Audit: QRS - Feverfew for Health & Longevity

Audit conducted on 16/08/2026 15:29 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	83
Failed	0
N/A	10
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 doses (6.25 mg three times daily; 50–150 mg; 100–300 mg at 0.2–0.4%), thresholds (≥50%/≥30%, <100 × 10⁹/L, INR >3.0, 14 days, four attacks per 28 days), biomarker ranges and cadence trace verbatim to the ER Therapeutic Protocol, Risk Mitigation, Discontinuation and Monitoring sections.
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.	🟢	“has been described as producing rebound headache” (time_3_sub) mirrors the ER’s own hedged wording; “usually permanent daisy-family allergy” preserves the ER Conclusion’s “usually permanent”.
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 and breastfeeding remain in the Contraindications gate, not the Key Interactions gate; the “real but small” framing of attack-frequency benefit is retained.
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 the ER Key Interactions & Contraindications section; Benefits/Risks tiers draw only from Expected Benefits / Potential Risks & Side Effects. No modifying-factor bullet appears in either 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 “MIG-99” and “Examine” appear; both are used in the ER Therapeutic Protocol for the same dosing facts. No PMIDs, NCT IDs, or author names carried over.
1.6	The QRS does not introduce new attributions.	🟢	No attribution appears that is absent from the ER.

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.	🟢	Measured, sceptical register matching the ER (“real but small”, “studies disagree”).
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified targets and decision points are given without hedging into vagueness.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is stated as evidence and thresholds, not as instructions to a patient.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No prescriptive verbs; gates are presented as populations/agents, not as orders.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of “should”, “recommend”, “advise”, “consult”, or “must”.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (neuraxial anaesthesia, Asteraceae/Compositae, international normalised ratio) are decision-critical and taken from the ER.
2.8	Information is presented in a concise and very compact manner	🟢	Gate and tier items are stripped to the key fact; sub-lines are single clauses.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by full-file search for second-person forms.
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.	🟢	Content assumes a headache diary, baseline bloods, and patch testing.
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.	🟢	A 4-week baseline diary, thrice-daily dosing, and a 2–4 week taper 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.	🟢	Seven-marker monitoring panel and a formal re-assessment gate exceed general-population framing.
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 “at least 30% or stop” decision rule and the sensitisation/bleeding trade-off are surfaced explicitly.
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.	🟢	The string “anti-aging” does not occur.
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.	🟢	“oral mucosal ulceration”, “allergic contact dermatitis”, “Asteraceae cross-sensitisation” used throughout; the plain register of [at_a_glance] is mandated 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 fourteen fixed strings match the template byte-for-byte (lines 445, 491, 542, 568, 589, 620, 647, 651–653, 775 and the eight tier labels).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 34 template variables present; the repeatable rows marker_#* and qualitative_item# are expanded to seven marker rows and six qualitative items.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	<span website="evidence_review">, <span website="audit"> and <span website="full_review"> are byte-identical to the template; a diff of the entire head/CSS block against the template shows no change other than [page_title].

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 source ER section that feeds 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.	🟢	“Standardised extract approach”, “Dried-leaf approach”, “Baseline biomarkers”, “Time to effect”, “Re-assessment point”, “Tapering protocol” all match the ER bold labels verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	No invented label; monitoring marker names are the ER biomarker-table row names verbatim.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Full-file search returns no tier emoji and no ⚠️ conflicted markers.
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.	🟢	Single .sheet container, no added blocks; gate and tier items condensed to one line each so the seven-row monitoring table and six qualitative items stay within budget.

---

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.
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 repeated 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, and it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: feverfew_2026-0825-1220_Opus_ER.md, matching the ER’s own filename frontmatter.
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 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)	🟢	Line 6: qrs_creation_date: 2026-0816-1520.
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: qrs_filename: feverfew_2026-0825-1220_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.	🟢	Values are single-space separated after the key with no trailing whitespace.

