Audit: QRS - Rosemary Oil for Health & Longevity
Audit conducted on 13/09/2026 10:38 using AI4L / Opus 5
Summary
| Items | Count |
|---|---|
| Total | 93 |
| Passed | 86 |
| Failed | 0 |
| N/A | 7 |
| Pass Rate | 100.00% |
- Total = Passed + Failed + N/A
- Pass Rate = Passed / (Passed + Failed) × 100
- N/A items are excluded from the pass rate calculation
1. General Rules
| # | Description | Result | Comments |
|---|---|---|---|
| 1.1 | Every claim, magnitude, label, recommendation, and statement in the QRS is literally supported by content in the source ER. | 🟢 | Every protocol value, time-to-effect figure, benefit/risk heading, gate item, marker row and cadence clause traces to ER lines 329–334, 358–364, 423–425, 153–215, 239–285, 307–325, 459–478. |
| 1.2 | Where the ER uses cautious phrasing (“not formally studied”, “None documented in human trials to date”, “theoretical concern”, “data are limited”), the QRS uses the same phrasing. | 🟢 | The ER’s “Speculative” tier is carried through unchanged for both benefits and risks; no hedged ER statement is rendered as settled. |
| 1.3 | The QRS never strengthens an ER claim (e.g., “not formally studied” → “not required”) or softens one (e.g., “do not use during pregnancy” → “use with caution during pregnancy”). | 🟢 | Absolute contraindications (antiepileptics, microneedling, pregnancy) stay in the Contraindications gate; “Caution”/”Monitor” verdicts match the ER verbatim. |
| 1.4 | The QRS does not relabel an ER fact under a different decision category. A “Benefit-Modifying Factor” from ER section is not surfaced as a “Caution”; a “Risk-Modifying Factor” is not surfaced as a “Side Effect”; etc. | 🟢 | Gates draw only from ER Key Interactions & Contraindications; risks only from Potential Risks & Side Effects; no Benefit- or Risk-Modifying Factor is promoted. |
| 1.5 | PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact. | 🟢 | No PMIDs, author names or NCT identifiers present; the only brand names (Vicks VapoRub, Tiger Balm) come from ER line 315. |
| 1.6 | The QRS does not introduce new attributions. | 🟢 | No attributions of any kind beyond the template’s AI4L / model subline. |
2. Focus, Tone & Audience
| # | Description | Result | Comments |
|---|---|---|---|
| 2.1 | The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing. | 🟢 | Sober, discounting register of the ER Conclusion is preserved in the At-A-Glance and throughout. |
| 2.2 | The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging | 🟢 | Actionable Protocol, Time to effect and Monitoring blocks give the reader concrete levers without overselling the evidence. |
| 2.3 | The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor | 🟢 | All gate and monitoring entries are noun phrases and stated targets, not instructions. |
| 2.4 | The QRS avoids language that implies medical or clinical advice | 🟢 | No “should”, “must”, “recommend”, “advise” or “consult” appears in any authored span. |
| 2.5 | The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” | 🟢 | Protocol cells state what trials used; Monitoring states targets rather than directives. |
| 2.6 | The QRS never addresses “the reader” directly — it presents evidence, not guidance | 🟢 | No second-person pronouns anywhere in the document. |
| 2.7 | The QRS is written in plain language, avoiding unnecessary medical jargon | 🟢 | “Pattern hair loss” rather than androgenetic alopecia; technical terms retained (CYP3A4, salicylates) are carried verbatim from the ER where no plain equivalent exists. |
| 2.8 | Information is presented in a concise and very compact manner | 🟢 | Benefits and Risks are single semicolon-separated lines per tier; gate items are trimmed to the key fact. |
| 2.9 | It DOES NOT address the reader directly | 🟢 | Confirmed by full-text scan for you/your/we/our — no hits. |
| 2.10 | The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review. | 🟢 | Six-month adherence expectation, patch testing and self-tracked scores all presume a proactive reader. |
| 2.11 | The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort. | 🟢 | Twice-daily scalp application for six months and monthly questionnaire scoring are presented without softening. |
