chapter one

1 Building on Quicksand: The challenges of Vibe Engineering

 

This chapter covers

  • The dangers and documented real-world failures of undisciplined "Vibe Coding"
  • The hidden, long-term cost of shipping unverified AI-generated code.
  • The cognitive cost required for developers to build a mental model and truly own AI-generated code.
  • Using human-authored, executable specifications as the central contract to guide and verify AI work.

In the new field of AI-assisted development, the software engineering process often feels like it's been pulled from an early-stage R&D lab. Surrounded by language-model APIs, AI agents, and esoteric prompting techniques, we iterate quickly - guided by intuition and an elusive “vibe” - to turn raw ideas into working software. There is nothing inherently bad in this, as the exploratory phase brings tangible value, with faster iteration toward product-market fit and earlier visibility into the dreaded unknown unknowns inherent to every project.

1.1 AIchemy: A new frontier of software creation

1.2 Illusion of speed or “Vibe over Engineering”

1.2.1 A startup hacked within days of launch

1.2.2 A command that erased an entire project

1.2.3 A pull request that turned into a trojan

1.2.4 An agent that decided to “clean up” production data

1.3 The end of scale worship: diminishing returns

1.4 Defining a new discipline: Vibe Engineering

1.4.1 Two faces of the vibe: coding vs engineering

1.4.2 Trust: a new kind of debt

1.4.3 From intelligent autocompletion to a partner

1.4.4 Stuck in old ritual: what stalls real adoption

1.5 A new mental model for vibe engineering

1.5.1 Practical example of using a cycle

1.5.2 Tools as force multipliers: IDE + CI/CD

1.5.3 The winning loop - and the risks ahead

1.6 Owning - The last mile of vibe engineering

1.6.1 The not-the-end-yet 70% Problem

1.7 The beginning of “Software Engineering”

1.8 Summary