Audit: QRS - Ayahuasca for Health & Longevity

Audit conducted on 04/08/2026 19:02 using AI4L / 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.	🟢	Protocol cells trace to ER lines 445–457; monitoring rows to the ER biomarker table (lines 524–535); gate items to line 415 and the interaction bullets 393–413.
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.	🟢	Hedges preserved, e.g. “Where they occur” on the mood time-to-effect cell and the Speculative tiers on both Benefits and Risks.
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”).	🟢	Absolute exclusions stay absolute (pregnancy and breastfeeding, uncontrolled epilepsy); washout windows carried at ER severity.
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 come only from Key Interactions & Contraindications; Benefits from Expected Benefits; Risks from Potential Risks & Side Effects; Monitoring and Qualitative from Monitoring Protocol & Defining Success.
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, author names, NCT identifiers, or brand names 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.	🟢	Matches the ER’s measured, non-promotional register, including its explicit flagging of where the signal is contested.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Thresholds and windows are given as decision data rather than instructions.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Statements are descriptive throughout; no imperative constructions.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No “should”, “must”, “recommended”, or “advised” appears in the document body.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	Cadence and monitoring content is stated as practice, not prescribed.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the body.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Retained technical terms (NYHA Class III–IV, Child-Pugh B or C, QTc) are load-bearing decision thresholds, not decoration.
2.8	Information is presented in a concise and very compact manner	🟢	Benefits and Risks reduced to bare tier lists; interactions reduced to single-line entries.
2.9	It DOES NOT address the reader directly	🟢	Confirmed by full-text scan for “you”/”your”.
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.	🟢	Screening thresholds, genotype panel, and electrolyte targets assume an actively optimising reader.
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.	🟢	Multi-week washouts, CYP2D6 genotyping, and a 12-marker baseline panel are presented without hedging on effort.
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 simplification toward a general-population reader.
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 names the expectation-adjusted shrinkage of the depression signal, the key caveat 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.	🟢	“Anti-aging” does not occur; the title uses “Health & Longevity”.
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.	🟢	“top-up”, “cup”, and “drinker” are the ER’s own terms for this preparation (ER lines 445, 455, 485).

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 headings byte-identical to the template; confirmed by diff against core/qrs/QRS.html.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All template variables present; marker_#_* expanded to 12 numbered rows and qualitative_item_# to 6 numbered items.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	The website="evidence_review", website="full_review", and website="audit" spans are untouched, as are the CSS block and footer disclaimer.

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.	🟢	Protocol labels (“Traditional Amazonian ceremonial protocol”, “Single versus split dosing”, “Best time of day”) and all six qualitative labels are verbatim from the ER bullets.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	The 12 marker names reproduce the ER biomarker column exactly, including “Serum magnesium (RBC)” and “PHQ-9 and GAD-7 questionnaire scores”.
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 were 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 oversized ER section is condensed rather than extended: 13 protocol bullets reduced to 3 cells, tiered lists reduced to bare headings, 12 interaction bullets compressed to 9 single-line entries.

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, immediately after 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.	🟢	Opening “—” line 3, closing “—” line 13; the preceding title line 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 duplicate rendering elsewhere.
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: "00:04" is quoted, correctly, because it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	er_filename: ayahuasca_2026-0804-1559_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]”	🟢	qrs_prompt_version: 26.7.02, matching the QRS.md badge.
5.7	Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430)	🟢	qrs_creation_date: 2026-0804-1843.
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢	qrs_creator_ai_nickname: Opus.
5.9	The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT)	🟢	Single word, no version.
5.10	The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]”	🟢	qrs_creator_ai_fullname: Opus 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” carries no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: ayahuasca_2026-0804-1559_Opus_QRS.html, matching the file 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.	🟢	Re-verified across all 10 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 &)	🟢	“Ayahuasca for Health & Longevity - Quick Reference Sheet” (line 22).
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	“Ayahuasca for Health & Longevity” (line 417).
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0804-1843 → “08/04/2026” (line 421).
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	“Opus 5” (line 425).
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	Header carries only the template subline; the ER’s “Also known as” line was correctly 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 ER lines 583–585: two-alkaloid mechanism, the depression signal and its shrinkage, and where serious harm concentrates.
7.2	[at_a_glance] is no longer than 60 words	🟢	57 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each clause maps to a separate sentence of the ER Conclusion.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	DMT, MAO-A, and 5-HT2A are all avoided in favour of “one ingredient” / “a second”; no acronyms present.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	Refers to “a later comparison” without naming it.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric results appear.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	Sourced from the “Populations who should avoid this intervention” bullet, ER line 415.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All 10 ER exclusion populations are present, in ER order.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Ten discrete <li> elements, lines 576–593.
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 inline glossary expansions for NYHA, QTc, and Child-Pugh were stripped; no trailing dash clauses 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).	🟢	160/100 mmHg, “within 6 months”, NYHA Class III–IV, QTc above 500 ms, and Child-Pugh Class B or C 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 inside parentheses in this section.
8.7	If no [stop_items] are present the section is left empty	N/A	Ten stop items are present.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	Drawn from ER lines 393–413.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Nine entries cover the antidepressant classes, MAOIs, serotonergic opioids, stimulants, triptans/decongestants/lithium, supplements, retreat adjuncts, and tyramine; none duplicates a stop item.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Nine discrete <li> elements, lines 601–630.
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 “Severity — … Consequence — … Mitigation:” scaffolding is fully stripped; only the drug class and its window remain.
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).	🟢	Named exemplars retained in parentheses and the 2-week / 5–6-week / 1-week / 24-hour windows all carried through.
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	If no [caution_items] are present the section is left empty	N/A	Nine caution items are present.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢	All three cells trace to ER Therapeutic Protocol, lines 445–455.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Dose and session structure, single versus split dosing, and time of day are the three decision points the ER treats as actionable.
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 well over 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 fields carry ER-derived content, including the 1 mL/kg trial dose and the 60–90 minute top-up window.

