<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Nishant Tamilselvan — Writing</title><description>Notes on enterprise AI governance, portfolio architecture, and the practical work of delivering secure digital services in the public sector.</description><link>https://tnishant.com/</link><language>en-ca</language><item><title>Model Context Protocol as an architecture knowledge system</title><link>https://tnishant.com/writing/mcp-as-an-architecture-knowledge-system/</link><guid isPermaLink="true">https://tnishant.com/writing/mcp-as-an-architecture-knowledge-system/</guid><description>Architecture standards fail at the moment of the decision. MCP moves them to where the decision is actually made.</description><pubDate>Thu, 25 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Six weeks, one mandate: architecture decisions when the date is not negotiable</title><link>https://tnishant.com/writing/six-weeks-one-mandate/</link><guid isPermaLink="true">https://tnishant.com/writing/six-weeks-one-mandate/</guid><description>A fixed launch date does not change what good architecture is. It changes which decisions you are allowed to defer.</description><pubDate>Thu, 09 Apr 2026 00:00:00 GMT</pubDate></item><item><title>What it actually takes to put AI inside a government delivery pipeline</title><link>https://tnishant.com/writing/ai-inside-a-government-delivery-pipeline/</link><guid isPermaLink="true">https://tnishant.com/writing/ai-inside-a-government-delivery-pipeline/</guid><description>Most AI pilots in the public sector fail at the governance seam. The work is in making governance something a delivery team can program against.</description><pubDate>Tue, 17 Feb 2026 00:00:00 GMT</pubDate></item></channel></rss>