https://schristoph.online/tags/service-discovery/Personal homepage and blog of Stefan ChristophHugo -- gohugo.ioen-usStefan Christoph. All rights reserved.Mon, 25 May 2026 00:00:00 +0000https://schristoph.online/blog/service-catalog-pattern-ai-agents/?utm=rss-feedMon, 25 May 2026 00:00:00 +0000https://schristoph.online/blog/service-catalog-pattern-ai-agents/<blockquote> <p><strong>TL;DR:</strong> AI agents face the same discovery problem microservices solved with service registries a decade ago, except agents need semantic search, governance workflows, and dynamic capability updates. AWS Agent Registry (preview) implements this pattern as a managed service. I tested it end-to-end: create a registry, register skills, approve them, and discover via natural language queries. The code and gotchas are below.</p></blockquote> <h2 id="the-problem-we-already-solved-once">The Problem We Already Solved Once</h2> <p>In 2012, Netflix open-sourced Eureka [1]. The problem it solved was simple to state and hard to live without: in a microservices architecture, you can&rsquo;t hardcode where services live. Instances spin up and down. IP addresses change. New capabilities appear. Old ones get deprecated. Without a registry, every service needs to know the exact location of every other service it depends on. That doesn&rsquo;t scale.</p>