<?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 Tim&#39;s Tech Thoughts</title>
    <link>https://cloudy.dev/tags/bedrock/</link>
    <description>Recent content in Bedrock on Tim&#39;s Tech Thoughts</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Thu, 30 Apr 2026 09:00:00 -0400</lastBuildDate>
    <atom:link href="https://cloudy.dev/tags/bedrock/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>OpenAI Comes to Amazon Bedrock: A Win for Model Consumers</title>
      <link>https://cloudy.dev/article/openai-on-amazon-bedrock/</link>
      <pubDate>Thu, 30 Apr 2026 09:00:00 -0400</pubDate>
      <guid>https://cloudy.dev/article/openai-on-amazon-bedrock/</guid>
      <description>&lt;p&gt;In a move that few would have predicted even a year ago, Amazon Web Services and OpenAI have announced a significant partnership that brings OpenAI&amp;rsquo;s frontier models — including Codex — directly into Amazon Bedrock. For those of us who build on AWS and care about where the AI ecosystem is headed, this is a genuinely exciting development.&lt;/p&gt;&#xA;&lt;p&gt;You can read the official announcements from both sides here: &lt;a href=&#34;https://openai.com/index/openai-on-aws/&#34; target=&#34;_blank&#34;&gt;OpenAI on AWS&lt;/a&gt;&#xA; and &lt;a href=&#34;https://www.aboutamazon.com/news/aws/bedrock-openai-models&#34; target=&#34;_blank&#34;&gt;AWS: Bedrock OpenAI Models&lt;/a&gt;&#xA;.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Amazon Bedrock&#39;s Security Model: What Enterprises Actually Need to Know</title>
      <link>https://cloudy.dev/article/amazon-bedrock-security/</link>
      <pubDate>Sat, 07 Mar 2026 10:32:00 -0400</pubDate>
      <guid>https://cloudy.dev/article/amazon-bedrock-security/</guid>
      <description>&lt;p&gt;One of the most common blockers I hear from enterprise teams evaluating generative AI isn&amp;rsquo;t about model quality — it&amp;rsquo;s about trust. &lt;em&gt;Where does our data go? Can AWS see our prompts? Will our inputs be used to train someone else&amp;rsquo;s model? Can we meet our compliance requirements?&lt;/em&gt; These are the right questions to ask, and Amazon Bedrock has spent considerable engineering effort making sure the answers are satisfying.&lt;/p&gt;&#xA;&lt;p&gt;This post walks through the core pillars of Bedrock&amp;rsquo;s security model: how inference stays private, what AWS commits to around your data, how to keep traffic off the public internet, what compliance certifications are in place, how IAM gives you fine-grained access control, and how AgentCore&amp;rsquo;s Cedar policies extend that control to the level of individual agent tool calls.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Amazon Bedrock AgentCore: The Infrastructure Layer Your AI Agents Have Been Missing</title>
      <link>https://cloudy.dev/article/amazon-bedrock-agentcore/</link>
      <pubDate>Mon, 02 Feb 2026 09:22:00 -0400</pubDate>
      <guid>https://cloudy.dev/article/amazon-bedrock-agentcore/</guid>
      <description>&lt;p&gt;Building an AI agent that works in a demo is one thing. Getting it to reliably work in production — across thousands of concurrent users, with proper security, memory, and observability — is an entirely different challenge. If you&amp;rsquo;ve ever tried to take an AI agent from prototype to production, you know exactly what I&amp;rsquo;m talking about. Months of undifferentiated infrastructure work: session management, identity controls, persistent memory, tool integrations, monitoring. All of it built from scratch, all of it before you&amp;rsquo;ve written a single line of your actual business logic.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
