<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AWS Well-Architected on Andreas Nissen</title><link>https://andreasnissen.dev/tags/aws-well-architected/</link><description>Recent content in AWS Well-Architected on Andreas Nissen</description><generator>Hugo</generator><language>en-us</language><copyright>© Andreas Nissen</copyright><lastBuildDate>Mon, 15 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://andreasnissen.dev/tags/aws-well-architected/index.xml" rel="self" type="application/rss+xml"/><item><title>The Hard Part of Agentic AI Starts After the Demo</title><link>https://andreasnissen.dev/writing/agentic-ai-after-the-demo/</link><pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate><guid>https://andreasnissen.dev/writing/agentic-ai-after-the-demo/</guid><description>&lt;p&gt;The hard part of agentic AI is not building the agent.&lt;/p&gt;&#10;&lt;p&gt;It is everything that happens after the demo works.&lt;/p&gt;&#10;&lt;p&gt;A prototype can take a few days. Production is a different discipline. Agents reason in loops, invoke tools, change external state, keep memory, and sometimes produce different answers to the same request. The request-response playbook that teams have used for conventional applications does not cover all of those behaviors.&lt;/p&gt;&#10;&lt;p&gt;The &lt;a href="https://docs.aws.amazon.com/wellarchitected/latest/agentic-ai-lens/agentic-ai-lens.html"&gt;AWS Well-Architected Agentic AI Lens&lt;/a&gt; gives teams a framework for closing that gap. It adapts all six Well-Architected pillars to the way agentic systems actually behave: operational excellence, security, reliability, performance efficiency, cost optimization, and sustainability.&lt;/p&gt;</description></item></channel></rss>