Claude Code Lead Boris Cherny Says His Code Is 100% AI-Written
Original: Claude Code 負責人 Boris Cherny：我的程式碼 100% 由 AI 撰寫，同時跑上百個 agent
Boris Cherny describes an agentic coding workflow where engineers direct AI agents instead of writing code manually.
Claude Code lead Boris Cherny says his code is now 100% written by AI while he runs hundreds of agents in parallel. The article frames engineers less as manual coders and more as conductors who define problems, review outputs, and shape architecture. It highlights a broader shift in software development workflows driven by AI coding agents, without presenting detailed benchmarks or implementation data.
This article compiles the thoughts of Claude Code lead Boris Cherny on the agentic development model. According to the original summary, Cherny says his own code is already 100% written by AI, and that in his work he runs hundreds of AI agents simultaneously to help produce code. The key point here is not that engineers withdraw entirely from development, but that the engineer's role is changing: in the past, an engineer's core output was often seen as "writing code by hand," but in a context where AI agents can generate code en masse, human value concentrates more on defining problems, articulating clear requirements, decomposing tasks, reviewing the quality of output, and making architecture-level judgments.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on INSIDE 硬塞 AI →Summaries are AI-generated; the original article is authoritative.