<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Search on Tomasz Półgrabia</title><link>https://polgrabia.me/tags/search/</link><description>Recent content in Search on Tomasz Półgrabia</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 04 Oct 2026 19:00:00 +0200</lastBuildDate><atom:link href="https://polgrabia.me/tags/search/index.xml" rel="self" type="application/rss+xml"/><item><title>How to crawl the world - do we need Google?</title><link>https://polgrabia.me/posts/20261004-how-to-crawl-the-world-do-we-need-google/</link><pubDate>Sun, 04 Oct 2026 19:00:00 +0200</pubDate><guid>https://polgrabia.me/posts/20261004-how-to-crawl-the-world-do-we-need-google/</guid><description>&lt;h1 id="pre-word"&gt;Pre-word&lt;/h1&gt;&#10;&lt;p&gt;This is a rather tricky question. Or, to put it better - a question worth thinking about:&#10;how much do we actually depend on search engines?&lt;/p&gt;&#10;&lt;p&gt;In the age of AI we are being charged pretty much for every query or MCP call. Every web&#10;search made by an agent costs tokens, API credits, or a subscription tier. And it adds up&#10;quickly, because agents search a &lt;em&gt;lot&lt;/em&gt;. But does it need to be this way?&lt;/p&gt;</description></item></channel></rss>