evipedia.aidev
← Back to Review

Audit: QRS - HMB for Health & Longevity of the ER frontmatter

Audit conducted on 23/06/2026 01:01 using AI4L / Opus 4.8

Iterations

Summary

Items Count
Total 91
Passed 85
Failed 0
N/A 6
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 content traces to the ER (Protocol, Benefits, Risks, Monitoring, Interactions/Contraindications).
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. 🟢 “caution, theoretical” for prescription drugs mirrors ER line 289; “Theoretical effects from long-term use” mirrors ER line 251.
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 and severity preserved; no strengthening or softening detected.
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/Interactions drawn from ER “Key Interactions & Contraindications”; 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 contains no PMIDs, citations, expert names, 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. 🟢 Objective, evidence-driven tone consistent with ER.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Tone is expert yet accessible throughout.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Presents information without prescribing.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 No directive/advisory language; footer disclaimer present.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 Content is presented, not recommended.
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 🟢 Plain language; technical terms explained inline.
2.8 Information is presented in a concise and very compact manner 🟢 Compact card/table layout.
2.9 It DOES NOT address the reader directly 🟢 No direct 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. 🟢 Framing matches the risk-aware longevity 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. 🟢 Protocol/monitoring framing assumes a proactive audience.
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 pitched to the general population.
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 notes “little for healthy, well-trained people”.
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”/”age-related muscle loss”; no “anti-aging”.
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 throughout (“gastrointestinal discomfort”, “lean body mass”).

3. Template Integrity

# Description Result Comments
3.1 The following labels and headings on the QRS are fixed and not modified (card/section headings, gate headings, tier labels, Monitoring column headers). 🟢 All fixed headings present and unmodified (“Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”, “Contraindications”, “Key Interactions”, tier labels, “Marker”/”Target”/”Why”).
3.2 All “…” from the [qrs_template] are present in the QRS. 🟢 All expected data-qrs-var spans present, including hidden benefits_high, risks_high, risks_medium.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 No unaddressed spans modified.

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 tiers (benefits_high, risks_high, risks_medium) are hidden via display:none rather than carrying empty-state text, per items 12.5/13.5; no ER section required verbatim empty-state phrasing.
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/Time labels align with ER concepts; tier labels verbatim.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Labels faithful to ER.
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 QRS body.
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 single-page layout.

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 first element after doctype (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 — at 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. 🟢 Enclosed in 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 because it contains a colon.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 “er_filename: hmb_2026-0623-0005_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: 26.5.18” (line 5).
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: 2026-0623-0058” (line 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: Opus” (line 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) 🟢 “Opus” is a single word.
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” (line 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” — nickname plus version, no qualifier.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 “qrs_filename: hmb_2026-0623-0005_Opus_QRS.html” (line 9).
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. 🟢 Consistent with 5.4; all values clean.

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”. The [canonical_topic] is HTML-entity-encoded as needed. 🟢 “HMB 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. 🟢 “HMB for Health & Longevity” (line 417).
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 qrs_creation_date 2026-0623-0058 → “06/23/2026” (line 421).
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 “Opus 4.8” (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 contains only title, date, and model; no extra content.

7. At-A-Glance Section

# Description Result Comments
7.1 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Distills the ER Conclusion (lines 445-447).
7.2 [at_a_glance] is no longer than 60 words 🟢 54 words.
7.3 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 Each claim maps to the ER Conclusion.
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 Plain language (“muscle loss”, “grip strength”); no acronyms.
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; “small gains” is qualitative.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 Drawn from ER lines 285-299.
8.2 [stop_items] represent the Contraindications from the ER 🟢 Pregnant/breastfeeding, children/adolescents, liver/kidney impairment match ER line 299.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Three <li> items present.
8.4 Items are as concise as possible. No trailing explanations, elaborations, mechanistic rationale, attributions, citations, study details, or content after a dash. Just the key fact. 🟢 Concise; no 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. 🟢 “(medical supervision only)” preserves the ER qualifier for organ impairment.
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 contraindications use no ranking-notation parentheticals.
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 🟢 Drawn from ER line 289.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 “Prescription drugs (caution, theoretical)” from ER line 289; no overlap with contraindications.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 One <li> item present.
9.4 Items are as concise as possible. No trailing explanations, elaborations, mechanistic rationale, attributions, citations, study details, or content after a dash. Just the key fact. 🟢 Concise.
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. 🟢 “(caution, theoretical)” preserves the ER severity qualifier.
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 No ranking-notation parentheticals in the ER interactions.
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 🟢 Drawn from ER Therapeutic Protocol (lines 317-341).
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Standard dose, split dosing, form selection are the key actionable aspects.
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 actionable aspects are present.
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 All three action cells populated from ER (3 g/day ~38 mg/kg, 2–3 doses, HMB-Ca/HMB-FA).

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 🟢 Clinical/Aging weeks-to-months, Trained ≥6 weeks, Loading none required.
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Clinical/Aging (strongest, Medium-tier benefit) precedes trained-individual (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. N/A Three distinct time-to-effect aspects are present.
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 All three time cells populated from ER lines 333, 374.
11.5 If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel 🟢 ER provides time-to-effect info (lines 333, 374); section retained correctly.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 Drawn from ER Expected Benefits (lines 156-211).
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four span variables present.
12.3 Items are as concise as possible. No explanations, elaborations, effect sizes, qualifiers, attributions, citations, study details, or mechanistic explanations. Just the key fact. 🟢 Benefit headings condensed without magnitudes or mechanism.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parentheticals retained.
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 set to display:none (no High-tier benefits in ER).

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 Drawn from ER lines 235-261.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four span variables present.
13.3 Items are as concise as possible. No explanations, elaborations, effect sizes, qualifiers, attributions, citations, study details, or mechanistic explanations. Just the key fact. 🟢 Risk items condensed.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parentheticals retained.
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 set to display:none (no High/Medium risks in ER).

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 Drawn from ER Monitoring Protocol (lines 396-411).
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 Lean body mass, handgrip strength, gait speed, SPPB — all four ER biomarkers present.
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, reassess at ~8–12 weeks, then every 3–6 months” matches ER lines 400/404.

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 Drawn from ER qualitative markers (lines 413-421).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 All four qualitative markers from ER present.

Issues 23/06/2026 01:01

Pass rate 100.00%. No issues found.