23 articles in AI engineering
AI code passes review on day one and ages worst by month six — not because it's wrong, but because the design intent that makes it refactorable was never part of the diff. The fix is encoding intent in artifacts the next iteration must read.
AI can generate a complete test suite — descriptive names, 94% coverage, green CI — in the same session it writes the implementation. The gap is behavioral: tests written after code verify what the code does, not what it should. Mutation testing makes this visible.
59% of developers ship AI-generated code they don't fully understand. The output looks professional. The reasoning underneath is absent. Here's what broke, why it matters, and how engineering discipline rebuilds the apprenticeship AI bypassed.
The demo works. The prototype impresses. Then it hits production and quietly fails — wrong answers at scale, cascading LLM timeouts, no way to know when the prompt regressed. This is not an AI problem. It is an engineering problem with a known solution.
AI agents and offshore teams break in exactly the same way. They are execution accelerators, not thinking substitutes. The work that doesn't compress — specs, architecture, test design, critique — is the work you have to keep in-house. Outsource the typing. Keep the thinking.
AI didn't take your job. It exposed it. The work was never typing characters into an editor — it was translating ambiguous business intent into something that adds value to users. Code was always the byproduct. The translation was always the work.
When AI generates code that breaks production, ownership doesn't transfer to the model — the post-mortem still names the human who clicked merge. Vibe engineering is the craftsmanship answer: you delegate the typing, but never the understanding, the design intent, or the accountability.
AI coding agents are multipliers. Multiply zero, get zero. Multiply a typical outsourced codebase, and you don't accelerate delivery — you accelerate rework. Here's the founder math on why your AI ROI is landing on the wrong substrate.
Engineering resistance to AI tools is not a change management problem. Every complaint maps to a specific missing prerequisite. Here is how to read the resistance as a diagnostic — and the five-stage sequence that resolves it.