Does FAQPage schema raise AI crawl frequency or citation?

Status: closed as inconclusive on 21 October 2026. The original review date remains 8 July 2026. The design below records what was intended in that window; it is not a promise that the current article versions remain unchanged.

Closure review — 21 October 2026

The production readout inspected on 21 October 2026 was inconclusive: treatment 5 before / 7 after (12 total), control 5 before / 6 after. The treatment total was below the existing minimum of 20 claimed requests. These are historical User-Agent counts, not verified identities. The analyser uses 14 calendar days before and 14 after 8 June (25 May–7 June and 8–21 June); this is narrower than the protocol's 8 July review date. We disclose that mismatch rather than retrospectively change the analysis window to seek a result. The observation does not establish that the intervention caused more citations. Crawler requests are a proxy, not human exposure or citation. Historical requests cannot be retrospectively verified without appropriate IP evidence. A small pair and short baseline cannot settle a weak effect; a null or unavailable observation is not evidence that the method never works.

We preserved the article and protocol snapshots with SHA-256 checksums before the October editorial updates. That preservation establishes the pre-update state, not byte identity across the original window. The scheduled July review was overdue; this closure must not be backdated to July.

The monthly site-wide citation history is available in the Lab, including a September citation. It is not page-level attribution and is outside the original review window. No new paid panel run was made for closure. A restart requires a new versioned protocol, dates, page snapshots, equal measurement of both arms, minimum analysable sample, missing-data rules and an approved provider budget. This protocol has not restarted.

Historical protocol

The question

Does shipping a visible FAQ with FAQPage JSON-LD actually earn more AI attention, or do the crawlers just read the page and ignore the markup? This is the smaller, on-site version of the MVP-4 Schema.org A/B test design — one matched pair on our own domain, as a first signal before any multi-domain study.

The design

• Treatment: a real, visible FAQ section was added to GEO vs AEO vs LLMO vs SGE, built from the article's own term-comparison content. The FAQPage JSON-LD is emitted automatically by the lib/seo builder — the schema mirrors exactly the questions a reader sees.
• Control: Knowledge cutoff and web access was designated to remain unchanged during the original window.
• Primary metric: AI-crawler hits per page, before vs after, treatment minus control (difference-in-differences). This is the free, page-level signal from the nginx-log pipeline.
• Window: the before window is whatever per-page crawl history exists (short — tracking began ~2026-05-31); the review is 2026-07-08.

Why these two pages

Both are foundations explainer spokes, so page type is held roughly constant — the cleaner design the original proposal said to wait for. The treatment page had FAQ-able term-comparison content but no FAQ block yet; the control is the nearest comparable foundations explainer. Residual differences in length and topic remain and are disclosed above.

The parked half: site-wide citation

The secondary signal — whether site-wide citation rate moves — needs the LLM-API citation harness, which is parked. No harness was run for this launch. If/when API spend is re-enabled, the site-wide citation trend will be attached at review as directional context only (it is never page-attributable). The primary read is the FREE crawler re-fetch frequency, already accruing.

What would count as a result

A clear, repeated rise in crawler hits on the treatment page that the control page does not share, sustained across the window. Anything smaller, on a two-page sample, we will report as inconclusive rather than dress up as a finding — and on this short before-window, an early inconclusive is the expected, honest outcome.