This experience has lead most developers to “watch and wait” for the tools to improve until they can handle ‘production-level’ complexity in software. While genAI is improving dramatically in some sense (multi-modal, faster, smaller, cheaper), this barrier has so far proven more stubborn, with o1 seeing relatively low adoption and multi-agent frameworks failing to significantly scale reasoning capabilities.

Make Your Tools Work for You
Instead of trying to force genAI tools to tackle thorny issues in legacy codebases, human experts should do the work of refactoring legacy code until genAI can operate on it smoothly. When direct refactoring is still too risky, teams can adjust their development strategy with approaches like strangler fig to build greenfield modules which can benefit immediately from genAI tooling.