Audit: QRS - Green Light Therapy to Treat Migraine
Audit conducted on 24/08/2026 13:52 using AI4L / Opus 5
Summary
| Items | Count |
|---|---|
| Total | 93 |
| Passed | 84 |
| Failed | 0 |
| N/A | 9 |
| 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. | 🟢 | Protocol cells, gate items, benefit/risk lines, monitoring rows, and the At-A-Glance text were each traced back to a specific ER passage. |
| 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. | 🟢 | “rated very low certainty” and “studies where everyone knew the treatment” mirror the ER Conclusion; the “no reported harm” clause retains its brightness caveat via the closing “brighter light makes headaches worse”. |
| 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 keep absolute framing; interaction items keep the ER’s own “caution” / “no interaction” designations. |
| 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. | 🟢 | Stop items derive from the ER’s “Populations who should avoid” list plus the bullet the ER itself labels “absolute contraindication”; caution items derive only from the ER’s interaction bullets. |
| 1.5 | PubMed IDs, study citations, expert names, clinical trial identifiers (NCT*), and brand names appear in the QRS only if they appear in the source ER for the same fact. | 🟢 | The QRS carries no PMIDs, NCT identifiers, investigator names, or device brand names at all. |
| 1.6 | The QRS does not introduce new attributions. | 🟢 | No attributions present; “Arizona preventive protocol” and “Boston acute protocol” are the ER’s own bold bullet labels. |
2. Focus, Tone & Audience
| # | Description | Result | Comments |
|---|---|---|---|
| 2.1 | The QRS follows the tone of the ER, which is determined by the ER’s own language, phrasing, and framing. | 🟢 | Measured, evidence-weighted register carried over, including the ER’s British spelling (“colour”, “sensitising”). |
| 2.2 | The tone of the QRS is simultaneously expert, accessible, objective, and data-driven, but also empowering and encouraging | 🟢 | Sheet states what was measured and where the limits lie without hedging into discouragement. |
| 2.3 | The QRS reads as a trusted, knowledgeable guide rather than a prescriptive doctor | 🟢 | Protocol and monitoring cells are descriptive noun phrases, not instructions. |
| 2.4 | The QRS avoids language that implies medical or clinical advice | 🟢 | No imperatives; cadence text is phrased passively (“Baseline panel drawn before the first session”). |
| 2.5 | The QRS “presents information” instead of “providing guidance”, “recommending”, or “advising” | 🟢 | No “recommended”, “should”, or “advised” 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 | 🟢 | Retained technical terms (photophobia, 6-sulfatoxymelatonin) are ER-sourced and necessary for the marker table. |
| 2.8 | Information is presented in a concise and very compact manner | 🟢 | Gate items, benefit lines, and risk lines are trimmed to the key fact. |
| 2.9 | It DOES NOT address the reader directly | 🟢 | Confirmed by full-text scan for you/your/we/our. |
| 2.10 | The target audience is health- and longevity-oriented adults who are risk-aware, proactive, and actively seeking to optimize health or apply the intervention under review. | 🟢 | Content assumes a reader running a headache diary, a baseline lab panel, and a bounded self-trial. |
| 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. | 🟢 | 1–2 hours daily in a dark room for 10 weeks is presented without softening. |
| 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 simplification of the burden; the seven-marker panel and seven qualitative trackers are retained in full. |
| 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 the very-low-certainty base and still names the conditions under which a bounded trial is defensible. |
| 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 in the file. |
| 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. | 🟢 | “Sedating over-the-counter sleep aids”, “intraocular or refractive surgery”, “eye-specialist clearance” all match the ER’s clinical register. |
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 headings, gate titles, tier labels, and the three table column headers are byte-identical to the template. |
| 3.2 | All “…” from the [qrs_template] are present in the the QRS. | 🟢 | Variable-name diff against the template shows only the expected expansions of marker_#_* into 1–7 and qualitative_item_# into 1–7. |
| 3.3 | Spans that are not addressed in a checklist item are left unchanged | 🟢 | Structural diff (text nodes stripped) shows no unexpected changes; the website="evidence_review", website="audit", and website="full_review" spans are untouched. |
4. Formatting
| # | Description | Result | Comments |
|---|---|---|---|
| 4.1 | When the source ER section is empty, the QRS uses the ER’s own empty-state phrasing verbatim. Typical phrasings are “None documented in human trials to date” and “Not formally studied” | N/A | No source ER section is empty; the only absent element is the Risks Medium tier, which is governed by item 13.5. |
| 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. | 🟢 | “Arizona preventive protocol”, “Boston acute protocol”, “Wavelength and intensity” reproduce the ER Therapeutic Protocol bold labels; interaction items reproduce the ER’s bold interaction labels including their parenthetical designations. |
