evipedia.ai ← Back to Review

Audit: QRS - Topical NMN for Skin Rejuvenation

Audit conducted on 03/08/2026 04:41 using AI4L / Opus 4.8

Iterations

Summary

Items Count
Total 91
Passed 84
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 content traces to the ER (protocol, benefits, risks, monitoring, at-a-glance all supported).
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. 🟢 QRS mirrors ER caution: “largely unproven”, “uncertain”, “barely studied”, “theoretical concern”.
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/breastfeeding kept “(precautionary)” as in ER; no strengthening/softening.
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 from “Populations who should avoid”; cautions from “Key Interactions”; no relabeling.
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. 🟢 QRS carries no citations, NCT IDs, or brand names.
1.6 The QRS does not introduce new attributions. 🟢 No new attributions present.

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. 🟢 Skeptical, evidence-weighing tone matches ER.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Meets tone requirement.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Presents evidence, not directives.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 Protocol framed as studied regimen, not advice.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 Descriptive throughout.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No second-person address.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Technical terms are the compound/measures themselves; plain elsewhere.
2.8 Information is presented in a concise and very compact manner 🟢 Compact card layout.
2.9 It DOES NOT address the reader directly 🟢 No “you”/”your”.
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 fits this audience.
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. 🟢 Cost/effort framing consistent.
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. 🟢 Not 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. 🟢 Weighting reflects the audience.
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 “counter aging”; no “anti-aging” in own voice.
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 terminology used.

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 fixed headings/labels present and unmodified.
3.2 All “…” from the [qrs_template] are present in the the QRS. 🟢 Full complement of template spans present.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 Non-checklist spans (e.g., website markers) 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” 🟢 Empty benefit/risk tiers handled per 12.5/13.5 (display:none); no mishandled empty section.
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. 🟢 Tier and monitoring labels mirror the ER; protocol cell labels derive per section 10.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Benefit/risk/monitoring labels verbatim.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 No emoji indicators in the QRS.
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. 🟢 Content condensed to one page.

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 (lines 2–14).
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 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. 🟢 Inside HTML comment; 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; duration quoted (contains colon).
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 er_filename: topical_nmn_skin_2026-0803-0222_Opus_ER.md
5.6 Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]” 🟢 qrs_prompt_version: 26.7.02 matches 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) 🟢 qrs_creation_date: 2026-0803-0432.
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 “Opus”.
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 4.8.
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) 🟢 “Opus 4.8” with no qualifier.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 qrs_filename: topical_nmn_skin_2026-0803-0222_Opus_QRS.html
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 clean and consistent.

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 &) 🟢 “Topical NMN for Skin Rejuvenation - 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., &amp; for &) 🟢 “Topical NMN for Skin Rejuvenation”.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 2026-0803-0432 → 08/03/2026.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 “Opus 4.8”.
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 limited to title and standard subline.

7. At-A-Glance Section

# Description Result Comments
7.1 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Condenses the Conclusion faithfully.
7.2 [at_a_glance] is no longer than 60 words 🟢 55 words.
7.3 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 Each clause maps to a Conclusion passage.
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 Only “NMN” (the subject compound) appears; otherwise plain language.
7.5 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 No trial citations.
7.6 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 No statistics.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 Derived from “Populations who should avoid” bullet.
8.2 [stop_items] represent the Contraindications from the ER 🟢 All four ER contraindications present.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Each item is an <li>.
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. 🟢 Concise; no trailing dash 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). 🟢 “(precautionary)” and “until evaluated” preserved.
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 ER uses no ranking notation in these items.
8.7 If no [stop_items] are present the section is left empty N/A stop_items are present.

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 Derived from the Key Interactions bullets.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 Retinoids, exfoliating acids/BPO, energy-based procedures captured.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Each item is an <li>.
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. 🟢 Concise; no trailing dash clauses.
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 drug lists preserved in parens.
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 ER uses no ranking notation in these items.
9.7 If no [caution_items] are present the section is left empty N/A caution_items are present.

10. Protocol

# Description Result Comments
10.1 The section is derived from the ER Protocol section 🟢 Derived from the Therapeutic Protocol section.
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Concentration/product, application frequency, storage.
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 Three distinct aspects available and used.
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 All three cells meaningfully populated.

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 🟢 Visible change ≥8 wk, first reassessment 4 wk, immediate glow (vehicle).
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Primary studied endpoint first, then earliest timepoint, then vehicle-only.
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 aspects available and used.
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 All cells meaningfully populated.
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 ER provides time-to-effect information.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 Derived from Expected Benefits.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four variables present.
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. 🟢 Benefit names condensed without elaboration.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical detail carried.
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. 🟢 High and Medium set to display:none (ER has none).

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 Derived from Potential Risks & Side Effects.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four variables present.
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. 🟢 Risk names condensed without elaboration.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical detail carried.
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. 🟢 High and Medium set to display:none (ER has none).

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 Derived from Monitoring Protocol & Defining Success.
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 All five biomarker-table rows present with targets and rationale.
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. 🟢 “Baseline, then reassess at 4 and 8 weeks, then every 3 months if continued.”

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 Derived from the qualitative markers list in Monitoring.
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 All four qualitative markers present.

Issues 03/08/2026 04:41

Pass rate 100.00%. No issues found.

Issues 03/08/2026 04:38

  1. 8.4 — Rationale retained on pregnancy contraindication: The [stop_items] entry “Pregnancy or breastfeeding (precautionary, absent data)” (line 544) keeps the trailing rationale “absent data”, which 8.4 requires stripping; only the severity qualifier “(precautionary)” should remain.

Fixes 03/08/2026 04:38

  1. 8.4 — Pregnancy contraindication rationale stripped: Removed the trailing rationale “absent data” from the pregnancy/breastfeeding contraindication; changed “(precautionary, absent data)” to “(precautionary)”.