1 Building on quicksand: the challenges of vibe engineering
This chapter covers
- Documented failures of undisciplined vibe coding
- Hidden costs of unverified AI-generated code
- Building mental models for code ownership
- Executable specifications as verification contracts
In AI-assisted development, the engineering process often resembles an early-stage R&D lab. Developers iterate quickly - guided by intuition and an elusive "vibe" - using language-model APIs, AI agents, and prompting techniques to turn raw ideas into working software. This kind of rapid experimentation brings tangible value: faster iteration toward product-market fit and earlier visibility into unknown unknowns inherent to every project.
However, rapid experimentation without engineering discipline has a dark side. Vibe Coding - generating apps at lightning speed but without professional rigor or security awareness - creates an illusion of progress that often fails miserably. Real-world failures, from startups being hacked within days of launch to AI commands deleting entire projects, are painful lessons in the danger of trusting AI-generated code without deep verification. Shipping AI-generated code without deep verification accumulates an invisible, long-term cost of shipping code that no one on the team truly understands or owns. Projects are built quickly… but often become unmaintainable almost immediately.