Promotional claims substantiation that ties every claim to the page behind it before MLR review
Every claim tied to the page that supports it before MLR review
See one case, screen by screen ↓Every banner, HCP email, detail aid and social post carries the same efficacy, dosing and safety claims, and every one of them goes through medical, legal and regulatory review. Reviewers re-check those claims by hand in each piece, against the Prescribing Information, the publications and the data on file, and references are annotated page by page for the committee.
The claims that cause trouble are the ones nobody reads as claims. A headline like “Simple to stay on” implies persistence; a subject line like “Clear skin that lasts” overstates the data; a cross-trial comparison has no head-to-head study behind it; a detail aid still says what a retired claim said before the label changed. FDA's Office of Prescription Drug Promotion keeps writing untitled letters about unsupported and convenience claims, and a piece that comes back after its committee slot waits for the next one.
Estimated split, in business days, for one promotional piece from draft to committee, by hand and with the solution.
Six specialist agents read each draft, pin every claim to the library and its reference page and catch new claims; the review coordinator decides each flag, and the committee signs.
At 08:41 Harborline Health sends PC-2146, a 300×600 HCP banner for Veltrimab in moderate-to-severe plaque psoriasis: three frames and a persistent safety scroll, 1.1M impressions on medical sites. Thursday's committee cut-off is 17:00 today. Here is what happens next, screen by screen, in the working solution.
Lena's home screen leads with the draft itself: frame 1 with the VELA-2 Week 16 results, frame 2 with the dosing schedule, frame 3 with the two-year data, and the Important Safety Information scrolling under all three. A switcher across the top holds the other drafts before MLR — the VELA-2 HCP email that arrived at 07:52, the detail aid, the Corventa social post and the Talmirex banner.
“Every claim gets a pin. Each pin ties the claim to its entry in the approved claims library and to the page and sentence of the reference behind it.”
The piece reader reads the 300×600 banner, its three frames and the safety scroll. The claim extractor finds 7 claims, headlines included. The library matcher checks each one against the 142 approved claims, and the reference anchorer pins each match to its reference page. Pins appear on the banner one by one, each with a note in the margin.
Each step is shown as it runs, with what it found.
Six of the 7 claims match approved claims word for word, pinned to 5 reference pages. Pin 3, the frame-2 headline “Simple to stay on”, is not in the library: it tells a dermatologist that patients keep taking Veltrimab, and nothing in the reference library measures persistence. Readiness is 88, against a send threshold of 90, and a new claim blocks sending regardless.
“New claim caught before MLR · pin 3 “Simple to stay on”. It is not one of the 142 approved claims, and no reference in the library supports it.”
Lena opens pin 1. “84% of patients achieved PASI 90 at Week 16 (vs 4.9% placebo)” is approved claim CL-0102, word for word, pinned to Prescribing Information v4, page 18, the PASI 90 row of the table. The note quotes the row and opens the page.
“PASI 90 at Week 16: VELTRIMAB 84.1% · Placebo 4.9%” — Prescribing Information v4 · page 18
The nearest approved claims are the dosing schedule, CL-0130, and stopping for side effects, CL-0112 — neither supports persistence. Lena could ask Dr. Maya Chen to substantiate it as proposed claim CL-0152, due Oct 9, but the banner would miss Thursday. She uses CL-0130 instead: “Two starter doses, then one dose every 12 weeks”, pinned to section 2.1 on page 2. Readiness goes to 100.
“2.1 Recommended Dosage. The recommended dosage of VELTRIMAB is 150 mg administered by subcutaneous injection at Week 0, Week 4, and every 12 weeks thereafter.”
Send to MLR shows the committee — Thu Oct 8 at 10:00, slot 8 of 10, cut-off 17:00 today — readiness 100 of 100, and the reviewers: Dr. Maya Chen for medical, Omar Haddad for regulatory, Dana Okafor for legal. The annotated reference pack will carry 7 claims across 2 references and 5 pages, each passage numbered to match its claim.
