<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Bedrock on Ted Factory</title><link>https://tedfactory.com/en/tags/bedrock/</link><description>Recent content in Bedrock on Ted Factory</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 19 Jul 2026 20:04:48 +0900</lastBuildDate><atom:link href="https://tedfactory.com/en/tags/bedrock/index.xml" rel="self" type="application/rss+xml"/><item><title>I Thought AWS Bedrock Was Just Relaying Models — Turns Out It Runs Them Directly</title><link>https://tedfactory.com/en/notes/essays/aws-bedrock-how-it-works/</link><pubDate>Sun, 14 Jun 2026 00:00:00 +0900</pubDate><guid>https://tedfactory.com/en/notes/essays/aws-bedrock-how-it-works/</guid><description>&lt;h1 id="i-thought-aws-bedrock-was-just-relaying-models--turns-out-it-runs-them-directly"&gt;I Thought AWS Bedrock Was Just Relaying Models — Turns Out It Runs Them Directly&lt;a class="anchor" href="#i-thought-aws-bedrock-was-just-relaying-models--turns-out-it-runs-them-directly"&gt;#&lt;/a&gt;&lt;/h1&gt;
&lt;p&gt;&lt;img src="https://tedfactory.com/images/notes/aws-bedrock-how-it-works-cover.png" alt="How AWS Bedrock runs external AI models directly inside an encrypted vault" /&gt;&lt;/p&gt;
&lt;h2 id="it-started-with-a-small-question"&gt;It Started With a Small Question&lt;a class="anchor" href="#it-started-with-a-small-question"&gt;#&lt;/a&gt;&lt;/h2&gt;
&lt;p&gt;I knew that with AWS Bedrock you could call external LLMs (Large Language Models) like Claude or GPT. But the more I thought about it, the stranger it seemed. Claude is a model owned by Anthropic, and GPT is a model owned by OpenAI. These are another company&amp;rsquo;s core assets — so how on earth does AWS get to offer them inside its own service?&lt;/p&gt;</description></item></channel></rss>