<?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>Microsoft Entra on Yogesh Thanvi</title>
    <link>https://yogeshthanvi.com/tags/microsoft-entra/</link>
    <description>Recent content in Microsoft Entra on Yogesh Thanvi</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 13 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yogeshthanvi.com/tags/microsoft-entra/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Securing Agentic AI on Azure: Guardrails for Azure OpenAI and AI Foundry Agents</title>
      <link>https://yogeshthanvi.com/posts/securing-agentic-ai-on-azure/</link>
      <pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://yogeshthanvi.com/posts/securing-agentic-ai-on-azure/</guid>
      <description>An AI agent that can call tools and take actions is not a chatbot. It is a new identity and a new attack surface. Here are the guardrails I would put around agentic workloads on Azure OpenAI and AI Foundry, built from the same principle I apply everywhere: enforce at the point every request passes through.</description>
    </item>
  </channel>
</rss>
