Field notes
Practical reads on getting cited by AI.
How AI assistants describe brands — and what to change so they describe yours accurately.
Research
The AI Visibility Benchmark: what we will publish, and what it cannot prove
A reproducible protocol for measuring how AI assistants describe brands, with pinned prompts, model snapshots, raw answers, and no invented causality.
3 min readby What The Model Says
AnalysisWhat llms.txt does, what it does not do, and who actually reads it
Adoption is climbing and the crawlers that matter are ignoring the file. Here is what the logs show, and why this site ships one anyway.
AnalysisWhy third-party sources outrank your own marketing pages
An assistant asked to recommend a tool rarely quotes the vendor. It quotes whoever wrote about the vendor — and the concentration is more extreme than most teams expect.
HackWrite one page that answers exactly one question
A page answering one question gets quoted. A page answering eight gets skimmed, and the assistant picks the wrong paragraph.