Audit: QRS - Fecal Transplant for Health & Longevity

Audit conducted on 01/09/2026 09:44 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.	🟢	Spot-checked every populated span against the ER: at-a-glance vs ER Conclusion (472–476), protocol cells vs ER 347/357/361, time cells vs ER 401/154, benefits vs ER 146–212 headings, risks vs ER 238–282 headings, gates vs ER 300–325, markers vs ER table 431–441, cadence vs ER 429, qualitative vs ER 445–450.
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.	🟢	Cautious framings preserved, e.g. action_3_sub “no trial has compared timing directly” (ER 357) and marker_9_target “No target; change from own baseline” (ER 441).
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”).	🟢	Contraindications retain absolute framing (“Pregnancy and breastfeeding”); cautions retain “Caution” / “Caution to contraindication by degree of suppression”.
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.	🟢	All stop_items come from ER “Populations who should avoid Fecal Transplant” (318–325); all caution_items from the ER interaction bullets (300–316). No Benefit-/Risk-Modifying Factor content leaked into the gates.
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, NCT IDs, author names or trial names in the QRS. Drug names (vancomycin, prednisone, infliximab, tacrolimus, omeprazole, loperamide, pembrolizumab, nivolumab, etc.) all appear in the ER for the same facts.
1.6	The QRS does not introduce new attributions.	🟢	No attributions of any kind; the ER’s trial attribution in the qualitative bullet (“improved alongside cognition in the liver trials”, ER 447) was correctly dropped rather than replaced.

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.	🟢	Sober, evidence-weighted register matching the ER: strong for one indication, explicitly thin elsewhere.
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢	Expert and objective throughout; benefit tiers and monitoring targets give the reader actionable structure without exhortation.
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢	Impersonal, declarative statements; no imperatives directed at a patient.
2.4	The QRS avoids language that implies medical or clinical advice	🟢	Sections present ER-derived facts; the footer disclaimer is the template’s own.
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢	No “recommended”, “advised”, or “should” constructions in the document’s own voice.
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢	No second-person pronouns anywhere in the file.
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢	Technical terms are confined to where they are load-bearing (marker names, drug classes); at-a-glance is fully plain-language.
2.8	Information is presented in a concise and very compact manner	🟢	Gate and tier entries are stripped to key facts; no ER rationale clauses carried over.
2.9	It DOES NOT address the reader directly	🟢	Confirmed — no direct address.
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.	🟢	Optimal functional ranges rather than conventional lab cut-offs, engraftment tracking, and explicit longevity framing address this audience.
2.11	The target audience is willing to employ lifestyle and behavioral changes as well as follow protocols that may be inconvenient, costly, or require effort.	🟢	Protocol and monitoring content assumes willingness to undergo an invasive procedure and a multi-timepoint biomarker panel.
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.	🟢	Content depth (9-marker panel, 6–12 month follow-up cadence) is not general-population material.
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 states plainly that rejuvenation findings are animal-only and blood-sugar gains fade — the exact correction a longevity-motivated reader needs.
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 in the file; header 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 outside at-a-glance (“adverse events”, “mucosal inflammation”, “engraftment”); the plain-language at-a-glance wording is mandated by 7.4 and mirrors the ER Conclusion.

3. Template Integrity

#	Description	Result	Comments
3.1	The following labels and headings on the QRS are fixed and not modified: Card and section headings: “Protocol”, “Time to effect”, “Benefits”, “Risk & Side Effects”, “Monitoring”, “Qualitative Assessment”; Gate headings: “Contraindications”, “Key Interactions”; Tier labels: “High”, “Medium”, “Low”, “Speculative”; Table column headers in Monitoring: “Marker”, “Target”, “Why”	🟢	All fixed headings and tier labels byte-identical to [qrs_template] (lines 446, 490, 535, 569, 584, 627, 652, 656–658, 795).
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢	Diffed against the template: all 34 template variable names present; the only additions are the expected numbered expansions of the repeatable marker_#_* and qualitative_item_# spans.
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢	Full-file diff against [qrs_template] shows changes only inside spans governed by checklist items; the website="evidence_review", website="full_review" and website="audit" spans, the stylesheet link and the footer 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.	🟢	Protocol labels (“Standard protocol for recurrent infection”, “Single versus repeated dosing”, “Best time of day”) and all nine interaction labels reproduce the ER bold labels; only the parenthetical drug lists are shortened, as 9.5 permits.
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢	Benefit and risk entries reuse the ER H4 headings verbatim; marker names reuse the ER table’s biomarker names.
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 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 section governed by a conciseness rule (8.4, 9.4, 12.3, 13.3) is condensed to key-fact level with rationale clauses stripped; residual length is driven by the completeness requirements of 8.2, 9.2, 14.2 and 15.2.

