Alice: “Would you tell me, please, which way I ought to go from here?”
The Cheshire Cat: “That depends a good deal on where you want to get to.”
Alice: “I don’t much care where—”
The Cheshire Cat: “Then it doesn’t matter which way you go.”
Vibe Coding Circa 2026
Structured Prompts examines how AI-generated software systems can be made reliable through specification, measurement, and process control.
As large language models increasingly participate in software design and implementation, the central problem shifts. The question is no longer simply how to write code — but how to govern a stochastic production (one where the same input can produce different outputs) process. This site explores how structured specifications, contracts, and measurable feedback loops can serve as control mechanisms for AI-assisted development.
The perspective is influenced by the work of W. Edwards Deming (Father of the Quality Movement). While studying for a Master’s degree in Computing for Commerce and Industry in the 1990s, I was struck by Deming’s impact on manufacturing — and by the long-standing difficulty of applying those principles to software engineering. For decades, software was too informal and too human-driven to be treated as a production system.
AI may change that.
When code is generated rather than handcrafted, software development begins to resemble the kind of measurable, repeatable process that Deming's methods were designed to govern. The opportunity — and the challenge — is to apply quality principles first articulated more than 75 years ago to AI-native systems.
In 2015, I contributed two chapters to Software Quality Assurance in Large Scale and Complex Software-Intensive Systems, edited by leading figures in software architecture and standards including Richard Mark Soley. My work examined the relationship between requirements, architecture, and verification in large-scale environments.
Now semi-retired, I am extending on those principles to AI-generated systems and I am available for part-time remote engagements that bridge research and practical implementation in specification-driven and AI-assisted quality engineering.
Contact: structuredprompts@gmail.com