| 2.12 | The document is NOT written for the general population, who are unwilling to employ lifestyle and behavioral changes or follow protocols that may be inconvenient, costly, or require effort. | 🟢 | Content assumes fixed-position photography, patch testing and index-based sleep scoring. |
| 2.13 | Framing, takeaways, and risk/benefit weighting throughout the document reflect this audience, including where an intervention’s signal for the average person differs from its signal for this audience. | 🟢 | “Evidence is thin — mostly single small trials” and the displacement-of-proven-treatment risk both foreground opportunity cost for an optimiser. |
| 2.14 | The document’s own voice frames usage in longevity terms, not “anti-aging” (e.g., “anti-aging clinics”, “anti-aging community”, “anti-aging medicine”). Proper names that contain “anti-aging” (e.g., “American Academy of Anti-Aging Medicine”) are quoted verbatim. | 🟢 | “Anti-aging” does not appear; the title uses “Health & Longevity”. |
| 2.15 | The document’s own voice uses formal clinical and scientific terminology, not colloquial or consumer-grade language (e.g., “oral medication” not “pill(s)”; “oral” / “administered orally” not “taken by mouth” / “given by mouth”; “injection” not “shot”; “adverse event” not “bad reaction”). This holds on EVERY surface, including the QRS lede — the stricter plain-language bar (see 2.7) does not license lay phrasing for route of administration. Direct quotes from sources are exempt. | 🟢 | Routes are stated as “applied to the scalp or inhaled” and “high-dose or ingested use”; no lay substitutes anywhere. |
3. Template Integrity
| # | Description | Result | Comments |
|---|---|---|---|
| 3.1 | The following labels and headings on the QRS are fixed and not modified: Card and section headings: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”; Gate headings: “Contraindications”, “Key Interactions”; Tier labels: “High”, “Medium”, “Low”, “Speculative”; Table column headers in Monitoring: “Marker”, “Target”, “Why” | 🟢 | All fourteen fixed strings present and byte-identical to the template (lines 446, 489, 536, 568, 588, 625, 653, 657–659, 754). |
| 3.2 | All “…” from the [qrs_template] are present in the the QRS. | 🟢 | All template variables present; the generic marker_#* and qualitative_item# spans are instantiated as marker_1–7 and qualitative_item_1–6. |
| 3.3 | Spans that are not addressed in a checklist item are left unchanged | 🟢 | Structural diff against the template shows changes only inside data-qrs-var spans; the website=”evidence_review”, website=”full_review” and website=”audit” spans and the footer disclaimer are untouched. |
4. Formatting
| # | Description | Result | Comments |
|---|---|---|---|
| 4.1 | When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied” | N/A | No ER section feeding the QRS is empty; the absent High-risk tier is governed by item 13.5 instead. |
| 4.2 | Where the ER presents a bulleted item as “Label: content”, the QRS uses the ER’s bold label verbatim as the cell or row label. | 🟢 | Protocol labels (“Standard scalp protocol”, “Practical home equivalent”, “Inhalation protocol”) and all gate bold labels reproduce the ER labels. |
| 4.3 | Labels are not paraphrased, abbreviated, or invented. | 🟢 | Only the ER’s own parenthetical plain-language glosses are trimmed, as permitted by 8.5 / 9.5; no label is reworded. |
| 4.4 | The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. | 🟢 | Full-text scan returns no emoji; the ER’s “⚠️ Conflicted” marker on the Memory benefit is correctly dropped. |
| 4.5 | The QRS is designed to render on one A4 page. Any section that has more content in the ER than fits the per-section budget is condensed by the LLM, not extended onto a second page. | 🟢 | Per-section condensation is evident throughout: drug lists trimmed to three exemplars, monitoring targets and instrument names shortened, benefit/risk tiers collapsed to one line each. |
5. Metadata
| # | Description | Result | Comments |
|---|---|---|---|
| 5.1 | The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content. | 🟢 | Lines 2–14, immediately after the doctype. |
| 5.2 | Inside that HTML comment the YAML block is delimited by a line “—” opening and a line “—” closing. Text before the opening “—” is permitted but is not parsed as YAML. | 🟢 | Opening “—” at line 3, closing “—” at line 13. |
