@PrajwalTomar_: Andrew Ng just mapped why vibe-coded apps break with real users. Agents can write the code. But you still own the decis…

X AI KOLs Following News

Summary

Andrew Ng has shared an AI Engineering Skills map for software engineering fundamentals in agentic coding, highlighting that while agents can generate code, developers must manage critical decisions like data, architecture, security, and production.

Andrew Ng just mapped why vibe-coded apps break with real users. Agents can write the code. But you still own the decisions around data, architecture, security, and production. If you're shipping with coding agents, study this.
Original Article
View Cached Full Text

Cached at: 08/30/26, 06:03 AM

Andrew Ng just mapped why vibe-coded apps break with real users.

Agents can write the code. But you still own the decisions around data, architecture, security, and production.

If you’re shipping with coding agents, study this.

Andrew Ng (@AndrewYNg): How have software engineering fundamentals changed with agentic coding? Here is our AI Engineering Skills map for software engineering fundamentals.

Similar Articles

Vibe coding and agentic engineering are getting closer than I'd like

Simon Willison's Blog

Simon Willison reflects on how vibe coding and agentic engineering are converging in his own workflow, raising concerns about code review responsibilities as AI coding agents like Claude Code become increasingly reliable. He explores the ethical tension between trusting AI-generated code in production and maintaining software engineering standards.