---

5. Metadata

#	Description	Result	Comments
5.1	The metadata is placed inside a single HTML comment that is the first element after “<!doctype html>” and before any other comment, head, or body content.	🟢	Lines 2–14; the first element after <!doctype html> on line 1.
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 “QRS — Metadata” text precedes the opening delimiter.
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.	🟢	Wholly inside an HTML comment; no metadata value is echoed by any visible element other than the independently-required header date and model name.
5.4	All frontmatter values are trimmed: no leading or trailing whitespace, no surrounding quotes unless the value contains a colon, bracket, or leading special character that requires YAML quoting.	🟢	Only duration: "00:03" is quoted, correctly, because it contains a colon. All other values are bare and trimmed.
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢	Line 4: er_filename: fecal_transplant_2026-0901-0605_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]”	🟢	Line 5: qrs_prompt_version: 26.7.02, matching the QRS.md version badge.
5.7	Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430)	🟢	Line 6: qrs_creation_date: 2026-0901-0857, correct format.
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢	Line 7: qrs_creator_ai_nickname: Opus.
5.9	The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT)	🟢	“Opus” — 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]”	🟢	Line 8: qrs_creator_ai_fullname: Opus 5.
5.11	The full name of the AI consists of the [qrs_creator_ai_nickname] and the model version number and no additional qualifier (e.g., Opus 4.6, Sonnet 3.2, Grok 4.5, Gemini 3.1, ChatGPT 5.4)	🟢	“Opus 5” — nickname plus version number, no qualifier.
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢	Line 9: qrs_filename: fecal_transplant_2026-0901-0605_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 nine keys including the appended git_user and git_issue; all clean.

6. Page Title & Header

#	Description	Result	Comments
6.1	[page_title] is set to the [canonical_topic] of the ER frontmatter followed by “ - Quick Reference Sheet” (e.g., “Intervention - Quick Reference Sheet”). The [canonical_topic] is HTML-entity-encoded as needed (e.g., & for &)	🟢	Line 22: “Fecal Transplant for Health & Longevity - Quick Reference Sheet”, matching ER canonical_topic with the ampersand encoded.
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢	Line 417: “Fecal Transplant for Health & Longevity”.
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢	Line 421: “09/01/2026”, correctly derived from qrs_creation_date: 2026-0901-0857.
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢	Line 425: “Opus 5”.
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢	Header holds only the title and 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	🟢	Tracks the ER Conclusion (472–476) in order: what it is, the one strong indication, the two small-trial indications, the fading metabolic signal, the animal-only rejuvenation data, then harms.
7.2	[at_a_glance] is no longer than 60 words	🟢	55 words.
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢	Each of the six clauses maps to a distinct ER Conclusion sentence (472, 472, 472, 474, 474, 476).
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢	No acronyms; specialist terms deliberately replaced — “Clostridioides difficile” → “a bowel infection that keeps returning after antibiotics”, “ulcerative colitis” → “inflamed bowel”, “hepatic encephalopathy” → “repeat liver-related confusion”, “insulin sensitivity” → “blood-sugar gains”.
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢	No trial names, years, cohort sizes or p-values.
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢	No risk ratios, odds ratios, confidence intervals or percentages.