| 5.3 | The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet. | 🟢 | Enclosed in an HTML comment; no metadata value is echoed in the body. |
| 5.4 | All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. | 🟢 | Only duration: "00:03" is quoted, correctly so because the value contains a colon. |
| 5.5 | The filename of the source ER is stated as “er_filename: [er_filename]” | 🟢 | Line 4: er_filename: rosemary_oil_2026-0913-0806_Opus_ER.md. |
| 5.6 | Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]” | 🟢 | Line 5: qrs_prompt_version: 26.9.11, matching the prompt version. |
| 5.7 | Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430) | 🟢 | Line 6: qrs_creation_date: 2026-0913-1026. |
| 5.8 | The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]” | 🟢 | Line 7: qrs_creator_ai_nickname: Opus. |
| 5.9 | The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) | 🟢 | “Opus” — single word, no version. |
| 5.10 | The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]” | 🟢 | Line 8: qrs_creator_ai_fullname: Opus 5. |
| 5.11 | The full name of the AI consists of the [qrs_creator_ai_nickname] and the model version number and no additional qualifier (e.g., Opus 4.6, Sonnet 3.2, Grok 4.5, Gemini 3.1, ChatGPT 5.4) | 🟢 | “Opus 5” — nickname plus version, no qualifier. |
| 5.12 | The filename of the document is stated as “qrs_filename: [filename of this document]” | 🟢 | Line 9 matches the file’s actual name on disk. |
| 5.13 | All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting. | 🟢 | Re-verified across all nine keys; no stray whitespace or unnecessary quoting. |
6. Page Title & Header
| # | Description | Result | Comments |
|---|---|---|---|
| 6.1 | [page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &) |
🟢 | Line 22: “Rosemary Oil for Health & Longevity - Quick Reference Sheet”. |
| 6.2 | [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &) |
🟢 | Line 417: “Rosemary Oil for Health & Longevity”, matching ER frontmatter line 8. |
| 6.3 | [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] | 🟢 | Line 421: “09/13/2026”, correct reformatting of 2026-0913-1026. |
| 6.4 | [header_subline_model] is set to [qrs_creator_ai_fullname] | 🟢 | Line 425: “Opus 5”. |
| 6.5 | No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. | 🟢 | Header contains only the template’s title and subline; the ER’s “Also known as” line is not carried over. |
7. At-A-Glance Section
| # | Description | Result | Comments |
|---|---|---|---|
| 7.1 | [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section |
🟢 | Condensed from ER lines 502–506, keeping route, duration, best-supported outcomes, evidence strength and harms. |
| 7.2 | [at_a_glance] is no longer than 60 words | 🟢 | 55 words. |
| 7.3 | Every fact in [at_a_glance] is supported by a distinct passage in the ER. | 🟢 | Each clause maps to a distinct sentence of the ER Conclusion (lines 502, 504, 504, 504). |
| 7.4 | It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead | 🟢 | No acronyms; “skin allergy”, “scalp itching”, “blood-pressure rise” are all lay terms. |
| 7.5 | It DOES NOT cite specific trials (names, years, sample sizes, p-values) | 🟢 | No study names, years or sample sizes appear. |
| 7.6 | It DOES NOT cite effect sizes, relative risks, or statistical results | 🟢 | No numeric outcome figures; “six months” is a duration, not an effect size. |
8. Contraindications
| # | Description | Result | Comments |
|---|---|---|---|
| 8.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | All eight items trace to ER lines 309, 323 and 329–334. |
| 8.2 | [stop_items] represent the Contraindications from the ER | 🟢 | All six “Populations who should avoid” bullets plus both absolute contraindications (antiepileptics, microneedling/laser) are present. |
| 8.3 | Individual [stop_items] are formatted as <li></li> | 🟢 | Eight discrete <li> elements, lines 571–583. |
| 8.4 | Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. | 🟢 | Each item is a bare condition or scope clause; the ER’s mechanistic sentences (“Camphor- and cineole-rich oils can provoke breakthrough seizures”, “Breached skin barrier turns…”) are dropped. |
