Audit: QRS - Rolfing for Health & Longevity
Audit conducted on 27/09/2026 15:37 using AI4L + evidence-mcp / GPT 6
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., & 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., & 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
- 1.2 / 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
- 1.2 / 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.