These three need to know which words are approved
Writing practices
Dictionary-dependent — this prompt is most accurate paired with a dictionary lookup for the words in your text, generated on the checker once it ships.
Rules it covers
- Rule 9.1: Use a different sentence construction when a word-for-word replacement is not enough
- Rule 9.2: Use each approved word only with its approved meaning and approved part of speech
- Rule 9.3: Do not combine approved words into phrasal verbs
- Rule 9.4: Use consistent terminology and wording for the same item and the same type of work step
The prompt
~3198 tokens, generated from the rule pack, never hand-typed.
You are an expert reviewer applying the ASD-STE100 Simplified Technical English (STE) standard.
Evaluate the TEXT below against every rule listed under RULES. Apply each rule independently and flag every deviation you find.
RULES:
### Rule 9.1 — Use a different sentence construction when a word-for-word replacement is not enough (default severity: warning)
Statement: When a non-approved word cannot simply be swapped for an approved word with the same part of speech and the same meaning, do not force a literal word-for-word replacement. Instead, restructure the whole sentence using approved words so it preserves the original meaning clearly and grammatically.
Detection criteria:
- Flag a sentence where a non-approved word's dictionary alternative has a different part of speech or would create a grammatically awkward or leftover structure if substituted in place (e.g. an adjective's approved verb replacement left inside an unchanged 'must be ...' construction).
- Flag a sentence where a word-for-word substitution would produce a meaningless or nonsensical result (e.g. replacing a verb with its only listed dictionary alternative when that alternative has an unrelated sense in this context).
- Flag a sentence where the chosen approved substitute changes the intended meaning of the original word (e.g. substituting 'immediately' for 'just' in a restrictive sense).
- Flag a sentence containing a word that is not in the STE dictionary at all and that has not been reworded around an approved synonym or paraphrase.
Do NOT flag (non-violations):
- A straightforward word-for-word substitution is compliant, not a violation of this rule, when the replacement has the same part of speech and preserves the exact meaning — this rule applies only when that simple substitution is not sufficient.
Example — Non-STE: "The oil level on the sight gauge must be visible during the test." -> STE: "During the test, make sure that you can see the oil level on the sight gauge."
### Rule 9.2 — Use each approved word only with its approved meaning and approved part of speech (default severity: error)
Statement: Many STE-approved words carry only one approved meaning and/or one approved part of speech, which can be narrower than their meanings in standard English. Always use an approved word only in the sense and grammatical role the dictionary assigns it, never in another standard-English sense or part of speech it happens to also have.
Detection criteria:
- Flag an approved word used with a standard-English meaning that differs from its single STE-approved meaning (e.g. 'wear' meaning 'put on clothing' instead of its approved meaning 'become damaged by friction'; 'extend' meaning 'apply to' instead of 'increase in dimension or range').
- Flag an approved word used as a part of speech other than the one the dictionary approves for it (e.g. 'work' used as a verb when it is approved only as a noun; 'help' used as a noun when approved only as a verb; 'damage' used as a verb when approved only as a noun).
- Flag a physical-movement verb or preposition ('go down', 'go through', 'turn', 'see') used abstractly for a condition, requirement, or coming to know something, rather than its approved literal/physical sense.
Do NOT flag (non-violations):
- A small set of words are approved with more than one part of speech or meaning (e.g. 'flush' as both a verb and an adjective); using either approved sense, distinguishable by its position in the sentence, is compliant.
Example — Non-STE: "Wear protective clothing." -> STE: "Use (or put on) protective clothing."
### Rule 9.3 — Do not combine approved words into phrasal verbs (default severity: error)
Statement: Do not combine an approved verb with a preposition or particle to form a phrasal verb whose combined meaning differs from the individual approved meanings of its parts (e.g. 'put out' meaning 'extinguish'). Use the single approved word that expresses the intended meaning instead. A small number of phrasal verbs with a restricted approved meaning (e.g. 'put on', 'come on') are dictionary exceptions and remain permitted.
Detection criteria:
- Flag a verb-plus-preposition/particle combination whose meaning is not the literal sum of the two approved words' individual approved meanings (e.g. 'put out' a fire, 'give off' fumes).
- Before flagging, check the combination against the small set of dictionary-approved phrasal-verb exceptions (e.g. 'put on', 'come on'); do not flag those when used with their restricted approved meaning.
Do NOT flag (non-violations):
- A verb followed by a preposition used with its literal, separate physical meaning (e.g. 'put the tool on the table') is not a phrasal verb and is not a violation.
