Measurements, mechanisms and corrections from a practice building software with agents. Every figure carries how it was measured and when.https://www.aintelligenttech.com/en-gbhttps://www.aintelligenttech.com/blog/why-we-built-sentinel-enforcement-into-agent-development-tools/https://www.aintelligenttech.com/blog/why-we-built-sentinel-enforcement-into-agent-development-tools/Lifecycle hooks are stateless, but agent governance often depends on something that happened one or two events earlier. Here is the pattern we built to bridge that gap.Fri, 13 Mar 2026 04:40:00 GMThttps://www.aintelligenttech.com/blog/eslint-rules-prevent-lying-tests/https://www.aintelligenttech.com/blog/eslint-rules-prevent-lying-tests/How we turned our false-confidence taxonomy into three AST-level ESLint rules that catch deceptive test patterns before they reach CI.Thu, 12 Mar 2026 00:00:00 GMThttps://www.aintelligenttech.com/blog/false-confidence-testing/https://www.aintelligenttech.com/blog/false-confidence-testing/A systematic audit of 656 test files revealed that most of our test suite was providing the illusion of coverage while catching nothing.Thu, 12 Mar 2026 00:00:00 GMT