| 4.3 | Labels are not paraphrased, abbreviated, or invented. | 🟢 | Marker names match the ER monitoring table verbatim; Time-to-Effect cell labels subdivide the single ER “Time to effect” bullet, which supplies no per-cell bold labels. |
| 4.4 | The QRS DOES NOT use emoji indicators (no 🟩, 🟥, 🟨, etc.). Color and emphasis are conveyed through CSS and bold labels. | 🟢 | No emoji in the file; the ER’s “⚠️ Conflicted” marker on the monthly-headache-days benefit was 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 is condensed rather than extended: gate items trimmed to the key fact, benefit and risk tiers collapsed into single semicolon-separated lines, qualitative items shortened from the ER wording. |
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 template’s own “blank template” comment follows at 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 “—” at line 3, closing “—” at line 13. |
| 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 repeated in the header, footer, or 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, and it contains a colon requiring it. |
| 5.5 | The filename of the source ER is stated as “er_filename: [er_filename]” | 🟢 | Line 4: er_filename: green_light_therapy_migraine_2026-0824-1058_Opus_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]” | 🟢 | 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: 2026-0824-1308. |
| 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) | 🟢 | 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]” | 🟢 | 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, no qualifier. |
| 5.12 | The filename of the document is stated as “qrs_filename: [filename of this document]” | 🟢 | Line 9 matches the file’s actual name 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 &) |
🟢 | Line 22: “Green Light Therapy to Treat Migraine - Quick Reference Sheet”; no characters requiring entity encoding. |
| 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 matches the ER frontmatter canonical_topic exactly. |
| 6.3 | [header_subline_date] is set to [qrs_creation_date reformatted as MM/DD/YYYY] | 🟢 | Line 421: “08/24/2026”, the correct reformatting of 2026-0824-1308. |
| 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 contains only the title and the template subline; the ER’s alternate_names list was 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 |
🟢 | Covers what is done, the one solid claim, the weakness of the frequency evidence, and the decision balance — the four moves of the ER Conclusion. |
| 7.2 | [at_a_glance] is no longer than 60 words | 🟢 | Scripted word count: exactly 60. |
| 7.3 | Every fact in [at_a_glance] is supported by a distinct passage in the ER. | 🟢 | Each clause maps to a distinct sentence of the ER Conclusion (lines 384, 386, 388). |
| 7.4 | It DOES NOT use acronyms or technical classifications that require specialist knowledge, uses plain-language terms instead | 🟢 | No acronyms; “narrow-band”, “low brightness”, “very low certainty” are all self-explanatory in context. |
| 7.5 | It DOES NOT cite specific trials (names, years, sample sizes, p-values) | 🟢 | No study names, years, or sample sizes. |
| 7.6 | It DOES NOT cite effect sizes, relative risks, or statistical results | 🟢 | No numeric outcomes; the ER’s headache-day figures were deliberately omitted. |
8. Contraindications
| # | Description | Result | Comments |
|---|---|---|---|
| 8.1 | The section is derived from the ER Key Interactions & Contraindications section |
🟢 | All six items come from that section — five from the “Populations who should avoid” list, one from the bullet the ER labels “absolute contraindication”. |
| 8.2 | [stop_items] represent the Contraindications from the ER | 🟢 | The ER’s six avoid-list entries are all present, in ER order. |
| 8.3 | Individual [stop_items] are formatted as <li></li> | 🟢 | Six <li> elements inside the stop_items span (lines 542–547). |
| 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. | 🟢 | The ER’s trailing explanations (“on brain-wave testing”, “in whom no green light trial for migraine has been conducted”) are stripped; 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). | 🟢 | “within 4 weeks”, “>5 mg/kg/day or beyond 5 years”, “advanced proliferative”, “wet … under active treatment”, “Bipolar I” 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 “>” only as a numeric dose threshold (“>5 mg/kg/day”), not as severity-ordering notation. |
| 8.7 | The section is left empty ONLY IF the ER’s Key Interactions & Contraindications section identifies no population, condition, or scenario for which the intervention should be avoided, deferred, or used only under specialist supervision. |
🟢 | The ER names six such populations and the section is correctly populated rather than empty. |
| 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 seven items map one-to-one onto ER interaction bullets (lines 259–266). |
| 9.2 | [caution_items] represent the Key Interactions from the ER, excluding any that are already listed as Contraindications | 🟢 | Seven of the ER’s eight interaction bullets appear; the “Retina-damaging prescription drugs (absolute contraindication)” bullet is correctly excluded and surfaced in the Contraindications gate instead. |
| 9.3 | Individual [caution_items] are formatted as <li></li> | 🟢 | Seven <li> elements inside the caution_items span (lines 555–561). |
