Audit: QRS - Rolfing for Health & Longevity

Audit conducted on 27/09/2026 15:37 using AI4L + evidence-mcp / GPT 6

Iterations

Summary

Items Count
Total 94
Passed 89
Failed 0
N/A 5
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. 🟢 Content maps to ER Conclusion, Therapeutic Protocol, benefit/risk tiers, decision gates, and Monitoring.
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. 🟢 Unproven longevity, uncertain serious-injury frequency, theoretical supplement interaction, and unvalidated schedules remain explicit.
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”). 🟢 Assessment times are not described as established onset; no optimal dose or force is claimed.
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. 🟢 Decision gates follow ER avoid/defer wording, including items within its interaction list; tiers match the source.
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. 🟢 Named medicines and supplements occur in the ER for the same interaction; no new study identifiers appear.
1.6 The QRS does not introduce new attributions. 🟢 No additional attribution is introduced.

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, evidence-qualified tone matches the ER.
2.2 The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging 🟢 Practical schedule and monitoring information is accessible and evidence-qualified.
2.3 The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor 🟢 Descriptive studied schedules and uncertainty avoid prescribing a treatment course.
2.4 The QRS avoids language that implies medical or clinical advice 🟢 Content presents study schedules and ER precautionary boundaries with an educational disclaimer.
2.5 The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” 🟢 The protocol describes published treatment and validation limits.
2.6 The QRS never addresses “the reader” directly — it presents evidence, not guidance 🟢 No direct reader address in populated content.
2.7 The QRS is written in plain language, avoiding unnecessary medical jargon 🟢 Plain descriptions predominate; anticoagulants and analgesics retain the ER explanations.
2.8 Information is presented in a concise and very compact manner 🟢 Compact cells, short gate entries, and tiered descriptors.
2.9 It DOES NOT address the reader directly 🟢 No second-person address in populated content.
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. 🟢 The summary distinguishes health-oriented symptomatic adults from symptom-free active adults.
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. 🟢 Ten sessions over twenty weeks and ongoing monitoring retain effort requirements.
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. 🟢 The framing concerns active adults considering additional treatment.
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. 🟢 Unproven added health protection for symptom-free active adults is explicit.
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. 🟢 Longevity and slower aging are used without anti-aging marketing language.
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. 🟢 No colloquial route, treatment, or adverse-event terminology is introduced.

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 specified card, gate, tier, and table headings are retained.
3.2 All “<span data-qrs-var=”NAME”>…</span>” from the [qrs_template] are present in the the QRS. 🟢 Source comparison found every template data-qrs-var anchor present.
3.3 Spans that are not addressed in a checklist item are left unchanged 🟢 Unassigned website spans remain 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 High tiers use the required hidden-tier treatment under 12.5 and 13.5; no substituted empty-section statement appears.
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, interaction, and qualitative bold labels match the source ER.
4.3 Labels are not paraphrased, abbreviated, or invented. 🟢 Time labels use exact ER benefit headings; monitoring labels match its table.
4.4 The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. 🟢 No emoji indicators appear in the sheet.
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. 🟢 Source has A4 print sizing, compact print typography and spacing, three-column protocol grids, and condensed content; no browser render was performed.

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 immediately follows the doctype.
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. 🟢 The single metadata block has opening and closing YAML delimiters.
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. 🟢 The metadata block remains inside an HTML comment; visible date/model follow the required header fields.
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 are trimmed; duration quoting protects its colon.
5.5 The filename of the source ER is stated as “er_filename: [er_filename]” 🟢 er_filename names the supplied Rolfing source review.
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 matches 26.9.27.
5.7 Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430) 🟢 Creation timestamp uses YYYY-MMDD-HHMM.
5.8 The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]” 🟢 Creator nickname is present.
5.9 The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) 🟢 GPT is a single-word model nickname.
5.10 The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]” 🟢 Creator fullname is present.
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) 🟢 GPT 6 consists of nickname and version.
5.12 The filename of the document is stated as “qrs_filename: [filename of this document]” 🟢 qrs_filename matches the target basename.
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 have no extraneous whitespace or unnecessary quoting.

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 matches the ER canonical topic and required suffix, with ampersand encoded.
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 matches the ER canonical topic with ampersand encoded.
6.3 [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] 🟢 09/27/2026 matches the creation date.
6.4 [header_subline_model] is set to [qrs_creator_ai_fullname] 🟢 Header model matches GPT 6.
6.5 No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. 🟢 Only required header content and unchanged website hooks are present.

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 🟢 Opening identifies hands-on tissue work with movement education and its comfort/movement purpose.
7.2 [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section 🟢 Summary covers possible symptom benefits, longevity limits, harms, and time commitment.
7.3 [at_a_glance] is no longer than 70 words 🟢 67 whitespace-delimited words.
7.4 Every fact in [at_a_glance] is supported by a distinct passage in the ER. 🟢 Each statement maps to the three ER Conclusion paragraphs.
7.5 It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead 🟢 No specialist acronyms or technical classifications appear in the summary.
7.6 It DOES NOT cite specific trials (names, years, sample sizes, p-values) 🟢 No named trials, years, sample sizes, or p-values.
7.7 It DOES NOT cite effect sizes, relative risks, or statistical results 🟢 No effect sizes or statistical results.