| 8.5 | Parenthetical qualifiers from the ER bullet — time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). | 🟢 | “within the past 12 months”, “under 6 years”/”under 10 years”, “medicinal-dose topical or inhaled use”, “resting above 160/100 mmHg”, “high-dose or ingested use” and “within 48 hours” are all retained. |
| 8.6 | When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. | 🟢 | The ER uses no ranking notation; all parenthetical lists are already comma-separated and carried through as such. |
| 8.7 | The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision. |
🟢 | The ER identifies eight such populations/scenarios and the section is correspondingly populated, not empty. |
| 8.8 | If the section is left empty, an HTML comment inside the [stop_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g. | N/A | The section is not empty. |
9. Key Interactions
| # | Description | Result | Comments |
|---|---|---|---|
| 9.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | All eight items map one-to-one to ER bullets at lines 307, 311, 313, 315, 317, 319, 321 and 325. |
| 9.2 | [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications | 🟢 | Ten ER interaction bullets minus the two absolute contraindications (antiepileptics, microneedling/laser) leaves exactly the eight items shown. |
| 9.3 | Individual [caution_items] are formatted as <li></li> | 🟢 | Eight discrete <li> elements, lines 591–615. |
| 9.4 | Items are as concise as possible. No trailing explanations, no elaborations, no mechanistic rationale, no attributions, no citations, no study details. No content after an em-dash, en-dash, or hyphen-dash (e.g., “— dose reduction required”, “— reduced efficacy”) — these trailing clauses are stripped. Just the key fact. | 🟢 | Each item is the bold ER label plus the single-word verdict; the ER’s consequence and mitigation sentences are dropped. |
| 9.5 | Parenthetical qualifiers from the ER bullet — example drug lists, time windows, severity classes, threshold values, clinical staging — ARE preserved as part of the item, kept as concise as possible (shortened or trimmed where needed to fit the one-page budget, but never dropped entirely). | 🟢 | Every drug list is retained, trimmed to three named exemplars where the ER listed four or five (apixaban/ticagrelor, Bengay, ylang-ylang, liquorice root). |
| 9.6 | When the ER uses ranking notation inside parens (e.g., “>” for severity ordering) that depends on an explanatory phrase to interpret, normalize the items to a plain comma-separated list rather than carrying through the bare symbol. | 🟢 | No ranking notation in the ER; all retained parentheticals are plain comma-separated lists. |
| 9.7 | The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no interaction, additive effect, or exposure that changes how the intervention is used. |
🟢 | The ER identifies eight such interactions and the section is populated accordingly. |
| 9.8 | If the section is left empty, an HTML comment inside the [caution_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g. | N/A | The section is not empty. |
10. Protocol
| # | Description | Result | Comments |
|---|---|---|---|
| 10.1 | The section is derived from the ER Protocol section |
🟢 | All three action sets trace to ER Therapeutic Protocol lines 358, 360 and 364. |
| 10.2 | The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section |
🟢 | Trial regimen, practical home equivalent and inhalation regimen — the three self-administrable rosemary-only protocols in the ER. |
| 10.3 | If less that three distinct actionable implementation aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. | N/A | The ER supplies more than three actionable aspects; all three sets are used. |
| 10.4 | All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. |
🟢 | All nine spans populated: labels verbatim from ER bold labels, values give dose/dilution, subs give vehicle and duration. |
11. Time to Effect
| # | Description | Result | Comments |
|---|---|---|---|
| 11.1 | The three sets of [time] items cover the three most important time-to-effect aspects from the ER | 🟢 | Topical hair count (ER line 423), inhaled alertness/anxiety (ER line 425) and four-week sleep-quality change (ER line 177). |
