<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Guardrails on Fernando Hermida</title><link>https://www.fernandohermida.com/tags/guardrails/</link><description>Recent content in Guardrails on Fernando Hermida</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 10 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.fernandohermida.com/tags/guardrails/index.xml" rel="self" type="application/rss+xml"/><item><title>Human-in-the-Loop Interrupts</title><link>https://www.fernandohermida.com/posts/agentic-ai-engineering-journey/06-human-in-the-loop-interrupts/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.fernandohermida.com/posts/agentic-ai-engineering-journey/06-human-in-the-loop-interrupts/</guid><description>How LangGraph&amp;rsquo;s interrupt() pauses a running graph mid-step to ask a human before a risky action, and how Command(resume=&amp;hellip;) picks it back up.</description></item><item><title>Structured Output as a Guardrail</title><link>https://www.fernandohermida.com/posts/agentic-ai-engineering-journey/07-structured-output-as-a-guardrail/</link><pubDate>Mon, 10 Aug 2026 00:00:00 +0000</pubDate><guid>https://www.fernandohermida.com/posts/agentic-ai-engineering-journey/07-structured-output-as-a-guardrail/</guid><description>How binding a Pydantic schema to a model or agent turns a probably-shaped response into a validated object, and what still isn&amp;rsquo;t guaranteed once it is.</description></item></channel></rss>