Cloudflare Web Search API Makes Crawler Rules Part of the Contract
Cloudflare’s Web Search API requires provider crawler identity, robots.txt compliance and source links. Here is what publishers and AI teams can verify.
Tagged collection
Latest articles tagged “AI Search Measurement”
Open an article for the complete method, evidence, limitations, and a focused reader discussion.
-
-
CITECHOICE Study: More Citation Credit, Uncertain First-Citation Gains
A controlled AI-search replay found more citation markers for structured source text, but no clear gain in whether a source was cited at all. Here is what publishers should measure.
-
ChatGPT and Gemini Shared No Source Domains in 76.7% of Product Checks
A product-advice preprint found no shared displayed source domains in 76.7% of matched ChatGPT and Gemini checks. What the test means for AI visibility audits.
-
AuthGR: What Authority-Aware Generative Retrieval Changes
An ACL 2026 industry paper connects authority-aware retrieval with stronger ranking judgments and higher click behavior inside a commercial search system.
-
GPT-6 Prompt Caching: The Real Cost Math for AI Search Audits
Prompt caching can materially reduce repeated AI-search evaluation costs, but only when the shared prefix survives tool, schema and configuration changes.
-
Top-500 Retrieval Still Missed Useful Evidence
Re:CAP recovered relevant documents missed by flat retrieval, including gaps left by a 1,500-candidate ensemble. That changes how retrieval coverage should be audited.
-
Baidu and Google Gave Similar AI Answers From Different Source Webs
A 500-query bilingual study found high answer similarity but very low cited-host overlap between Baidu and Google AI overviews.
-
AI Answer Citations Can Fail at Four Separate Layers
Four recent papers expose separate failure points between retrieval and a trustworthy AI citation. SearchEngineAnswer reproduced PageRecall’s public tier-0 checks and built a claim-level audit ledger.
-
AI Search Engines Cited Different Websites in a 960-Answer Study.
A 960-answer experiment and a separate B2B panel show why AI citations vary by engine, prompt type and measurement unit. Their percentages should not be pooled.
