Originally published on hexisteme notes.
Everyone writing about SEO now has a second acronym to sell you: GEO — generative engine optimization, getting your content surfaced when someone asks an AI assistant instead of typing into a search box. The advice is abundant and reasonable: FAQ schema, a question-and-answer voice, clean canonical HTML. What almost nobody does is check whether any of it worked. You can pour weeks into being AI-legible with no idea whether a single assistant has ever surfaced you to a single person. That is not optimization; it is superstition with a publishing calendar. Here's the cheap harness I built to turn the question into a number I can watch.
GEO is unfalsifiable until you measure citations. The probe is small: a fixed set of questions your users would actually ask, fired weekly at a grounded model that returns citation URLs (Perplexity Sonar, via OpenRouter), and a deterministic substring check for your owned patterns. Append every run to a ledger and the citation rate becomes a trend — the falsifier: if the rate doesn't move after you "optimize," the optimization was fiction. The hard parts aren't the code; they're keeping the match honest, stopping failures from faking a zero, and not measuring too early.
