AI engines disagree with each other and with themselves. A cross-engine consistency audit scores three dimensions across 50 UK queries to separate durable positions from noise.
We took 10 UK pages, applied one isolated change each, and measured citation rate after 4 weeks. Direct-answer block lifted +19pp; meta-description rewrites produced 0pp. Full ranked list with implementation time.
We tested 50 UK service firms across law, healthcare, accountancy, SaaS and construction against 60 prompts on ChatGPT, Perplexity and Gemini. SaaS led the league; construction posted zero citations. Full benchmark data.
We ran 30 family-law queries against ChatGPT, Perplexity and Gemini, logging every cited domain. Here is the league table of UK family-law firms and what separates the cited from the invisible.