Audit: QRS - Follistatin for Muscle Growth

Audit conducted on 12/09/2026 20:48 using AI4L / Opus 5

Iterations

Summary

Items	Count
Total	93
Passed	85
Failed	0
N/A	8
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.	🟢
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.	🟢
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”).	🟢
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.	🟢
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.	🟢
1.6	The QRS does not introduce new attributions.	🟢

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.	🟢
2.2	The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging	🟢
2.3	The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor	🟢
2.4	The QRS avoids language that implies medical or clinical advice	🟢
2.5	The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising”	🟢
2.6	The QRS never addresses “the reader” directly — it presents evidence, not guidance	🟢
2.7	The QRS is written in plain language, avoiding unnecessary medical jargon	🟢
2.8	Information is presented in a concise and very compact manner	🟢
2.9	It DOES NOT address the reader directly	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢
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.	🟢

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”	🟢
3.2	All “…” from the [qrs_template] are present in the the QRS.	🟢
3.3	Spans that are not addressed in a checklist item are left unchanged	🟢

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 ER section is empty; the Benefits Medium tier carries explanatory prose, and tier emptiness is governed by 12.5.
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.	🟢
4.3	Labels are not paraphrased, abbreviated, or invented.	🟢
4.4	The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels.	🟢
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 against the ER: magnitudes, citations, mechanisms and trailing clauses are all stripped and no section is carried over verbatim. Content sits at the upper end of the one-page budget, the item counts being fixed by 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.	🟢
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.	🟢
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.	🟢
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.	🟢
5.5	The filename of the source ER is stated as “er_filename: [er_filename]”	🟢
5.6	Version of the QRS.md file used to create the document is stated as “qrs_prompt_version: [Version of QRS.md]”	🟢
5.7	Creation date and time of the document is stated as “qrs_creation_date: [YYYY-MMDD-HHMM]” (e.g., 2026-0501-1430)	🟢
5.8	The nickname of the AI used to create the document is stated as “qrs_creator_ai_nickname: [qrs_creator_ai_nickname]”	🟢
5.9	The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT)	🟢
5.10	The full name of the AI used to create the document is stated as “qrs_creator_ai_fullname: [qrs_creator_ai_fullname]”	🟢
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)	🟢
5.12	The filename of the document is stated as “qrs_filename: [filename of this document]”	🟢
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.	🟢

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 &)	🟢
6.2	[header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &)	🟢
6.3	[header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY]	🟢
6.4	[header_subline_model] is set to [qrs_creator_ai_fullname]	🟢
6.5	No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker.	🟢

7. At-A-Glance Section

#	Description	Result	Comments
7.1	[at_a_glance] is dense, execution-oriented summary of the ER Conclusion section	🟢
7.2	[at_a_glance] is no longer than 60 words	🟢
7.3	Every fact in [at_a_glance] is supported by a distinct passage in the ER.	🟢
7.4	It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead	🟢
7.5	It DOES NOT cite specific trials (names, years, sample sizes, p-values)	🟢
7.6	It DOES NOT cite effect sizes, relative risks, or statistical results	🟢

8. Contraindications

#	Description	Result	Comments
8.1	The section is derived from the ER Key Interactions & Contraindications section	🟢
8.2	[stop_items] represent the Contraindications from the ER	🟢
8.3	Individual [stop_items] are formatted as <li></li>	🟢
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.	🟢
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).	🟢
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’s Key Interactions & Contraindications section uses no ranking notation inside parentheses.
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.	🟢
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 [stop_items] span is not empty (11 items), so no empty-state HTML comment is required.

9. Key Interactions

#	Description	Result	Comments
9.1	The section is derived from the ER Key Interactions & Contraindications section	🟢
9.2	[caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications	🟢
9.3	Individual [caution_items] are formatted as <li></li>	🟢
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.	🟢
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).	🟢
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’s Key Interactions & Contraindications section uses no ranking notation inside parentheses.
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.	🟢
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 [caution_items] span is not empty (10 items), so no empty-state HTML comment is required.

10. Protocol

#	Description	Result	Comments
10.1	The section is derived from the ER Protocol section	🟢
10.2	The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section	🟢
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 Therapeutic Protocol section names more than three actionable aspects, so no [action] set is unused.
10.4	All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section.	🟢

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	🟢
11.2	The sets are picked and ordered by the magnitude of the related benefit	🟢
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.	🟢
11.4	All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER.	🟢
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 (Practical Considerations, ER line 416), so the section is retained.

12. Benefits

#	Description	Result	Comments
12.1	The section is derived from the ER Expected Benefits section	🟢
12.2	Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative]	🟢
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.	🟢
12.4	Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢
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.	🟢

13. Risks

#	Description	Result	Comments
13.1	The section is derived from the ER Potential Risks & Side Effects section	🟢
13.2	Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative]	🟢
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.	🟢
13.4	Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved.	🟢
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 carry items in the ER, so no [risks] span needs display:none.

