Audit: QRS - Bergamot Oil for Health & Longevity

Audit conducted on 17/08/2026 05:55 using AI4L / Opus 5

Iterations

Summary

Items Count
Total 93
Passed 84
Failed 0
N/A 9
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. 🟢 Spot-checked every populated span against the ER: at-a-glance vs Conclusion, protocol cells vs Therapeutic Protocol, time cells vs Practical Considerations, benefit/risk tiers vs the ER headings, gates vs Key Interactions & Contraindications, and all 8 monitoring rows + cadence + 6 qualitative items vs Monitoring Protocol & Defining Success. No unsupported statement found.
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. 🟢 No cautious empty-state phrasing in the ER is carried into a QRS field; where the ER hedges (e.g. speculative tiers), the QRS keeps the item in the Speculative tier rather than promoting it.
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”). 🟢 Pregnancy/lactation stays in the STOP gate (line 565), not in Key Interactions; the CYP3A4 ingestion contraindication keeps “Intended ingestion” scoping (lines 561–562).
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. 🟢 Contraindications come from the ER “Populations who should avoid Bergamot Oil” list, Key Interactions from the ER interaction bullets, risks from Potential Risks & Side Effects headings. No Benefit-Modifying Factors or Risk-Modifying Factors content appears in the gates.
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, NCT IDs, expert names or brands in the QRS. The study descriptors in the Monitoring “Why” column (“the schoolteacher aromatherapy study”, “the postmenopausal trial”, “the pre-surgical bergamot trial”, “the bergamot vapour trial”) are copied verbatim from the ER biomarker table.
1.6 The QRS does not introduce new attributions. 🟢 No attribution appears that is not already in the ER table it was drawn from.

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. 🟢 Same measured, non-promotional register as the ER; hazard framing (“avoidable with care about sun exposure”) mirrors the ER Conclusion.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Tiered benefits/risks, concrete dose and timing figures, explicit monitoring targets.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Content is stated as what trials used and measured, not as orders.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 No imperative or second-person constructions; cadence line uses impersonal nominal phrasing (“Baseline over two weeks before starting; … whole protocol reassessed every 6–12 months”).
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 No occurrence of “recommend”, “advise”, or “should” in the document body.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No “you”/”your” anywhere in the file.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Technical terms retained (CYP3A4 substrate, oxidized linalool, Fitzpatrick skin type I) are all load-bearing decision terms carried from the ER; nothing is jargon for its own sake.
2.8 Information is presented in a concise and very compact manner 🟢 Gate and tier entries are stripped to key facts; no mechanism or study detail carried into any card.
2.9 It DOES NOT address the reader directly 🟢 Confirmed: no second-person pronouns or imperatives.
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. 🟢 Contents (8-marker monitoring panel, salivary cortisol and overnight RMSSD, patch testing) assume a proactive self-quantifying 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. 🟢 Two-week baseline, weekly-then-monthly re-rating and photopatch testing are all retained rather than simplified away.
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. 🟢 No general-consumer simplification; full contraindication and interaction detail retained.
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. 🟢 At-a-glance names the modest short-term signal and the single avoidable hazard, matching the ER’s own weighting.
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. 🟢 No occurrence of “anti-aging”; 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)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt. 🟢 Formal register throughout (“phototoxic skin reaction”, “allergic contact dermatitis”, “mucosal irritation”); the plain wording in At-A-Glance is required by item 7.4.

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 present verbatim (lines 444, 484, 528, 552, 570, 595, 617, 621–623, 741) with unchanged tier labels in both Benefits and Risks.
3.2 All “” from the [qrs_template] are present in the the QRS. 🟢 All 34 template variable names present; the repeatable marker_#_* and qualitative_item_# rows are expanded to marker_1–8 and qualitative_item_1–6 as intended.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 Diff against the template shows only variable regions changed; <span website="evidence_review">, <span website="audit"> and <span website="full_review"> are untouched, as are the CSS block, footer disclaimer and structural markup.

