<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="/rss-style.xsl"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>IntentGate — Field Notes</title>
    <link>https://intentgate.app/blog</link>
    <atom:link href="https://intentgate.app/rss.xml" rel="self" type="application/rss+xml" />
    <description>Field notes on AI agent authorization, runtime control, and IntentGate.</description>
    <language>en-gb</language>
    <lastBuildDate>Mon, 29 Jun 2026 15:12:04 GMT</lastBuildDate>
    
      <item>
        <title>Your DLP doesn&apos;t see what your agents send</title>
        <link>https://intentgate.app/blog/dlp-doesnt-see-agents/</link>
        <guid isPermaLink="true">https://intentgate.app/blog/dlp-doesnt-see-agents/</guid>
        <pubDate>Tue, 23 Jun 2026 00:00:00 GMT</pubDate>
        <description><![CDATA[Agent-to-model, model-to-agent, and agent-to-tool traffic are three new flows that bypass every DLP system built for humans moving files. Content classification belongs inside the authorization decision, not next to it.]]></description>
        <author>noreply@intentgate.app (Joe Cordoba)</author>
        <category>Strategy</category>
      </item>
      <item>
        <title>The 8th Domain: AI Security&apos;s Missing Control Category</title>
        <link>https://intentgate.app/blog/the-eighth-domain/</link>
        <guid isPermaLink="true">https://intentgate.app/blog/the-eighth-domain/</guid>
        <pubDate>Mon, 15 Jun 2026 00:00:00 GMT</pubDate>
        <description><![CDATA[Seven AI security domains are well-documented. The eighth, agent runtime authorization, is the one production AI agents actually need.]]></description>
        <author>noreply@intentgate.app (Joe Cordoba)</author>
        <category>Category</category>
      </item>
      <item>
        <title>What is IntentGate?</title>
        <link>https://intentgate.app/blog/what-is-an-intent-gate/</link>
        <guid isPermaLink="true">https://intentgate.app/blog/what-is-an-intent-gate/</guid>
        <pubDate>Sat, 13 Jun 2026 00:00:00 GMT</pubDate>
        <description><![CDATA[IntentGate is the runtime authorization layer that evaluates an AI agent's proposed actions against policy, before they execute. Self-hosted, auditable, vendor-neutral.]]></description>
        <author>noreply@intentgate.app (Joe Cordoba)</author>
        <category>Category</category>
      </item>
      <item>
        <title>The Replit Incident: What IntentGate Would Have Caught</title>
        <link>https://intentgate.app/blog/the-replit-incident/</link>
        <guid isPermaLink="true">https://intentgate.app/blog/the-replit-incident/</guid>
        <pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate>
        <description><![CDATA[In July 2025, an AI coding agent destroyed Replit's production database during a code freeze and fabricated audit log entries. The incident sits cleanly in the gap that IntentGate category exists to fill.]]></description>
        <author>noreply@intentgate.app (Joe Cordoba)</author>
        <category>Incident</category>
      </item>
      <item>
        <title>Why blocking AI agents is not the answer</title>
        <link>https://intentgate.app/blog/why-blocking-ai-agents-is-not-the-answer/</link>
        <guid isPermaLink="true">https://intentgate.app/blog/why-blocking-ai-agents-is-not-the-answer/</guid>
        <pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate>
        <description><![CDATA[The most common response to AI agent risk in enterprises today is to block the agents. Blocking is not a control. It is the absence of a control, and it costs more than it saves.]]></description>
        <author>noreply@intentgate.app (Joe Cordoba)</author>
        <category>Strategy</category>
      </item>
  </channel>
</rss>