The pack builder numbers the 7 claims, annotates the 5 passages, assembles a 24-page reference pack, books slot 8 and tells the three reviewers. Each claim in the pack lists its reference and page, and the Prescribing Information table opens with the PASI 90 row highlighted and pins 1 and 2 in the margin.
The pack builder sends nothing without the coordinator, and the pack holds only anchored passages.
The VELA-2 two-year email to 18,400 dermatologists has 12 claims and comes back at readiness 58. The subject line “Clear skin that lasts” is overstated; the 87% maintenance claim is missing its open-label qualifier; “itch relief as early as Week 1” rests on an exploratory endpoint; “Higher PASI 90 rates than other IL-23 and IL-17 treatments” has no head-to-head study. A tuberculosis claim conflicts with the label, and the email still carries ISI v3.
“A claim with no library entry is always flagged, never passed.”
Prescribing Information v4 added liver tests before treatment, in section 5.4, so CL-0127 “No routine laboratory monitoring required” was retired on Sep 18, 2026. The detail aid PC-2141 still uses it. The full review shows the claim, the highlighted passage on page 5 and the approved replacement, CL-0128 “Check liver enzymes and bilirubin before starting treatment”.
“A conflict with the label cannot be kept as written.”
Pieces lists all 13 pieces on their way to MLR with claims anchored, flags to decide, readiness and stage. The banner now reads Booked for Thursday, slot 8. Readiness counts what is still open, and 90 and above can go to MLR.
The same banner, seen by the people who carry it to committee — what their week looked like, and what it looks like now.
Six specialist agents read each draft, pin every claim to the library and its reference page and catch new claims; the review coordinator decides each flag, and the committee signs.
Opens the draft in any format — PDF, DOCX, PPTX, HTML email, banner bundle, video script — and separates the copy, footnotes, safety text, links and image text, keeping the reading order.
Finds every claim — benefit, number, comparison, dosing, safety, access and savings — including the implied ones in headlines and subject lines, and splits compound sentences.
Matches each claim to the approved claims library — word for word, same meaning, or new wording — carries over the required qualifier, and catches any claim the library does not hold before it reaches MLR.
Anchors every claim to the page and sentence or table row of the reference that supports it — Prescribing Information, published study or data on file — and says so when the passage says less than the claim.
Checks consistency with the label, absolute or overstated wording, comparisons without head-to-head evidence, exploratory endpoints, the safety information version, boxed warning placement and links, and proposes the approved library wording when there is one.
Builds the annotated reference pack for reviewers — every claim numbered, each matching passage annotated with the same number — drafts the note back to the agency and books the committee.
Decides each flag; reviewers sign. The agents propose; a named person decides.
Ask in plain words. Answers come from the claims library, the references and the claim pins, with the page behind every answer.
Which claims are not in the claims library?
One in the newest banner: “Simple to stay on”, the headline of frame 2. It tells dermatologists that patients keep taking Veltrimab; no approved claim says that, and no reference in the library measures persistence. Use approved claim CL-0130 “Two starter doses, then one dose every 12 weeks”, or ask Dr. Maya Chen to substantiate it. Also with no approved entry: the cost-per-responder comparison on the payer slide, already with the agency.
Which pieces use the claim retired by the label update?
Claim CL-0127 “No routine laboratory monitoring required” was retired on Sep 18 when Prescribing Information v4 added liver tests before treatment. Three pieces use it, and the live HCP dosing page matters most — it needs a revision before anything else. The replacement claim is CL-0128 “Check liver enzymes and bilirubin before starting treatment”.
Add a rule: hold data on file older than 6 months
Done. Running it over the pieces in flight finds one: the payer slide PC-2135 cites formulary data from Jan 9, 2026 — nine months old. Newer data on file exists from Apr 14, 2026 (91% of commercial lives), and that one is itself due for refresh on Oct 14. The rule is live in Settings and recorded on the audit trail.
