Skip to content

R0021/2026-03-25/Q006 — ACH Matrix

Matrix

H1: Formally applied H2: Not applied H3: Adjacent, not prompt-specific
SRC01-E01: deliberate.codes blog uses RFC 2119 for AI agents + -- ++
SRC02-E01: RFC 2119 scope includes "limiting harmful behavior" N/A N/A +

Legend: ++ Strongly supports · + Supports · -- Strongly contradicts · - Contradicts · N/A Not applicable

Diagnosticity Analysis

Most Diagnostic Evidence

Evidence ID Why Diagnostic
SRC01-E01 The only published example, discriminating between H2 (not applied) and H1/H3 (applied). Its scope (AI agent specs, not prompt engineering) discriminates between H1 and H3.

Outcome

Hypothesis supported: H3 — RFC 2119 applied to AI-adjacent specifications but not to prompt engineering as commonly practiced.

Hypotheses eliminated: H2 — At least one published example exists.

Hypotheses inconclusive: H1 — The single example is a blog post, not a formal standard.