14. Monitoring

#	Description	Result	Comments
14.1	The section is derived from the ER Monitoring section	🟢
14.2	All measurable/quantifiable biomarkers from the Monitoring section are listed	🟢
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.	🟢

15. Qualitative Assessment

#	Description	Result	Comments
15.1	The section is derived from the ER Monitoring section	🟢
15.2	All subjective/qualitative biomarkers from the Monitoring section are listed	🟢

Issues 12/09/2026 20:48

Pass rate 100.00%. No issues found.

Issues 12/09/2026 20:36

1. 4.5 — Content exceeds one A4 page: The sheet’s estimated rendered height is roughly 2.2 A4 pages; the Monitoring card (13 rows plus a four-line cadence paragraph, lines 640–802, ~456pt) and the Decision Gates (11 multi-line contraindications and 10 interactions, lines 569–605, ~320pt) alone consume the entire ~774pt one-page budget, before the lede, protocol panel, benefits, risks and qualitative cards.

Fixes 12/09/2026 20:36

1. 4.5 — Gate items shortened to fit: Contraindications were tightened (“Cancer history, or hereditary cancer syndrome (…), without counselling clearance” → “Any cancer history or hereditary cancer syndrome (…) without clearance”; “ejection fraction below 50%” → “<50%”; “titre above 1:100” → “>1:100”; dropped trailing “afterwards”), and each Key Interactions drug list was trimmed from three examples to two (e.g. “(warfarin, apixaban, clopidogrel)” → “(warfarin, clopidogrel)”), with every parenthetical qualifier retained.
2. 4.5 — Monitoring rows and cadence condensed: Row targets and rationales were cut to single lines (“Fold-change from own baseline; no set target (adults roughly 1–10 ng/mL)” → “Fold-change from baseline; no set target (roughly 1–10 ng/mL)”; “Earliest sign of follistatin-linked insulin resistance” → “Earliest sign of insulin resistance”; five further “Why” cells shortened), and the cadence lost its trailing rationale clause “as gene transfer is not reversible”.
3. 4.5 — Protocol and time-to-effect subs condensed: Removed non-load-bearing detail from the three action subs (“under image guidance”; the four named injection muscles replaced by “four muscle groups”; “measured against a three-month serum follistatin change”) and shortened the muscle-volume time sub.
4. 4.5 — Tiered lists compressed: Benefits now read “reduced intramuscular fat — conflicted” and merge the two “not central to muscle growth” speculative items into one clause, keeping all ER items and their flags while saving two rendered lines.
5. 4.5 — Lede and qualitative items tightened: The At-a-Glance lede went from 56 to 51 words (“yet bigger muscle has not reliably become stronger muscle” → “yet not reliably stronger”), and three qualitative items lost their trailing explanatory clauses.

Issues 12/09/2026 20:33

1. 2.15 — Consumer-grade term for manufacturer: The At-A-Glance lede (QRS line 436) says “the maker stopped its programme”; “maker” is consumer-grade where the ER’s own voice uses “the manufacturer, Acceleron Pharma” and “the company”.

Fixes 12/09/2026 20:33

1. 2.15 — Consumer-grade term for manufacturer: Replaced “the maker” with “the manufacturer” in the At-A-Glance lede, matching the ER’s own voice. Word count unchanged at 56.

Issues 12/09/2026 20:22

1. 4.5 — Sheet overruns one A4 page: The Contraindications gate (11 items, several 120–146 characters, lines 577–587) and the Monitoring table (13 rows carrying full ER sentences in the target and why cells, lines 653–794) together already exceed the 273 mm print height before the header, at-a-glance, protocol, benefits, risks and qualitative blocks are counted.
2. 11.3 — Third time-to-effect set filled with empty-state text: The ER’s “Time to effect” bullet (ER line 416) names only two aspects, yet the third set is populated with time_3_value = “Not established” (line 534) rather than being left empty and made invisible.

Fixes 12/09/2026 20:22

1. 11.3 — Unused time-to-effect set hidden: The third time-to-effect cell, which carried the empty-state value “Not established”, was emptied and its .pcell set to display: none, leaving only the two aspects the ER actually states.
2. 4.5 — Monitoring cells condensed: Ten target and why cells were shortened to cut wrapped lines from the 13-row table (e.g. marker_7_why from “Detects suppression of the activin axis follistatin acts on” to “Detects activin-axis suppression”; marker_5_target from “Below 20 U/L (men), below 17 U/L (women)” to “Below 20 U/L men; below 17 U/L women”).
3. 4.5 — Contraindication items condensed: Seven of the eleven gate items were tightened while keeping every threshold, stage and time window (e.g. “Prior exposure to any adeno-associated virus gene therapy, or an antibody titre above 1:100” → “Prior adeno-associated virus gene therapy, or antibody titre above 1:100”).
4. 4.5 — Cadence and qualitative items condensed: The cadence sentence and three qualitative items were shortened without dropping content (e.g. “Visible limb girth asymmetry, which after single-muscle injection is expected rather than alarming” → “Visible limb girth asymmetry, expected after single-muscle injection”).