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: Feverfew 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: Feverfew for Health & Longevity.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: 08/16/2026, from qrs_creation_date 2026-0816-1520.
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 block (lines 415–428) is structurally identical to the template; no alternate-names line despite the ER carrying nine.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Condenses all four Conclusion paragraphs: modest frequency benefit, weak duration/pain signal, preclinical-only broader claims, harm profile, absolute exclusion.
7.2	[at_a_glance] is no longer than 60 words	🟢	59 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to a distinct Conclusion sentence; “Pregnancy is the one absolute exclusion.” is verbatim.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronym; “daisy-family allergy” replaces Asteraceae/Compositae; “cells and animals” replaces preclinical.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial name, year, n, or p-value.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	“real but small” is qualitative; no numbers appear.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All six items come from the ER’s “Populations who should avoid Feverfew” list within that section.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All six ER avoid-list bullets are present, none omitted, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Six <li> elements inside the [stop_items] span (lines 571–584).
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.	🟢	Rationale clauses stripped: “on grounds of uterine-stimulant activity and absent safety data” and “in the absence of paediatric dosing evidence” removed; no dash-trailing clause remains.
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).	🟢	“(chamomile, arnica, ragweed, chrysanthemum, echinacea)”, “(above 3.0)”, “below 100 × 10⁹/L”, “under 2 years”, “within 14 days” 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 ER names six such populations and the section is correctly 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 seven items map one-to-one to ER bullets in that section.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	The ER’s elective-surgery/dental/neuraxial bullet is correctly carried in Contraindications only and not duplicated here.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Seven <li> elements inside the [caution_items] span (lines 592–610).
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.	🟢	All “Caution/Monitor” severity words and every “Mitigation:” clause stripped; the ER’s “(NSAIDs — the ibuprofen class: …)” dash clause is reduced to the drug list alone.
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).	🟢	All six named-drug and named-supplement parentheticals preserved in full.
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 ER names seven such interactions and the section is correctly populated, not empty.
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.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Standardised extract regimen, dried-leaf alternative, and the mandatory baseline headache diary are the three decision-bearing bullets; the remainder are contextual (who popularised, half-life, genetics).
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 at least three distinct 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; 6.25 mg three times daily, 50–150 mg daily, 4-week headache diary and their sub-lines all trace to the ER.

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 window (Practical Considerations), re-assessment point and taper duration (Discontinuation & Cycling) are the ER’s three time-bearing facts.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	All three attach to the High-tier attack-frequency benefit and run in the order the user encounters them: onset, decision point, discontinuation.
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	The ER supplies three distinct time-to-effect aspects; 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.	🟢	12–16 weeks, Week 12–16, and 2–4 weeks with sub-lines drawn verbatim in substance from the ER.
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 information (“a fair trial therefore runs 12–16 weeks”).

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All seven benefit headings from that section are represented.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 544–561).
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.	🟢	Headings only; no magnitude figures, no ⚠️ Conflicted markers, no mechanism text 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 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 ER benefit tiers contain items.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All seven risk headings from that section are represented.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 622–641).
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.	🟢	Headings only; the 8.4% vs 10.2% adverse-event figures and all Magnitude text are omitted.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses 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 ER risk tiers contain items.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows and cadence come from the ER Monitoring Protocol & Defining Success section.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All seven ER biomarker-table rows present with ranges verbatim (≥50%/≥30%; <10 and <5 days; 150–400 × 10⁹/L; 0.8–1.2; 10–26 / 10–33 U/L; <1.0 mg/L; negative at 48 and 96 hours).
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 765–769 reproduce the ER’s 4/8/12–16-week diary review, 6-monthly stable review, 2- and 6-week coagulation retest, and annual bloods.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Taken from the ER’s “Qualitative markers worth tracking alongside the labs” list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers present and verbatim (lines 778–811).

Issues 16/08/2026 15:29

Pass rate 100.00%. No issues found.

Issues 16/08/2026 15:25

1. 2.5 — Imperative stop rule in Time to Effect: [time_2_sub] begins “Stop if monthly migraine days have not fallen meaningfully”, which advises rather than presents; the ER states the same rule descriptively at line 366.
2. 8.4 — Paediatric rationale not stripped: The contraindication at line 576 retains a rationale clause, “Children under 2 years, and children generally (no paediatric dosing evidence)”, where 8.4 requires only the key fact.

Fixes 16/08/2026 15:25

1. 2.5 — Imperative stop rule removed: Reworded [time_2_sub] from the imperative “Stop if monthly migraine days have not fallen meaningfully” to the descriptive “Where monthly migraine days have not fallen meaningfully, continuing adds risk without return”, matching the ER’s own framing at line 366.
2. 8.4 — Paediatric rationale stripped: Removed the trailing parenthetical “(no paediatric dosing evidence)” from the contraindication, leaving “Children under 2 years, and children generally”.