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢	All eight entries trace to the “Populations who should avoid Fecal Transplant” list at ER 318–325.
8.2	[stop_items] represent the Contraindications from the ER	🟢	All six ER bullets represented; the two compound bullets (ER 320, 321) are correctly split into four separate items.
8.3	Individual [stop_items] are formatted as <li></li>	🟢	Eight <li> elements inside the stop_items span (lines 571–580).
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.	🟢	ER glosses stripped throughout: “in which donor immune cells attack the recipient’s tissues”, “(human immunodeficiency virus)”, “(a measure of immune-cell numbers)”, “(dangerous ballooning of the colon)”, “(rapidly worsening, severe colon inflammation)”, “where no safety data exist”. No dash-trailing 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).	🟢	All decision-relevant qualifiers retained: “below 500 cells/µL”, “Within 90 days”, “CD4 below 200 cells/µL”, “High-dose”, “Severe”, “Uncontrolled”, “(capsule, nasoenteric)”.
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; thresholds are written out as “below”.
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 does identify 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 entries trace to the interaction bullets at ER 300–316.
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢	All nine ER interaction bullets present, none duplicated in the Contraindications gate.
9.3	Individual [caution_items] are formatted as <li></li>	🟢	Nine <li> elements inside the caution_items span (lines 586–618).
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 ER em-dash rationale clause stripped (e.g. ER 300 “— concurrent antibiotics destroy the transplanted community…”), and the ER’s Canadian-trial citation in the fiber bullet (ER 312) removed.
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 parenthetical drug list is retained in shortened form; none 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 parentheticals in this section are plain comma-separated drug lists with no ranking notation.
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 nine such interactions 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 action sets derive from the ER Therapeutic Protocol section (347, 357, 361).
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢	Covers the regimen itself, dose frequency, and administration timing — the three directly executable bullets; the remaining ER bullets are comparative approaches or response modifiers.
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 well more than three actionable aspects; all three sets are used.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢	All nine spans populated with 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	🟢	Exactly the three the ER names at line 401: recurrent infection, colitis remission, insulin sensitivity.
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢	Order matches the ER benefit tiering: recurrent infection (High, first), colitis remission (High, second), insulin sensitivity (Medium).
11.3	If less that three distinct time-to-effect aspects are mentioned in the ER the unused sets are left empty and made invisible, not filled with placeholder text or empty-state phrasing.	N/A	The ER provides 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; sub-cells add the ER’s own qualifiers (“cure assessed at 8 weeks”, “faded by 18”).
11.5	If the ER does not provide any information on time to effect, the section is removed completely from the Protocol Panel	N/A	The ER provides time-to-effect information (line 401), so the section is correctly retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢	All eleven entries are the ER Expected Benefits H4 headings (146–212), tier for tier.
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢	All four spans present and populated (lines 537, 544, 550, 557).
12.3	Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details. Just the key fact.	🟢	No Magnitude figures (RR 1.92, OR 3.63, NNT 3, waist −10.0 cm, etc.), no mechanisms and no trial references carried over.
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses anywhere in the four benefit spans.
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	The ER populates all four tiers, 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 seven entries are the ER Potential Risks & Side Effects H4 headings (238–282), tier for tier.
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢	All four spans present and populated (lines 629, 632, 638, 644).
13.3	Items are as concise as possible. No explanations, no elaborations, no effect sizes, no qualifiers, no attributions, no citations, no study details. Just the key fact.	🟢	No Magnitude figures (RR 3.12, “under 1%”, “14.9%”, “3 of 22”), no case details and no trial references carried over.
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢	No parentheses anywhere in the four risk spans.
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	The ER populates all four tiers, so no span needed hiding.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢	Table and cadence derive from the ER Monitoring Protocol & Defining Success section (427–441).
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢	All nine ER biomarker table rows present with matching targets; the prose baseline panel at ER 427 introduces no additional measurable marker beyond these nine.
14.3	[monitoring_cadence] is populated with the monitoring cadence/frequency derived from the ER Monitoring section. It is not left with placeholder text or empty.	🟢	Lines 785–789 reproduce the ER cadence at 429: baseline, 1 week, 8-week stool retest, markers at 8 weeks and 6 months, then every 6–12 months for a chronic indication.

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢	All six entries derive from the ER qualitative marker list at 445–450.
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢	All six ER qualitative markers present, in ER order; the trial attribution attached to the energy bullet (ER 447) was correctly dropped.

Issues 01/09/2026 09:44

Pass rate 100.00%. No issues found.

Issues 01/09/2026 09:37

1. 11.4 — Time-to-effect sub restates value: [time_2_sub] at line 513 reads “Remission measured at 8 weeks”, which only repeats [time_2_value] “8 weeks” at line 510 and carries no additional ER-derived information.

