A methodology note: how we run 210 prompts a week without asking permission

The exact scan cadence, retry logic, and how we handle a model that starts rate-limiting mid-week.

The exact scan cadence, retry logic, and how we handle a model that starts rate-limiting mid-week. Published because this audience will ask.

Full post coming soon.

Marcus Webb
Writes about AI citation behavior and measurement methodology at doclight.
XGitHub
Want this measured for your own site?
Join the waitlist — we'll email you when it's your turn, no pricing promises.
Join waitlist
Choosing 40 prompts instead of 4,000: a case for a smaller, sharper prompt list6 minGoogle AI Overviews cites almost nothing you'd expect from ten years of SEO8 minWhat ChatGPT actually cites when you ask about developer tools9 min