An AI agent implements a feature. The code compiles. The tests pass. It still misses the point. The wrong kind of correct. Most of our software tooling is optim

MattRickard's platform  covers topics related to software development, technology trends, and coding tutorials. Through articles, tutorials, and personal anecdotes, MattRickard offers insights into programming languages, development frameworks, and best practices in software engineering. Readers can learn about software design principles, development methodologies, and emerging technologies to enhance their coding skills and build high-quality software applications.

Matt Rickard

AI agents fail differently than humans — they don't break builds, they disable failing tests, reuse nearest patterns, and make locally valid but globally wrong decisions. The root cause is underconstrained execution: too much freedom at the point of action. Spec-driven development (SDD) is proposed as a solution: writing durable intent before implementation to constrain what agents can decide on their own. Drawing on protocol engineering (RFCs, TLS, HTML specs) and formal methods (TLA+, Dijkstra), the post argues for a layered model where specs constrain intent, plans constrain approach, tasks constrain sequencing, and tests/lint constrain behavior. Tools like GitHub Spec Kit, Kiro, OpenSpec, and Augment Intent are surveyed. The ideal spec is declarative, layered, and cheap to revise — with mechanical rules pushed into lint and tests rather than prose. The goal: smaller specs, harder checks, less agent guessing.

The Spec Layer