<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Trinh Vo — Writing</title><description>Notes on shipping LLM features, full-stack architecture and reliable systems.</description><link>https://trinhvo.com/</link><item><title>Webhooks time out. LLM workflows don&apos;t care.</title><link>https://trinhvo.com/blog/async-llm-workflows/</link><guid isPermaLink="true">https://trinhvo.com/blog/async-llm-workflows/</guid><description>Why long-running LLM evaluations broke behind synchronous webhooks, and the async pattern that fixed it.</description><pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate></item><item><title>A match nobody can explain is a match nobody trusts</title><link>https://trinhvo.com/blog/explainable-ai-matching/</link><guid isPermaLink="true">https://trinhvo.com/blog/explainable-ai-matching/</guid><description>Notes from building an LLM-powered business matching pipeline where traceability mattered as much as accuracy.</description><pubDate>Sun, 02 Aug 2026 00:00:00 GMT</pubDate></item><item><title>Designing one platform for four kinds of users</title><link>https://trinhvo.com/blog/one-engineer-four-roles/</link><guid isPermaLink="true">https://trinhvo.com/blog/one-engineer-four-roles/</guid><description>What building a garage booking system for customers, merchants, staff and admins taught me about schema-first product work.</description><pubDate>Sat, 20 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>