Audit: QRS - Bacopa monnieri for Health & Longevity

Audit conducted on 06/09/2026 08:56 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.	🟢	Every populated span traces to ER text: at_a_glance to Conclusion, actions to Therapeutic Protocol, time cells to Practical Considerations / Expected Benefits, benefits and risks to the tiered ER headings, gates to Key Interactions & Contraindications, markers and cadence to Monitoring Protocol & Defining Success.
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.	🟢	No empty-state or hedged ER phrasing is altered; “Evidence points to no benefit in established memory disease” mirrors the ER Conclusion wording.
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”).	🟢	Avoidance populations remain in the Contraindications gate; monitor-level interactions remain in the Key Interactions gate.
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.	🟢	No item from Benefit-Modifying Factors, Risk-Modifying Factors, Risk Mitigation Strategies or Sourcing and Quality is surfaced in a gate or tier card.
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 carries no PMIDs, citations, expert names, NCT identifiers or extract brand names at all.
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.	🟢	Measured, hedged, non-promotional register matching the ER.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Quantified doses, durations and marker ranges alongside plain-language framing.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is stated as evidence and protocol description, not as instruction.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperative or prescriptive constructions; no “should”, “must”, “recommend”, or “advise” anywhere in the body.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	All cards present facts, ranges and labels only.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns occur in the rendered body.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms appear only where the ER uses them and are confined to the monitoring and gate sections.
2.8	Information is presented in a concise and very compact manner	🟢	Every list item is a condensed noun phrase; no explanatory prose outside the cadence line.
2.9	It DOES NOT address the reader directly	🟢	Confirmed: no “you”/”your” in the body.
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.	🟢	Content assumes willingness to run a 12-week course with laboratory monitoring.
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.	🟢	Weekly pulse checks, thyroid and liver panels, and rotating memory testing are presented without qualification.
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.	🟢	Monitoring and interaction detail exceeds 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 at-a-glance foregrounds both the small durable effect and the product-authentication problem, the two decision-relevant facts 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” 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.	🟢	“Gastrointestinal upset”, “resting heart rate”, “cholinergic excess”; no consumer-grade substitutes present.

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 headings, tier labels and column headers are byte-identical to the template.
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 38 template variable names are present; the repeatable marker_#_* and qualitative_item_# spans are instantiated as marker_1–7 and qualitative_item_1–6.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A masked diff against the template shows changes only inside data-qrs-var spans and in the metadata block; the website="evidence_review", website="audit" and website="full_review" spans are untouched.

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.	🟢	“Standard dose”, “Minimum duration” and “Best time of day” are the ER Therapeutic Protocol bold labels verbatim; interaction labels reproduce the ER bold labels.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Protocol labels and monitoring marker names are verbatim; time-to-effect labels track the ER benefit headings.
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢	No emoji characters occur in the file; the ER’s 🟩/🟥/🟨 tier markers and ⚠️ conflict flags were correctly stripped.
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 rather than transcribed: interaction bullets reduced to label plus drug parenthetical, the ER’s four-column monitoring table reduced to three with shortened “Why” text, and the two cadence paragraphs compressed into one line.

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 first element 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; the title line precedes it.
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 and not duplicated anywhere in 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: bacopa_monnieri_2026-0906-0623_Opus_ER.md, matching the ER’s own filename frontmatter value.
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 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)	🟢	qrs_creation_date: 2026-0906-0816.
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 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]”	🟢	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 context-window or other qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	qrs_filename: bacopa_monnieri_2026-0906-0623_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: no stray whitespace and no unnecessary quoting on any key.

