Audit: QRS - St. John’s Wort for Health & Longevity

Audit conducted on 22/09/2026 19:43 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	94
Passed	86
Failed	0
N/A	8
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.	🟢	All protocol values (900 mg/day, 300 mg TID, ~0.3% hypericin, up to 1,800 mg/day), time values (2–4 weeks, ~6 weeks, 4–12 weeks), tier items, gates, markers and cadence trace to ER lines 337–345, 386, 360, 156–209, 230–283, 301–315, 410–431.
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.	🟢	Hedges are carried over: “Neither is established as superior” (ER line 339), “no circadian requirement” (ER line 345), “Speculative” tiers retained for preclinical-only items.
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”).	🟢	Contraindications keep full force (“Pregnancy or breastfeeding”, “Any SSRI, SNRI, or MAOI”); no hedge is dropped or added.
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 it” bullet (line 315), Key Interactions from the six interaction bullets (lines 301–311); no modifying factor is promoted to a gate.
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.	🟢	Only WS 5570, LI 160 and Ze 117 appear; all three are named in the ER Protocol section (line 339) for the same extract-choice fact. No PMIDs, NCT IDs or expert names.
1.6	The QRS does not introduce new attributions.	🟢	No authors, institutions, or manufacturers are attributed beyond the ER-named extract designations.

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.	🟢	Matches the ER’s measured, interaction-focused framing, including the “interference, not toxicity” framing of ER line 453.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified values and tiers throughout; plain-language lede without alarmism.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Statements are descriptive (“Taken with meals to reduce stomach upset”), not prescriptive orders.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No “should”, “must”, “consult”, or imperative instruction to a reader anywhere in the sheet.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	Protocol and monitoring cells state what trials and the ER report, not what to do.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns present.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Lede is jargon-free; the technical terms that remain (CYP3A4, P-gp, DOACs) sit only in the interaction gate where the drug identity is the decision-relevant fact.
2.8	Information is presented in a concise and very compact manner	🟢	Tier lists are bare item names; gate items are single clauses; subs are one to two lines.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by full-text scan for second-person address.
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.	🟢	Monitoring includes hs-CRP and 25-OH vitamin D as longevity-relevant context, matching ER lines 420–422.
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.	🟢	Three-times-daily dosing, baseline labs and drug-specific INR checks are presented without simplification.
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.	🟢	Assumes willingness to reconcile medications and run lab panels.
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.	🟢	The lede elevates the interaction liability (the decisive issue for a supplement-stacking reader) over efficacy.
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.	🟢	Uses “Relevant to Aging” (ER heading, line 203) and “longevity-relevant marker”; “anti-aging” does not appear.
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.	🟢	Route of administration is stated as “standardized oral extract”; “antidepressant medications” is used rather than a colloquial equivalent; the remaining plain terms (“blood thinners”, “birth control”) are the ER’s own Conclusion wording (line 453).

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 headings, gate titles, tier labels and the Marker/Target/Why column headers are byte-identical to the template.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 template variable names are present; marker_#/qualitative_item_# are instantiated as marker_1–6 and qualitative_item_1–6.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A structural diff against the template shows differences only inside variable spans; the website= spans, CSS, footer and 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 mapped into the QRS is empty.
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 dose and formulation”, “Competing approaches, presented without a default”, “Best time of day”), “Intended duration”, and all six Key Interaction bold labels are verbatim from ER lines 301–311, 337–345, 360.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Benefit and risk item names reproduce the ER H4 headings verbatim; the two time-cell sub-labels distinguish the two phases inside the ER’s single “Time to effect” bullet rather than replacing an existing ER label.
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 menopausal hot flashes 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 section is within its budget: gates 7 and 6 single-clause items, tiers one line each, Monitoring six rows, Qualitative six short items.

---

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 “—” line 3, closing “—” 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.	🟢	Fully enclosed in the HTML comment; no metadata value is echoed on the page except the template-driven date and model in the subline.
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, which is required because the value contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	er_filename: st_johns_wort_2026-0803-0002_Opus_ER.md (line 4).
5.6	Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]”	🟢	qrs_prompt_version: 26.9.22, matching the QRS.md version badge.
5.7	Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430)	🟢	qrs_creation_date: 2026-0922-1934.
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢	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)	🟢	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]”	🟢	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 context-window or other qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: st_johns_wort_2026-0803-0002_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: all values trimmed; quoting only where a colon requires it.

