Audit: QRS - Muira Puama for Health & Longevity

Audit conducted on 13/10/2026 19:20 using AI4L + evidence-mcp / Muse 1.0

Iterations

Summary

Items Count
Total 94
Passed 87
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. 🟢 All QRS spans traced to ER passages: Protocol (ER 236-241), Benefits (ER 125-149), Risks (ER 175-189), Interactions/Contraindications (ER 205-217), Monitoring (ER 287-296).
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. 🟢 Cautious phrasing retained: ‘No comparison … exists for muira puama alone’ (QRS 472 = ER 241), ‘onset for muira puama alone is unknown’ (QRS 500 = ER 270), ‘(theoretical)’ (QRS 548-554 = ER 205-211).
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”). 🟢 No strengthening or softening found; avoid-populations stay contraindications (QRS 538-540 = ER 213-217) and timing retains ‘in practice’ (QRS 461 = ER 239).
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. 🟢 No relabeling: ER Benefit-/Risk-Modifying Factors (ER 152-199) are not surfaced as cautions or side effects in the QRS.
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 PubMed IDs, NCT identifiers, expert names, or brand names in the QRS; all drug names come from ER 205-211 for the same facts.
1.6 The QRS does not introduce new attributions. 🟢 No attributions or citations appear anywhere in the QRS body.

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. 🟢 Tone matches the ER’s cautious framing (e.g., ‘remain unproven in people’, QRS 433 = ER 309).
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Expert yet accessible and objective throughout, with evidence strength stated rather than implied.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Presents evidence and protocol data without issuing directives to any reader.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 No advice language; footer states ‘Not medical advice’ (QRS 639).
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 Content is presented as labeled information (labels/values/lists); no ‘recommend’ or ‘advise’ wording.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No second-person or ‘the reader’ address anywhere in the visible text.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Plain language in summary areas; technical names are limited to ER drug/class names in the gates, with plain-language parentheticals preserved from the ER.
2.8 Information is presented in a concise and very compact manner 🟢 All content is condensed into single-sheet cells and short list items.
2.9 It DOES NOT address the reader directly 🟢 Checked again with 2.6: no direct address in any span.
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. 🟢 Framing (protocol, monitoring cadence, questionnaires) targets proactive health- and longevity-oriented adults, matching ER Motivation (ER 37).
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. 🟢 Assumes willingness to follow protocol and monitoring effort (QRS 615, 623-632).
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-population framing or population-level thresholds are used; success is framed against individual baseline (QRS 594).
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. 🟢 Risk/benefit weighting reflects this audience: unproven benefits stated plainly alongside monitoring (QRS 433, 578-617).
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 ‘Longevity’ framing (QRS 22, 417); ‘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. 🟢 Formal terminology used (‘oral botanical supplement’, QRS 433; ‘Oral administration’, QRS 461); no colloquial route/effect terms.

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” 🟢 Headings verified at QRS 440, 477, 519, 564, 579, 621; gate headings at QRS 535, 545; tier labels and Monitoring column headers unchanged.
3.2 All “…” from the [qrs_template] are present in the the QRS. 🟢 Script comparison against core/qrs/QRS.html: every template span present; template pattern spans marker_#* and qualitative_item# are instantiated as marker_1/2_* and qualitative_item_1-3.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 Diff against the template shows changes only inside addressed spans and the metadata block; CSS and structure unchanged.

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 N/A — no QRS section is sourced from an empty ER section; empty benefit/risk tiers are handled under 12.5/13.5.
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. 🟢 Bold ER labels used verbatim: ‘Concentrated extract dose’, ‘Best time of day’, ‘Single versus split doses’ (ER 236-241) and the interaction labels (ER 205-211).
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 No paraphrased, abbreviated, or invented labels found in protocol, gates, or monitoring rows.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 No emoji characters in the QRS source.
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. 🟢 Template one-page layout retained with condensed per-section content; no sections added or extended (source audit per QRS.md).

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. 🟢 Metadata comment is the first element after <!doctype html> (QRS 1-2).
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. 🟢 YAML delimited by ‘—’ lines (QRS 3 and 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. 🟢 Metadata sits inside an HTML comment and is not rendered.
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. 🟢 Values trimmed; the only quoted value, duration ‘00:03’, contains a colon (QRS 4-12).
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 er_filename stated at QRS 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: 26.10.8 (QRS 5) matches QRS.md line 1.
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: 2026-1013-1915 in required format (QRS 6).
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 stated at QRS 7.
5.9 The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) 🟢 Nickname ‘Muse’ is a single word without 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 stated at QRS 8.
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) 🟢 ‘Muse 1.0’ gives the model name plus version with no additional qualifier.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 qrs_filename at QRS 9 matches the audited filename.
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-checked with 5.4: all frontmatter 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., &amp; for &) 🟢 Page title (QRS 22) is the ER canonical_topic (ER 8) plus ‘ - Quick Reference Sheet’, with & encoded as &.
6.2 [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., &amp; for &) 🟢 header_topic (QRS 417) equals the ER canonical_topic with & encoding.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 header_subline_date 10/13/2026 (QRS 421) is qrs_creation_date 2026-1013-1915 reformatted as MM/DD/YYYY.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 header_subline_model (QRS 425) equals qrs_creator_ai_fullname.
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 title and subline (QRS 415-428); no badges, AKA line, or audit stamps.

