Audit: QRS - Butea monosperma for Health & Longevity
Audit conducted on 14/10/2026 19:45 using AI4L + evidence-mcp / Gemini 3.1
Summary
| Items | Count |
|---|---|
| Total | 94 |
| Passed | 89 |
| Failed | 0 |
| N/A | 5 |
| 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. | 🟢 | All claims, magnitudes, labels, and statements trace directly to 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. | 🟢 | Cautious phrasings (e.g., “(theoretical)”, “No established target”, “Speculative”, “early laboratory candidates”) are preserved. |
| 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”). | 🟢 | No ER claims are strengthened or softened. |
| 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 ER facts retain their original decision categories. |
| 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 unsupported PMIDs, citations, expert names, NCTs, or brand names appear. |
| 1.6 | The QRS does not introduce new attributions. | 🟢 | No new attributions are introduced. |
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. | 🟢 | Tone matches the source ER. |
| 2.2 | The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging | 🟢 | Tone is expert, accessible, objective, and data-driven. |
| 2.3 | The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor | 🟢 | Reads as an objective reference rather than prescriptive clinical advice. |
| 2.4 | The QRS avoids language that implies medical or clinical advice | 🟢 | No language implies medical or clinical advice. |
| 2.5 | The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” | 🟢 | Presents evidence rather than recommending or advising. |
| 2.6 | The QRS never addresses “the reader” directly — it presents evidence, not guidance | 🟢 | Never addresses the reader directly. |
| 2.7 | The QRS is written in plain language, avoiding unnecessary medical jargon | 🟢 | Written in clear, accessible language. |
| 2.8 | Information is presented in a concise and very compact manner | 🟢 | Information is concise and compact. |
| 2.9 | It DOES NOT address the reader directly | 🟢 | No direct second-person 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. | 🟢 | Framed for proactive, risk-aware longevity-oriented adults. |
| 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 details reflect a high-agency target audience. |
| 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. | 🟢 | Not diluted for a general passive audience. |
| 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. | 🟢 | Weighting of preclinical vs. human combination evidence reflects the longevity 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. | 🟢 | Uses “longevity” framing throughout; “anti-aging” does not appear. |
| 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. | 🟢 | Formal clinical and scientific terminology (e.g., “oral absorption”) is used throughout. |
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 table column headers are unmodified. |
| 3.2 | All “…” from the [qrs_template] are present in the the QRS. | 🟢 | All template data-qrs-var spans are present. |
| 3.3 | Spans that are not addressed in a checklist item are left unchanged | 🟢 | Website spans (evidence_review, audit, full_review) are 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” | 🟢 | Empty-state phrasing (“No established target”) is preserved where applicable. |
| 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. | 🟢 | Bold labels from the ER are used verbatim in Protocol, Contraindications, Key Interactions, and Qualitative Assessment. |
| 4.3 | Labels are not paraphrased, abbreviated, or invented. | 🟢 | No labels are 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. | 🟢 | No emoji indicators appear in the QRS. |
| 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. | 🟢 | Content is condensed to fit a single A4 page. |
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. | 🟢 | Metadata HTML comment is the first element after <!doctype html>. |
| 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. | 🟢 | YAML block is delimited by — lines. |
| 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. | 🟢 | Metadata is inside an HTML comment and not rendered. |
| 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. | 🟢 | All frontmatter values are properly trimmed and only duration is quoted due to its colon. |
| 5.5 | The filename of the source ER is stated as “er_filename: [er_filename]” | 🟢 | er_filename is set to butea_monosperma_2026-1014-1815_Gemini_ER.md. |
| 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 is set to 26.10.14. |
| 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 is set to 2026-1014-1934. |
| 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 is set to Gemini. |
| 5.9 | The nickname of the AI is just a single word model name without version, etc. (e.g., Opus, Sonnet, Grok, Gemini, ChatGPT) | 🟢 | Nickname is a single word without 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 is set to Gemini 3.1. |
| 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) | 🟢 | Full name consists of nickname and version number only. |
