Getting started
It asks me to verify my email. What if I do not?
You can frame the question, prepare the search and write criteria. Those features include a few trial calls without verification. But screening, full text, extraction, risk of bias, manuscript and assistant will not start until you verify the address. Check spam. If it is not there, request another link from the app without signing in. The link lasts 24 hours and works once. Waiting does not erase your work.
Where should I start?
Use the quick start. Follow the path from question to export and open detailed pages as needed.
Can I change the research question later?
Yes, in the same review. While stage 1 is open, “Edit the question” changes it and revisia updates the concepts. Once you approve it, the concepts are fixed, but you can reword the question until screening is finished: search and criteria stay as they are. To change the concepts, press “Change the concepts” and reopen stage 1. Later approved stages lose their approval and you approve them again, but nothing is deleted and AI credits stay in the review. More in Question.
Does it only support treatment questions (PICO)?
No. Seven frameworks are available on every plan: PICO (intervention), PECO (exposure), PCC (scoping review), CoCoPop (prevalence), PIRD (diagnostic tests), PEO (prognosis) and SPIDER (qualitative research). When you select “Check”, revisia picks one based on your question, and you can change it at stage 1. See Question.
What can I do on the free plan?
The whole path, from question to export. AI screens your first 100 records; the rest are marked for you to verify. AI full-text screening, extraction, risk-of-bias draft and manuscript draft are paid. On the free plan, you do the first three manually with the same decision record. Double screening and the invited reviewer are also paid. Export is always free on every plan. See plans.
Does it work in English?
Yes. Each review sets the AI language under “Review settings” at stage 1: it is the language of criteria, verdicts and reasons. You can also change the interface language.
Search and documents
The search returns zero or very few results
Check the language filter and year range first: the “English” chip is on by default, and you can try “All languages”. Then look at “By term”: a name with zero adds nothing, and a MeSH heading that does not exist reduces the search to zero. For broader coverage, import results from SciELO, LILACS or Dialnet. See Your search.
How do I import from Web of Science, Scopus, Embase or Zotero?
If your search is already done, choose “Import your search” at stage 2. If you built it with revisia, use the optional stage Add more studies, which also gives you the query already translated for Web of Science, Embase and Cochrane. Either way you drop the files together: RIS, BibTeX, CSV, PubMed (.nbib), Web of Science (.txt) or WHO ICTRP (XML). References are deduplicated and each file counts in PRISMA under its database; anything that does not come from a database goes to “Other methods”.
How do I know my search finds the studies I already know?
Use “Check articles in your search” at stage 2. Paste the DOI or PMID, or type the title or an author, and see in which databases your query brings it. With “Pin”, revisia rechecks it every time you change the query and tells you which term drops it. See check and run.
It cannot find the PDF of an open-access article
Automatic retrieval only brings the PDF when the source offers a direct file link, or the text from PubMed Central or Europe PMC. Many open-access articles link only to their webpage. Use “Upload PDF” to add it manually: it takes priority over retrieval.
Screening and control
Screening marks too many studies as “Review”
revisia does not exclude for uncertainty: excluding needs a study to fail a required criterion, with the sentence that proves it in the text. What shortens the queue most is writing more specific criteria, which leave fewer “uncertain” verdicts. See how the band works.
A study switches between “Include” and “Review” on repeat runs
The model is not perfectly deterministic. By design, any variation ends in human review, never silent exclusion. Code calculates the decision from criterion verdicts.
Does AI decide for me?
No. It evaluates each criterion and code applies deterministic rules. Uncertain cases go to your queue, your decisions are audited and prevail, and no stage advances without approval.
Limits and export
What limits does my account have?
Limits cover active reviews, AI budget, 50 searches every 24 hours (each database counts as one) and imports of up to 5 MB per file. The number of AI-screened and stored records depends on your plan. The app shows the effective limit in “Project status”. On the free plan, OpenAlex allows three searches per review.
The AI budget is exhausted
You can continue screening and making manual decisions, and nothing is lost. The budget limits actions that call the model, not your work or exports.
Can I export all my work?
Yes, and export is always free. You can download references, screening, extraction and risk-of-bias tables, PRISMA 2020, a PROSPERO protocol, the audit log and a manuscript draft. See PRISMA and export.
More help
Ask the assistant inside your project about the method, criteria, searches or results. It suggests and explains without changing anything. If that does not answer your question, email equipo@revisia.es.