Answers are grounded in this paper and cite their sources.
This technical report presents a controlled comparison of Lighthouse 13.5.0 and 13.6.0 Agentic Browsing audits against the same production website, conducted on 2 November 2026. Two preserved Lighthouse JSON reports, collected approximately 108 seconds apart, were analysed to determine how software-version changes affect Agentic Resource Discovery (ARD) validation and audit applicability. Key findings: Lighthouse 13.5.0 reported 3/3 applicable checks passed, with the legacy ARD audit marked Not Applicable. Lighthouse 13.6.0 reported 4/4 checks passed, including successful ARD v0.91 manifest validation. Both versions retained a category score of 100% and identical recorded Cumulative Layout Shift values. The difference reflected changed audit applicability and discovery support, not demonstrated improvement in autonomous agent performance. The report documents the testing methodology, preserved evidence, reproducibility procedures and SHA-256 file-integrity hashes. It distinguishes technical conformance from actual AI-agent execution and does not claim improved search rankings, independent agent adoption or confirmed causation for earlier historical PageSpeed results. Author: Keith Rowley, Sydney Business WebTechnical Report: 13Version: 1.0.0Publication date: 15 November 2026
No takes yet. Share an insight, caveat, or question.
Keith Rowley (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: