Audit: QRS - Heavy Metal Detox for Health & Longevity

Audit conducted on 29/08/2026 04:47 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	83
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, benefit, risk, gate, monitoring and qualitative content traces to ER sections Therapeutic Protocol, Expected Benefits, Potential Risks & Side Effects, Key Interactions & Contraindications, Practical Considerations, Monitoring Protocol & Defining Success and Conclusion.
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.	🟢	The ER’s hedges are carried through (“unsettled”, “kidney findings come from one research group”, “heart-disease results conflict”).
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 remains a contraindication, not a caution; the diabetes cardiovascular signal stays in the Low tier.
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 come only from the ER’s “Populations who should avoid” list; Key Interactions only from the ER’s interaction bullets; no modifying factors are promoted.
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.	🟢	The QRS contains no PMIDs, citations, expert names, NCT identifiers or brand names.
1.6	The QRS does not introduce new attributions.	🟢	No attributions appear anywhere in the sheet.

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.	🟢	Wording mirrors the ER (“strip zinc, copper and calcium”, “buys better health”, “resolve rapidly”).
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Concrete regimens, thresholds and monitoring targets are given without exhortation.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Statements are descriptive (“only documented poisoning is treated”), never directive.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives; the Cadence line and gates are stated as practice, not instruction.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of “recommend”, “advise”, “should” or “must” in the rendered text.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns in the rendered text.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms used are the clinical entities themselves (eGFR, transaminases, hypocalcaemia); no avoidable jargon added.
2.8	Information is presented in a concise and very compact manner	🟢	Every gate, benefit, risk and monitoring entry is a short phrase without elaboration.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by scan for “you”/”your”; none present.
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.	🟢	Functional ranges tighter than conventional cut-offs and a full 12-marker panel address 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.	🟢	The 40-infusion, 30-week regimen and weekly laboratory cadence are presented without hedging on burden.
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.	🟢	No simplified or population-level framing appears.
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 foregrounds the unsettled outcome evidence and the mineral-depletion cost, the decision-relevant weighting for this 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.	🟢	The string “anti-aging”/”anti-ageing” does not occur.
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.	🟢	“Oral succimer”, “infusions”, “adverse events”, “mucocutaneous reactions”; the informal-sounding “strip” and “buys” are carried verbatim from the ER Conclusion.

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, gate heads, tier labels and table column headers match the template byte-for-byte.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 template variables are present; the repeatable marker_#_* and qualitative_item_# rows are expanded to 12 and 6 numbered instances respectively.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	The website="evidence_review", website="audit" and website="full_review" spans, the CSS block and the footer disclaimer are unchanged from the template.

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 that feeds 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.	🟢	All three protocol labels and all seven Key Interactions labels, including their parenthetical drug lists, match the ER bold labels verbatim; monitoring row names match the ER Biomarker column exactly.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Protocol, interaction and biomarker labels are taken as-is; the three Time-to-effect labels are derived from the ER’s own time-to-effect content rather than invented.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji present; the ER’s “⚠️ Conflicted” markers are correctly dropped.
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 section is condensed to single-phrase entries with no elaborations, citations or effect sizes; item counts are those mandated by items 8.2, 9.2, 14.2 and 15.2.

---

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.	🟢	Lines 2–14; the comment opens immediately after <!doctype html>.
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; the preceding title text is permitted.
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 element repeats the values.
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: heavy_metal_detox_2026-0829-0223_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]”	🟢	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: 2026-0829-0427, correct format.
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” is nickname plus version with no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9 matches the actual filename heavy_metal_detox_2026-0829-0223_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.	🟢	Re-verified across all nine keys; no stray 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 &)	🟢	Line 22: “Heavy Metal Detox for Health & Longevity - 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., & for &)	🟢	Line 417: “Heavy Metal Detox for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “08/29/2026” from qrs_creation_date: 2026-0829-0427.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”.
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 the title and the template subline; the ER’s “Also known as” line 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	🟢	Compresses all four Conclusion paragraphs into what is established, what is unsettled, and what it costs.
7.2	[at_a_glance] is no longer than 60 words	🟢	59 words (60 tokens counting the standalone em-dash).
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to a distinct Conclusion sentence: metal lowering, single research group, conflicting cardiac trials, no cognitive restoration in children, mineral stripping, contaminated detox products.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “binding drugs”, “blood lead”, “thinking” replace chelators, biomarkers and cognition.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial names, years or sample sizes appear.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric results; magnitudes are qualitative (“substantially”, “smaller amounts”).