| 11.2 | The sets are picked and ordered by the magnitude of the related benefit | 🟢 | Ordered High (scalp hair density), High (alertness/anxiety), Medium (sleep quality), matching the ER benefit tiers. |
| 11.3 | If less that three distinct time-to-effect aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing. | N/A | Three distinct time-to-effect aspects exist in the ER; all three sets are used. |
| 11.4 | All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. | 🟢 | All nine spans populated; subs carry the ER’s own qualifiers (“No change detectable at three months”, “fades within the hour”, “in older adults with diabetes”). |
| 11.5 | If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel |
N/A | The ER provides explicit time-to-effect data (lines 423–425), so the section is correctly retained. |
12. Benefits
| # | Description | Result | Comments |
|---|---|---|---|
| 12.1 | The section is derived from the ER Expected Benefits section |
🟢 | All ten entries correspond to the ten ER benefit sub-headings at lines 155–215. |
| 12.2 | Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] | 🟢 | All four spans present and populated (lines 538, 544, 550, 556). |
| 12.3 | Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. | 🟢 | Each tier is a semicolon-separated list of the ER’s own sub-headings; no Magnitude figures or study references carried over. |
| 12.4 | Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses appear in any benefits span. |
| 12.5 | If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. | N/A | All four benefit tiers contain items in the ER, so no span needed hiding. |
13. Risks
| # | Description | Result | Comments |
|---|---|---|---|
| 13.1 | The section is derived from the ER Potential Risks & Side Effects section |
🟢 | All seven entries correspond to the ER risk sub-headings at lines 245–285. |
| 13.2 | Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] | 🟢 | All four spans present (lines 627, 630, 636, 642). |
| 13.3 | Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details, no mechanistic explanations, etc. Just the key fact. | 🟢 | Each tier is a semicolon-separated list of the ER’s own sub-headings; no Magnitude data or citations carried over. |
| 13.4 | Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses appear in any risks span. |
| 13.5 | If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. | 🟢 | ER line 241 states no risk reaches High; the [risks_high] span at line 627 carries style="display: none" with no empty-state text. |
14. Monitoring
| # | Description | Result | Comments |
|---|---|---|---|
| 14.1 | The section is derived from the ER Monitoring section |
🟢 | Every row maps to the ER Monitoring Protocol & Defining Success biomarker table (lines 461–469). |
| 14.2 | All measurable/quantifiable biomarkers from the Monitoring section are listed |
🟢 | All seven ER table rows are present as marker_1 through marker_7, in ER order. |
| 14.3 | [monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty. |
🟢 | Lines 744–748 reproduce the ER cadence paragraph (line 459) plus the 96-hour patch re-read and monthly sleep score from the ER table’s Context column. |
15. Qualitative Assessment
| # | Description | Result | Comments |
|---|---|---|---|
| 15.1 | The section is derived from the ER Monitoring section |
🟢 | All six items come from the ER’s “Qualitative markers worth tracking alongside the measurements” list (lines 473–478). |
| 15.2 | All subjective/qualitative biomarkers from the Monitoring section are listed |
🟢 | All six ER qualitative bullets are present, verbatim and in ER order. |
Issues 13/09/2026 10:38
Pass rate 100.00%. No issues found.
Issues 13/09/2026 10:30
- 12.4 — Parenthetical not stripped in benefits: [benefits_low] at QRS line 552 reads “Memory and cognitive task performance (conflicted)”; item 12.4 requires parenthetical content to be stripped, and the “Low” tier already encodes the evidence-strength qualifier.
Fixes 13/09/2026 10:30
- 12.4 — Parenthetical stripped from benefits: Removed “ (conflicted)” from [benefits_low], leaving “Memory and cognitive task performance; blood pressure support in persistently low blood pressure; muscular and joint pain relief from topical use”.