<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>tailtest blog -- AI software testing in practice</title><description>Essays from the team building tailtest, the open-source testing platform for AI-built software.</description><link>https://www.tailtest.com/</link><language>en-us</language><item><title>From 47 OSS repos to 16 real bugs: testing Python with AI</title><link>https://www.tailtest.com/blog/47-oss-repos-16-real-bugs/</link><guid isPermaLink="true">https://www.tailtest.com/blog/47-oss-repos-16-real-bugs/</guid><description>We ran tailtest&apos;s adversarial test generation against 47 open source Python repos and filed 16 real bugs upstream. Methodology, categories, and what it implies.</description><pubDate>Wed, 13 May 2026 00:00:00 GMT</pubDate><author>Shridip Chandole</author></item><item><title>Building dev tools from Pune: distributed teams, timezone math</title><link>https://www.tailtest.com/blog/building-dev-tools-from-pune/</link><guid isPermaLink="true">https://www.tailtest.com/blog/building-dev-tools-from-pune/</guid><description>Building dev tools from Pune in 2026 with a US co-founder and a distributed team. What we learned about timezones, hiring, and the India dev ecosystem.</description><pubDate>Wed, 20 May 2026 00:00:00 GMT</pubDate><author>Varun Borawake</author></item><item><title>R15 adversarial mode: 8 edge cases AI agents miss</title><link>https://www.tailtest.com/blog/r15-adversarial-mode-8-edge-case-categories/</link><guid isPermaLink="true">https://www.tailtest.com/blog/r15-adversarial-mode-8-edge-case-categories/</guid><description>Adversarial test generation against 47 OSS Python repos found 16 real bugs across 8 categories of edge cases AI agents systematically miss. The full taxonomy.</description><pubDate>Wed, 04 Mar 2026 00:00:00 GMT</pubDate><author>Pallavi Joshi</author></item><item><title>The 5 Levels of AI Testing Maturity</title><link>https://www.tailtest.com/blog/the-5-levels-of-ai-testing-maturity/</link><guid isPermaLink="true">https://www.tailtest.com/blog/the-5-levels-of-ai-testing-maturity/</guid><description>Most teams shipping with AI coding agents are at Level 1 even when they think they&apos;re at Level 3. A maturity ladder for testing AI-built software: from manual catch-up to fully autonomous coverage.</description><pubDate>Tue, 28 Apr 2026 00:00:00 GMT</pubDate><author>Shridip Chandole</author></item><item><title>Why we open-sourced tailtest (and why MIT, not BSL)</title><link>https://www.tailtest.com/blog/why-we-open-sourced-tailtest/</link><guid isPermaLink="true">https://www.tailtest.com/blog/why-we-open-sourced-tailtest/</guid><description>An open source AI testing tool only earns trust if you can read the code. Why we picked MIT over BSL, and what we will never gate behind a paid tier.</description><pubDate>Wed, 04 Feb 2026 00:00:00 GMT</pubDate><author>Varun Borawake</author></item><item><title>Why Testing AI-Generated Code Is Fundamentally Different</title><link>https://www.tailtest.com/blog/why-testing-ai-generated-code-is-different/</link><guid isPermaLink="true">https://www.tailtest.com/blog/why-testing-ai-generated-code-is-different/</guid><description>Testing human-written code and testing AI-generated code share a name but very little else. Five differences that matter, and what they imply for which testing strategies actually work in 2026.</description><pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate><author>Shridip Chandole</author></item><item><title>AI software testing for non-developers (vibe coders)</title><link>https://www.tailtest.com/blog/ai-software-testing-for-non-developers/</link><guid isPermaLink="true">https://www.tailtest.com/blog/ai-software-testing-for-non-developers/</guid><description>AI software testing if you do not write code yourself: what the tools do, why your Claude Code app needs them, and how to set one up in one command.</description><pubDate>Tue, 17 Mar 2026 00:00:00 GMT</pubDate><author>Varun Borawake</author></item><item><title>AI test failure classification: real_bug vs test_bug</title><link>https://www.tailtest.com/blog/ai-test-failure-classification/</link><guid isPermaLink="true">https://www.tailtest.com/blog/ai-test-failure-classification/</guid><description>AI test failure classification routes broken tests by cause: real_bug, test_bug, or environment. Why three labels, the heuristics, and how R12 makes triage work.</description><pubDate>Mon, 13 Apr 2026 00:00:00 GMT</pubDate><author>Pramod W.</author></item><item><title>Hook-based testing: enforcing the test cycle outside the LLM</title><link>https://www.tailtest.com/blog/hook-based-testing-explained/</link><guid isPermaLink="true">https://www.tailtest.com/blog/hook-based-testing-explained/</guid><description>Hook-based testing fires the test loop at the agent&apos;s event boundary, not from the prompt. Why this jumps test compliance from 70 percent to 100 in practice.</description><pubDate>Wed, 18 Feb 2026 00:00:00 GMT</pubDate><author>Nikhil Jathar</author></item><item><title>Inside the Claude Code PostToolUse hook: what fires on edit</title><link>https://www.tailtest.com/blog/inside-claude-code-post-tool-use-hook/</link><guid isPermaLink="true">https://www.tailtest.com/blog/inside-claude-code-post-tool-use-hook/</guid><description>What the Claude Code PostToolUse hook fires when Claude edits a file: event payload, matchers, exit codes, and how tailtest hooks the lifecycle.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate><author>Vaishnavi Bangale</author></item></channel></rss>