| 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. | 🟢 | Each item reduces to the ER bold label plus its named example agents; the ER’s mitigation sentences (three-hour separation, staggered introduction) are 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). | 🟢 | Named agents retained throughout: diphenhydramine/doxylamine; amiodarone/voriconazole/doxycycline/hydrochlorothiazide; valproate/lamotrigine/topiramate; sumatriptan/ubrogepant/erenumab; magnesium/riboflavin/coenzyme Q10. |
| 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 interaction bullets contain 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 names eight interactions and the section is correctly populated. |
| 9.8 | If the section is left empty, an HTML comment inside the [caution_items] span records the ER basis for the absence, naming or quoting the ER text relied on. E.g. | N/A | The section is not empty. |
10. Protocol
| # | Description | Result | Comments |
|---|---|---|---|
| 10.1 | The section is derived from the ER Protocol section |
🟢 | All three cells derive from the ER Therapeutic Protocol bullets (lines 291, 292, 294). |
| 10.2 | The three sets of [action] items cover the three most important actionable implementation aspects from the ER Protocol section |
🟢 | The two named dosing protocols plus the wavelength/intensity specification are the three bullets that determine what is actually done; the remaining bullets are 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 supplies eleven protocol bullets; 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 carry ER-derived content; no placeholder text remains. |
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 | 🟢 | The three cells reproduce exactly the three components of the ER’s “Time to effect” bullet (line 327): single-session acute relief, 4–10 week preventive accrual, and the ≥10 week assessment horizon. |
| 11.2 | The sets are picked and ordered by the magnitude of the related benefit | 🟢 | Acute intensity relief precedes the frequency reduction, matching the ER’s own ordering within the Medium benefit tier; the assessment horizon closes the row. |
| 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 aspects are present in the ER; 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; time_3_sub draws on the ER’s carry-over statement (“benefit in trials accrued across weeks and faded after exposure stopped”, line 296). |
| 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 information, so the section is correctly retained. |
12. Benefits
| # | Description | Result | Comments |
|---|---|---|---|
| 12.1 | The section is derived from the ER Expected Benefits section |
🟢 | All seven ER benefit headings are represented across the four tiers. |
| 12.2 | Key variables are [benefits_high], [benefits_medium], [benefits_low], [benefits_speculative] | 🟢 | All four spans present and populated (lines 521–532). |
| 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. | 🟢 | Each tier is a semicolon-separated list of the ER’s benefit headings; no magnitudes, mechanisms, or study references carried over. |
| 12.4 | Parenthetical content — including effect sizes, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses in any benefit line. |
| 12.5 | If no items of a specific sub-section (high, medium, low, speculative) are present the respective is set to “display=none”, not filled with “None documented in human trials to date” or similar empty-state phrasing. | N/A | All four benefit tiers contain at least one ER item, so the condition does not arise. |
13. Risks
| # | Description | Result | Comments |
|---|---|---|---|
| 13.1 | The section is derived from the ER Potential Risks & Side Effects section |
🟢 | All five ER risk headings across High, Low, and Speculative are represented. |
| 13.2 | Key variables are [risks_high], [risks_medium], [risks_low], [risks_speculative] | 🟢 | All four spans present (lines 573–584). |
| 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. | 🟢 | The ER’s percentages (40%, 3%, 39%, 27%) and mechanistic explanations are all stripped. |
| 13.4 | Parenthetical content — including frequencies, severity grades, sample notes, mechanistic hints, and example studies — is stripped, NOT preserved. | 🟢 | No parentheses in any risk line. |
| 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. | 🟢 | The ER states “No risk reaches Medium”; risks_medium carries style="display: none" with an empty item rather than empty-state text (line 576). |
14. Monitoring
| # | Description | Result | Comments |
|---|---|---|---|
| 14.1 | The section is derived from the ER Monitoring section |
🟢 | Rows and cadence derive from the ER Monitoring Protocol & Defining Success section (lines 346–356). |
| 14.2 | All measurable/quantifiable biomarkers from the Monitoring section are listed |
🟢 | All seven ER table biomarkers present with their optimal ranges and “why” text intact. |
| 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. |
🟢 | Line 681 reproduces both the lab cadence (baseline, 3 months, 6–12 months) and the diary review schedule (4 weeks, 10 weeks, quarterly). |
15. Qualitative Assessment
| # | Description | Result | Comments |
|---|---|---|---|
| 15.1 | The section is derived from the ER Monitoring section |
🟢 | All items come from the ER’s “Qualitative markers to track alongside the labs” list (lines 360–366). |
| 15.2 | All subjective/qualitative biomarkers from the Monitoring section are listed |
🟢 | All seven ER qualitative markers present, condensed but complete. |
Issues 24/08/2026 13:52
Pass rate 100.00%. No issues found.
