Microsoft Web IQ: Audit Evidence Objects Before Trusting Benchmarks
Audit Web IQ source passages, ownership, support, freshness, duplication, context selection, latency, and failures without inheriting vendor benchmark claims.
-
-
Perplexity Router API vs Agent API: Which Provides Web Grounding?
Compare Perplexity Router and Agent API by retrieval ownership, tool evidence, citations and fallback using a 24-field run ledger.
-
Google-GeminiNotebook Replaced Google-NotebookLM: Update Log Parsers Without Losing History
Google renamed the NotebookLM crawler token. Update exact-match rules and analytics without splitting one crawler into two histories.
-
Brave Search MCP for Claude: Preserve Retrieval Evidence and Citation Provenance
Brave documents a Claude and Bedrock MCP workflow for live search. Preserve the request, generated query, raw response, selected evidence, and final citation separately.
-
Kagi AI-On vs AI-Off: A Reproducible Search Test Protocol
Compare Kagi AI-on and AI-off search through paired queries, fixed account settings, randomized order, separate result layers, transparent limitations and a reusable ledger.
-
Which Schema.org Types Are Actually Used Across the Web? July 2026 Data
Official May–July data shows Product and Offer entering the 10M+ domain bucket in June and Article entering it in July, with important coverage limits.
-
How to Test Whether a Public ChatGPT Site Is Indexable
OpenAI allows eligible users to publish ChatGPT Sites publicly, but public access is not proof of indexability. Use this controlled technical audit before reporting results.
-
WordPress 7.1 SEO and Performance Preparation Checklist
Prepare WordPress 7.1 on staging by testing responsive controls, theme breakpoints, interactive states, media processing, technical signals, and rollback.
-
Cloudflare Pay Per Use: Build a 31-Field Pilot Ledger
Separate Cloudflare’s experimental Pay Per Use partner models from live controls, then reconcile reported uses, rights, deductions, payouts and rollback evidence.