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 with kind and use: ‘oral botanical supplement prepared from the root and bark … used in connection with sexual vitality, mental sharpness, energy, and mood’ (QRS 433) before the evidence verdict.
7.2 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Dense summary of the ER Conclusion (ER 309): thin combined-product human evidence, unproven healthy-aging benefits, mild digestive/headache complaints.
7.3 [at_a_glance] is no longer than 70 words 🟢 58 words (script-counted), within the 70-word limit.
7.4 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 Each fact is supported in ER 37 and ER 309.
7.5 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 No acronyms or specialist classifications; plain terms only.
7.6 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 No trial names, years, sample sizes, or p-values.
7.7 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 No effect sizes, relative risks, or statistical results.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 Derived from ER Key Interactions & Contraindications (ER 201-217).
8.2 [stop_items] represent the Contraindications from the ER 🟢 stop_items reproduce the ER ‘Populations who should avoid Muira Puama’ list (ER 213-217).
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Individual items formatted as <li></li> (QRS 538-540).
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. 🟢 Items carry only the key fact; ER ‘because …’ explanations and the NCT attribution are stripped.
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). 🟢 The ER avoid-population bullets contain no parenthetical time/severity/threshold qualifiers requiring preservation (ER 215-217).
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 N/A — ER Key Interactions & Contraindications bullets (ER lines 205-217) use no ranking notation.
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. 🟢 Section is populated because the ER identifies populations who should avoid the intervention (ER 213-217).
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 N/A — section is not empty (QRS lines 538-540).

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 Derived from ER Key Interactions & Contraindications (ER 201-211).
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 caution_items reproduce all seven ER key interactions (ER 205-211) and none of the contraindication populations.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Individual items formatted as <li></li> (QRS 548-554).
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. 🟢 Only the bold label plus ‘Caution/Monitor (theoretical)’ is kept; all ER em-dash rationale clauses are stripped.
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). 🟢 Parenthetical example-drug lists and ‘(theoretical)’ qualifiers preserved for every item (QRS 548-554 = ER 205-211).
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 N/A — ER interaction bullets (ER lines 205-211) use no ranking notation.
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. 🟢 Section is populated because the ER identifies interactions that change use (ER 205-211).
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 N/A — section is not empty (QRS lines 548-554).

10. Protocol

# Description Result Comments
10.1 The section is derived from the ER Protocol section 🟢 Derived from the ER Therapeutic Protocol section (ER 232-247).
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Covers dose, time of day, and single versus split dosing (ER 236, 239, 241), the central implementation aspects for a single-ingredient product.
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 N/A — ER Protocol names three or more actionable aspects (ER lines 236-241).
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 All action_1-3 label/value/sub spans are filled with ER-derived content (QRS 442-474).

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 🟢 Time sets cover the two ER time-to-effect aspects (ER 270; benefit sections ER 125-135).
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Ordered as in the ER benefit sections (women, ER 125-129, before men, ER 131-135), both at the Low tier.
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. 🟢 Only two distinct aspects exist in the ER; time_3 spans are empty with style=’display:none’ (QRS 503-513).
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 All time_1-2 label/value/sub spans are filled with ER-derived content (QRS 481-502).
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 N/A — ER provides time-to-effect information (ER line 270).

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 Derived from ER Expected Benefits (ER 111-150).
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 benefits_high/medium/low/speculative spans all present (QRS 521-528).
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. 🟢 Items are the ER benefit headings only (ER 125, 131, 139, 143, 147), with no explanations, effect sizes, or citations.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical content carried over; ER magnitudes (ER 129, 135) are omitted.
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. 🟢 benefits_high and benefits_medium are empty with display:none (QRS 521-522), matching ‘No benefit reaches High/Medium’ (ER 117-121).

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 Derived from ER Potential Risks & Side Effects (ER 161-190).
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 risks_high/medium/low/speculative spans all present (QRS 566-573).
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. 🟢 Items are the ER risk headings only (ER 175, 183, 187), with no frequencies, citations, or added explanations.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical content carried over; the ER magnitude (ER 179) is omitted.
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. 🟢 risks_high and risks_medium are empty with display:none (QRS 566-567), matching ‘No risk reaches High/Medium’ (ER 167-171).

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 Derived from the ER Monitoring Protocol & Defining Success section (ER 285-292).
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 Both measurable biomarkers from the ER monitoring table are listed: Blood pressure and Resting pulse (ER 291-292).
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. 🟢 monitoring_cadence populated from ER 287 (baseline; repeats at 2 weeks, 1 month, then every 1-3 months) at QRS 615.

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 Derived from the same ER Monitoring section (ER 285-296).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 All three subjective/qualitative ER items are listed verbatim (QRS 623-632 = ER 294-296).

Issues 13/10/2026 19:20

Pass rate 100.00%. No issues found.