Panel · Template
Document Review.
LiveDocument ReviewGive a document to specialists who each review it in their own lane, and get back one recommendation, a ledger with a verdict, a risk and a required or suggested change for every item, and a list of what the review could not check.
Add it to your library to reuse from New → From template. Edit the saved copy in your library on the service form.
When to use it
A document is about to go to a committee, a payer, a regulator, a journal or a site, and you want it checked item by item before it does.
Who it is for. Leads who review or sign off documents: brand, compliance, regulatory, medical, evidence, clinical operations, quality and safety leads.
Why a review needs a ledger
An item can be literally true and still fail on omission or emphasis, and a reviewer can drift outside their remit into style. This template reviews item by item in document order, gives each seat a lane, requires every comment to state the exact change and whether it is required or only suggested, and records what support was offered and whether the panel could locate it.1,2
What you get
The document under review, and one recommendation. The document type, audience and intended use, the framework the panel applied, and a disposition: approve, approve with required changes, revise and re-review, or do not proceed. The recommendation is analyst judgment and not a sign-off.1
The review by seat. Each seat states its lane, the items it reviewed, its read, and its most important findings by item number. Seats flag items outside their lane and do not rule on them.2
An item-by-item ledger. One row per item in document order: location, verdict, risk, the change needed, the substantiation needed and the seat that raised it.3
Substantiation and required changes. For each factual, comparative or causal claim, the evidence it needs, what was supplied and the gap. Then one consolidated list of changes the author can work from, with duplicates merged.
Rebuttal, and what could not be checked. At Full depth, each seat answers the strongest defense of the author’s position. Every review closes with what was not supplied, what the panel could not verify and which checks only a real reviewer can do.4
What is in it, by length
| Section | Brief | Standard | Comprehensive |
|---|---|---|---|
| The document under reviewThe document, its use and the framework applied | ● | ● | ● |
| Overall recommendationThe disposition and the items that decide it | ● | ● | ● |
| The review, by seatEach seat’s read and findings | ● | ● | ● |
| Item-by-item ledgerVerdict, risk and change for every item | ● | ● | ● |
| Substantiation and evidence gapsThe evidence each claim needs and what was supplied | – | ● | ● |
| Required changes and conditions for approvalThe consolidated list of changes | – | ● | ● |
| Rebuttal roundWhether verdicts stand against the strongest defense | – | – | ● |
| What this review could not checkThe limits of the review | ● | ● | ● |
A Light review has three seats and about two pages with the ledger. Standard has four seats and adds the substantiation table and the consolidated changes. Full has five seats and adds the rebuttal round.
Choosing a length
Choose Standard for most documents. Choose Full when seats are likely to disagree on a verdict and you want to see which verdicts survive a defense.
The standards and practice behind it
The structure and the checks come from published practice in promotional review, reporting guidelines and journal peer review. These are the references we drew on and what we took from each. None of their authors has reviewed the template.
| What we took | From | Where it shows |
|---|---|---|
| Check that promotion is not false or misleading, with fair balance of efficacy and risk and disclosure of material facts | FDA Office of Prescription Drug Promotion, Bad Ad Program page1 | A separate check for omission and emphasis, apart from accuracy |
| Annotate every claim to its support and resolve prior reviewer comments | The ProPharma medical, legal and regulatory submission checklist (a consultancy page)2 | The substantiation table: what was offered and whether it could be located |
| Use the reporting guideline that fits the study design | The EQUATOR Network library of reporting guidelines (CONSORT, STROBE, PRISMA and others)3 | The framework named in the first section |
| Be impartial and courteous, review only what you are competent to assess, and keep confidences | The COPE Ethical Guidelines for Peer Reviewers, version 2 (2017)4 | The closing statement of what the panel was and was not competent to assess |
| Require material that is accurate, balanced, fair, objective and sufficiently complete, with sources quoted | The EFPIA Code module on promotion to healthcare professionals5 | The check on omission, exaggeration and undue emphasis |
| Guard against score inflation and overconfidence when language models review documents | Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models (arXiv, 2025)6 | Verdicts that change only on new evidence, and a ledger that cites the item |
What it will not do
It is analyst judgment from AI specialists and not a regulatory, medical or legal sign-off.
It does not rewrite the document. It states the change and leaves the writing to the author.
It does not check original data or the approved label held by the company. Those checks need a real reviewer.
References
- [1] U.S. Food and Drug Administration. Bad Ad Program (Office of Prescription Drug Promotion). Read in the template research of 9 October 2026: false or misleading promotion patterns, fair balance and material facts.
- [2] ProPharma Group. Medical, legal and regulatory (MLR) submission checklist. Consultancy page, read in the template research. Practitioner source.
- [3] EQUATOR Network. Enhancing the QUAlity and Transparency Of health Research: library of reporting guidelines. Home page read in the template research.
- [4] Committee on Publication Ethics. Ethical Guidelines for Peer Reviewers, version 2, September 2017. The PDF could not be opened (access refused); the duties are as summarized in search results.
- [5] European Federation of Pharmaceutical Industries and Associations. Module 1: Promotion of prescription-only medicines to healthcare professionals. The PDF was not machine-readable in the template research; criteria are from search-result excerpts.
- [6] Akella, Siravuri and Rohatgi. Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models. arXiv:2512.22145. Preprint, read in the template research: score inflation, overconfidence and safeguards.
Links checked 9 October 2026
These are the sources the template drew on. None of their authors or issuers has reviewed it.
About the Panel service
Each panelist answers in their own voice, then the discussion is drawn together. You get the question and who was in the room, every position in full, what they agreed on, where they split, and what follows. Disagreements are written down rather than smoothed into a consensus nobody actually holds, because the split is usually the part you needed.
Use cases for the Document Review
7 ready-to-run use cases. Each opens its own page with the question, the specialists, the standards and the references.
To edit a saved template, open New → Panel → From template, or the library rail on the service form.