<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Anthropic on Jack Monte — AI Engineer</title><link>https://jackmonte.com/tags/anthropic/</link><description>Recent content in Anthropic on Jack Monte — AI Engineer</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 10 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jackmonte.com/tags/anthropic/index.xml" rel="self" type="application/rss+xml"/><item><title>A Green Eval Was Lying to Me</title><link>https://jackmonte.com/posts/a-green-eval-was-lying/</link><pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate><guid>https://jackmonte.com/posts/a-green-eval-was-lying/</guid><description>Adding strict typing to my eval harness exposed an intermittent judge failure. Fixing that exposed a second bug a passing, zero-error evaluation had been hiding the whole time. A green eval is not a correct eval.</description></item><item><title>What I Learned Reading a Production SDK Cover to Cover</title><link>https://jackmonte.com/posts/reading-a-production-sdk/</link><pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate><guid>https://jackmonte.com/posts/reading-a-production-sdk/</guid><description>I made my RAG project production-ready by reading the Anthropic Python SDK end to end and stealing four patterns from it. Here is each one, why it mattered, and the lesson about reading source instead of docs.</description></item></channel></rss>