<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Raito&apos;s Runtime</title><description>Clear thinking about the systems we build, the tools we use, and the tradeoffs that shape both.</description><link>https://yaobieting.com/</link><language>en-US</language><item><title>Making Agent Workflows Reliable</title><link>https://yaobieting.com/articles/making-agent-workflows-reliable/</link><guid isPermaLink="true">https://yaobieting.com/articles/making-agent-workflows-reliable/</guid><description>A practical framework for turning capable but probabilistic AI agents into observable, recoverable, and testable production systems.</description><pubDate>Fri, 14 Aug 2026 00:00:00 GMT</pubDate><category>AI Engineering</category><category>AI agents</category><category>reliability</category><category>observability</category><category>testing</category></item><item><title>What Good API Boundaries Actually Buy You</title><link>https://yaobieting.com/articles/what-good-api-boundaries-actually-buy-you/</link><guid isPermaLink="true">https://yaobieting.com/articles/what-good-api-boundaries-actually-buy-you/</guid><description>API boundaries are more than interface style: they localize change, enforce invariants, and create operational leverage across a backend system.</description><pubDate>Fri, 07 Aug 2026 00:00:00 GMT</pubDate><category>Backend Systems</category><category>API design</category><category>architecture</category><category>backend</category><category>distributed systems</category></item><item><title>Debugging Distributed Systems Without Guessing</title><link>https://yaobieting.com/articles/debugging-distributed-systems-without-guessing/</link><guid isPermaLink="true">https://yaobieting.com/articles/debugging-distributed-systems-without-guessing/</guid><description>A disciplined method for moving from vague symptoms to testable hypotheses using timelines, correlation, and evidence from production systems.</description><pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate><category>Engineering Practice</category><category>debugging</category><category>observability</category><category>distributed systems</category><category>incident response</category></item></channel></rss>