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 &)	🟢	“St. John’s Wort for Health & Longevity - Quick Reference Sheet” (line 22).
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	“St. John’s Wort for Health & Longevity” (line 417).
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0922-1934 → “09/22/2026” (line 421).
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	“Opus 5” (line 425).
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 holds only the title and the template subline; the ER’s “Also known as” line was not carried over.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] opens by saying what the intervention is — its kind (e.g., dietary supplement, prescription medication, peptide, plant, procedure, practice) — and what it is used for, in plain language, before any verdict on the evidence	🟢	Opens “St. John’s Wort is a flowering plant sold as a standardized oral extract for low mood” — kind and use before any verdict.
7.2	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Compresses all three Conclusion paragraphs (ER lines 451–455): the supported benefit, the weaker signals, and the interference liability.
7.3	[at_a_glance] is no longer than 70 words	🟢	59 words.
7.4	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to ER lines 451 and 453.
7.5	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; enzyme induction is rendered as “speeds drug clearance” and the affected drug classes as “birth control, blood thinners, and transplant medicines”.
7.6	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial, author, or year is named.
7.7	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numbers of any kind appear in the lede.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	Every item derives from the “Populations who should avoid it” bullet, ER line 315.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All seven ER-named groups are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Seven <li> elements inside the span (lines 574–583).
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 noun phrase; no dashes introducing trailing clauses.
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).	🟢	Preserved: the narrow-therapeutic-index examples, “Severe major depression or active suicidality”, and the “within about 5 days” surgical window.
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; the drug-class examples are rendered as a plain comma-separated list.
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 such populations and the section is populated accordingly.
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 items map one-to-one onto the ER interaction bullets, lines 301–311.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Oral contraceptives, anticoagulants, immunosuppressants, HIV drugs and SSRIs/SNRIs/MAOIs are correctly omitted here because they appear as Contraindications.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Six <li> elements inside the span (lines 591–617).
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: … consequence: …” tails are stripped from every item; only the label and the drug list 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).	🟢	Example drugs are retained in trimmed form (simvastatin, digoxin, carbamazepine, imatinib, sumatriptan); no parenthetical class is dropped entirely.
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 symbols in the ER bullets; all example sets 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 six interaction classes and all are represented.
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 the ER “Therapeutic Protocol” bullets, lines 337–345.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose/formulation, extract choice (high- vs low-hyperforin), and timing/administration are the three decision-bearing bullets; split dosing is folded into the dose cell.
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 names 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 action variables carry substantive ER-sourced content; no placeholders remain.

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	🟢	Onset (2–4 weeks, ER line 386), fuller effect (~6 weeks, ER line 386), and course length (4–12 weeks, ER line 360).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered by the High-tier mood benefit first, then its fuller expression, then the duration frame.
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 aspects are available and 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 time variables carry ER-sourced content, including the “no change by 6 weeks argues against continued benefit” note from ER line 417.
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 (line 386).

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All eight items match the ER H4 benefit headings, lines 158–209.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 544–564).
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.	🟢	Bare heading names only; the ER magnitude lines (e.g., “relative risk ~1.28–1.53”) are not carried over.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheticals appear in any benefit item.
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 tiers have items in the ER.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All eight items match the ER H4 risk headings, lines 232–283.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 629–645).
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 heading names only; the ER magnitude lines (e.g., “30–70% reductions”) are not carried over.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheticals appear in any risk item.
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 tiers have items in the ER.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows derive from the ER “Monitoring Protocol & Defining Success” table, lines 415–422.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All six ER biomarkers present (PHQ-9, ALT, INR, hs-CRP, TSH, 25-hydroxyvitamin D) with their ER target ranges verbatim.
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.	🟢	Reproduces ER line 412: baseline, 2 and 6 weeks, then every 3–6 months, plus INR within 1–2 weeks of starting and stopping.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Items derive from the ER qualitative-markers list, lines 426–431.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers are present, in ER order.

Issues 22/09/2026 19:43

Pass rate 100.00%. No issues found.

Issues 22/09/2026 19:39

1. 4.5 — Sheet overruns one A4 page: Cumulative content exceeds the A4 text block; the Key Interactions gate (lines 593–622) alone wraps to roughly twenty lines and the three protocol sub-cells (lines 456–490) run five to six lines each.
2. 9.4 — Key Interactions gate too verbose: The first interaction item (lines 594–601) lists six drug classes with two named examples each, and items 4 and 5 (lines 610–617) repeat SAMe and saffron, so the gate is not trimmed to the one-page budget.
3. 12.3 / 12.4 — Parenthetical qualifier in Benefits: [benefits_medium] carries “Relief of Menopausal Hot Flashes (conflicted)” (line 553); parenthetical qualifiers must be stripped because the tier already encodes evidence strength.

Fixes 22/09/2026 19:39

1. 4.5 — Condensed over-budget cells: Tightened [at_a_glance] (67 → 59 words), all three [action_#sub] cells, all three [time#_sub] cells, [monitoring_cadence], [marker_4_why], and [qualitative_item_6], cutting roughly a dozen wrapped lines without dropping any ER fact.
2. 9.4 — Key Interactions gate trimmed: Reduced each drug class in the first item to a single named example (e.g., “statins (simvastatin, atorvastatin)” → “statins (simvastatin)”, “cardiac drugs (digoxin, some calcium channel blockers)” → “cardiac drugs (digoxin)”) and shortened “standardized saffron extract” to “saffron”; every interaction class and at least one example per class is retained.
3. 12.3 / 12.4 — Benefits parenthetical stripped: Removed “(conflicted)” from [benefits_medium], leaving “Relief of Menopausal Hot Flashes”.