Issues 24/08/2026 13:45
- 1.3 — Population qualifier dropped from balance claim: [at_a_glance] (line 433) states “One-time cost and no reported harm tilt the balance toward a bounded personal trial” while the ER Conclusion (line 388) conditions that judgment on “the balance for someone with frequent attacks”, broadening a subgroup finding to all readers.
Fixes 24/08/2026 13:45
- 1.3 — Population qualifier restored: [at_a_glance] now reads “With frequent attacks, one-time cost and no reported harm tilt the balance toward a bounded trial”, restoring the ER Conclusion’s subgroup condition; “Claims of fewer headache days” was tightened to “Reductions in headache days” to keep the passage within the 60-word budget.
Issues 24/08/2026 13:36
- 11.2 — Time-to-effect cells misordered:
time_1presents the preventive headache-day effect ahead oftime_2acute relief, but the QRS’s ownbenefits_mediumline (line 525), following the ER, ranks “Reduced headache intensity during an acute attack” ahead of “fewer monthly headache days” — the latter carrying the ER’s “⚠️ Conflicted” flag (ER line 158).
Fixes 24/08/2026 13:36
- 11.2 — Time-to-effect cells reordered: Swapped the first two
timecells so acute relief (“Single 1–2 hour session”) now precedes the preventive headache-day effect (“4–10 weeks”), matching the benefit ordering the QRS already uses inbenefits_medium.
Issues 24/08/2026 13:27
- 9.5 — Example drugs dropped from two interactions: “Migraine drugs (no interaction; additive symptom relief)” at line 559 and “Other nerve-stimulation devices (caution; confounded assessment)” at line 561 drop the ER’s named examples (sumatriptan, ubrogepant, erenumab at ER line 263; arm-worn, scalp-current and neck-worn units at ER line 266), while the four sibling items at lines 556–558 and 560 all carry theirs.
Fixes 24/08/2026 13:27
- 9.5 — Example drugs restored to two interactions: Added the ER’s named examples to both under-specified Key Interactions items — “Migraine drugs (no interaction; additive symptom relief)” became “…; sumatriptan, ubrogepant, erenumab)”, and “Other nerve-stimulation devices (caution; confounded assessment)” became “…; arm-worn, scalp-current, neck-worn units)”, bringing them into line with the four sibling items that already carried theirs.
Issues 24/08/2026 13:19
- 4.2 / 4.3 — ER bold labels altered in Key Interactions: Five [caution_items] (lines 556–561) modify the ER’s bold-label parentheticals — “caution” is dropped from three items, “(additive benefit; monitor)” is rewritten, and line 558 replaces the ER’s “flicker not colour” (ER line 264) with the invented directive “flicker-free lamps only”.
- 9.4 — Mitigation instructions appended to gate items: Line 558 (“flicker-free lamps only”) and line 561 (“stagger 4 weeks”) add action instructions drawn from the ER bullets’ explanatory bodies rather than the labels, contrary to the “just the key fact” rule.
- 7.1 — At-A-Glance omits the ER’s bottom line: Line 433 reproduces only the ER Conclusion’s caveats and drops its execution-relevant verdict (ER line 388: one-time cost, no reported harm at low brightness, “the balance … tilts toward a bounded personal trial”).
Fixes 24/08/2026 13:19
- 4.2 / 4.3 — ER bold labels restored in Key Interactions: Rewrote five [caution_items] so each carries the ER’s bold-label parenthetical verbatim first, with the named example drugs appended — e.g. “Antiseizure medications (caution; flicker not colour; valproate, lamotrigine, topiramate)” replaces “(valproate, lamotrigine, topiramate; flicker-free lamps only)”; “caution” was likewise restored to the sleep-aid and light-sensitising-drug items and “(additive benefit; monitor)” to the supplements item.
- 9.4 — Mitigation instructions removed from gate items: Dropped the appended action clauses “flicker-free lamps only” and “stagger 4 weeks”, leaving “Other nerve-stimulation devices (caution; confounded assessment)” as the ER states it.
- 7.1 — At-A-Glance now carries the ER’s bottom line: Rewrote [at_a_glance] to add the ER Conclusion’s verdict (“One-time cost and no reported harm tilt the balance toward a bounded personal trial”), tightening the opening and caveat clauses to stay within the 60-word cap at 59 words.
Issues 24/08/2026 13:12
- 9.4 — Added optic-nerve monitoring elaboration: The “Light-sensitising drugs” interaction at line 557 appends “amiodarone optic-nerve monitoring”, an elaboration lifted from the ER bullet body (ER line 262) rather than a qualifier, threshold, or example-drug name that item 9.5 requires be preserved.
Fixes 24/08/2026 13:12
- 9.4 — Trimmed optic-nerve elaboration: Removed the trailing “, amiodarone optic-nerve monitoring” from the “Light-sensitising drugs” interaction item, leaving the ER’s own parenthetical qualifier “skin reaction is not the issue” alongside the preserved example-drug list.