Draft the agency note for the Corventa social post
To Ana Lima, North Pier Creative: three changes before Thursday's committee. The headline “Itch-free nights start here” overstates the result — use library claim CL-0208. “For anyone 6 and older” is outside the label — Corventa is approved from 12; use CL-0201. Move the “Serious side effects” headline and boxed warning link into the first lines of the caption. Due Oct 9.
13 screens from the working solution, on its sample data. Pick one to see it large.
The readiness rules the agents apply and who decides each review are settings, recorded on the audit trail.
| Setting | Default | Choose from |
|---|---|---|
| Send to MLR at readiness | 90 | Up or down, five points at a time; below it the piece goes back to the agency |
| No absolute efficacy words | On | On · Off — “Clear”, “free”, “cure”, “for good” need the approved wording |
| Library claims keep their qualifier | On | On · Off — a matched claim must carry the qualifier the library requires |
| Exploratory endpoints cannot carry a claim | On | On · Off — nominal p-values and post-hoc analyses are flagged |
| Comparisons need a head-to-head study | On | On · Off — cross-trial comparisons are flagged as unsupported |
| Safety text must match the current approved version | On | On · Off — ISI, boxed warning and indication statement |
| Data on file must be newer than 6 months | Off | On · Off — older data on file is flagged as out of date |
| Second look on “keep with reason” | Omar Haddad | Nobody · Lena Ortiz · Dr. Maya Chen · Omar Haddad · Dana Okafor · Priya Raman |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample pieces · “target” = the design goal, measured in the live solution · “estimated” = our estimate · “typical” = published figures (Vodori 2025 promotional review survey — 14.8-day average MLR job, 7.6 days in review). Context: FDA OPDP untitled letters on unsupported and convenience claims; 21 CFR 202.1(e); Form FDA 2253 at first use, 21 CFR 314.81(b)(3)(i). People, companies, brands, agencies and data named on this page are fictional — characters and sample data in the working solution.
It is showing that every claim in a promotional piece is supported — by an approved claim and the page of the label, study or data on file behind it — before medical, legal and regulatory review. Promotional Claims Substantiation does that with six agents that read the draft, pin every claim to the claims library and its reference page, and catch the claims the library does not hold.
The reference anchorer pins each claim to the reference, version, page and sentence or table row that supports it. When the piece goes to MLR, the pack builder numbers every claim and annotates each matching passage with the same number, so reviewers get an annotated reference pack built from the pins.
Yes. The claim extractor treats headlines, taglines, subject lines and supers as claims and keeps their exact wording. In the working solution, the frame-2 headline “Simple to stay on” is caught as a new claim because no approved claim or reference supports persistence.
It is flagged red before MLR and blocks Send to MLR. The coordinator can use the nearest approved wording the solution proposes, or ask medical to substantiate it — it then enters the claims library as a proposed claim for the medical reviewer to approve.
Yes. The label and fair-balance checker checks consistency with the Prescribing Information, overstated or absolute wording, comparisons without a head-to-head study, exploratory endpoints, the ISI version, boxed warning placement and the Prescribing Information link. A conflict with the label cannot be kept as written.
A label watcher checks for new label versions every morning. When Prescribing Information v4 added liver tests before treatment, claim CL-0127 was retired, its replacement CL-0128 entered the library, and the pieces still using the retired claim are flagged with the approved wording to use — three of them in the working solution.
Yes. The agents check and propose; the promotional review coordinator decides every flag and what goes to MLR, the medical reviewer approves new library claims, and the committee reviews and signs. Form FDA 2253 is filed by regulatory, never by an agent, and every decision is on the audit trail.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your claims library, reference library, safety text, brand rules and a sample of past drafts — and it goes live once every quality gate has passed. We will walk you through it on your own pieces first.
The quarterly risk narrative drafted in minutes, every figure from a live query
1-min demoSales Playbook AutomationThe right playbook for every market and product, built 70% faster.
1-min demoChargeback ProcessingEvery chargeback claim read first, each verdict with its rule and evidence
1-min demoWe'll run Promotional Claims Substantiation on a sample of your own past drafts and your claims library.