AI coding tools can rapidly generate scaffolding and basic patterns, but often leave developers struggling with the remaining 70% of work—integration, security, edge cases, and debugging. Google's Addy Osmani discusses how AI-generated code creates a code review bottleneck for senior engineers, as trust in AI output declines despite rising adoption. He recommends understanding generated code thoroughly, investing in context engineering, maintaining strong test coverage, and using AI as a learning tool rather than a crutch. Real productivity gains appear to be less than 2x, with greenfield projects seeing better results than legacy codebases with technical debt.
Table of contents
The Deceptively Convincing Nature of AI-Generated CodeSolving the ‘70% Problem’ in AI-Assisted ProgrammingThe Importance of Better Context EngineeringDoes AI-Assisted Coding Really Save Time?How Code Review Is Becoming the New BottleneckSort: