Entity Name Consistency

What this parameter measures

Two things keep your entities legible to AI systems, and this parameter checks both: consistent brand-name capitalisation, and H2 sections that stand on their own. friendly4AI collects multi-word capitalised phrases (two or more consecutive capitalised words, with leading articles and prepositions stripped) from your headings and paragraphs, groups them by their lowercase form, and flags any group that appears in two or more distinct case forms — for example "GEO Scanner" alongside "Geo scanner". It then examines each H2 section's first sentence and flags those that open with an anaphoric pronoun: It, This, or They. The check is English-only; pages whose lang is not English are skipped.

Why it matters for AI-readiness

AI knowledge graphs resolve your brand into a single entity by matching its name across mentions. When the same name appears in several capitalisations, the graph can fragment it into separate entities and dilute the authority signal you have built. Anaphoric openings cause a related problem at extraction time: a section that begins "It also handles billing" loses all meaning when a model lifts it out of context, because "It" no longer points to anything. Naming the entity explicitly in each H2 section keeps every passage self-contained and citable.

How we score it

Under the v4.4 methodology, this Content Structure parameter is a penalty-based gradient. The processor starts at 100 and computes max(0, 100 - brandInconsistencies * 15 - pronounDriftInstances * 10). A page passes with no brand-name case variants and no anaphoric H2 openings. It earns a partial with one or two of either issue — each brand inconsistency costs 15 points and each pronoun-drift section costs 10. It fails when penalties accumulate to a confused entity graph (roughly three or more brand variants, three or more anaphoric openings, or a mix). Non-English pages return SKIPPED (non_english_language) rather than a score, since the detection rules are tuned for English capitalisation and pronouns.

How to fix common issues

• Choose one canonical capitalisation for your brand name and apply it everywhere in headings and body copy.
• Rewrite H2 section openers that start with "It", "This", or "They" to name the subject explicitly in the first sentence.
• Keep each section's opening sentence understandable on its own, as if a reader landed there directly from a search.
• Remember each brand variant costs 15 points and each anaphoric opening costs 10 — fixing the most frequent offenders first recovers the most score.
• Re-scan and check the brandVariants, brandInconsistencies, and pronounDriftInstances evidence fields.