Run a review as a team

Personal libraries and team workspaces

New analyses can live in your personal library or in a team workspace. Personal projects are fastest for solo work. Team projects are best when multiple reviewers need role-based access, independent decisions, assignments, comments, and approval checkpoints.

Every team review has an owner: the person its scheduled updates run for and who receives its alerts. Workspace admins can transfer a review to a lead reviewer or admin of the workspace from the review's overview page — do this when the owner leaves the team. Transferring a review does not change what members can do: that always follows their role in the workspace. Removing someone from a workspace removes their access to its reviews, including the ones they created — transfer those first. Someone who was removed can be invited again; accepting the new invitation gives them the role it names.

Admins and lead reviewers invite people from the team page — a lead reviewer to a role no higher than their own. Invitations arrive by email. Each link works once and for seven days. If an email doesn't arrive, the team page lets you resend it — the new link replaces the old one — or, if the email could not be sent, copy the link and share it yourself.

A team's admins can delete it from the bottom of its team page. Each of its reviews then becomes a personal review of the person who created it, and the other members lose access to it; everyone leaves the team, pending invitations are cancelled, and the team's own review methods are deleted. Deleting a team cannot be undone. A team with an active subscription cancels it from its Billing page first.

Roles

Assignments and review modes

For small reviews, every reviewer can work from the full screening list. For larger reviews, lead reviewers can split work by phase and reviewer slot so each person sees a focused queue. Review mode controls whether a study needs one human decision, an AI suggestion plus a human decision, or two independent human decisions.

• Use single-reviewer mode for rapid scoping or early exploration.
• Use AI + human mode when you want a machine suggestion but a human final decision.
• Use two-human mode when your protocol or sponsor requires independent human screening.

In AI + human mode, a lead reviewer or admin can turn on Show AI verdict before I decide in Configure, with the screening policy. The human reviewer then sees the AI's verdict before deciding. That gives up independent review, so inter-rater reliability no longer measures agreement between two independent judgements; use it for triage and training. It is not offered with a single reviewer or two human reviewers, and choosing a different screening policy resets it.

If a review is switched from AI + human to two human reviewers part of the way through, the AI's earlier decisions no longer take a reviewer's place: each person's decision is paired with the other person's, and a disagreement between them goes to the conflicts queue.

Dual review at full-text screening

Full-text screening follows the review mode of the abstract phase. In AI + human mode the AI reviewer holds Reviewer A's slot and assesses each full text; the human reviewer decides in the other slot. With two human reviewers, the AI reviewer does not screen full texts: both people read the papers and decide themselves. In either case, automatic confirmation is not available, so every full-text decision is made by a person.

Decisions stay blinded as they do at the abstract phase. A reviewer does not see the AI reviewer's full-text assessment, its criterion verdicts or its quotes, until they have recorded their own decision, unless the review is set to show the AI verdict first. The other human reviewer's decision is never shown early. History and the review's approval record keep the same blind, at both phases: a vote in dual review appears there once both reviewers have decided.

A reviewer's answers to a study's criteria (Met or Not met) are theirs alone: the other reviewer never sees them, and they never count toward the other reviewer's assessment. The AI reviewer's verdicts count only as its own decision, so you answer every criterion you want settled yourself. Answers are offered while the AI reviewer's assessment is shown to you, so in dual review only when the review shows the AI verdict first; once you have included or excluded the study, your answers stay as they are. Which document the AI reviewer read is hidden until you decide, like its assessment. Re-checking automatic decisions finds nothing at full text in dual review, since none is confirmed automatically.

When the two decisions disagree, the study goes to the conflicts queue, labelled with its phase. Conflicts are adjudicated per phase: a ruling on a study's abstract conflict never closes its full-text conflict, and the other way round. Once full text has decided a study, that decision stands: a ruling on the study's abstract conflict is recorded and closes the conflict, and the study stays where full text put it. Reopening the study, or accepting, rejecting or importing it in the living-review inbox, is refused; change the decision on the full-text screening page. When the lead reviewer rules to exclude at full text, they choose the reason for the exclusion from the same list reviewers use at full text; the study is removed from the review and counted among the reports excluded after full text, under that reason. The conflict shows the AI reviewer's assessment of each criterion, with the reason it gave, and its reason for excluding the study when it did, and each reviewer's own exclusion reason. When both reviewers exclude a study at full text without a conflict, the exclusion is recorded with its reason in the same way: the first reviewer's reason is kept when the second gives none.

Conflicts, comments, and sign-off

Disagreements are routed to an adjudication workflow instead of being hidden. Reviewers can compare decisions, capture the reason for the final call, and leave comments or mentions for teammates. This holds in single-reviewer screening too: each person's decision on a record is kept as theirs, so when two people decide the same record differently it goes to the conflicts queue, and analysis waits until the conflict is resolved. An automated re-screen never overturns a person's decision; where it disagrees, it leaves the person's decision in place. Optional milestones let a team request and approve sign-off before moving from protocol, screening, extraction, analysis, or manuscript work into the next phase. A lead reviewer or admin asks for a sign-off from the Configure page or the Sign-off status page; any other admin of the workspace approves it, or turns it down with a reason, from Configure or the review's Versions page, where the request's notification leads. Nobody approves their own request.