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 source section mapped into the QRS is empty; every source section (Expected Benefits, Potential Risks & Side Effects, Key Interactions & Contraindications, Therapeutic Protocol, Monitoring Protocol & Defining Success) carries content.
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. 🟢 All six Key Interaction labels reproduce the ER bold labels verbatim (lines 573–585); protocol labels “Standard inhalation protocol”, “Best time of day”, “Single versus split dosing” match ER bullets exactly.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Monitoring marker names are verbatim from the ER biomarker table; benefit/risk items reuse the ER headings. Time-to-effect labels are the only derived labels, and the ER supplies no bold labels for them.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 No emoji in the file; the ER’s “⚠️ Conflicted” marker on the sleep benefit was 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. 🟢 Every card is condensed relative to the ER: benefit/risk tiers are single semicolon-separated lines, gate items are stripped of consequence and mitigation clauses, and monitoring targets drop the ER’s “Context/Notes” column entirely.

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 <!doctype html> on line 1 and before the template comment on line 16.
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 --- on line 3, closing --- on line 13; the descriptive text sits on line 2 before the opening delimiter.
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 repeated in the header, footer or any card.
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, because it contains a colon.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 Line 4: er_filename: bergamot_oil_2026-0825-0244_Opus_ER.md, matching the ER’s own filename frontmatter value.
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: 26.7.02, matching the version badge at the top of QRS.md.
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: 2026-0817-0547, correct format.
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 or qualifier.
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 + version, no qualifier.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 Line 9: qrs_filename: bergamot_oil_2026-0825-0244_Opus_QRS.html, matching the file 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 including git_user and git_issue; 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., &amp; for &) 🟢 Line 22: “Bergamot Oil for Health & Longevity - Quick Reference Sheet”; matches ER canonical_topic with the ampersand encoded.
6.2 [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., &amp; for &) 🟢 Line 417: “Bergamot Oil for Health & Longevity”.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 Line 421: 08/17/2026, correctly derived from qrs_creation_date: 2026-0817-0547.
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 title and the template subline; the ER’s alternate_names line was 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 🟢 Compresses all four Conclusion paragraphs: what the oil is and how it is used, the short-term anxiety signal, the thinner mood/sleep/pain/dementia evidence, and the single avoidable hazard.
7.2 [at_a_glance] is no longer than 60 words 🟢 56 words.
7.3 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 “Pressed peel oil … Italian citrus fruit” (ER 458), “clearest signal is short-term” (ER 460), “thinner ground” (ER 460), “light-activated … avoidable with care about sun exposure” (ER 462, 464).
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 Uses “breathing the aroma”, “light-activated skin burns” rather than “inhalation”, “phototoxicity” or “phytophotodermatitis”; no acronyms.
7.5 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 Only the generic “from many small brief studies”; no trial name, year, n or p-value.
7.6 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 No numeric effect estimate or confidence interval.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 All six entries map one-to-one to the ER “Populations who should avoid Bergamot Oil” list (ER 308–313) inside that section.
8.2 [stop_items] represent the Contraindications from the ER 🟢 All six ER avoid-populations present, none added.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Six discrete <li> elements inside the stop_items span (lines 555–565).
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. 🟢 The ER’s trailing rationale is stripped, e.g. “where safety data are absent” dropped from the pregnancy item (ER 313 → line 565); no dash-trailing clause anywhere in the gate.
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). 🟢 Named diseases, the “more than one non-melanoma skin cancer” threshold, Fitzpatrick type I, the named NTI drugs, and the under-6/infant age qualifiers 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. N/A The ER uses no ranking notation inside parentheses in this section.
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 section is populated, and the ER does identify avoid-populations, so the constraint holds.
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 six entries map to the six ER interaction bullets (ER 294–304).
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 The CYP3A4 entry is retained because it covers a broader drug set (simvastatin, apixaban, felodipine) than the narrow-therapeutic-index ingestion contraindication; no entry duplicates a STOP item outright.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Six discrete <li> elements inside the caution_items span (lines 573–585).
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. 🟢 The ER’s severity word (“Caution.”, “Monitor.”), consequence sentence and “Mitigation:” clause are stripped from every item; only label plus named agents remain.
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). 🟢 Named example drugs retained throughout, e.g. doxycycline, ciprofloxacin, hydrochlorothiazide, isotretinoin (line 573–575) and lime, bitter orange, grapefruit (line 581).
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. N/A The ER uses no ranking notation inside parentheses in this section.
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 section is populated, and the ER lists six interactions, so the constraint holds.
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 cells derive from ER Therapeutic Protocol bullets (ER 335, 343, 347).
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Dose/duration (“Standard inhalation protocol”), timing (“Best time of day”) and frequency structure (“Single versus split dosing”) are the three execution-critical bullets; the remaining ER bullets are attribution, mechanism or subgroup commentary.
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: “3–5 drops, 15 min”, “Pre-stressor or evening”, “Split dosing is the norm”, each with an ER-derived sub-line.

