Audit: QRS - Ferrous Bisglycinate for Health & Longevity

Audit conducted on 23/08/2026 10:52 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 span traces to ER text: at-a-glance to Conclusion; protocol cells to Therapeutic Protocol; time cells to Practical Considerations and Risk Mitigation Strategies; benefit/risk lines to the ER H4 headings; 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 cautious/empty-state phrasing in the ER was altered; tier assignments carry the ER’s own 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”).	🟢	Absolute contraindications stay absolute (iron chelators, therapeutic phlebotomy); ER “caution”/”monitor” interactions stay 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 content from Benefit-Modifying Factors or Risk-Modifying Factors appears in the gates or the Risks card; each QRS section draws only from its designated ER section.
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, author names, NCT identifiers, or brand names (Ferrochel/TRAACS are not carried over).
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind appear in the QRS.

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.	🟢	Restrained, evidence-first register matching the ER, including the ER’s “repletion not maximisation” framing.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Numeric targets, thresholds, and timelines are given without alarm or exhortation.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Content is stated as findings and ranges, not orders.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	No imperative instruction to the reader in any populated span.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No occurrence of “should”, “must”, “recommend”, or “advise” in the populated content.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the document body.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms retained are the biomarker and condition names required for the decision gates; no avoidable jargon added.
2.8	Information is presented in a concise and very compact manner	🟢	Gate and tier items are noun phrases; sub-lines are single sentences.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no “you”/”your” in the populated spans.
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.	🟢	HFE genotyping, functional ranges tighter than conventional, and alternate-day dosing are all optimiser-level content.
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.	🟢	Nine-marker panel, staged retesting, and dose separation from interacting drugs are retained without simplification.
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 general-population framing; the sheet assumes testing before treating.
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 the longevity-relevant caution that higher lifelong iron tracks with shorter life expectancy, which is the optimiser-specific signal.
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.	🟢	Formal register throughout (“adverse-event burden”, “transferrin saturation”, “gastrointestinal”); “iron tablets” in the at-a-glance is the ER’s own wording and a standard dosage-form term.

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 strings match the template byte-for-byte, including “Risk & Side Effects” (singular) and “Time to effect” (lower-case “e”).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	All 34 template variable names are present; the only additions are the legitimate row expansions marker_1–9 and qualitative_item_1–8.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	A structural diff against the template shows changes only inside variable spans and the metadata block; CSS, footer disclaimer, and the website="…" 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 mapped by this 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 repletion dose”, “Alternate-day scheduling”, and “Best time of day” are the ER Therapeutic Protocol bold labels verbatim.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Time-to-effect labels (“Hemoglobin”, “Ferritin and symptom relief”, “Full store repletion”) are lifted from the ER’s Practical Considerations time-to-effect bullet; marker names match the ER biomarker table verbatim.
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” suffixes on two benefit headings 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 to the minimum permitted by the completeness requirements (8.2, 9.2, 14.2, 15.2): gate items are bare noun phrases with mechanism and rationale stripped, benefit/risk tiers are one line each, and marker “Why” cells are single clauses.

---

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 <!doctype html> on line 1 and before the template comment on line 16.
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 --- on line 3, closing --- on line 13; the preceding caption 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 metadata value is echoed 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: "00:02" 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: ferrous_bisglycinate_2026-0823-0812_Opus_ER.md (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: 26.7.02 (line 5), 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: 2026-0823-1028 (line 6).
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 (line 7).
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” — 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 (line 8).
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: ferrous_bisglycinate_2026-0823-0812_Opus_QRS.html (line 9), 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 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 &)	🟢	“Ferrous Bisglycinate 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 &)	🟢	“Ferrous Bisglycinate for Health & Longevity” (line 417).
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	2026-0823-1028 renders as “08/23/2026” (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 block matches the template exactly apart from the three variable substitutions.

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢	All four sentences map to the ER Conclusion paragraphs, ending on the executable pattern (confirm depletion, dose minimally, stop at target).
7.2	[at_a_glance] is no longer than 60 words	🟢	Exactly 60 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Chelate structure, equivalence at half the dose, fewer digestive complaints, depletion-confined benefit, lifespan signal, and clean-trial pattern each map to a separate Conclusion clause.
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	Plain-language throughout — “amino acid molecules”, “older iron tablets”, “stored iron”, “digestive complaints”; no acronyms.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	“The cleanest trials” is a generic characterisation with no name, year, or sample size.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No numeric effect estimates; “roughly half the iron dose” is a dose comparison, not a statistic.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All nine items trace to that ER section — seven from “Populations who should avoid” plus the two absolute contraindications embedded in the interaction bullets.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All seven ER avoid-populations are present, plus iron chelators and therapeutic phlebotomy for iron overload, both flagged absolute in the ER. Nothing is omitted.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Nine discrete <li> elements inside the stop_items span (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.	🟢	No dashes carry trailing clauses; the ER’s explanatory parentheticals for porphyria, sideroblastic anemia, and myelodysplastic syndrome were correctly 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).	🟢	HFE C282Y homozygote/compound heterozygote scope, the 45% saturation and 300/200 µg/L ferritin thresholds, “even with normal iron indices”, and the under-6 age cut-off 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 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 such populations and the section is correspondingly 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 nine items map one-to-one onto the ER’s interaction bullets.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	Iron chelators are excluded (contraindication), and the ER’s combined “Blood donation and therapeutic phlebotomy” bullet is correctly split, with only blood donation retained here.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Nine discrete <li> elements inside the caution_items span (lines 601–612).
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.	🟢	Mechanistic rationale and separation intervals from the ER bullets are stripped; only the drug/class name plus the ER’s additive flag 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 example drugs are preserved for every class: doxycycline/minocycline/ciprofloxacin/levofloxacin, alendronate/risedronate, omeprazole/famotidine, dolutegravir/raltegravir.
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 ten interaction bullets and the section is correspondingly 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, frequency, and timing — the three variables the ER treats as decisive, with alternate-day scheduling explicitly called “the single most actionable protocol variable” in the ER.
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 twelve protocol bullets, so 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 spans populated: labels verbatim from the ER, values (“25–30 mg elemental iron”, “Every second day”, “Morning, empty stomach”) and sub-lines condensed from the same bullets.

