<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Posts on The Agentic Architect</title>
    <link>https://theagenticarch.com/posts/</link>
    <description>Recent content in Posts on The Agentic Architect</description>
    <image>
      <title>The Agentic Architect</title>
      <url>https://theagenticarch.com/og-image.png</url>
      <link>https://theagenticarch.com/og-image.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 10 Nov 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://theagenticarch.com/posts/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>What 20 Years of API Design Taught Me About Agents</title>
      <link>https://theagenticarch.com/posts/what-20-years-of-api-design-taught-me-about-agents/</link>
      <pubDate>Tue, 10 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/what-20-years-of-api-design-taught-me-about-agents/</guid>
      <description>We spent two decades making APIs easy for developers to discover and consume. Agents change the consumer, and the old lessons apply in a stricter form.</description>
    </item>
    <item>
      <title>Your Agent Shouldn&#39;t Need Your Laptop</title>
      <link>https://theagenticarch.com/posts/always-on-agents-need-a-home/</link>
      <pubDate>Thu, 05 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/always-on-agents-need-a-home/</guid>
      <description>Proactive agents need integrations, live events, and compute that stays reachable. A better sandbox on a Mac mini is not production. The real requirement is an agent that is always available, not always running.</description>
    </item>
    <item>
      <title>A Simple Agent Request Is Actually a Distributed System</title>
      <link>https://theagenticarch.com/posts/agent-request-is-a-distributed-system/</link>
      <pubDate>Tue, 03 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agent-request-is-a-distributed-system/</guid>
      <description>Ask an agent for the weather and ten messages cross five components. Agentic AI is not only an AI problem. It is a distributed-systems problem, and it needs distributed-systems discipline.</description>
    </item>
    <item>
      <title>Start Here: Six Essays on the Architecture Beneath AI Agents</title>
      <link>https://theagenticarch.com/posts/start-here/</link>
      <pubDate>Mon, 02 Nov 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/start-here/</guid>
      <description>A reading guide to The Agentic Architect: six essays on the APIs, events, context, memory, and control beneath useful, trustworthy AI agents, in the order that makes the argument easiest to follow.</description>
    </item>
    <item>
      <title>AGNTCon &#43; MCPCon San Jose: MCP Grows Up, and So Do the Attackers</title>
      <link>https://theagenticarch.com/posts/agntcon-mcpcon-san-jose-recap/</link>
      <pubDate>Wed, 28 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agntcon-mcpcon-san-jose-recap/</guid>
      <description>My takeaways from two days at AGNTCon &#43; MCPCon North America: MCP tasks and events, skills over MCP, agent identity, and what Solo.io announced, including Agent Shield, standalone agentgateway, and Agent Substrate.</description>
    </item>
    <item>
      <title>Events Are APIs Too</title>
      <link>https://theagenticarch.com/posts/events-are-apis-too/</link>
      <pubDate>Tue, 27 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/events-are-apis-too/</guid>
      <description>Event streams are business products, not an ungoverned firehose. Treating them like APIs makes real-time context usable for people, applications, and agents.</description>
    </item>
    <item>
      <title>Your AI Agent Needs a History, Not Just a Memory.</title>
      <link>https://theagenticarch.com/posts/agents-need-history-not-just-memory/</link>
      <pubDate>Tue, 20 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agents-need-history-not-just-memory/</guid>
      <description>Current state and semantic memory are useful, but a durable ordered history is what makes agent decisions explainable and recoverable.</description>
    </item>
    <item>
      <title>Agents Don’t Really Talk. They Exchange Context.</title>
      <link>https://theagenticarch.com/posts/agents-exchange-context/</link>
      <pubDate>Tue, 13 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agents-exchange-context/</guid>
      <description>Multi-agent systems are context-distribution systems. Reliable handoffs need contracts, ownership, and evidence—not conversational improvisation.</description>
    </item>
    <item>
      <title>Building the Context Layer</title>
      <link>https://theagenticarch.com/posts/building-the-context-layer/</link>
      <pubDate>Tue, 06 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/building-the-context-layer/</guid>
      <description>A practical architecture for connecting agents to APIs, events, knowledge, and controls without creating another centralized bottleneck.</description>
    </item>
    <item>
      <title>iPaaS Was Built for Applications. Agents Need a Context Layer.</title>
      <link>https://theagenticarch.com/posts/agents-need-a-context-layer/</link>
      <pubDate>Tue, 29 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agents-need-a-context-layer/</guid>
      <description>Traditional integration moves data along predetermined paths. Agentic systems need a governed context layer that can be discovered and assembled at runtime.</description>
    </item>
    <item>
      <title>Your Agents Don’t Need Better Models. They Need Better Plumbing.</title>
      <link>https://theagenticarch.com/posts/agents-need-better-plumbing/</link>
      <pubDate>Tue, 22 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/agents-need-better-plumbing/</guid>
      <description>Agentic systems usually fail at the integration layer: context, capabilities, identity, and controls—not at the model.</description>
    </item>
    <item>
      <title>The Agentic AI Race Starts With APIs</title>
      <link>https://theagenticarch.com/posts/the-agentic-ai-race-starts-with-apis/</link>
      <pubDate>Sun, 20 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/the-agentic-ai-race-starts-with-apis/</guid>
      <description>API infrastructure offers a strong foundation for agentic AI—but only vendors that treat agents as first-class architectural concerns will lead the transition.</description>
    </item>
    <item>
      <title>From Pong to Minecraft: How GenAI Is Redefining the User Experience</title>
      <link>https://theagenticarch.com/posts/from-pong-to-minecraft-genai-ux/</link>
      <pubDate>Thu, 20 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/from-pong-to-minecraft-genai-ux/</guid>
      <description>Generative AI shifts enterprise software from predefined workflows to intent-driven experiences—and makes architecture the foundation of UX.</description>
    </item>
    <item>
      <title>Welcome to The Agentic Architect</title>
      <link>https://theagenticarch.com/posts/hello-agentic-arch/</link>
      <pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://theagenticarch.com/posts/hello-agentic-arch/</guid>
      <description>A point of view on the architecture, capabilities, and controls that make AI agents useful in the real world.</description>
    </item>
  </channel>
</rss>
