Audit: QRS - Kanna for Health & Longevity

Audit conducted on 22/09/2026 18:03 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	94
Passed	88
Failed	0
N/A	6
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.	🟢	Every protocol dose, time-to-effect figure, gate item, benefit/risk descriptor, biomarker target and qualitative marker traces to a literal ER passage.
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.	🟢	“Reported harms have been mild” and “Nothing supports a broad mood lift” mirror the ER Conclusion hedging.
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 and MAOI use remain in Contraindications, not Key Interactions; serotonergic supplements remain cautions, as in the ER.
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 from the ER “Populations who should avoid Kanna” list; Key Interactions from the ER interaction bullets; no modifying factor is 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.	🟢	No PMIDs, author names, NCT identifiers or brand names (Zembrin, HG&H, PLT) appear anywhere in the QRS.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind 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.	🟢	Same measured, British-spelling, evidence-first register as the ER.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Concrete doses, thresholds and self-assessable markers give the reader actionable levers without overclaiming.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Protocol cells describe what was studied (“the design under which anxiety and amygdala effects were demonstrated”) rather than instructing.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperatives directed at a reader; the only advisory text is the fixed template disclaimer.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of recommend/advise/should/must in document voice.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the sheet.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms that remain (amygdala, serotonergic) are the ER’s own and carry no plainer equivalent at this density.
2.8	Information is presented in a concise and very compact manner	🟢	Gate items, benefit and risk tiers are reduced to bare descriptors; protocol subs are single clauses.
2.9	It DOES NOT address the reader directly	🟢	Confirmed: no “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.	🟢	Sheet assumes willingness to run bloodwork, track GAD-7 weekly and verify a certificate-of-analysis-grade product.
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.	🟢	Eight-biomarker monitoring panel with a staged cadence presupposes exactly that willingness.
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.	🟢	Functional (not conventional) reference ranges and a six-item qualitative log are beyond general-population framing.
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.	🟢	The lede names product unreliability and antidepressant stacking as the real hazards — the two that matter to a self-experimenting reader.
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 appear; the title carries the ER’s “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)”; “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.	🟢	action_1_sub uses “administered orally”; the ER’s “by mouth” was correctly upgraded. No “pill”/”shot”/”bad reaction”.

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, gate heads, tier labels and column headers match the template byte-for-byte.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 34 template variables present; the repeatable marker_#* and qualitative_item# spans are instantiated 8× and 6× 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 are untouched; head, CSS and footer diff clean against 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 feeding 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.	🟢	“Standard daily protocol”, “Low-dose alternative”, “Acute situational protocol” and every Key Interaction label are the ER’s bold labels verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Monitoring marker names are taken verbatim from the ER biomarker table; time-to-effect labels are drawn from the ER’s own “Time to effect” clauses.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	Unicode scan returns no emoji; the ER’s ⚠️ Conflicted flags 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 section is already at its minimum: the gate lists, the eight biomarkers and six qualitative markers are mandated in full by 8.2/9.2/14.2/15.2, and all discretionary prose is single-clause.

---

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 --- at line 3, closing --- at line 13.
5.3	The metadata is not visible in any rendered view of the QRS and is not surfaced by any other element on the sheet.	🟢	Enclosed in an HTML comment; no metadata value is echoed into the body.
5.4	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Only duration: "00:03" is quoted, and it contains a colon.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	er_filename: kanna_2026-0825-1904_Opus_ER.md at line 4.
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: 26.9.22 matches 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: 2026-0922-1743.
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” — nickname plus version, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: kanna_2026-0825-1904_Opus_QRS.html matches 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 nine keys; no stray whitespace or 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 &)	🟢	“Kanna 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 &)	🟢	“Kanna for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0922-1743 → 09/22/2026.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	“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 is title plus the template subline only; the ER’s “Also known as” line is correctly omitted.

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	🟢	Opens “Kanna is a southern African succulent, sold as a standardised capsule for stress, focus, and social ease.”
7.2	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	Compresses all three Conclusion paragraphs into effects, non-effects and the two real hazards.
7.3	[at_a_glance] is no longer than 70 words	🟢	67 words.
7.4	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Succulent/capsule framing from Motivation; the three effects, the absent mood lift and the two hazards from Conclusion.
7.5	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “succulent”, “capsule”, “antidepressants” are everyday terms.
7.6	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	“Small trials in healthy volunteers” carries no name, year or n.
7.7	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No η², Cohen’s d or p-values.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All seven items map to the ER “Populations who should avoid Kanna” list.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All seven ER avoid-populations are present, none added.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Seven <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.	🟢	Every ER em-dash tail (“— no safety or efficacy data exist”, “— untested, and serotonergic agents can precipitate mania”, etc.) is stripped.
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).	🟢	“within 14 days of stopping one”, “above 9, or any suicidality item above 0” and “(above 160/100 mmHg)” all preserved.
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.	🟢	The ER uses no ranking notation; items are plain comma-separated text.
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.	🟢	Section is populated, and the ER does identify such populations.
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 eight items map to ER interaction bullets.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	The SSRI, SNRI and MAOI bullets are correctly excluded as contraindications; the remaining eight are all present.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Eight <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.	🟢	Every “Caution; …” rationale and “Mitigation: …” tail from the ER is 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).	🟢	Drug lists preserved for all six items that carry one; “(in cough syrups such as Robitussin DM, Delsym)” is trimmed to “(in cough syrups)” rather than dropped.
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.	🟢	The ER uses no ranking notation; all parentheticals are comma-separated lists.
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.	🟢	Section is populated, and the ER identifies eleven interactions.
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 come from the ER Therapeutic Protocol bullets, with time-of-day from the same section.
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Standard daily dose, low-dose alternative and acute situational dose are the three actionable bullets; the remainder of the ER section is descriptive (half-life, genetics, sex, age).
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 provides three or more 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.	🟢	Nine populated spans, each traceable to a Therapeutic Protocol bullet.

