet: date, prompt, mentioned yes/no, position, cited sources. The answers vary a lot between runs, so I run each prompt three times and count how many of the three mention us. A single answer tells you almost nothing.