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 &)	🟢	“Bacopa monnieri 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 &)	🟢	“Bacopa monnieri for Health & Longevity” (line 417).
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0906-0816 → “09/06/2026” (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.	🟢	The header carries only the title and the template subline; the ER’s “Also known as” list 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	🟢	Condenses all three Conclusion paragraphs, including the food-with-dosing and product-authentication points.
7.2	[at_a_glance] is no longer than 60 words	🟢	59 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Five clauses map to five distinct Conclusion sentences.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; “established memory disease” replaces dementia and “digestive” replaces gastrointestinal.
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	🟢	The ER’s “60%” authentication figure and all p-values and confidence intervals were correctly omitted.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All six items come from the “Populations who should avoid Bacopa monnieri” list inside that ER section.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All five ER avoidance bullets are represented; the bradycardia / heart-block bullet is split into two items without loss.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Six <li> elements inside the stop_items span (lines 574–579).
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.	🟢	Trailing rationale is stripped throughout, e.g. the pregnancy em-dash clause, “given the animal thyroxine signal”, and “since the paediatric evidence covers males aged 6–14 only”.
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).	🟢	“Uncontrolled”, “under 50 bpm”, “second- or third-degree”, “untreated Graves’ disease, toxic nodular goitre” and “outside supervised trials” are 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 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 names avoidance 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 ten items map to bullets in that ER section.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Ten of the ER’s eleven interaction bullets are carried; muscarinic agonists are correctly omitted because they already appear as a contraindication.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Ten <li> elements inside the caution_items span (lines 587–596).
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.	🟢	Em-dash glosses (“— drugs that raise acetylcholine”, “— blood-pressure drugs that relax arteries”) and the “Caution / Monitor / Monitor closely” verdicts 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 parenthetical survives in shortened form; none is dropped entirely.
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 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 names eleven 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 derive from 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	🟢	Dose, minimum duration and timing/food are the three decision-critical levers in the ER protocol list.
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 thirteen protocol bullets, well above three.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine action spans carry substantive ER-derived content; no placeholders remain.

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	🟢	Delayed verbal recall, speed of attention, and anxiety/stress reactivity — the three outcomes for which the ER states a time course.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Order follows the ER benefit tiers: two High-tier outcomes, then the Medium-tier anxiety outcome.
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 time-to-effect aspects are available in the ER.
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢	“6–12 weeks” derives from “at least six weeks … maximal effects at 12”; the two 12-week values derive from the ER’s stated 12-week dosing windows.
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 an explicit “Time to effect” bullet and per-outcome timing.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All nine benefit entries correspond one-to-one with the ER’s tiered benefit headings.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 542–564).
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 condensed heading text; the ER’s “Magnitude” paragraphs and ⚠️ Conflicted markers are excluded.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content is carried into any benefit item.
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 benefit tiers contain items in the ER.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All seven risk entries correspond to the ER’s tiered risk headings.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 608–627).
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.	🟢	Condensed heading text only; the p-values, the 2.3% pooled figure and the 60% authentication rate are excluded.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content is carried into any risk item.
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 risk tiers contain items in the ER.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Table and cadence both derive from Monitoring Protocol & Defining Success.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All seven ER table rows are present: TSH, free T4, ALT, resting heart rate, hs-CRP, delayed recall score, and INR.
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 set, weekly-then-monthly pulse, 12-week and 6–12-month panels, 12-week and 6-month memory testing, and the 2/4-week INR checks are all captured.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Taken from the “Qualitative markers worth tracking alongside the numbers” list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers are reproduced verbatim as qualitative_item_1–6.

Issues 06/09/2026 08:56

Pass rate 100.00%. No issues found.

Issues 06/09/2026 08:48

1. 4.3 — Interaction labels paraphrased: Four caution_items labels are rewritten rather than taken verbatim from the ER’s bold labels — “Sedating antihistamines and sleep aids” (line 592) for “Over-the-counter antihistamines and sedating sleep aids”, “Acid suppressants” (line 593) for “Over-the-counter acid suppressants”, “Cholinergic supplements” (line 594) for “Supplements with additive cholinergic effect”, and “Sedative supplements” (line 595) for “Sedative and calming supplements”.
2. 2.6 / 2.9 — Implicit direct address in marker target: marker_6_target reads “No established target; track own baseline” (lines 707-709), an elliptical imperative whose dangling “own” implies “your own”; the ER states it in the third person as “track change from the individual’s own baseline”.

Fixes 06/09/2026 08:48

1. 4.3 — Interaction labels restored to ER wording: Restored the four paraphrased caution_items labels to the ER’s bold labels — “Sedating antihistamines and sleep aids” to “Over-the-counter antihistamines and sedating sleep aids”, “Acid suppressants” to “Over-the-counter acid suppressants”, “Cholinergic supplements” to “Supplements with additive cholinergic effect”, and “Sedative supplements” to “Sedative and calming supplements”. Trimmed drug lists were left as-is per item 9.5.
2. 2.6 / 2.9 — Implicit direct address removed: Changed marker_6_target from “No established target; track own baseline” to “No established target; change from individual baseline”, replacing the elliptical imperative with the ER’s third-person framing.

Issues 06/09/2026 08:42

1. 1.1 — Cadence overstates baseline set: [monitoring_cadence] (line 733) begins “All markers at baseline”, but the ER (line 450) enumerates the baseline set as a thyroid panel, liver enzymes, a resting seated pulse and a memory test, with a narrow-therapeutic-index drug’s own marker added only for users on such a drug; hs-CRP is not part of the ER’s baseline set and INR is explicitly “Relevant only to anticoagulated users” (ER line 462).

