error · Section 7: Safety instructions
Rule 7.2: Start a safety instruction with a clear and accurate command or condition
Begin a safety instruction with a clear, accurate command telling the reader what to do or not do; if the reader needs to know a condition before starting the procedure or work step, begin with that condition instead. Either way, the actionable part must come first so the reader immediately knows how to prevent an accident.
Safety instructions are where a model's findings are least reliable and a wrong rewrite costs most. Nothing a prompt returns on a warning or caution should reach a reader without a person who knows the standard having read it first.
What a checker looks for
A clear deviation from the rule.
- Flag a safety instruction that opens with the explanation of risk or consequence before stating the command or condition, instead of leading with the actionable command/condition.
- Flag a command that is vague or abstract rather than a clear, specific, actionable instruction (e.g., "be careful," "use caution" instead of naming the specific action to take or avoid).
- Flag a safety instruction whose hazard only applies during a specific circumstance (e.g., while performing a certain action) but that omits the triggering "when"/"while" condition, leaving the reader unsure when the precaution applies.
How to fix it
Rewrite the opening of the safety instruction as a direct command (e.g., "Do not..." / "Always make sure that...") or, when a condition must be known first, open with a "when"/"while" clause stating that condition — then follow with the explanation of risk required by rule 7.3.
Constraints on the fix
- Keep the command in direct imperative/second-person form; do not bury it in the middle or end of the sentence.
Examples
Not STE: WARNING: THE SPRAY PAINT CAN CAUSE INJURY TO YOUR EYES. WHILE YOU USE THE SPRAY PAINT, POINT THE SPRAY AWAY FROM YOUR FACE.
STE: WARNING: WHILE YOU USE THE SPRAY PAINT, POINT THE SPRAY AWAY FROM YOUR FACE. THE SPRAY PAINT CAN CAUSE INJURY TO YOUR EYES.
Not STE: CAUTION: THESE CLEANING AGENTS CAN CAUSE CORROSION. DO NOT USE BLEACH OR CLEANSERS THAT CONTAIN CHLORINE TO CLEAN THE UNIT.
STE: CAUTION: DO NOT USE BLEACH OR CLEANSERS THAT CONTAIN CHLORINE TO CLEAN THE UNIT. THESE CLEANING AGENTS CAN CAUSE CORROSION.
Related rules
Where this fits in AI governance
A rule a checker can test is a rule a model can be held to. The same discipline, on the governance side of this site.
- Inadequate human oversight design
A safety instruction is the last place to discover that the review step was designed to be skipped. - Human-in-the-loop review
Warnings and cautions should never publish from a model call without a person having read them. - Output validation guardrails
A controlled language is a checkable output constraint. This is the control that treats model output as something to be checked rather than trusted.
Source
ASD-STE100 Issue 9, Section 7 - Safety instructions, page 1-7-3.
This page is commentary and does not reproduce the standard. About this rule pack.