What AI Secretly Changed About My Engineering
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
After hundreds of hours using AI coding tools like Claude, Copilot, and JetBrains Junie on real production services, the author found that AI didn't just make coding faster — it exposed weak engineering habits. Key lessons include: writing clear specifications before requesting code, treating AI context as a finite resource by keeping tasks small and focused, always reviewing AI-generated plans before implementation, avoiding having the same AI review its own output, and maintaining strict diff size discipline. The author advocates for spec-driven development as the core workflow shift, arguing that the habits AI rewards — clear requirements, small changes, independent review, meaningful tests — are simply good engineering practices that outlast any specific tool.
Table of contents
The First Promise Was SpeedWhen Vague Thinking Becomes Expensive CodeEvery Task Deserves Its Own ContextPlans Are Cheaper Than CodeSpec-Driven Development Was Not the Trick I ExpectedSmall Diffs Beat Heroic RewritesNever Let The Same AI Review Its Own WorkMy Workflow TodayFinal ThoughtsFurther Reading67.6K Impressions3 Comments