Practical reference notes on prompt sets, citations, brand mentions, and honest measurement of AI visibility.
Matching posts
9 matching posts
Why ChatGPT Recommends Your Competitor
A diagnostic sequence for working out whether it's a model change, a prompt artifact, sampling noise, or a real visibility gap.
Nov 4, 2026 • RankRift
Read moreReading Variance: Telling A Real Change From Noise
It moved 12% — is that anything? How to decide when a change is worth acting on.
Nov 4, 2026 • RankRift
Read morePrompt-Set Mistakes That Make Your Visibility Score Meaningless
Seven ways a prompt set quietly flatters you, and a self-audit to catch each one.
Nov 4, 2026 • RankRift
Read moreWhen A Mention Isn't A Recommendation
Being named isn't the same as being recommended — and raw mention counts hide the difference.
Nov 4, 2026 • RankRift
Read moreHow To Measure AI Visibility In A Spreadsheet Before You Buy Anything
The free method, start to finish — and the exact point where it stops scaling.
Nov 4, 2026 • RankRift
Read moreHow Many Prompt Runs Do You Need? A Practical Sampling Guide
Three runs, three answers. How to size a test so the number you report means something.
Nov 4, 2026 • RankRift
Read moreNine Ways AI-Visibility Reports Mislead Executives
Cherry-picked prompts, single runs, brand-baiting, silent model changes — how to audit a report before you present it.
Nov 4, 2026 • RankRift
Read moreHow To Build A Prompt Set That Reflects How Your Buyers Actually Ask
Your score is only as honest as your prompts. A buyer-stage method for building a set that doesn't flatter you.
Nov 4, 2026 • RankRift
Read more