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 🟢 The ER’s Time to effect bullet (ER 388) supplies exactly three data points — 10–20 minutes for autonomic/anxiety, 1–4 weeks for mood and sleep, and 2 weeks for the postpartum depression trial — and all three are used.
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Order runs Medium-tier benefit (acute anxiety reduction) first, then the two Low-tier benefits (depressive mood, then sleep), following the ER’s own tier and within-tier ordering.
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: “10–20 minutes”, “2 weeks”, “1–4 weeks”, each with an ER-derived sub-line.
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 does provide time-to-effect information, so the section is correctly retained.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 All nine items correspond to the nine ER benefit headings across the Medium, Low and Speculative tiers.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four spans present (lines 530–545).
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 item is the bare ER heading, semicolon-separated within its tier; no magnitude figure, p-value or mechanism carried over.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parentheses remain in any benefit entry.
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. 🟢 The ER has no High-tier benefit, and benefits_high carries style="display: none" with an empty item (lines 530–532); no empty-state text used.

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 All eight items correspond to the eight ER risk headings across High, Medium, Low and Speculative.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four spans present and populated (lines 597–611).
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. 🟢 Bare ER headings only; the Magnitude paragraphs, prevalence figures and IFRA commentary are all omitted.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 “(Phytophotodermatitis)” correctly stripped from the High-tier item (ER 228 → line 598); no parentheses remain.
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. N/A All four risk tiers carry items in the ER, so no sub-section needed hiding.

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 Rows reproduce the ER Monitoring Protocol & Defining Success biomarker table (ER 418–427), including the Optimal Functional Range and Why Measure It columns.
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 All 8 ER biomarkers present in ER order: salivary cortisol, overnight RMSSD, resting blood pressure, resting heart rate, PSQI, STAI state form, photopatch/ROAT, and NTI CYP3A4 substrate trough level.
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 731–735 condense the ER’s Baseline and Ongoing paragraphs (ER 414, 416) into one cadence line covering baseline, weekly/monthly ratings, 4-week and 3–6-month re-checks, skin inspection and 6–12-month reassessment.

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 Items reproduce the ER “Qualitative markers worth tracking alongside the numbers” list (ER 431–436).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 All 6 ER qualitative markers present in ER order, with only terminal full stops removed.

Issues 17/08/2026 05:55

Pass rate 100.00%. No issues found.

Issues 17/08/2026 05:52

  1. 9.5 — Example drugs dropped from interaction: The “Photosensitizing prescription drugs” item (QRS lines 573–574) lists only the drug classes and drops the ER’s parenthetical example drugs from ER line 294 — doxycycline, ciprofloxacin, hydrochlorothiazide and isotretinoin.

Fixes 17/08/2026 05:52

  1. 9.5 — Example drugs restored to interaction: Added the ER’s parenthetical example drugs back to the “Photosensitizing prescription drugs” item — tetracyclines (doxycycline), fluoroquinolones (ciprofloxacin), thiazide diuretics (hydrochlorothiazide), oral retinoids (isotretinoin).