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	🟢	Mood change within 24 h, wellbeing/mindfulness/behaviour at 1–6 months, and acute onset at 30–60 min (ER lines 457, 498).
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered High tier (depressive symptoms) → Medium tier (wellbeing, mindfulness, behaviour) → acute pharmacology.
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	The ER supplies more than three; 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 fields populated; the 7-to-21-day attenuation note matches ER line 480.
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 data, so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All 13 entries map one-to-one onto the ER benefit subheadings.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated at the ER’s own tier assignments.
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.	🟢	Reduced to bare subheading text; the Cohen’s d, response-rate, and percentage magnitudes from the ER are all omitted.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses remain in any benefit 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 contain items in the ER, so no span needed hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All 14 entries map one-to-one onto the ER risk subheadings.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated at the ER’s own tier assignments.
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.	🟢	The 62% vomiting rate, 10–25 mmHg rise, and 1–3% persistence figures are all left out.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses remain in any risk 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 contain items in the ER, so no span needed hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows reproduce the ER biomarker table at lines 522–535.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All 12 ER biomarkers present, from blood pressure through PHQ-9/GAD-7, with targets carried verbatim.
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.	🟢	Condenses ER line 537 including the 24 h, 48 h, 1/4-week, 3-month, and 6-to-12-month intervals.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Drawn from the qualitative-marker bullets at ER lines 541–551.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six present: rumination frequency, emotional range and reactivity, sleep quality, persisting behavioural change, cognitive clarity and flexibility, absence of warning signs.

Issues 04/08/2026 19:02

Pass rate 100.00%. No issues found.

Issues 04/08/2026 18:52

1. 4.5 — Sheet overflows one A4 page: At the print stylesheet’s A4 geometry the sheet renders at roughly 2,500 px against 1,033 px of usable height (about 2.4 pages); the Key Interactions gate, the Monitoring card, the Qualitative Assessment card, and the Protocol sub-lines all exceed their per-section budget.

Fixes 04/08/2026 18:52

1. 4.5 — Key Interactions gate condensed: Trimmed example drug lists to their leading representatives (paroxetine, citalopram, clomipramine, selegiline, tapentadol, fermented meats, pre-workout formulas dropped), shortened “Opioid and cough preparations with serotonergic activity” to “Serotonergic opioids and cough preparations”, and abbreviated repeated time windows to “24 h either side”; all interaction classes, washout windows, and thresholds are retained.
2. 4.5 — Monitoring “Why” column and cadence tightened: Shortened six rationale strings (e.g., “Excludes the electrical-recovery abnormality that turns an adrenaline surge into an arrhythmia” → “…behind adrenaline-driven arrhythmia”; “The only measures against which a mood or anxiety benefit can actually be verified” → “The only measures verifying a mood or anxiety benefit”) and compressed the cadence sentence, keeping all twelve biomarkers and every target value unchanged.
3. 4.5 — Protocol and Time-to-effect sub-lines compressed: Replaced spelled-out units and connective prose with compact forms (e.g., “sessions run 4 to 6 hours, on 2 to 4 nights across a 5 to 10 day retreat” → “4–6 h sessions on 2–4 nights across a 5–10 day retreat”) and dropped the editorial clause “this rapidity is the single most distinctive clinical feature”; all doses, windows, and the “Where they occur” and “at least 24 hours” hedges are preserved.
4. 4.5 — Qualitative Assessment items shortened: Removed redundant clauses across all six items (e.g., “whether previously flattened emotional responses return, and whether reactions to provocation are less automatic” → “whether flattened responses return and reactions are less automatic”), keeping every ER bold label and each item’s warning-sign content intact.