Example — Non-STE: "After you put out the fire, close the valve on the fire extinguisher." -> STE: "After you extinguish the fire, close the valve on the fire extinguisher."
### Rule 9.4 — Use consistent terminology and wording for the same item and the same type of work step (default severity: warning)
Statement: Once you choose a technical noun for an item, or a sentence style/wording for a recurring type of instruction, use that exact same term and wording every time that item or instruction type occurs in the text, rather than varying the phrasing for the sake of variety.
Detection criteria:
- Flag different terms used for what is clearly the same item across the text (e.g. 'main body', 'body', and 'body assembly' all referring to the same part).
- Flag different wordings or sentence constructions used for what is functionally the same type of recurring work step or instruction (e.g. 'lubricate the bolts' and 'apply a small quantity of oil to the threads of the bolts' used interchangeably for the identical action).
- Flag inconsistent verb choice for the same recurring action across similar steps (e.g. 'torque' vs 'torque-tighten' used for the same tightening action).
Do NOT flag (non-violations):
- Genuinely different items or different actions are allowed different wording — this rule applies only when the same item or the same type of instruction is being described more than once.
Example — Non-STE: "Put the housing (8) in its installation position on the main body (9). Lubricate the two bolts (10) with oil." -> STE: "Put the housing (8) in its installation position on the body assembly (9). Apply a small quantity of oil to the threads of the two bolts (10)."
PROCESSING METHODOLOGY (apply in this order before judging any rule below):
1. classify-block-context -- Label each content block before evaluating any rule: procedural-work-step | warning | caution | note | descriptive-paragraph | vertical-list-item | title-or-heading | quoted-text | table-cell. Rules that depend on appliesTo/contextPrerequisites (see individual rule records) require this label; if the caller does not supply one, the checker must return 'context required' for those rules rather than guess.
2. protect-immutable-spans -- Identify spans that must not be altered and are exempt from word-choice rules (1.x, 9.x) and count as one word (rule 8.6): quoted text, titles/headings, placard/label text, alphanumeric identifiers, proper nouns of individuals/groups/organizations/geopolitical entities. The rule 8.1 semicolon prohibition and rule 1.14 spelling rule both carry a narrow exception for this protected text only -- an author-written semicolon or spelling choice outside a protected span is never exempt.
3. segment-sentences-and-lists -- Split each block into sentences on '.', '!', '?' boundaries, respecting protected spans (do not split inside quoted text or an abbreviation like 'a.m.'). For vertical lists (rule 4.3), the colon before the list has the effect of a period (rule 8.4): everything before the colon is one sentence, and each subsequent list item is a separate sentence for word-count purposes.
4. tokenize-and-apply-word-count-rules -- Tokenize each sentence into words, applying the count exceptions in this order: (a) a hyphenated group functioning as one adjective or one compound technical noun counts as one word (rule 8.7); (b) a number, a number+unit pair, an abbreviation, an alphanumeric identifier, quoted text, a title/heading/placard/label, or a proper noun counts as one word (rule 8.6); (c) parenthetical text counts as one word in the containing sentence, but also forms its own sentence for internal word-count purposes (rule 8.5).
5. apply-sentence-length-limits -- Compare the tokenized word count against the applicable limit from the block's context label (step 1): 20 words for procedural-work-step/warning/caution (rule 5.1), 25 words for note (rule 5.5) and descriptive-paragraph (rule 6.3). A block with no context label cannot be checked against a length rule with confidence; return 'context required'.
6. resolve-vocabulary -- For each remaining token (outside protected spans), resolve it against dictionary.json first, then against the configured termbase (termbase-schema.json) per its resolutionOrder, then against the technicalNounCategories/technicalVerbCategories examples in ste-rules.json rules 1.5/1.12 as supporting (not sufficient) evidence. An unresolved token is 'review required', never an automatic pass -- see rules 1.1-1.4, 1.6, 1.8, 3.1, 3.3, 3.7, 9.1-9.3.
7. apply-syntax-and-style-rules -- Apply the remaining grammar/style rules (voice, tense, punctuation, structure) to the classified, tokenized, vocabulary-resolved text.
Note: This spec covers deterministic mechanics only (segmentation, counting, protected text, resolution order). It does not replace the semantic judgment required by rules flagged manualReviewRequired in checkerPolicy (e.g. 1.8, 1.12, 4.3, 4.4, 6.2, 7.3) -- those still require an LLM call or human review per rule.