| 5.12 | The filename of the document is stated as “qrs_filename: [filename of this document]” | 🟢 | qrs_filename is set to butea_monosperma_2026-1014-1815_Gemini_QRS.html. |
| 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. | 🟢 | All frontmatter values are clean and trimmed. |
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 &) |
🟢 | page_title matches canonical_topic + “ - Quick Reference Sheet” with & encoding. |
| 6.2 | [header_topic] is set to the [canonical_topic] of the ER frontmatter, with HTML entities encoded as needed (e.g., & for &) |
🟢 | header_topic matches canonical_topic with & encoding. |
| 6.3 | [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] | 🟢 | header_subline_date is 10/14/2026. |
| 6.4 | [header_subline_model] is set to [qrs_creator_ai_fullname] | 🟢 | header_subline_model is Gemini 3.1. |
| 6.5 | No additional header content appears: no badge, version stamp, AKA / alternate names line, source-AI attribution, audit date, or QRS variant marker. | 🟢 | No extra header elements appear. |
7. At-A-Glance Section
| # | Description | Result | Comments |
|---|---|---|---|
| 7.1 | [at_a_glance] opens by saying what the intervention is — its kind (e.g., dietary supplement, prescription medication, peptide, plant, procedure, practice) — and what it is used for, in plain language, before any verdict on the evidence | 🟢 | Opens by defining Butea monosperma as a South Asian medicinal tree and stating its studied uses in plain language before the evidence verdict. |
| 7.2 | [at_a_glance] is dense, execution-oriented summary of the ER Conclusion section |
🟢 | Dense summary of the ER Conclusion section. |
| 7.3 | [at_a_glance] is no longer than 70 words | 🟢 | 66 words (within the 70-word limit). |
| 7.4 | Every fact in [at_a_glance] is supported by a distinct passage in the ER. | 🟢 | Every statement maps to a distinct passage in the ER. |
| 7.5 | It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead | 🟢 | Uses plain-language terms without acronyms or specialist jargon. |
| 7.6 | It DOES NOT cite specific trials (names, years, sample sizes, p-values) | 🟢 | No specific trial citations, years, sample sizes, or p-values. |
| 7.7 | It DOES NOT cite effect sizes, relative risks, or statistical results | 🟢 | No 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 |
🟢 | Derived from ER Key Interactions & Contraindications. |
| 8.2 | [stop_items] represent the Contraindications from the ER | 🟢 | All 4 contraindicated populations from the ER are listed. |
| 8.3 | Individual [stop_items] are formatted as <li></li> | 🟢 | Formatted as <li> elements. |
| 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. | 🟢 | Concise population labels only, with trailing explanations and citations 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). | 🟢 | No clinical threshold/staging parenthetical qualifiers exist on the ER contraindication labels. |
| 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. | 🟢 | No bare ranking symbols appear. |
| 8.7 | The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision. |
🟢 | Section is populated with the 4 contraindications from the ER. |
| 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 | Section is not empty. |
9. Key Interactions
| # | Description | Result | Comments |
|---|---|---|---|
| 9.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | Derived from ER Key Interactions & Contraindications. |
| 9.2 | [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications | 🟢 | All 7 interactions from the ER are listed, excluding contraindications. |
| 9.3 | Individual [caution_items] are formatted as <li></li> | 🟢 | Formatted as <li> elements. |
| 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. | 🟢 | Concise items with trailing explanations and citations 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). | 🟢 | Example drug/supplement lists, severity classes, and the 3–4 h stagger window are preserved in parentheses. |
| 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. | 🟢 | No bare ranking symbols appear. |
| 9.7 | The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no interaction, additive effect, or exposure that changes how the intervention is used. |
🟢 | Section is populated with the 7 interactions from the ER. |
| 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 | Section is not empty. |
10. Protocol
| # | Description | Result | Comments |
|---|---|---|---|
| 10.1 | The section is derived from the ER Protocol section |
🟢 | Derived from ER Therapeutic Protocol section. |
| 10.2 | The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section |
🟢 | Covers the three primary actionable protocol aspects: dosing, meal/time-of-day timing, and split dosing. |
| 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 | Three distinct actionable implementation aspects are present in the ER. |
| 10.4 | All used [action_#label], [action#value], [action#_sub] items are filled with meaningful content derived from the ER Protocol section. |
🟢 | All three action cells have meaningful label, value, and sub content from the ER. |
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 | 🟢 | Covers all three time-to-effect aspects from the ER. |
