Most teams treat LLM output as deterministic. We measured 180,000 responses across four AI engines for 18 months and found the opposite: visibility drops 30% overnight, and the engines agree on 11%.
Over 90 days I tracked how six AI search engines cite sources across 50,000+ B2B software responses. The data broke several assumptions the GEO industry treats as settled, starting with the idea that AI visibility is one thing you can optimize for.
I tracked 50,000 citations across ChatGPT Search, Perplexity, Claude, Gemini, Google AI Overviews, and Bing Copilot for 90 days. What actually moved citation share, and what didn't.