Fixes 01/09/2026 09:37

1. 11.4 — Time-to-effect sub restates value: Replaced [time_2_sub] “Remission measured at 8 weeks” with “Assessed at the end of an eight-week course; rarely durable beyond a year without repeat dosing”, drawn from ER lines 154 and 401, so the cell now adds information beyond [time_2_value].

Issues 01/09/2026 09:29

1. 1.2 / 1.3 — Best-time-of-day caution dropped: Protocol cell 3 (QRS lines 477–486) presents “Morning delivery” with the supporting sub “Follows overnight fasting for colonoscopy or empty-stomach capsule dosing”, omitting the ER’s explicit caveat that “No trial has compared timing directly, so this reflects procedural convenience rather than demonstrated chronobiology” (ER line 357), which turns an untested convention into an established best time.

Fixes 01/09/2026 09:29

1. 1.2 / 1.3 — Best-time-of-day caution restored: Replaced [action_3_sub] “Follows overnight fasting for colonoscopy or empty-stomach capsule dosing” with “Near-universal convention; no trial has compared timing directly”, carrying the ER’s caveat (ER line 357) instead of a supporting rationale.

Issues 01/09/2026 09:22

1. 7.4 — Clinical-register “flares” in At-A-Glance: The harms clause at line 437 reads “bowel upset, flares, rare deadly infection transmission”; bare “flares” is clinical shorthand a non-specialist would not use unprompted, and it drops the ER’s scoping of flares to inflammatory bowel disease (ER line 476).

Fixes 01/09/2026 09:22

1. 7.4 — Plain-language wording for flares: Replaced the bare clinical noun “flares” in [at_a_glance] with “bowel-disease flare-ups”, restoring the ER’s scoping to inflammatory bowel disease; the summary remains within the 60-word limit at 55 words.

Issues 01/09/2026 09:14

1. 1.3 — Swallowing-disorder severity dropped: QRS line 576 renders ER line 325 “Uncontrolled swallowing disorder or high aspiration risk” as “Swallowing disorder, aspiration risk (capsule, nasoenteric)”, dropping the severity qualifiers and broadening the contraindication beyond what the ER states.
2. 4.2 / 4.3 — Interaction labels not verbatim: Two Key Interactions bold labels are abbreviated relative to the ER — QRS line 594 “Antimotility and adsorbent agents” for ER “Antimotility and adsorbent over-the-counter agents”, and QRS line 602 “Fermentable fiber and prebiotics” for ER “Fermentable fiber and prebiotic supplements”.

Fixes 01/09/2026 09:14

1. 1.3 — Swallowing-disorder severity restored: Contraindication item changed from “Swallowing disorder, aspiration risk (capsule, nasoenteric)” to “Uncontrolled swallowing disorder, high aspiration risk (capsule, nasoenteric)”, restoring the ER’s severity qualifiers.
2. 4.2 / 4.3 — Interaction labels made verbatim: Restored the ER’s bold labels — “Antimotility and adsorbent agents” to “Antimotility and adsorbent over-the-counter agents”, and “Fermentable fiber and prebiotics” to “Fermentable fiber and prebiotic supplements”.

Issues 01/09/2026 09:07

1. 4.5 — Sheet overflows one A4 page: The visible body text runs to 5,383 characters / 713 words (lines 431-842); at the template’s 9.5pt card typography the Key Interactions gate alone consumes ~19 wrapped lines and the Monitoring table ~19, so the sheet renders to roughly two A4 pages instead of one.

Fixes 01/09/2026 09:07

1. 4.5 — Condensed sheet toward one page: Trimmed visible body text from 5,383 to 4,866 characters, targeting the two blocks that wrapped worst — the Key Interactions gate (parenthetical drug lists shortened, e.g. “berberine, oregano oil, garlic extract, grapefruit-seed extract” to “berberine, oregano oil, garlic”; “Additive in intent but potentially competitive in effect” to “Additive but potentially competitive”) and the Monitoring table (e.g. “Confirms whether short-term insulin changes translate into lasting blood-sugar change” to “Whether insulin changes become lasting blood-sugar change”; ALT target to “Below 20 U/L men, 17 U/L women”). Also tightened the Contraindications items, the At-A-Glance line, the protocol and time-to-effect subs, and the monitoring cadence. Every biomarker, contraindication, interaction and qualitative item is retained, and all parenthetical qualifiers are shortened rather than dropped.