Before you send a request, it lists what the chosen milestone checks, each with a tick or a warning and its counts: Protocol lock checks the search strategy, Screening lock checks screening and full-text screening, Extraction lock checks extracted values and quotes, and Analysis freeze checks risk of bias, critical appraisal and the certainty ratings; Manuscript lock has nothing to check. Anything still waiting for a person links to its page and holds the request until it is done. Where nothing is approved yet and everything is still in review, the row shows a neutral mark instead of a tick, and does not hold the request. Values marked validated with nobody recorded are named but do not hold it. Approving a sign-off asks you to confirm first. Turning one down, withdrawing your own request and unlocking the protocol ask why in a dialog, and the reason is shown on the review's Versions page.

Each milestone freezes its part of the review. Once the protocol is locked, its settings stay as signed off — the search plan and queries, the screening settings and the outcomes — and nothing changes them: not a page, the configuration assistant, a search preview or a screening suggestion, even when the search strategy was never locked itself. An outcome's pooling model and network settings, the treatment grouping and the living-review schedule can still be changed. Once screening is complete, no records can be added from any source, and neither manual nor AI screening changes a decision. Once the manuscript is locked, saved reports can no longer be changed.

In two-reviewer extraction, the second reviewer fills in the same fields the extraction form shows for each outcome — for a time-to-event outcome, the hazard ratio, its confidence interval and the number analysed in each arm — without seeing the first reviewer's values. The two extractions are compared number by number on exactly those fields: the same number written differently (0.72 and 0.720) counts as a match, a value one reviewer filled in and the other left blank counts as a difference, and values the form never asked for are not compared. When the numbers differ, the lead reviewer sees them side by side and chooses, for each one, whose number to keep; everything else in the first extraction is kept as it was.

When a reviewer disagrees with a risk-of-bias assessment, the lead reviewer compares the two domain by domain and resolves it one of four ways: keep the AI assessment, keep the reviewer's assessment, set it aside so it is left out of certainty ratings, or decide later. A set-aside assessment can't be reviewed or re-run afterwards.

A ruling is a set of choices shown together on the conflict's card, and Resolve asks before it records anything. Keeping the AI's assessment, including or excluding a study, and including a set of values ask you to confirm. Keeping the reviewer's assessment instead, setting an assessment aside, sending a study back as Unsure and excluding extracted values ask why, and the reason is kept in the record. Decide later, and Unsure on extracted values, decide nothing: the conflict stays open for another ruling.

Sign-off status

The Sign-off status page, after Report in a review's sidebar, shows who approved what in the review and what still needs a person. It lists, stage by stage, everything a person approves — screening decisions, extracted values and quotes, risk-of-bias and certainty ratings, proposals and the review's publication — with three counts for each:

• Approved by a person: confirmed, validated, finalised or approved by someone the review names.
• Automatic: decided by the AI or by the review's own rules, and recorded as such.
• Needs a person: waiting for a person's decision, such as an unsure record, a draft rating or a proposal waiting for approval. Each row, and every count in it, opens its stage.

Counts that look finished but that no person checked say so: AI only, when the AI's decisions stand unchecked; Automatic only, when a fixed rule decided them and no person has checked them — quotes the quote check found in the paper, or treatment groups matched by their names; and person not recorded, when something is marked approved but nothing records who approved it. A stage whose only unchecked decisions are of one of these kinds shows it as its status. Anything your review does not need is marked Not required, with the reason — CERQual in a review that is not qualitative, for example — rather than shown as zero. Under the search strategy's Locked, the page says who locked it and when.

A team review also shows its milestones, from protocol lock to manuscript lock: which are locked and who approved them, which wait for approval, and which are still open. A lead reviewer or admin can request a sign-off from the page. A personal review has no milestones.

The page ends with the review's History, the latest first, each step with who did it, what it was about, when, and the reason they gave. History records screening decisions, on titles and abstracts and at full text, with their overrides and withdrawals; extracted values and their quotes, with validations, withdrawals, rejections and undoing them, and answers about quotes; finalising and reopening GRADE and CERQual ratings and CASP appraisals; rulings on screening and extraction conflicts; and automatic locks. Other stages will follow. History starts when this feature arrived; earlier steps are not listed. A vote in dual review appears once both reviewers have decided: until then each reviewer finds only their own vote, in History, its counts and the export, as on the screening page, so two reviewers' History can differ for a while. Choose Last 30 days, Last 90 days or All time; a line above the list counts the approvals, withdrawals and unlocks in that period, beside a small chart of the last 30 days, and Load older shows more. Export, in the page's header (in More actions on a phone), downloads the review's approval record, the steps History lists, as a spreadsheet (CSV) or as one record per line (NDJSON); like History, it starts when this feature arrived. Anyone who can review may export.

Every Word report ends with a Validation and sign-off record: the milestones and each approval point under its stage, in the page's words, as they stood when the report was generated. A report you download names people as the page does.

Notifications

Comments, mentions, assignments, conflict requests, sign-off requests, and living-review alerts appear in the notification inbox. Email delivery follows your notification preferences, while urgent review decisions stay visible in the app until they are handled.