How to run a research literature review without drowning in a PDF folder

Claire is a fictional 34-year-old public-health researcher drafting a scoping review in Kingston, Ontario. Claire has 180 saved PDFs, a protocol limited to primary studies with measured implementation outcomes, and a coauthor waiting on a table. A new commentary paper dropped that is adjacent but not in scope. The folder is named FINAL_review and is not.

A reference manager, a desktop folder, and comments in a shared doc all hold different inclusion decisions.

The new adjacent paper would make a better story and would reopen the protocol.

In You.one's Superboard view, Claire can give “Produce a screening table against the written protocol, with out-of-scope papers parked, so the coauthor can see what is in and why” a Board of its own. That Board connects source evidence, unresolved questions, decisions, and accountable judgment; opening “Choose the adjacent paper” creates a Room for its evidence, discussion, state, and decision.

The mission is specific: Produce a screening table against the written protocol, with out-of-scope papers parked, so the coauthor can see what is in and why.

The consequential choice is not something a board or an AI should quietly make: Whether Claire should exclude the new paper, park it for a later piece, or take a protocol-amendment proposal to her coauthor.

You.one can keep the work, several kinds of evidence, and “Choose the adjacent paper” decision visible through its Superboard view. The Owner boundary stays explicit: Claire chooses what to recommend; any protocol amendment requires her coauthor’s agreement. They own the review and every citation.

The Scoping review Board gives this mission one durable operating picture. Claire can use familiar language instead of translating the situation into project-management jargon. Its four Lists separate the kinds of attention this situation actually requires.

Its Cards deliberately distinguish actions, multiple kinds of evidence, and decisions. A Waiting List would be premature until a named request or outside condition is actually in motion. That separation makes the current choice, evidence, and next move easier to scan.

These Card titles come directly from Claire's situation: “Choose the adjacent paper” is the live choice, while “PDF folder FINAL_review” and “Excluded: editorial with no measured outcome” hold different facts that can change it. The point is recognition, not a perfect taxonomy.

Opening the Card gives the visible item durable depth. Stage can hold Inclusion brief: Place protocol rules, coauthor date, and exclude / park / propose-amendment options on one page. Chat keeps the request and response beside that artifact instead of in a detached thread. Pulse can show “Open decision: Claire will choose whether to exclude the adjacent paper, park it for later, or propose a protocol amendment.” Activity can preserve this attributed receipt: “Ava compared the options in Card Chat using the Inclusion brief and this Card Room's visible notes and left “Choose the adjacent paper” with Claire.”

A useful Card Chat request would be: “Using only the context visible in this Card Room, compare excluding the new paper, parking it for later, and taking a protocol-amendment proposal to the coauthor. Do not write the review, contact the coauthor, or choose for me.” When live AI is configured, current Ava can respond to an explicit Card mention using supported Room context and can make limited reversible changes inside this Card Room after an explicit request. She uses only supported Room context; she cannot summarize the Board, watch other Lists, or act outside this Card Room. She does not gain authority over the decision merely because the context is organized.

Claire's call remains explicit: Claire chooses what to recommend; any protocol amendment requires her coauthor’s agreement. They own the review and every citation.

These requests use the visible supported context inside the “Choose the adjacent paper” Card Room. They do not imply that current Ava automatically surveys the whole Board or follows up on her own; Claire must provide the relevant facts and check the result.

Current Ava can reply in this Room to an explicit Card mention using supported Room context. She cannot summarize the Board, make the choice, represent Claire, watch other Lists, or act outside this Card Room.

Claire owns the science, citations, and coauthor conversations. Ava does not write the review, invent sources, or decide inclusion.

A table that matches the protocol: saved is not screened, the adjacent paper is a decision, and the coauthor can see why.

• Request idea: using only the context visible in this Card Room, compare excluding the new paper, parking it for later, and taking a protocol-amendment proposal to the coauthor. Do not write the review, contact the coauthor, or choose for me.
• Request idea: use only the Inclusion brief and notes the Owner has placed in this Card Room to separate facts, assumptions, and unanswered questions
• Request idea: name which visible Room note could most change the comparison; do not watch other Lists or follow up autonomously

A reference manager plus a FINAL folder is enough when the set is already screened.

It starts to break when 180 PDFs and a tempting adjacent paper all feel equally in.

The Scoping review Board earns its place only when the familiar tool—a reference manager plus a FINAL folder—can no longer keep the reason, Inclusion brief, conversation, current state, decision, and history connected.

Claire should rename every List or Card that feels artificial. This recipe succeeds when “Choose the adjacent paper” becomes easier to decide and fewer open loops depend on memory—not when the Board looks tidy.

Later, Ava may help this Board notice when a screening Card is still undecided and the table is due, still leaving every inclusion with Claire.

A future unified You.one experience could carry relevant context from “Choose the adjacent paper” across guidance and the Superboard view. Broad proactive coordination, cross-surface personalized memory, realtime shared editing, and general external execution are not available today. Any future action would still require the applicable capability, connection, grant, and human authority.

• Claire is fictional and is not a customer, testimonial, research participant, or disguised real person.
• This is not a scientific finding, medical advice, or systematic-review claim.
• It does not show Ava writing papers or deciding inclusion.
• It is not a measured publication result.