Audit: QRS - Low-Level Light Therapy for Post-Training Recovery

Audit conducted on 10/08/2026 00:16 using AI4L + evidence-mcp / Opus 5

Iterations

Summary

Items Count
Total 91
Passed 81
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 protocol values (5–10 min pre-exercise, 20–60 J / 60–300 J, 655–950 nm, ~200 mW emitters), time-to-effect windows (24–96 h, 8+ weeks), benefit/risk headings, all 7 contraindications, all 5 interaction bullets, all 5 biomarkers and all 7 qualitative markers trace to the ER.
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. 🟢 ER hedging is carried through, e.g. time_3_sub retains “if it exists” from the ER Practical Considerations bullet.
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 remain contraindications and cautions remain cautions; the photodynamic-therapy absolute contraindication is placed in the stop gate, not the caution gate.
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 are drawn only from Key Interactions & Contraindications; risks only from Potential Risks & Side Effects; no Benefit- or Risk-Modifying Factor content appears anywhere.
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 PMIDs, NCT identifiers, author names or brand names (e.g. Multi Radiance Medical) appear anywhere in the QRS.
1.6 The QRS does not introduce new attributions. 🟢 No attributions of any kind are 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. 🟢 Measured, sceptical, non-promotional register matches the ER throughout.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Quantified protocol and monitoring content is paired with a plain-language at-a-glance summary.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 No imperatives or prescriptions; content is stated descriptively.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 Monitoring targets and gates are presented as evidence-derived reference values, not instructions.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 No occurrences of “recommend”, “advise”, or “should” in the QRS voice.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No second-person pronouns anywhere in the document.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Technical terms retained are the ER’s own outcome labels; the at-a-glance is jargon-free.
2.8 Information is presented in a concise and very compact manner 🟢 Benefits and risks are reduced to bare outcome labels; gates and protocol cells are single-clause.
2.9 It DOES NOT address the reader directly 🟢 Confirmed by full-text search for “you”/”your”/”we”/”our” — no matches.
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 training population willing to dose by joules and track blood markers.
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. 🟢 Monitoring cadence tied to untreated/treated training blocks and a five-marker blood panel presuppose this.
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. 🟢 Energy-dosing and biomarker sections are not general-population material.
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 explicitly narrows the claim (“real but narrow benefits”, unsupported uses named).
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 term “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)”; “injection” not “shot”; “adverse event” not “bad reaction”). Direct quotes from sources are exempt. 🟢 Formal register throughout (“erythema”, “post-inflammatory hyperpigmentation”, “irradiation”); only standard unit abbreviations are shortened.

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” 🟢 Verified at lines 445, 491, 541, 573, 593, 629, 661, 665–667, 757; all tier labels present unchanged in both Benefits and Risks.
3.2 All “…” from the [qrs_template] are present in the the QRS. 🟢 All 34 template variable names present; the repeatable marker_#_* and qualitative_item_# spans are correctly expanded to marker_1–5 and qualitative_item_1–7.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 Diff against the template shows the website="evidence_review", website="audit" and website="full_review" spans, all CSS and all markup 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 source ER section relevant to 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. 🟢 Key Interactions rows reuse the ER bold labels (“Photosensitising prescription drugs”, “Over-the-counter medications”, “Supplement interactions”, “Supplements with additive effects”, “Other intervention interactions”).
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Benefit, risk, biomarker and qualitative-marker labels reproduce the ER headings and bold terms.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 Full-text search returns no emoji characters, including the ER’s “⚠️ 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. 🟢 Every over-full ER section is condensed rather than carried over: benefits and risks are reduced to bare outcome labels, contraindications and interactions to single clauses, and the monitoring “Context/Notes” column is dropped entirely.

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. 🟢 Single comment at 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 header or 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, correctly, because it contains a colon.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 Line 4: er_filename: low_level_light_therapy_recovery_2026-0809-2054_Opus_ER.md, matching the ER 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: 2026-0810-0004.
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” is a single word with no version or qualifier.
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 qualifiers.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 Line 9 matches the actual file name 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. 🟢 All nine keys carry a single space after the colon and 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., &amp; for &) 🟢 Line 22: “Low-Level Light Therapy for Post-Training Recovery - Quick Reference Sheet”; no characters require entity encoding.
6.2 [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., &amp; for &) 🟢 Line 417 matches the ER canonical_topic exactly.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 Line 421: 08/10/2026, correctly derived from 2026-0810-0004.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 Line 425: Opus 5, matching the frontmatter value.
6.5 No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. 🟢 The header contains only the title and the template subline; the ER’s “Also known as” list is not carried over.