8. Contraindications

# Description Result Comments
8.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 All stop items derive from Key Interactions & Contraindications.
8.2 [stop_items] represent the Contraindications from the ER 🟢 Four avoid-population bullets plus sedation, local tissue healing, and device-clearance gates are retained.
8.3 Individual [stop_items] are formatted as <li></li> 🟢 Each stop entry is an li element.
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. 🟢 Entries contain the applicable condition and avoidance/defer boundary without rationale or citations.
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). 🟢 Active/suspected clot, uncontrolled bleeding, severe fragility, unhealed injury, and clearance conditions remain.
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. 🟢 No source ranking notation requires normalization.
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 section is populated because the ER identifies avoidance and deferral scenarios.
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. <!– empty: ER names no population that should avoid the intervention –> N/A The contraindication section is populated; the empty-section condition does not apply.

9. Key Interactions

# Description Result Comments
9.1 The section is derived from the ER Key Interactions & Contraindications section 🟢 The remaining medicine and supplement interactions derive from the ER interaction section.
9.2 [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications 🟢 Anticoagulants, analgesics, and supplements are retained; avoid/defer entries already appear in Contraindications.
9.3 Individual [caution_items] are formatted as <li></li> 🟢 Each interaction is an li element.
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 interacting exposures and the necessary theoretical qualification are included.
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). 🟢 Warfarin, apixaban, aspirin, frequent ibuprofen, ginkgo, and concentrated garlic examples remain.
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. 🟢 No source ranking notation requires normalization.
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 section is populated because relevant interactions are identified.
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. <!– empty: ER names no interaction that changes how the intervention is used –> N/A The interaction section is populated; the empty-section condition does not apply.

10. Protocol

# Description Result Comments
10.1 The section is derived from the ER Protocol section 🟢 All three protocol cells derive from Therapeutic Protocol.
10.2 The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section 🟢 Schedule, pressure/participation, and adaptation cover the main implementation decisions.
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.
10.4 All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. 🟢 Every used action label, value, and subtext contains source-derived information.

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 🟢 Disability, anxiety, and mobility provide three distinct assessment times.
11.2 The sets are picked and ordered by the magnitude of the related benefit 🟢 Clinically meaningful controlled disability findings lead; the weaker uncontrolled mobility observation is last.
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 timing aspects are available.
11.4 All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. 🟢 Twenty weeks, five weeks, and completion of ten sessions match their ER outcomes; onset/persistence limitations remain.
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 timing information, so removal is not applicable.

12. Benefits

# Description Result Comments
12.1 The section is derived from the ER Expected Benefits section 🟢 All benefit descriptors and grades match Expected Benefits.
12.2 Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] 🟢 All four benefit tier spans are 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. 🟢 Only benefit headings remain, without study details or magnitudes.
12.4 Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical study or effect details appear.
12.5 If no items of a specific sub-section (high, medium, low, speculative) are present the respective <SPAN> is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. 🟢 The empty High benefit span is hidden with display: none.

13. Risks

# Description Result Comments
13.1 The section is derived from the ER Potential Risks & Side Effects section 🟢 All risk descriptors and grades match Potential Risks & Side Effects.
13.2 Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] 🟢 All four risk tier spans are 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 entries retain source headings without added explanation or frequency.
13.4 Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. 🟢 No parenthetical severity, sample, or frequency details appear.
13.5 If no items of a specific sub-section (high, medium, low, speculative) are present the respective <SPAN> is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. 🟢 The empty High risk span is hidden with display: none.

14. Monitoring

# Description Result Comments
14.1 The section is derived from the ER Monitoring section 🟢 All monitoring rows come from the ER monitoring table.
14.2 All measurable/quantifiable biomarkers from the Monitoring section are listed 🟢 All four source rows are retained, including the absence of a laboratory target.
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, per-session, 24–48-hour, three-session, completion, and three-month timing are retained and identified as pragmatic.

15. Qualitative Assessment

# Description Result Comments
15.1 The section is derived from the ER Monitoring section 🟢 All qualitative entries derive from ER Monitoring.
15.2 All subjective/qualitative biomarkers from the Monitoring section are listed 🟢 Daily function, sleep and comfort, and treatment burden are all present.

Issues 27/09/2026 15:37

Pass rate 100.00%. No issues found.

Issues 27/09/2026 15:33

  1. 1.2 / 1.3 — Sedation threshold narrowed: In Contraindications, “Defer while sedation/intoxication prevents consent or reliable sensation” narrows the ER’s “interferes with consent or accurate sensation.” Impaired consent can meet the source precaution before consent becomes impossible.

Fixes 27/09/2026 15:33

  1. 1.2 / 1.3 — Sedation threshold restored: Replaced “prevents consent or reliable sensation” with the ER wording “interferes with consent or accurate sensation” in the sedation deferral gate.