Tag
Nolan Lawson argues that AI coding assistants can be used to write high-quality code slowly by employing multiple models for thorough code review and bug detection, improving codebase health rather than maximizing output speed.
Compares two AI agents handling skill reuse: one rewrites extraction logic from scratch each session while the other packages it into a dedicated, documented file, highlighting the need for agent skill persistence.
The article argues that teams should choose boring, well-understood technology for reliability, while being free to innovate in development practices like TCR (test && commit || revert), which are easier to adopt and abandon without long-term maintenance burden.