A progression from harness foundations and adoption criteria through specifications, regression prevention, automated validation, approval gates, and drift detection
8 postsAI gives different answers to the same question, and it does not remember previous sessions. This article explains how I use the term Harness Engineering for this site's AI operation practices.
A three-part framework—repeatability, specificity, and verifiability—for deciding which recurring AI workflow problems belong in a harness.
Writing a specification before asking AI to implement reduces mismatches and repeated revisions. This article explains the Spec First principle and what to include in a simple specification.
While asking AI to add a blog article, I discovered that the navigation layout had also been changed without instruction. This article describes why that happened and how I addressed it with a rule in CLAUDE.md.
Manually checking the consistency of configuration files has limits. This article covers the process of building a validation script with AI and why automated detection proved useful.
A record of how a production build command ran while I was asking AI to make a separate change, and the approval-required rule I put in place afterward.
How AI Learning Playground positions Playwright alongside structural checks, URL verification, and human review.
How harness drift separates shared rules from tool-specific configuration, and how synchronization checks detect the mismatch earlier.