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	🟢	Hemoglobin recovery, ferritin/symptom relief, and full store repletion — the three milestones named in the ER’s time-to-effect bullet.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Ordered to mirror the ER’s High-tier benefit sequence: anemia correction, then store replenishment and fatigue relief, then complete repletion.
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 names four time-to-effect milestones, so 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; values “3–4 weeks”, “8–12 weeks”, “3–6 months” match the ER exactly.
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 explicit 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 ten benefit phrases are the ER’s H4 headings under Expected Benefits.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 542–566).
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.	🟢	Semicolon-separated headings only; no magnitude figures, confidence intervals, or study names carried across.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content appears in any benefit tier.
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 ER benefit tiers contain items, so no span needs hiding.

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢	All ten risk phrases are the ER’s H4 headings under Potential Risks & Side Effects.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 624–649).
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 hazard ratios, incidence figures, or study attributions from the ER magnitude lines are carried across.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parenthetical content appears in any risk tier.
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 ER risk tiers contain items, so no span needs hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Marker names, targets, and rationales are taken from the ER Monitoring Protocol & Defining Success biomarker table.
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER table rows are present in order: ferritin, transferrin saturation, hemoglobin, MCV/RDW, soluble transferrin receptor, hs-CRP, ALT, HbA1c, HFE genotype.
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, 8- and 12-week, 3–6-month, and 6–12-month maintenance intervals plus the one-time HFE test, all matching the ER narrative.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	Drawn from the ER’s “Qualitative markers worth tracking alongside the laboratory panel” list.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All eight ER qualitative markers are present in the same order, with only the ER’s explanatory tails trimmed.

Issues 23/08/2026 10:52

Pass rate 100.00%. No issues found.

Issues 23/08/2026 10:45

1. 4.5 — Content overflows one A4 page: The sheet renders to roughly two A4 pages: the Contraindications gate occupies ~19 wrapped lines in a ~329 px column (lines 577–601), and header, At-A-Glance, Protocol, Benefits and gates alone already exceed the printable height before Risks, the nine-row Monitoring table and the eight-item Qualitative card are laid out.

Fixes 23/08/2026 10:45

1. 4.5 — Contraindications gate condensed: Tightened all seven population entries (e.g. “Households with children under 6 years where child-resistant storage cannot be guaranteed” → “Children under 6 in the household without child-resistant storage”), cutting the gate from ~19 to ~13 wrapped lines while keeping every threshold and qualifier.
2. 4.5 — Key Interactions items tightened: Shortened two bullets to single-line width (“Bisphosphonates (alendronate, risedronate), levodopa, methyldopa” and “Lactoferrin, heme iron polypeptide, iron-containing multivitamins; additive”), with all example drug lists preserved.
3. 4.5 — Protocol and Time-to-Effect sub-lines trimmed: Removed restatement and mechanism padding from action_1_sub, action_2_sub, action_3_sub, and time_1_sub, saving roughly one wrapped line per cell across the protocol panel.
4. 4.5 — Monitoring cadence and two marker cells compressed: Merged “at 8 weeks, again at 12 weeks” into “at 8 and 12 weeks”, and shortened marker_8_why and marker_9_target to their operative wording.
5. 4.5 — Qualitative Assessment items shortened: Stripped trailing explanatory clauses from items 1, 7, and 8 (e.g. dropped “, a specific and often-missed sign of iron deficiency” from the pica entry), keeping all eight ER markers listed.

Issues 23/08/2026 10:36

1. 7.4 — Technical term in At-A-Glance: “older iron salts” (line 435) is a chemical classification rather than plain language; the ER’s own Motivation section supplies the lay equivalent “Older iron tablets”.

Fixes 23/08/2026 10:36

1. 7.4 — Technical term in At-A-Glance: Replaced “older iron salts” with “older iron tablets” in [at_a_glance], adopting the ER Motivation section’s plain-language wording; word count remains 60.

Issues 23/08/2026 10:32

1. 2.4 / 2.5 / 2.6 / 2.9 — At-a-glance uses direct imperatives: [at_a_glance] (lines 437-438) ends with “Confirm depletion first, use the smallest dose, stop once stores are filled.” — three imperative clinical instructions that address the reader directly and read as advice, whereas the ER states the same content descriptively (“The trials with the cleanest results are those that confirmed depletion first, used the smallest dose that worked, … and stopped once stores were comfortably filled”, ER line 507).

Fixes 23/08/2026 10:32

1. 2.4 / 2.5 / 2.6 / 2.9 — At-a-glance imperatives removed: Replaced the closing directive “Confirm depletion first, use the smallest dose, stop once stores are filled.” with the descriptive “The cleanest trials confirmed depletion first, dosed minimally, and stopped once stores filled.”, mirroring the ER’s own past-tense framing; the opening “It raises” was trimmed to “Raises” to keep [at_a_glance] at exactly 60 words.