Category: Data & Experiments
Controlled experiments measuring how specific content variables affect AI citation rates. Each experiment isolates a single variable — structure, entity density, freshness, or platform behaviour — and tests it under documented conditions with replicable methodology. Results include raw citation data, statistical significance assessments, and practical recommendations based on observed effect sizes.
-
What llms.txt Actually Does (And What It Doesn’t): A Measured Assessment
Read more →: What llms.txt Actually Does (And What It Doesn’t): A Measured AssessmentBy Artur Ferreira · The GEO Lab · Published: July 2026 What llms.txt Actually Does (And What It Doesn’t): A Measured Assessment The GEO Lab has an llms.txt. We still…
-
The ChatGPT Pre-Retrieval Gate: How Query Construction Determines Whether ChatGPT Searches at All
Read more →: The ChatGPT Pre-Retrieval Gate: How Query Construction Determines Whether ChatGPT Searches at AllBy Artur Ferreira · The GEO Lab · Published: June 2026 The ChatGPT Pre-Retrieval Gate: How Query Construction Determines Whether ChatGPT Searches at All You checked ChatGPT. Zero citations. The…
-
10 Probe Queries We Use to Test AI Citation Behaviour
Read more →: 10 Probe Queries We Use to Test AI Citation BehaviourTen distinct query types, each targeting a different layer of the retrieval pipeline — the working query taxonomy behind every GEO Lab experiment.
-
10 Variables That Change Between AI Citation Measurements
Read more →: 10 Variables That Change Between AI Citation MeasurementsTen concrete things that shift between two citation rate measurements even when your content hasn’t — the sources of the noise floor every GEO experiment has to account for.
-
Google AI Mode and AI Overview Are Separate Citation Surfaces
Read more →: Google AI Mode and AI Overview Are Separate Citation SurfacesGoogle AI Mode cited The GEO Lab on 20/30 checks where AI Overview cited it on 0/10 — zero overlap. A measurement that reads only the AIO block is blind…
-
What Google’s New GSC Generative AI Report Actually Measures (And What It Can’t)
Read more →: What Google’s New GSC Generative AI Report Actually Measures (And What It Can’t)By Artur Ferreira · The GEO Lab · Published: 14 June 2026 What Google’s New GSC Generative AI Report Actually Measures (And What It Can’t) Google handed you AI-visibility data…
-
Does Agent-Readiness Conformance Predict AI Citation? Pre-Registering the Test
Read more →: Does Agent-Readiness Conformance Predict AI Citation? Pre-Registering the TestTwo agent-readiness tools score the same site with near-zero overlap. This pre-registration tests whether conformance predicts AI citation after controlling for domain authority. Stated prior: null.
-
Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index.
Read more →: Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index.Claude Hits Record +72 on Perplexity. Ahrefs Bounces Back to Dominant. The June 2026 GEO Brand Citation Index. By Artur Ferreira · The GEO Lab · Published: 17 June 2026…
-
Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1
Read more →: Month 0: Why Every GEO Content Plan Needs a Baseline Before Month 1The measurement step that makes every phase of a GEO content strategy interpretable — and the experiment at The GEO Lab that made it unavoidable.
-
Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean Anything
Read more →: Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean AnythingBy Artur Ferreira · The GEO Lab · Published: 14 June 2026 Share of Model: Why Citation-Share Metrics Need a Noise Floor Before They Mean Anything The metric is citation…