Field notes on AI accuracy, brand consensus, and the slow rewriting of search. Published weekly. No marketing fluff — only research, methodology, and the occasional polite teardown.
Consensus is a function of model diversity. We tested 11 LLMs against the same 60 brand questions. Three providers — ChatGPT, Gemini, Perplexity — captured 94% of the disagreement signal. Here's the math, the methodology, and the surprising omission.
A 4,000-domain audit reveals that brands with a well-formed llms.txt score 28 points higher on average — even when their JSON-LD is identical.
Google AI Overviews now appear on 47% of commercial queries. We pulled 12,000 SERPs to see which industries got hit hardest.
Christmasornot.com went from "ChatGPT doesn't know who you are" to top consensus in under a month. Here's the playbook.
Cohen's kappa was built for human raters. We adapted it for three stochastic models. The math is uglier than you'd hope.
Brands move slowly. Models move fast. Monitor Pro closes the gap with weekly automated re-scans and a CDN-cached AI Readiness Badge.
Anthropic's flagship is excellent at reasoning. It's also redundant with ChatGPT for consensus purposes. We picked diversity over depth.
Competitors measure visibility. We measure accuracy. Here's why the difference matters — and why your CMO should care.
"What does X cost?" is the single highest-disagreement query category. We analyzed 8,400 brand-pricing answers from three models.