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	🟢	Acute anxiety (60 minutes), cognitive flexibility (3 weeks) and reaction tasks (8 days) are the only three intervals the ER states.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Order matches the ER Expected Benefits Medium-tier ordering: acute anxiety, cognitive flexibility, complex reaction.
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 three distinct time-to-effect aspects; all three sets are used.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	All nine spans populated from the ER “Time to effect” bullet in Practical Considerations.
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 does provide 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	🟢	Each entry is an ER benefit sub-heading.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans 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.	🟢	Bare semicolon-separated descriptors; no Magnitude text, p-values or Cohen’s d carried over.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses in any benefits span.
12.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	🟢	The ER has no High-tier benefit; [benefits_high] is emptied and set to style="display: none".

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	Each entry is an ER risk sub-heading.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans 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.	🟢	No incidence figures (14% weight gain, 39-fold hordenine variation) or study detail carried over.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses in any risks span.
13.5	If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing.	🟢	The ER has no High-tier risk; [risks_high] is emptied and set to style="display: none".

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Rows mirror the ER Monitoring Protocol & Defining Success biomarker table.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All eight ER table rows present: blood pressure, resting heart rate, serum sodium, ALT, AST, morning cortisol, GAD-7, sleep-onset latency.
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.	🟢	Reproduces the ER’s ongoing-monitoring paragraph: weekly anxiety score, four-week vitals, three-month labs, then six-to-twelve-monthly.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six items come from the ER qualitative-marker bullet list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six present: subjective calm, task switching, reaction quality, sleep onset/grogginess, appetite direction, absence of serotonergic excess signs.

Issues 22/09/2026 18:03

Pass rate 100.00%. No issues found.

Issues 22/09/2026 17:57

1. 11.2 — Time-to-effect cells mis-ordered: The Time to effect cells run cognitive flexibility (3 weeks), acute anxiety (within 60 minutes), reaction tasks (8 days), while the ER Medium benefit tier and the QRS Benefits card both lead with acute blunting of situational anxiety, so the ordering does not follow the magnitude of the related benefit.

Fixes 22/09/2026 17:57

1. 11.2 — Time-to-effect cells reordered: Swapped the first two Time to effect cells so acute anxiety (within 60 minutes) now leads, followed by cognitive flexibility (3 weeks) and reaction tasks (8 days), matching the benefit ordering used in the ER and in the QRS Benefits card.

Issues 22/09/2026 17:50

1. 1.3 — Refuted claim listed as benefit: benefits_low (lines 548-553) presents “appetite and thirst suppression” as a low-evidence benefit, but the ER states the traditional claim “is not supported by the trial data” and that the only trial to record these outcomes “found the opposite direction” (ER lines 169-173), with the Conclusion adding that appetite suppression “ran the opposite way when it was actually measured” (ER line 456).

Fixes 22/09/2026 17:50

1. 1.3 — Refuted claim removed from benefits: Dropped “appetite and thirst suppression” from benefits_low, leaving “Subjective mood and sleep quality”, since the ER states the claim is unsupported and the measured direction was the opposite.

Issues 22/09/2026 17:48

1. 12.3 / 12.4 — Conflicted qualifier kept in Benefits: The benefits_medium item at line 544 (“Acute blunting of situational anxiety (conflicted)”) and the benefits_low item at line 550 (“appetite and thirst suppression (conflicted)”) retain a parenthetical evidence qualifier that the tier label already encodes.
2. 13.3 / 13.4 — Conflicted qualifier kept in Risks: The risks_medium item at line 613 (“Mild treatment-emergent adverse effects (conflicted)”) retains the same parenthetical evidence qualifier, which section 13 requires to be stripped.

Fixes 22/09/2026 17:48

1. 12.3 / 12.4 — Conflicted qualifier removed from Benefits: Stripped the parenthetical “(conflicted)” from the benefits_medium acute-anxiety item and the benefits_low appetite/thirst item, leaving only the key facts.
2. 13.3 / 13.4 — Conflicted qualifier removed from Risks: Stripped the parenthetical “(conflicted)” from the risks_medium “Mild treatment-emergent adverse effects” item.