Fixes 06/09/2026 08:42

1. 1.1 — Cadence baseline set corrected: Replaced “All markers at baseline” in [monitoring_cadence] with the ER’s own enumerated baseline set (“Thyroid panel, liver enzymes, resting pulse and one memory test at baseline”) and added the ER’s “for anticoagulated users only” qualifier to the INR check.

Issues 06/09/2026 08:37

1. 1.3 — Hedge dropped on dementia claim: [at_a_glance] (line 436) asserts “No benefit in established memory disease”, strengthening the ER Conclusion’s hedged “In established memory disease the evidence points to no benefit” (ER line 493).

Fixes 06/09/2026 08:37

1. 1.3 — Hedge restored on dementia claim: [at_a_glance] now reads “Evidence points to no benefit in established memory disease” instead of “No benefit in established memory disease”, matching the ER Conclusion’s hedging; “holding on to” was tightened to “retaining” to keep the section within the 60-word budget (59 words).

Issues 06/09/2026 08:32

1. 10.4 — Action sub sourced outside Protocol: [action_2_sub] (QRS line 470) opens with “Most self-trials stop at two to four weeks”, which comes from the ER Practical Considerations section (ER line 424) rather than from the ER Therapeutic Protocol section that item 10.4 requires.

Fixes 06/09/2026 08:32

1. 10.4 — Action sub sourced outside Protocol: Replaced the opening clause of [action_2_sub] — “Most self-trials stop at two to four weeks” (from the ER Practical Considerations section) — with “Twelve weeks before judging effect”, taken from the ER Therapeutic Protocol “Minimum duration” bullet.

Issues 06/09/2026 08:24

1. 4.5 — Sheet exceeds one A4 page: At the template’s print geometry the populated sheet runs roughly 1.7 A4 pages; the Key Interactions gate (lines 589-598, ten items with four-drug example lists in a half-width column), the seven-row monitoring table (lines 645-743) and the 3-4-line protocol and time sub-cells (lines 455-534) are the sections carrying more content than their per-section budget allows.
2. 2.8 — Duplicated and off-topic protocol text: action_2_sub (lines 469-472) restates its own value cell as “Twelve weeks before judging effect” and then repeats time_1_sub’s six-week/12-week sentence (lines 503-506), while time_3_sub (lines 531-534) closes with “Acute single doses move mood measures, not memory”, which does not describe the 12-week time-to-effect it labels.

Fixes 06/09/2026 08:24

1. 2.8 — Duplicated minimum-duration text: Replaced action_2_sub “Twelve weeks before judging effect. Every trial reporting memory gains dosed for at least six weeks, with maximal effects at 12.” with “Most self-trials stop at two to four weeks; shorter self-experiments cannot answer the question.”, removing the restatement of its own value cell and the overlap with time_1_sub.
2. 2.8 — Off-topic acute-dosing sentence: Dropped “Acute single doses move mood measures, not memory.” from time_3_sub, which described acute rather than the 12-week time-to-effect the cell labels.
3. 4.5 — Protocol and time sub-cells condensed: Shortened action_1_sub, action_3_sub and time_1_sub from three-line to two-line cells, e.g. “Leaf extract standardised to roughly 50–55% bacosides. 600 mg daily ranked first for working memory.” became “Leaf extract standardised to 50–55% bacosides; 600 mg ranked first for working memory.”
4. 4.5 — Key Interactions gate trimmed: Cut the four-drug example lists to two representative drugs each and dropped redundant “Over-the-counter” and “additive” wording, e.g. “Supplements with additive cholinergic effect (huperzine A, citicoline, choline bitartrate)” became “Cholinergic supplements (huperzine A, citicoline)”. All ten items and at least one example drug per item are retained.
5. 4.5 — Contraindications gate trimmed: Reduced four items to single-line width without dropping any qualifier, e.g. “resting heart rate under 50 beats per minute” became “resting heart rate under 50 bpm” and “People on a muscarinic agonist” became “Muscarinic agonist use”.
6. 4.5 — Monitoring table condensed: Shortened eight target and why cells across markers 2-7 so most rows occupy one line, e.g. “Tracks the inflammatory axis the mechanism claims to touch” became “Tracks the inflammatory axis”. All seven markers and their ranges are unchanged.
7. 4.5 — Monitoring cadence condensed: Trimmed monitoring_cadence from three lines to two by removing “while use continues” and “thereafter” and using the table-defined abbreviation INR; every checkpoint in the ER schedule is preserved.