7. At-A-Glance Section

# Description Result Comments
7.1 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Lines 433–437 compress the ER Conclusion’s benefit list, the pre-session timing, and the unsupported claims into three sentences.
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 distinct sentence of the ER Conclusion (lines 518–520).
7.4 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 No acronyms; “blood markers of muscle damage” and “work capacity” replace creatine kinase and time-to-exhaustion terminology.
7.5 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 No trial names, years, sample sizes or p-values.
7.6 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 No SMDs, mean differences or confidence intervals.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 All seven items come from the ER “Populations who should avoid this intervention” and “Photodynamic therapy agents — absolute contraindication” bullets.
8.2 [stop_items] represent the Contraindications from the ER 🟢 All seven ER contraindications are present and none is omitted; the “untested rather than contraindicated” Fitzpatrick V–VI note is correctly excluded.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Seven discrete <li> elements at lines 576–588.
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. 🟢 ER trailing clauses (“where safety data are absent rather than adverse”, “where data are absent”, “given reported effects on thyroid hormone requirements”) are stripped; no dashes introduce trailing text.
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 photodynamic agent list and the “typically 4–6 weeks for porfimer sodium” window, the “6 months” post-intraocular-surgery window, the “in the treatment field” scope and the “active cutaneous involvement” qualifier are 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 in the contraindication bullets.
8.7 If no [stop_items] are present the section is left empty N/A Seven stop items are present.

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 The five items map one-to-one onto the five caution bullets of that ER section.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 The photodynamic-therapy bullet is correctly excluded here because it appears in the Contraindications gate.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Five discrete <li> elements at lines 596–619.
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 “— caution, may require deferral”, “— caution, monitor”, “— no safety concern, monitor for redundancy” and “— caution, separate in time” clauses are stripped, as are all mitigation sentences.
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 named exemplars are retained (doxycycline, minocycline, ciprofloxacin, levofloxacin, isotretinoin, acitretin, hydrochlorothiazide, amiodarone, chlorpromazine, ibuprofen, naproxen, diphenhydramine, hypericin) along with the vitamin C 1 g / vitamin E 400 IU thresholds.
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 in the interaction bullets.
9.7 If no [caution_items] are present the section is left empty N/A Five caution items are present.

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 on timing, energy dosing and wavelength selection.
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Pre-exercise timing, total-energy dose per muscle-group size, and wavelength window are the three parameters the ER identifies as determining whether the protocol works.
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 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 spans carry ER-sourced content; values are quantified (5–10 min, 20–60 J / 60–300 J, 655–950 nm).

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 🟢 Soreness, muscle damage markers and training adaptation are the three outcomes named in the ER “Time to effect” bullet (line 444).
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 The two High-tier benefits precede the Low-tier adaptation outcome.
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 present; 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 spans carry ER-sourced content; the 24–96 hour and 8-week windows are the ER’s own.
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 time-to-effect information, so the section is correctly retained.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 All ten benefit labels correspond to the ten Expected Benefits sub-headings.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four spans present at lines 543, 549, 555, 561 with tier-matched content.
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. 🟢 Each tier is a semicolon-separated list of bare outcome labels; all Magnitude lines and narrative are omitted.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parentheses appear in any benefits span.
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 contain items in the ER.

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 All ten risk labels correspond to the ten Potential Risks & Side Effects sub-headings.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four spans present at lines 631, 637, 644, 650 with tier-matched content.
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. 🟢 Each tier is a semicolon-separated list of bare risk labels; Class 3B/4 detail and all Magnitude lines 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 risks span.
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 contain items in the ER.

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 All five rows come from the biomarker table in ER Monitoring Protocol & Defining Success (lines 476–482).
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 All five ER biomarkers present: creatine kinase, lactate dehydrogenase, hs-CRP, testosterone-to-cortisol ratio, ferritin, each with its ER target range.
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 747–750 reproduce the ER cadence: baseline in a normal training week, 24 h after a standardised damaging session at the end of an untreated and a treated block, then annually.

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 All seven items come from the qualitative marker list in ER Monitoring Protocol & Defining Success (lines 486–492).
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 All seven present: soreness rating, repetitions at fixed load, session RPE, sleep quality and duration, waking heart rate and HRV, subjective readiness, skin appearance.

Issues 10/08/2026 00:16

Pass rate 100.00%. No issues found.

Issues 10/08/2026 00:12

  1. 4.2 / 4.3 — Protocol labels not ER-verbatim: The three Protocol cell labels are paraphrased or invented rather than taken from the ER’s bold bullet labels — “Timing” (line 449) has no ER counterpart, “Energy dose” (line 463) abbreviates “Energy dosing:” (ER line 389), and “Wavelength” (line 477) abbreviates “Wavelength selection:” (ER line 387).

Fixes 10/08/2026 00:12

  1. 4.2 / 4.3 — Protocol labels made ER-verbatim: Replaced the three Protocol cell labels with the ER’s own bold bullet labels — “Timing” → “Pre-exercise application”, “Energy dose” → “Energy dosing”, “Wavelength” → “Wavelength selection”. The first action sub-line was reworded from “Pre-exercise application has the strongest pooled support…” to “This timing has the strongest pooled support…” to avoid repeating the new label.