<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Testing in Practice</title><description>Practical guides for experienced software testers moving into AI/LLM testing — mutation testing, prompt contracts, evals, and CI gates. By the author of the book “AI Testing in Practice”.</description><link>https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/</link><item><title>Codex or Claude wrote my tests — how do I actually trust them?</title><link>https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/trust-ai-generated-tests/</link><guid isPermaLink="true">https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/trust-ai-generated-tests/</guid><description>A green AI-generated suite proves the code does what it already does, bugs and all. The only way to earn confidence is to break the code on purpose and watch the tests fail.</description><pubDate>Fri, 30 Oct 2026 00:00:00 GMT</pubDate></item><item><title>From experienced tester to AI testing: the roadmap, in order</title><link>https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/experienced-tester-ai-testing-roadmap/</link><guid isPermaLink="true">https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/experienced-tester-ai-testing-roadmap/</guid><description>You don&apos;t need a data-science degree to test AI. Here&apos;s the order to actually learn it, built on what you already know as a tester.</description><pubDate>Thu, 29 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Real bug or model failure? How to tell the difference in AI tests</title><link>https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/real-bug-or-model-failure/</link><guid isPermaLink="true">https://ai-testing-in-practice.ai-testing-in-practice-site.workers.dev/articles/real-bug-or-model-failure/</guid><description>When an AI test goes red, it&apos;s either a genuine defect or the model behaving differently. Here&apos;s a practical way to separate the two instead of guessing.</description><pubDate>Tue, 27 Oct 2026 00:00:00 GMT</pubDate></item></channel></rss>