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’s “Populations who should avoid Heavy Metal Detox” list.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All seven ER avoidance populations are represented, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Lines 575–586: seven discrete <li> elements inside the span.
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.	🟢	The ER’s trailing “in whom…” rationales for pregnancy and for children are stripped; no dashes or explanations remain.
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).	🟢	Thresholds retained: eGFR below 30 mL/min/1.73 m², transaminases above twice ULN, blood lead below 45 µg/dL, platelets below 100,000/mm³; Wilson disease and haemochromatosis kept as a parenthetical.
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 inside parentheses in this section.
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 ER identifies seven such populations and the section is correctly populated.
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.	N/A	The section is not empty.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All seven items come from the ER’s interaction bullets.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All seven ER interactions are present; none duplicates a contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Lines 594–619: seven discrete <li> elements inside the span.
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.	🟢	Each item is reduced to the ER bold label plus the ER’s verdict word (“caution”, “caution to avoid”, “monitor”, “additive and protective; monitor”); the glucose-strip, creatinine, heparin and four-hour-separation rationales are all stripped.
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).	🟢	Every ER drug list is preserved: metformin/glipizide; gentamicin, amphotericin B, cisplatin, ibuprofen, naproxen; apixaban, rivaroxaban; levothyroxine, iron salts, lithium.
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 inside parentheses in this section.
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 ER identifies seven interactions and the section is correctly populated.
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.	N/A	The section is not empty.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three cells trace to the ER Therapeutic Protocol bullets.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	The three dosable regimens are selected — conventional medical, cardiovascular chelation, renal protection — over the non-dosable “Integrative approach” bullet.
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.	🟢	Succimer 10 mg/kg with the 8-hourly/12-hourly schedule, 40 weekly infusions over 30 weeks with the co-infused components, and 1 g weekly for five weeks of edetate calcium disodium all match the ER.

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	🟢	Blood lead, kidney function and poisoning-symptom resolution — the only three time-to-effect statements in the ER.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Order follows the ER benefit tiers: blood lead (High), kidney function (High), symptom resolution (Medium).
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 exist; 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.	🟢	“Days”, “Months to years” and “Rapid” with subs taken from ER Practical Considerations and the Medium benefit entry.
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; 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 headings from the ER are represented in the matching tiers.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans are present and populated (lines 543–565).
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 entry is the ER heading reduced to a phrase; no magnitudes, hazard ratios, confidence intervals or study names carried over.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses appear in any benefits entry.
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 have items in the ER.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All nine risk headings from the ER are represented in the matching tiers.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans are present and populated (lines 631–653).
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.	🟢	Frequencies (16% vs 15% discontinuation, 4.3% positive predictive value, 20.7% contamination) and study attributions are all stripped.
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 entry.
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 have items in the ER.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows and cadence come from the ER Monitoring Protocol & Defining Success section.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All twelve ER biomarker rows are present with their optimal functional ranges unchanged.
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 833–837 reproduce the ER’s baseline, weekly, day-fourteen, four-to-six-week and six-to-twelve-month schedule.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items come from the ER’s “Qualitative markers worth tracking” list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	Cognitive clarity, daytime energy, sleep quality, peripheral symptoms, skin/mouth changes and exercise tolerance — all six ER bullets.

Issues 29/08/2026 04:47

Pass rate 100.00%. No issues found.

Issues 29/08/2026 04:42

1. 1.3 — Hedge dropped from sleep marker: [qualitative_item_3] at line 857 reads “which infusion fluid loads disturb”, strengthening the ER’s hedged “which infusion fluid loads can disturb” (ER line 455) into an unqualified assertion.

Fixes 29/08/2026 04:42

1. 1.3 — Hedge restored on sleep marker: [qualitative_item_3] changed from “which infusion fluid loads disturb” to “which infusion fluid loads can disturb”, restoring the ER’s hedged wording.

Issues 29/08/2026 04:33

1. 1.1 / 7.3 — At-A-Glance metal antecedent wrong: The closing clause of at_a_glance (line 438), “The drugs also strip zinc, copper and calcium, and some products sold for detoxification contain those metals”, makes “those metals” refer to zinc, copper and calcium; the ER (lines 281, 482) documents contamination with lead, mercury and arsenic only.
2. 4.5 — Sheet overruns the A4 budget: Estimated rendered height is roughly double one A4 page, driven by the twelve Monitoring “Why” cells and the cadence paragraph (lines 677–840), the six Qualitative Assessment items (lines 847–881), the four-line nephrotoxic-drug caution_items entry (lines 595–602), and the three-line action_#_sub and time_#_sub cells.

Fixes 29/08/2026 04:33

1. 1.1 / 7.3 — At-A-Glance metal antecedent corrected: Changed the closing clause of at_a_glance from “some products sold for detoxification contain those metals” to “contain lead, mercury or arsenic”, matching the ER Conclusion; “also” was dropped from the preceding clause to hold the section at 59 words.
2. 4.5 — Monitoring “Why” cells condensed: Trimmed ten of the twelve marker_#_why cells to their load-bearing clause (e.g. “The single most important safety marker, given chelation-related fatal hypocalcaemia” to “Most important safety marker, given fatal chelation hypocalcaemia”), removing wrapped lines from the biomarker table.
3. 4.5 — Monitoring cadence shortened: Reduced monitoring_cadence from 282 to 232 characters (“during infusion protocols” to “during infusions”, “then every six to twelve months” to “then six- to twelve-monthly”), keeping all five cadence points from the ER.
4. 4.5 — Qualitative Assessment items tightened: Shortened all six qualitative_item_# entries by dropping trailing relative clauses and em-dash asides (e.g. “Peripheral symptoms — numbness, tingling, grip strength — which are the classic lead findings” to “Peripheral symptoms: numbness, tingling, grip strength”).
5. 4.5 — Protocol and Time-to-Effect sub-lines condensed: Compressed action_1_sub, action_3_sub, time_1_sub and time_2_sub (e.g. “Every eight hours for five days, then every twelve hours for fourteen days” to “Eight-hourly for five days, then twelve-hourly for fourteen days”) without dropping any dose, schedule or qualifier.