The AI audit rep-curve: why 1 run gives you 67 percent reliability

For most of 2025, the standard AI-search audit I saw from peer agencies looked the same: run a list of prompts once each, screenshot the outputs, code the citations, write the report. Sometimes the prompt list was thoughtful. Sometimes the engines were comprehensive. The methodology, though, almost always assumed that one run per prompt was enough. It isn't. We learned this slowly, then quickly, then expensively. The pilot that broke our methodology Our first GEO audit, back in mid-2025, ran 30