web-search

Coverage of how AI systems retrieve, filter, and rank results from the open web, and what that means for what users actually see. Expect hands-on testing of search backends, comparisons between proprietary filtering APIs and self-hosted options like SearXNG, and reproducible methods for measuring coverage and bias. The focus is practical: understanding the retrieval layer that feeds AI answers, where it narrows results, and how to audit or route around it.

ai-search, search-filtering, searxng, web-search, ai-tools

The AI "Web Search" That Quietly Decides What You're Allowed to Find

AI tools advertising 'web search' actually route queries through proprietary filtering APIs that silently decide what you can find. A reproducible three-query test found an unfiltered SearXNG instance returning 55 links versus 28 and 10 from two major AI search backends.