Author: Nick Clark

Nick Clark is a Research Engineer at Gumshoe and a Ph.D. candidate in Information Science at the University of Washington's Information School, one of the nation's top-ranked programs in the field. His research focuses on the intersection of artificial intelligence and information retrieval — specifically, how AI-native approaches can reshape the way people and organizations discover, evaluate, and act on knowledge.
At Gumshoe, Nick translates cutting-edge research into production AI search systems, working across the full stack from retrieval architectures to user-facing intelligence. His academic work at UW complements this applied focus, grounding it in rigorous study of how people interact with information and the social and technical implications of AI-mediated search.
With deep expertise spanning both industry R&D and academic research, Nick offers a rare perspective on where AI search is headed — and what it will take to get there responsibly. He is a sought-after voice on topics including retrieval-augmented generation, AI agents, and the future of search.

How Much Data Do You Need to Measure AI Visibility with Confidence?

Recent research from SparkToro and Gumshoe examined how consistent AI tools are when recommending brands and products. We found that individual AI responses are highly variable (you’ll rarely see the same answers twice), but the frequency with which a brand appears across many queries converges to a stable signal. Visibility, measured as the proportion of responses in which a brand appears, behaves like a well-defined probability that can be estimated with standard statistical tools.

How APIs Unlock Better Insights Into AI Search Visibility

A recent study from SurferSEO compared API responses to scraped web interface results across 1,000 ChatGPT prompts. They found the overlap between brands mentioned using the two methods was 24%. Their conclusion: “Monitoring responses from API as a proxy for your AI visibility is totally wrong.”
At Gumshoe, we read that study with interest. The data is real, but the conclusion misses the point.

What the Study Actually Shows

SurferSEO found significant differences between raw API calls and scr