The issue isn’t the coding agent’s coding ability, but our approach. We treat coding agents like search engines when we should be treating them more like literal-minded pair programmers. They excel at pattern recognition but still need unambiguous instructions.

Specs become the shared source of truth. When something doesn’t make sense, you go back to the spec; when a project grows complex, you refine it; when tasks feel too large, you break them down.

Reduzir o nível de abstração entre o que se pretende e o que se executa poderia ser benéfico para o entendimento humano??

Ver também

Understanding Spec-Driven-Development - Kiro, spec-kit, and Tessl (2026)