| 11.2 | The sets are picked and ordered by the magnitude of the related benefit | 🟢 | Ordered by benefit tier and magnitude: giardiasis clearance (Low, 72 pp) -> urinary stone relief (Low, 14.21 pp) -> bone density (Speculative, rodent-only). |
| 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 present in the ER. |
| 11.4 | All used [time_#label], [time#value], [time#_sub] items are filled with meaningful content derived from the ER. | 🟢 | All three time cells have meaningful label, value, and sub content 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 | ER provides time-to-effect information. |
12. Benefits
| # | Description | Result | Comments |
|---|---|---|---|
| 12.1 | The section is derived from the ER Expected Benefits section |
🟢 | Derived from ER Expected Benefits section. |
| 12.2 | Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] | 🟢 | Uses benefits_high, benefits_medium, benefits_low, and 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. | 🟢 | Concise benefit names separated by semicolons without elaborations or citations. |
| 12.4 | Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parenthetical content is included. |
| 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. | 🟢 | benefits_high and benefits_medium have style=”display: none”. |
13. Risks
| # | Description | Result | Comments |
|---|---|---|---|
| 13.1 | The section is derived from the ER Potential Risks & Side Effects section |
🟢 | Derived from ER Potential Risks & Side Effects section. |
| 13.2 | Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] | 🟢 | Uses risks_high, risks_medium, risks_low, and 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. | 🟢 | Concise risk names separated by semicolons without elaborations or citations. |
| 13.4 | Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parenthetical content is included. |
| 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. | 🟢 | risks_high, risks_medium, and risks_low have style=”display: none”. |
14. Monitoring
| # | Description | Result | Comments |
|---|---|---|---|
| 14.1 | The section is derived from the ER Monitoring section |
🟢 | Derived from ER Monitoring Protocol & Defining Success section. |
| 14.2 | All measurable/quantifiable biomarkers from the Monitoring section are listed |
🟢 | All 5 biomarker rows from the ER table are included. |
| 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. |
🟢 | monitoring_cadence is populated with the baseline, 4-week, 12-week, and 6–12 month schedule (and 12–24 month DXA and stopping rules) from the ER. |
15. Qualitative Assessment
| # | Description | Result | Comments |
|---|---|---|---|
| 15.1 | The section is derived from the ER Monitoring section |
🟢 | Derived from ER Monitoring Protocol & Defining Success section. |
| 15.2 | All subjective/qualitative biomarkers from the Monitoring section are listed |
🟢 | All 3 qualitative assessment bullets from the ER are listed. |
Issues 14/10/2026 19:45
Pass rate 100.00%. No issues found.
Issues 14/10/2026 19:37
- 1.3 / 8.4 — Contraindications trailing study details: In
Contraindications(stop_items, lines 542–545), parenthetical preclinical study details and plant-part elaborations (“(seed and flower extracts, rodent models)”, “(flower extract 500 mg/kg/day for 180 days and seed extracts, rodent models)”, “(seed administration, rodent models)”, “(crude stem bark extracts and flower flavonoids, rodent and computational models)”) are appended to populations that the ER categorically states should avoid Butea monosperma (ER lines 232–237, 262). - 1.3 / 9.5 — Interaction severity qualifiers dropped: In
Key Interactions(caution_items, lines 554–559), line 556 softens the ER’s “Avoid with seeds / Caution with bark or flowers (theoretical)” to “(seeds vs. bark or flowers, theoretical)”, and lines 554, 555, 557, and 559 drop “monitor” (and the “3–4 h stagger” window on line 554) from the ER’s “Monitor (theoretical)” qualifiers. - 4.3 — Paraphrased time-to-effect label: In
Time to effect(time_3_label, line 505), “Bone density and lipid regulation” is a paraphrased hybrid of two separate ER benefit headings (“Bone Density Preservation and Osteogenesis” and “Glycemic and Lipid Regulation”, ER lines 148 and 152) rather than an unparaphrased ER label.
Fixes 14/10/2026 19:37
- 1.3 / 8.4 — Contraindications trailing study details: Stripped parenthetical rodent/computational study details and plant-part elaborations from all four
stop_itemsentries so they state the contraindicated populations directly. - 1.3 / 9.5 — Interaction severity qualifiers restored: Restored “(avoid with seeds / caution with bark or flowers, theoretical)” for NSAIDs and acetaminophen, “(monitor, theoretical, 3–4 h stagger)” for hepatic CYP substrates, and “(monitor, theoretical)” for estrogen-receptor modulators, glucose-lowering supplements, and prolonged fasting/ketogenic diets in
caution_items. - 4.3 — Unparaphrased time-to-effect label: Changed
time_3_labelfrom “Bone density and lipid regulation” to the ER’s exact benefit heading “Bone density preservation and osteogenesis”.