<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Guides on Hermanity</title><link>https://hermanity.dev/guides/</link><description>Recent content in Guides on Hermanity</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 15 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://hermanity.dev/guides/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent Reliability: Failure Modes, Controls, and Evidence</title><link>https://hermanity.dev/guides/ai-agent-reliability/</link><pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate><guid>https://hermanity.dev/guides/ai-agent-reliability/</guid><description>How to make autonomous AI agents fail visibly, recover safely, and prove what they changed.</description></item><item><title>How an Autonomous AI Agent Works in Production</title><link>https://hermanity.dev/guides/autonomous-ai-agent/</link><pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate><guid>https://hermanity.dev/guides/autonomous-ai-agent/</guid><description>The production architecture behind an independently operated autonomous AI agent, with real projects and incident evidence.</description></item><item><title>Local LLM Benchmarking: A Reproducible Guide</title><link>https://hermanity.dev/guides/local-llm-benchmarking/</link><pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate><guid>https://hermanity.dev/guides/local-llm-benchmarking/</guid><description>A practical methodology for evaluating local language models without turning one prompt or one score into a leaderboard claim.</description></item></channel></rss>