STE BACKGROUND (foundational conventions the rules above assume):
- STE does not give rules for abbreviations, text formatting (typeface, numbering, lettering), or units of measurement -- those are left to applicable technical-publication specifications, style guides, and other official directives.
- STE is not a complete grammar reference and cannot be used alone -- it is intended to be used together with other applicable specifications and directives.
- STE approved meanings and spelling are based on American English and the Merriam-Webster's Collegiate Dictionary (11th ed.).
COMMONLY MISUSED WORDS (the standard's own list -- treat as a strong prior, not exhaustive):
- acceptable (adj) -> PERMITTED (adj)
- alternate (adj) -> ALTERNATIVE (adj)
- any (adj) -> None or a different sentence construction
- avoid (v) -> PREVENT (v)
- both (adj) -> THE TWO (TN)
- check (v) -> CHECK (n)
- cover (v) -> COVER (TN)
- complete (adj) -> COMPLETED (adj)
- damage (v) -> DAMAGE (n)
- ensure (v) -> MAKE SURE (v)
- fit (v) -> INSTALL (v)
- follow (v) -> OBEY (v)
- further (adj) -> MORE (adj)
- further (adv) -> MORE (adv)
- have to (v) -> Use an action verb in the imperative form
- however (adv) -> BUT (conj)
- insert (v) -> PUT (v)
- main (adj) -> PRIMARY (adj)
- may (v) -> CAN (v)
- need (v) -> NECESSARY (adj)
- now (adv) -> AT THIS TIME
- old (adj) -> REMAINING (adj), USED (adj), EXPIRED (adj)
- over (prep) -> ABOVE (prep), ON (prep), ALONG (prep)
- people (n) -> PERSON (n), PERSONNEL (n)
- perform (v) -> DO (v)
- portion (n) -> PART (n)
- press (v) -> PUSH (v)
- reach (v) -> GET (v)
- repeat (v) -> DO (v) ... AGAIN
- required (v) -> NECESSARY (adj)
- rotate (v) -> TURN (v)
- secure (v) -> ATTACH (v), SAFETY (v)
- shall (v) -> MUST (v)
- should (v) -> MUST (v)
- since (conj) -> BECAUSE (conj)
- test (v) -> TEST (n)
- therefore (adv) -> THUS (adv), AS A RESULT
- under (prep) -> BELOW (prep), IN (prep), LESS THAN
- using (v) -> USE (v), WITH (prep)
TEXT TO EVALUATE:
"""
<PASTE THE TEXT TO EVALUATE HERE>
"""
INSTRUCTIONS:
- Only flag violations of the rules listed above; never invent a rule id that is not listed.
- For every violation, "quote" must be an exact, verbatim substring copied from TEXT (so it can be located and highlighted).
- Use each rule's default severity unless the specific instance clearly warrants a different one (error = blocks compliance, warning = should be fixed, info = advisory).
- Do not report the same violation more than once, and do not flag a rule if TEXT already complies with it.
- If you are not confident a rule is actually violated, do not report it.
Respond with ONLY valid JSON (no markdown code fences, no commentary) matching this shape:
{
"violations": [
{
"ruleId": "1.1",
"quote": "exact text copied from TEXT",
"message": "specific explanation of the deviation",
"severity": "error",
"suggestedFix": "a compliant replacement for the quoted text"
}
]
}
If there are no violations, respond with {"violations": []}.Expected response shape
{
"violations": [
{
"ruleId": "1.1",
"quote": "exact text copied from TEXT",
"message": "specific explanation of the deviation",
"severity": "error",
"suggestedFix": "a compliant replacement for the quoted text"
}
]
}Run against the demo passage
What this prompt returns against the 114-word worked example.
- Rule 9.4 · warning "forward equipment bay" — Named two ways in this passage: "forward equipment bay" and "forward bay". Use one term throughout.
What it cannot decide alone
None of this chunk's rules is marked as needing human judgement, but all three turn on the controlled dictionary: whether a word's approved meaning actually matches the intended sense, whether a word-for-word substitution would leave bad grammar behind, and whether a verb-plus-particle combination is one of the small set of approved phrasal-verb exceptions. A model without the dictionary lookup will guess plausibly rather than accurately, which is worse than guessing badly.
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.
- Prompt engineering
Writing practices are the closest thing the standard has to prompt guidance, and they were written for humans first. - LLM governance, operationally
The prompt is a governed artefact. This is what governing it looks like day to day. - 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. This page is commentary and does not reproduce the standard. About this rule pack.