Whitepaper on How to Optimise for AEO and GEO
Results from a two-month experiment testing what actually affects AI answers across ChatGPT, Gemini, Perplexity, Copilot and Google.
Ben Rees - 21 January 2026
Below are the details of 2-month experiment I undertook, to understand what affects AI answers in ChatGPT, Gemini, Perplexity, Copilot and Google.
A Weighted Sum of Everything Ever Written About You
What Bayesian linear regression, copied by hand from a textbook I've owned since January 2007, tells us about getting cited by AI.
Making decisions in a Bayesian world
Most marketing decisions can't be A/B tested. Bayesian logic, combining prior knowledge with whatever data you do have, fills the gap.
Your B2B claim is too broad for AI to cite. Narrow the scope
Why B2B marketing claims that are too broad get absorbed into category noise by AI systems, and how to reframe them into queries AI actually cites.
There's a precise point where your brand and a competitor collapse into the same thing
A 2026 theory of feature geometry shows superposition isn't a vague crowding problem, it's a specific mathematical collapse. Here's what that means for how much content actually earns its own identity.